[llvm] 1741b9c - [LV] Generalize check lines for interleave group costs.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 11 07:22:12 PDT 2024
Author: Florian Hahn
Date: 2024-09-11T15:21:32+01:00
New Revision: 1741b9c3d75ee34550210fadb9c6156419c3c892
URL: https://github.com/llvm/llvm-project/commit/1741b9c3d75ee34550210fadb9c6156419c3c892
DIFF: https://github.com/llvm/llvm-project/commit/1741b9c3d75ee34550210fadb9c6156419c3c892.diff
LOG: [LV] Generalize check lines for interleave group costs.
Check cost of all instructions in an interleave group, to prepare for
follow-up changes.
Added:
Modified:
llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-5.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-7.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-8.ll
llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-8.ll
llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-5.ll
index de178cdf19308d..29dce5f21173af 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load float, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load float, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,136 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 75 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 150 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 75 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 150 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 9 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 18 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 35 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 145 for VF 32 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 400 for VF 64 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load float, ptr %in4, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-7.ll
index 1f54b7485aa8f5..0e7b1c58e587c1 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load float, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load float, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,179 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 49 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 98 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 23 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 49 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 105 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 210 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 49 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 105 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 210 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 70 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 280 for VF 32 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load float, ptr %in6, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-8.ll
index d53dca05155b77..8830aff579c322 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load float, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load float, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,30 +14,203 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load float, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load float, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load float, ptr %in7, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load float, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load float, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 120 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load float, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 240 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load float, ptr %in7, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load float, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load float, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load float, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 240 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load float, ptr %in7, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load float, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load float, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load float, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 40 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load float, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 92 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load float, ptr %in7, align 4
+; AVX512: LV: Found an estimated cost of 320 for VF 32 For instruction: %v0 = load float, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load float, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load float, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load float, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load float, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load float, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load float, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load float, ptr %in7, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll
index 1575f92465d524..cfd3d7841caa2d 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,35 +14,67 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 24 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 48 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 14 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 28 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 56 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 112 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 22 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 64 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load double, ptr %in1, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll
index 89175a65990f6d..5ec5b517313856 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,32 +14,86 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 36 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 42 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 84 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 16 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 32 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 51 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 120 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load double, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 240 for VF 64 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load double, ptr %in2, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll
index 8db9fd364133ec..450743df723251 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,107 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 24 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 28 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 56 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 112 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 28 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 56 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 22 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load double, ptr %in3, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-5.ll
index 25c49e3b8a8117..5e5c718dba97d2 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,116 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
; SSE2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
; SSE2: LV: Found an estimated cost of 30 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 100 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load double, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 200 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load double, ptr %in4, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll
index 42c980b6d3985a..62541fa2368c6a 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,137 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
; SSE2: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
; SSE2: LV: Found an estimated cost of 36 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 42 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 84 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 51 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 120 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load double, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 240 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load double, ptr %in5, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-7.ll
index 68afa6d17f02f8..cfed8554b978b8 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,158 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
; SSE2: LV: Found an estimated cost of 42 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 49 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 98 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 49 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 98 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load double, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 280 for VF 32 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load double, ptr %in6, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-8.ll
index 7894912c88fab6..07939b914d0224 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load double, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load double, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,27 +14,171 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load double, ptr %in7, align 8
; SSE2: LV: Found an estimated cost of 48 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load double, ptr %in7, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load double, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load double, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load double, ptr %in7, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load double, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load double, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load double, ptr %in7, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load double, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load double, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 40 for VF 4 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load double, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 8 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load double, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 16 For instruction: %v0 = load double, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load double, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load double, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load double, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load double, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load double, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load double, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load double, ptr %in7, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll
index d8eaa0aad61d57..964a9b660942e1 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i16, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i16, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,193 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
; SSE2: LV: Found an estimated cost of 22 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
; SSE2: LV: Found an estimated cost of 43 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
; SSE2: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
; SSE2: LV: Found an estimated cost of 170 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX1: LV: Found an estimated cost of 25 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX1: LV: Found an estimated cost of 43 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX1: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX1: LV: Found an estimated cost of 175 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX1: LV: Found an estimated cost of 350 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX2: LV: Found an estimated cost of 20 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX2: LV: Found an estimated cost of 40 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX2: LV: Found an estimated cost of 80 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX2: LV: Found an estimated cost of 165 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX2: LV: Found an estimated cost of 330 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 25 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 175 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 355 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512DQ: LV: Found an estimated cost of 710 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 14 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 28 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 55 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
; AVX512BW: LV: Found an estimated cost of 235 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-7.ll
index 9c0d102a70d1ed..6653198397dd25 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i16, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i16, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,265 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
; SSE2: LV: Found an estimated cost of 35 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
; SSE2: LV: Found an estimated cost of 60 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
; SSE2: LV: Found an estimated cost of 119 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
; SSE2: LV: Found an estimated cost of 238 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX1: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX1: LV: Found an estimated cost of 62 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX1: LV: Found an estimated cost of 119 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX1: LV: Found an estimated cost of 245 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX1: LV: Found an estimated cost of 490 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX2: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX2: LV: Found an estimated cost of 231 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX2: LV: Found an estimated cost of 462 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 64 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 121 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 245 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 497 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512DQ: LV: Found an estimated cost of 994 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i16, ptr %in6, align 2
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 15 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 19 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 56 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 112 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
; AVX512BW: LV: Found an estimated cost of 469 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i16, ptr %in6, align 2
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-8.ll
index 7654185635d3e5..b3a5cbeccc09c4 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i16, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i16, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,301 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
; SSE2: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i16, ptr %in7, align 2
; SSE2: LV: Found an estimated cost of 68 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i16, ptr %in7, align 2
; SSE2: LV: Found an estimated cost of 136 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i16, ptr %in7, align 2
; SSE2: LV: Found an estimated cost of 272 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i16, ptr %in7, align 2
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX1: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX1: LV: Found an estimated cost of 68 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX1: LV: Found an estimated cost of 136 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX1: LV: Found an estimated cost of 280 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX1: LV: Found an estimated cost of 560 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i16, ptr %in7, align 2
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX2: LV: Found an estimated cost of 32 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX2: LV: Found an estimated cost of 64 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX2: LV: Found an estimated cost of 128 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX2: LV: Found an estimated cost of 264 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX2: LV: Found an estimated cost of 528 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i16, ptr %in7, align 2
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 68 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 136 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 280 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 568 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512DQ: LV: Found an estimated cost of 1136 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v7 = load i16, ptr %in7, align 2
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 17 for VF 2 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 22 for VF 8 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 64 for VF 16 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 148 for VF 32 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i16, ptr %in7, align 2
; AVX512BW: LV: Found an estimated cost of 616 for VF 64 For instruction: %v0 = load i16, ptr %in0, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i16, ptr %in1, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i16, ptr %in2, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i16, ptr %in3, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i16, ptr %in4, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i16, ptr %in5, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i16, ptr %in6, align 2
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v7 = load i16, ptr %in7, align 2
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
index 86590c0fa6a9c5..c0ea210385dfda 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i32, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i32, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,35 +14,67 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 30 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 60 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 120 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 10 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 20 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 42 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 84 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 168 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 50 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 13 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 50 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 160 for VF 64 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i32, ptr %in1, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-5.ll
index 63901617bb9dd0..2a261ca4de4fa4 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i32, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i32, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,136 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 35 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 75 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 150 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 23 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 95 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 190 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 170 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 9 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 18 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 35 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 145 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 400 for VF 64 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i32, ptr %in4, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-7.ll
index 1eabac4e0b9c35..8bf3071d29fbe1 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i32, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i32, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,179 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 49 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 105 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
; SSE2: LV: Found an estimated cost of 210 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 63 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 133 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX1: LV: Found an estimated cost of 266 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 119 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX2: LV: Found an estimated cost of 238 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 70 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
; AVX512: LV: Found an estimated cost of 280 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i32, ptr %in6, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-8.ll
index a1bb2efd73963f..3182de2df058a8 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i32, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i32, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,30 +14,203 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 56 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i32, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 120 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i32, ptr %in7, align 4
; SSE2: LV: Found an estimated cost of 240 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i32, ptr %in7, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 36 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 72 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 152 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX1: LV: Found an estimated cost of 304 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i32, ptr %in7, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 32 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 64 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX2: LV: Found an estimated cost of 272 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i32, ptr %in7, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 40 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i32, ptr %in7, align 4
; AVX512: LV: Found an estimated cost of 92 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i32, ptr %in7, align 4
+; AVX512: LV: Found an estimated cost of 320 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i32, ptr %in2, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i32, ptr %in3, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i32, ptr %in4, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i32, ptr %in5, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i32, ptr %in6, align 4
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i32, ptr %in7, align 4
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll
index bd230166ebe78d..27e2ee0392615b 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,35 +14,67 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 28 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 56 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
; SSE2: LV: Found an estimated cost of 112 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 22 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 44 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 88 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX1: LV: Found an estimated cost of 176 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX2: LV: Found an estimated cost of 48 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 22 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 64 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i64, ptr %in1, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll
index e03d3c2f8b3a47..c37723257c1f75 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,32 +14,86 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 42 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
; SSE2: LV: Found an estimated cost of 84 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 33 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 66 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX1: LV: Found an estimated cost of 132 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 16 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX2: LV: Found an estimated cost of 32 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 51 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 120 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
; AVX512: LV: Found an estimated cost of 240 for VF 64 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i64, ptr %in2, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll
index f7249666918dd8..2eb7c5e93078f5 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,31 +14,107 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
; SSE2: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 20 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 44 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 88 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX1: LV: Found an estimated cost of 176 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 28 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX2: LV: Found an estimated cost of 56 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 22 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-5.ll
index 96946bd58dea13..c11da4309737d2 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,116 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
; SSE2: LV: Found an estimated cost of 35 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
; SSE2: LV: Found an estimated cost of 70 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 25 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 55 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 20 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX2: LV: Found an estimated cost of 90 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 100 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i64, ptr %in4, align 8
; AVX512: LV: Found an estimated cost of 200 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i64, ptr %in4, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll
index 2355c6e8b57a17..de57af6ebe3984 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,137 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
; SSE2: LV: Found an estimated cost of 42 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
; SSE2: LV: Found an estimated cost of 84 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 30 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 66 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX1: LV: Found an estimated cost of 132 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 51 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 120 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i64, ptr %in5, align 8
; AVX512: LV: Found an estimated cost of 240 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i64, ptr %in5, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-7.ll
index 646003a41dcf51..949c1af1fdad3b 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,28 +14,158 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
; SSE2: LV: Found an estimated cost of 49 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
; SSE2: LV: Found an estimated cost of 98 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 35 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 77 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX1: LV: Found an estimated cost of 154 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 63 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX2: LV: Found an estimated cost of 126 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 35 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i64, ptr %in6, align 8
; AVX512: LV: Found an estimated cost of 280 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i64, ptr %in6, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-8.ll
index 568ab74068f949..4388ccfbdcfc4f 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i64, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i64, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -14,27 +14,171 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
; SSE2: LV: Found an estimated cost of 56 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i64, ptr %in7, align 8
; SSE2: LV: Found an estimated cost of 112 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i64, ptr %in7, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 40 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 88 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX1: LV: Found an estimated cost of 176 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i64, ptr %in7, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 32 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 72 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX2: LV: Found an estimated cost of 144 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i64, ptr %in7, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 40 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i64, ptr %in7, align 8
; AVX512: LV: Found an estimated cost of 160 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i64, ptr %in4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i64, ptr %in5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i64, ptr %in6, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i64, ptr %in7, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-5.ll
index 6c1dd916311aba..6078fb440f9d13 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-5.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i8, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i8, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,193 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
; SSE2: LV: Found an estimated cost of 38 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
; SSE2: LV: Found an estimated cost of 75 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
; SSE2: LV: Found an estimated cost of 155 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
; SSE2: LV: Found an estimated cost of 315 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX1: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX1: LV: Found an estimated cost of 83 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX1: LV: Found an estimated cost of 165 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX1: LV: Found an estimated cost of 335 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX2: LV: Found an estimated cost of 20 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX2: LV: Found an estimated cost of 40 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX2: LV: Found an estimated cost of 80 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX2: LV: Found an estimated cost of 160 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX2: LV: Found an estimated cost of 325 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 24 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 165 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 335 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512DQ: LV: Found an estimated cost of 675 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 41 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 99 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 198 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
; AVX512BW: LV: Found an estimated cost of 395 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll
index 1ff3bc57a50d9f..ed8bc84e771f85 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i8, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i8, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,229 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
; SSE2: LV: Found an estimated cost of 47 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
; SSE2: LV: Found an estimated cost of 90 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
; SSE2: LV: Found an estimated cost of 186 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
; SSE2: LV: Found an estimated cost of 378 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX1: LV: Found an estimated cost of 27 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX1: LV: Found an estimated cost of 52 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX1: LV: Found an estimated cost of 99 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX1: LV: Found an estimated cost of 198 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX1: LV: Found an estimated cost of 402 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX2: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX2: LV: Found an estimated cost of 46 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX2: LV: Found an estimated cost of 88 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 21 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 45 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 85 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512DQ: LV: Found an estimated cost of 810 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 25 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 49 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 119 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 237 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
; AVX512BW: LV: Found an estimated cost of 591 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-7.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-7.ll
index d77bca6b7aa5a4..778a4e7dfd7d9d 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-7.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i8, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i8, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,265 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
; SSE2: LV: Found an estimated cost of 57 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
; SSE2: LV: Found an estimated cost of 110 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
; SSE2: LV: Found an estimated cost of 217 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
; SSE2: LV: Found an estimated cost of 441 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX1: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX1: LV: Found an estimated cost of 62 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX1: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX1: LV: Found an estimated cost of 231 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX1: LV: Found an estimated cost of 469 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX2: LV: Found an estimated cost of 112 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX2: LV: Found an estimated cost of 224 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX2: LV: Found an estimated cost of 455 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 34 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 62 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 120 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 233 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 469 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512DQ: LV: Found an estimated cost of 945 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i8, ptr %in6, align 1
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 29 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 57 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 138 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 413 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
; AVX512BW: LV: Found an estimated cost of 826 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i8, ptr %in6, align 1
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-8.ll
index 00ad2f68814b84..a230b5a0b1f2b7 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load i8, ptr %in0"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i8, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -15,44 +15,301 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
; SSE2: LV: Found an estimated cost of 56 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i8, ptr %in7, align 1
; SSE2: LV: Found an estimated cost of 120 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i8, ptr %in7, align 1
; SSE2: LV: Found an estimated cost of 248 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i8, ptr %in7, align 1
; SSE2: LV: Found an estimated cost of 504 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
+; SSE2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i8, ptr %in7, align 1
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX1: LV: Found an estimated cost of 33 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX1: LV: Found an estimated cost of 66 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX1: LV: Found an estimated cost of 132 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX1: LV: Found an estimated cost of 264 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX1: LV: Found an estimated cost of 536 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX1: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i8, ptr %in7, align 1
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX2: LV: Found an estimated cost of 32 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX2: LV: Found an estimated cost of 64 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX2: LV: Found an estimated cost of 128 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX2: LV: Found an estimated cost of 256 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX2: LV: Found an estimated cost of 520 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX2: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i8, ptr %in7, align 1
;
; AVX512DQ-LABEL: 'test'
; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 33 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 66 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 132 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 264 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 536 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512DQ: LV: Found an estimated cost of 1080 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512DQ: LV: Found an estimated cost of 0 for VF 64 For instruction: %v7 = load i8, ptr %in7, align 1
;
; AVX512BW-LABEL: 'test'
; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 1 for VF 1 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 2 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 33 for VF 4 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 4 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 65 for VF 8 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 8 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 158 for VF 16 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 16 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 472 for VF 32 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 32 For instruction: %v7 = load i8, ptr %in7, align 1
; AVX512BW: LV: Found an estimated cost of 1100 for VF 64 For instruction: %v0 = load i8, ptr %in0, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v1 = load i8, ptr %in1, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v2 = load i8, ptr %in2, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v3 = load i8, ptr %in3, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v4 = load i8, ptr %in4, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v5 = load i8, ptr %in5, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v6 = load i8, ptr %in6, align 1
+; AVX512BW: LV: Found an estimated cost of 0 for VF 64 For instruction: %v7 = load i8, ptr %in7, align 1
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-8.ll
index 678bb8917bd0d0..2ad37bee35bedc 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-8.ll
@@ -14,12 +14,14 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: store float %v7, ptr %out7, align 4
; SSE2: LV: Found an estimated cost of 56 for VF 4 For instruction: store float %v7, ptr %out7, align 4
; SSE2: LV: Found an estimated cost of 112 for VF 8 For instruction: store float %v7, ptr %out7, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: store float %v7, ptr %out7, align 4
; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: store float %v7, ptr %out7, align 4
; AVX1: LV: Found an estimated cost of 120 for VF 8 For instruction: store float %v7, ptr %out7, align 4
@@ -27,6 +29,7 @@ define void @test() {
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
; AVX2: LV: Found an estimated cost of 24 for VF 2 For instruction: store float %v7, ptr %out7, align 4
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: store float %v7, ptr %out7, align 4
; AVX2: LV: Found an estimated cost of 120 for VF 8 For instruction: store float %v7, ptr %out7, align 4
@@ -34,6 +37,7 @@ define void @test() {
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v7, ptr %out7, align 4
; AVX512: LV: Found an estimated cost of 11 for VF 2 For instruction: store float %v7, ptr %out7, align 4
; AVX512: LV: Found an estimated cost of 23 for VF 4 For instruction: store float %v7, ptr %out7, align 4
; AVX512: LV: Found an estimated cost of 46 for VF 8 For instruction: store float %v7, ptr %out7, align 4
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-8.ll
index 394d1d4de00f57..c1a66c1a41d74f 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store double %v7, ptr %out7"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store double %v., ptr %out."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -13,27 +13,172 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: store double %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 48 for VF 4 For instruction: store double %v7, ptr %out7, align 8
;
; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: store double %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: store double %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: store double %v7, ptr %out7, align 8
;
; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 24 for VF 2 For instruction: store double %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 56 for VF 4 For instruction: store double %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 112 for VF 8 For instruction: store double %v7, ptr %out7, align 8
;
; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store double %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 23 for VF 2 For instruction: store double %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store double %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 46 for VF 4 For instruction: store double %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store double %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 8 For instruction: store double %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store double %v6, ptr %out6, align 8
+; AVX512: LV: Found an estimated cost of 160 for VF 16 For instruction: store double %v7, ptr %out7, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-8.ll
index 4d9aad54b0c8fe..7be9577960efe3 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store i64 %v7, ptr %out7"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store i64 %v., ptr %out."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
@@ -13,27 +13,172 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 56 for VF 2 For instruction: store i64 %v7, ptr %out7, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v0, ptr %out0, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v1, ptr %out1, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v2, ptr %out2, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v3, ptr %out3, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v4, ptr %out4, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v5, ptr %out5, align 8
+; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v6, ptr %out6, align 8
; SSE2: LV: Found an estimated cost of 112 for VF 4 For instruction: store i64 %v7, ptr %out7, align 8
;
; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 40 for VF 2 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 88 for VF 4 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v6, ptr %out6, align 8
; AVX1: LV: Found an estimated cost of 176 for VF 8 For instruction: store i64 %v7, ptr %out7, align 8
;
; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 40 for VF 2 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 88 for VF 4 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX2: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v6, ptr %out6, align 8
; AVX2: LV: Found an estimated cost of 176 for VF 8 For instruction: store i64 %v7, ptr %out7, align 8
;
; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: store i64 %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 23 for VF 2 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: store i64 %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 46 for VF 4 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: store i64 %v6, ptr %out6, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 8 For instruction: store i64 %v7, ptr %out7, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v0, ptr %out0, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v1, ptr %out1, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v2, ptr %out2, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v3, ptr %out3, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v4, ptr %out4, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v5, ptr %out5, align 8
+; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: store i64 %v6, ptr %out6, align 8
+; AVX512: LV: Found an estimated cost of 160 for VF 16 For instruction: store i64 %v7, ptr %out7, align 8
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
index 741dd0746b744c..13a844230f89d9 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
@@ -22,6 +22,8 @@ define void @test1(ptr noalias nocapture %points, ptr noalias nocapture readonly
; DISABLED_MASKED_STRIDED-LABEL: 'test1'
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %0, ptr %arrayidx2, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %2, ptr %arrayidx7, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 13 for VF 4 For instruction: store i16 %0, ptr %arrayidx2, align 2
@@ -34,6 +36,8 @@ define void @test1(ptr noalias nocapture %points, ptr noalias nocapture readonly
; ENABLED_MASKED_STRIDED-LABEL: 'test1'
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, ptr %arrayidx2, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 12 for VF 2 For instruction: store i16 %2, ptr %arrayidx7, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, ptr %arrayidx2, align 2
@@ -79,6 +83,8 @@ define void @test2(ptr noalias nocapture %points, i32 %numPoints, ptr noalias no
; DISABLED_MASKED_STRIDED-LABEL: 'test2'
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 5 for VF 2 For instruction: store i16 %0, ptr %arrayidx2, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: store i16 %2, ptr %arrayidx7, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 10 for VF 4 For instruction: store i16 %0, ptr %arrayidx2, align 2
@@ -91,6 +97,8 @@ define void @test2(ptr noalias nocapture %points, i32 %numPoints, ptr noalias no
; ENABLED_MASKED_STRIDED-LABEL: 'test2'
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, ptr %arrayidx7, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, ptr %arrayidx2, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 10 for VF 2 For instruction: store i16 %2, ptr %arrayidx7, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, ptr %arrayidx2, align 2
@@ -145,6 +153,7 @@ for.end:
define void @test(ptr noalias nocapture %points, ptr noalias nocapture readonly %x, ptr noalias nocapture readnone %y) {
; DISABLED_MASKED_STRIDED-LABEL: 'test'
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx6, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, ptr %arrayidx6, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, ptr %arrayidx6, align 2
; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, ptr %arrayidx6, align 2
@@ -152,6 +161,7 @@ define void @test(ptr noalias nocapture %points, ptr noalias nocapture readonly
;
; ENABLED_MASKED_STRIDED-LABEL: 'test'
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, ptr %arrayidx6, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, ptr %arrayidx6, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, ptr %arrayidx6, align 2
; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, ptr %arrayidx6, align 2
More information about the llvm-commits
mailing list