[llvm] f92961d - [NFC] Fixup newly-added costmodel tests to actually test what they should
Roman Lebedev via llvm-commits
llvm-commits at lists.llvm.org
Tue Oct 5 11:36:16 PDT 2021
Author: Roman Lebedev
Date: 2021-10-05T21:35:47+03:00
New Revision: f92961d238efdfeccce27f9bb7b0a6629c376d4a
URL: https://github.com/llvm/llvm-project/commit/f92961d238efdfeccce27f9bb7b0a6629c376d4a
DIFF: https://github.com/llvm/llvm-project/commit/f92961d238efdfeccce27f9bb7b0a6629c376d4a.diff
LOG: [NFC] Fixup newly-added costmodel tests to actually test what they should
Added:
Modified:
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll
index 3080b0485e7f..8497f4739b41 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll
@@ -13,34 +13,31 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 15 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 30 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 24 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 48 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 24 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 48 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 13 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 50 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 2
+; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
define void @test() {
entry:
@@ -62,7 +59,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.0.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 2
+ %iv.next = add nuw nsw i64 %iv, 2
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll
index 71b2992fcab9..463f4d528b35 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll
@@ -13,32 +13,29 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 62 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 47 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 94 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 47 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 94 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 9 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 144 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
@@ -66,7 +63,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.1.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 3
+ %iv.next = add nuw nsw i64 %iv, 3
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll
index 2ee62ea5bc62..6236771cb93f 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll
@@ -13,32 +13,31 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 34 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 25 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 50 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 25 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 50 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 3 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 21 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 78 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+;
+; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
define void @test() {
entry:
@@ -61,7 +60,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.1.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 3
+ %iv.next = add nuw nsw i64 %iv, 3
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll
index 258a9901c2ea..96a304f26bb0 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll
@@ -13,29 +13,28 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 90 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 32 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 32 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 4 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 6 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 17 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 71 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
@@ -67,7 +66,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.2.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 4
+ %iv.next = add nuw nsw i64 %iv, 4
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
index dc191c308ff7..e2d2ee955472 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll
@@ -13,32 +13,29 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 30 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 60 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 22 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 96 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 22 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 48 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 96 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 13 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 50 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 160 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
@@ -67,7 +64,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.2.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 4
+ %iv.next = add nuw nsw i64 %iv, 4
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll
index 0c7b21a4a299..ebe6257a96f5 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll
@@ -13,31 +13,28 @@ target triple = "x86_64-unknown-linux-gnu"
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 15 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 30 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 26 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 52 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 26 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 52 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 5 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX512: LV: Found an estimated cost of 29 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
@@ -64,7 +61,7 @@ for.body:
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
store i8 %reduce.add.2.narrow, i8* %out
- %iv.next = add nuw nsw i64 %iv.0, 4
+ %iv.next = add nuw nsw i64 %iv, 4
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
More information about the llvm-commits
mailing list