[llvm] a5c45c4 - [CostModel][X86] Auto generate gather/scatter LV costs using UTC_ARGS --filter control
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Thu May 12 09:39:16 PDT 2022
Author: Simon Pilgrim
Date: 2022-05-12T17:39:06+01:00
New Revision: a5c45c4dc12c14cf3a657726ab04a025d6ea924b
URL: https://github.com/llvm/llvm-project/commit/a5c45c4dc12c14cf3a657726ab04a025d6ea924b
DIFF: https://github.com/llvm/llvm-project/commit/a5c45c4dc12c14cf3a657726ab04a025d6ea924b.diff
LOG: [CostModel][X86] Auto generate gather/scatter LV costs using UTC_ARGS --filter control
Also fix a sse42 -> sse4.2 typo so that we actually test costs for sse4.2
Added:
Modified:
llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll
llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll
index 564e5796b7d17..ce87bded62719 100644
--- a/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB = load i16, i16\* %inB, align 2"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,47 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i16] zeroinitializer, align 128
@C = global [1024 x i16] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
+define void @test() {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 194 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 388 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 194 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 388 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 34 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 68 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 34 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 68 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 58 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 116 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER: LV: Found an estimated cost of 58 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX2-FASTGATHER: LV: Found an estimated cost of 116 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 62 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 124 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 248 for VF 64 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 62 for VF 16 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 124 for VF 32 For instruction: %valB = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 248 for VF 64 For instruction: %valB = load i16, i16* %inB, align 2
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB = load i16, i16* %inB, align 2
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll
index 64cdcac6daf69..aa161ddf5a00f 100644
--- a/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB = load i32, i32\* %inB, align 4"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,54 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i32] zeroinitializer, align 128
@C = global [1024 x i32] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 102 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 204 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE2: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE2: LV: Found an estimated cost of 102 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE2: LV: Found an estimated cost of 204 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 102 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 204 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE42: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE42: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE42: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; SSE42: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 98 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 196 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 392 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 98 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 196 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 392 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 18 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 36 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 72 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 18 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 36 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 72 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: %valB = load i32, i32* %inB, align 4
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB = load i32, i32* %inB, align 4
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll
index 54d34d7c15391..248375326a1a5 100644
--- a/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB = load i64, i64\* %inB, align 8"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,52 +15,54 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i64] zeroinitializer, align 128
@C = global [1024 x i64] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 50 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 100 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 200 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE2: LV: Found an estimated cost of 50 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE2: LV: Found an estimated cost of 100 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE2: LV: Found an estimated cost of 200 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 102 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 204 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE42: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE42: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE42: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; SSE42: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 50 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 100 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 200 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 400 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 50 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 100 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 200 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 400 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 10 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 20 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 80 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 10 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 20 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 80 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %valB = load i64, i64* %inB, align 8
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB = load i64, i64* %inB, align 8
-
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll
index 5d722f47cdd77..c26891440fc1e 100644
--- a/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB = load i8, i8\* %inB, align 1"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,54 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128
@C = global [1024 x i8] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 103 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 207 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE2: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE2: LV: Found an estimated cost of 103 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE2: LV: Found an estimated cost of 207 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 51 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 103 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 207 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE42: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE42: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE42: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; SSE42: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 386 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 48 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 96 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 192 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 386 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 32 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 66 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 32 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 66 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 56 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 114 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER: LV: Found an estimated cost of 56 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX2-FASTGATHER: LV: Found an estimated cost of 114 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 60 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 122 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 244 for VF 64 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 60 for VF 16 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 122 for VF 32 For instruction: %valB = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 244 for VF 64 For instruction: %valB = load i8, i8* %inB, align 1
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB = load i8, i8* %inB, align 1
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll
index 80047cc7d8b44..155397c14002b 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB.loaded = load i32, i32\* %inB, align 4"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,47 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i32] zeroinitializer, align 128
@C = global [1024 x i32] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; SSE42: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+define void @test() {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; SSE: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; SSE: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; SSE: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; SSE: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 22 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 22 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: %valB.loaded = load i32, i32* %inB, align 4
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB.loaded = load i32, i32* %inB, align 4
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll
index b7d46853734b2..36360dc77a658 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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*%valB.loaded = load i64, i64\* %inB, align 8"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-SLOWGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2-FASTGATHER
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,47 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i64] zeroinitializer, align 128
@C = global [1024 x i64] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; SSE42: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+define void @test() {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; SSE: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; SSE: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; SSE: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; SSE: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER-LABEL: 'test'
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER-LABEL: 'test'
+; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 24 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 24 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %valB.loaded = load i64, i64* %inB, align 8
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB.loaded = load i64, i64* %inB, align 8
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll
index 49bf928d72972..39c6086ef110e 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 i32 %valB, i32\* %out, align 4"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i32] zeroinitializer, align 128
@C = global [1024 x i32] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 11 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 22 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 5 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 11 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 22 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 11 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 22 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 40 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 16 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 40 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 40 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 40 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 11 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 11 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: store i32 %valB, i32* %out, align 4
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i32 %valB, i32* %out, align 4
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll
index 3adc70b314b5f..d0c3f2ee9a3f0 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 %valB, i64\* %out, align 8"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i64] zeroinitializer, align 128
@C = global [1024 x i64] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 4 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 8 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 16 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 12 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 12 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: store i64 %valB, i64* %out, align 8
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i64 %valB, i64* %out, align 8
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll
index 426ec4b68dbb1..4058f3fe25e50 100644
--- a/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 i16 %valB, i16\* %out, align 2"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i16] zeroinitializer, align 128
@C = global [1024 x i16] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 56 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 112 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 224 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 28 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 56 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 112 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 224 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; SSE2: LV: Found an estimated cost of 56 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; SSE2: LV: Found an estimated cost of 112 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; SSE2: LV: Found an estimated cost of 224 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 108 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; SSE42: LV: Found an estimated cost of 26 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; SSE42: LV: Found an estimated cost of 52 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; SSE42: LV: Found an estimated cost of 104 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; SSE42: LV: Found an estimated cost of 208 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 108 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 28 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 64 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 144 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 288 for VF 64 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 144 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 288 for VF 64 For instruction: store i16 %valB, i16* %out, align 2
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i16 %valB, i16* %out, align 2
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll
index 573c3c20e311e..cf18faa01fc5e 100644
--- a/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 i32 %valB, i32\* %out, align 4"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i32] zeroinitializer, align 128
@C = global [1024 x i32] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 29 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 59 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 118 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; SSE42: LV: Found an estimated cost of 236 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 26 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 52 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 104 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; SSE42: LV: Found an estimated cost of 208 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 32 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 32 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 14 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 32 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 64 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction: store i32 %valB, i32* %out, align 4
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i32 %valB, i32* %out, align 4
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll
index 64aa3377b5092..8a7356ddd8864 100644
--- a/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 %valB, i64\* %out, align 8"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i64] zeroinitializer, align 128
@C = global [1024 x i64] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 58 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 116 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; SSE2: LV: Found an estimated cost of 232 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 29 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 58 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 116 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; SSE42: LV: Found an estimated cost of 232 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 58 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 116 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; SSE2: LV: Found an estimated cost of 232 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 26 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 52 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 104 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; SSE42: LV: Found an estimated cost of 208 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 32 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 56 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 112 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 224 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 16 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 32 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 64 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 16 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 32 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 64 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: store i64 %valB, i64* %out, align 8
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i64 %valB, i64* %out, align 8
-define void @test() {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll
index 30cff4fe03337..ae7b6364f9a04 100644
--- a/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll
+++ b/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll
@@ -1,9 +1,10 @@
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
-; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
+; 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 i8 %valB, i8\* %out, align 1"
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -14,51 +15,46 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128
@C = global [1024 x i8] zeroinitializer, align 128
-; CHECK: LV: Checking a loop in 'test'
-;
-; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 119 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 239 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 29 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 59 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 119 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 239 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+define void @test() {
+; SSE2-LABEL: 'test'
+; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 119 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 239 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 108 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 216 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42-LABEL: 'test'
+; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 26 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 52 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 104 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 208 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 56 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 108 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 216 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 448 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 14 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 28 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 56 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 128 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 14 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 28 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 56 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 128 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 60 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 136 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 288 for VF 64 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 30 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 60 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 136 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 288 for VF 64 For instruction: store i8 %valB, i8* %out, align 1
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i8 %valB, i8* %out, align 1
-define void @test() {
entry:
br label %for.body
More information about the llvm-commits
mailing list