[llvm] 14e83ad - [CostModel][X86] Auto generate masked load/store LV costs using UTC_ARGS --filter control
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Thu May 12 09:40:53 PDT 2022
Author: Simon Pilgrim
Date: 2022-05-12T17:40:40+01:00
New Revision: 14e83ada16b3944a4431617ed4ce7088f7f7cd9a
URL: https://github.com/llvm/llvm-project/commit/14e83ada16b3944a4431617ed4ce7088f7f7cd9a
DIFF: https://github.com/llvm/llvm-project/commit/14e83ada16b3944a4431617ed4ce7088f7f7cd9a.diff
LOG: [CostModel][X86] Auto generate masked load/store 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/masked-interleaved-load-i16.ll
llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
llvm/test/Analysis/CostModel/X86/masked-load-i16.ll
llvm/test/Analysis/CostModel/X86/masked-load-i32.ll
llvm/test/Analysis/CostModel/X86/masked-load-i64.ll
llvm/test/Analysis/CostModel/X86/masked-load-i8.ll
llvm/test/Analysis/CostModel/X86/masked-store-i16.ll
llvm/test/Analysis/CostModel/X86/masked-store-i32.ll
llvm/test/Analysis/CostModel/X86/masked-store-i64.ll
llvm/test/Analysis/CostModel/X86/masked-store-i8.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll
index 6aea5d5cddf0..4552b32055df 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%i[2,4] = load i16, i16\* %[a-zA-Z0-7]+, align 2"
; RUN: opt -loop-vectorize -enable-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=DISABLED_MASKED_STRIDED
; RUN: opt -loop-vectorize -enable-interleaved-mem-accesses -enable-masked-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=ENABLED_MASKED_STRIDED
; REQUIRES: asserts
@@ -17,41 +18,31 @@ target triple = "x86_64-unknown-linux-gnu"
; }
; (relates to the testcase in PR50566)
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test1'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test1'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 17 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-
define void @test1(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test1'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test1'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 17 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+;
entry:
br label %for.body
@@ -84,41 +75,31 @@ for.end:
; y[i] = points[i*4 + 1];
; }
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test2'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test2'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 17 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
-
define void @test2(i16* noalias nocapture %points, i32 %numPoints, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test2'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test2'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 17 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2
+;
entry:
%cmp15 = icmp sgt i32 %numPoints, 0
br i1 %cmp15, label %for.body.preheader, label %for.end
@@ -161,23 +142,31 @@ for.end:
; x[i] = points[i*3];
; }
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 7 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
-
define void @test(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readnone %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 2 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 7 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 4 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 4 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 8 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 9 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2
+;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
index 0ec969f856ce..739f89eb027d 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store i16 %[0,2], i16\* %[a-zA-Z0-7]+, align 2"
; RUN: opt -loop-vectorize -enable-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=DISABLED_MASKED_STRIDED
; RUN: opt -loop-vectorize -enable-interleaved-mem-accesses -enable-masked-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=ENABLED_MASKED_STRIDED
; REQUIRES: asserts
@@ -17,41 +18,31 @@ target triple = "x86_64-unknown-linux-gnu"
; }
; (relates to the testcase in PR50566)
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test1'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test1'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 12 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
-
define void @test1(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test1'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 6 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 30 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test1'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 12 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
+;
entry:
br label %for.body
@@ -84,41 +75,31 @@ for.end:
; points[i*4 + 1] = y[i];
; }
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test2'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 5 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 23 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 50 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test2'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 10 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
-
define void @test2(i16* noalias nocapture %points, i32 %numPoints, i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test2'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 5 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 11 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 23 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 50 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test2'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 2 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 10 for VF 2 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 4 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 4 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 8 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 14 for VF 8 For instruction: store i16 %2, i16* %arrayidx7, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 0 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 27 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2
+;
entry:
%cmp15 = icmp sgt i32 %numPoints, 0
br i1 %cmp15, label %for.body.preheader, label %for.end
@@ -161,23 +142,21 @@ for.end:
; points[i*3] = x[i];
; }
-; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test'
-;
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %0, i16* %arrayidx6, align 2
-
-; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test'
-;
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, i16* %arrayidx6, align 2
-; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %0, i16* %arrayidx6, align 2
-
define void @test(i16* noalias nocapture %points, i16* noalias nocapture readonly %x, i16* noalias nocapture readnone %y) {
+; DISABLED_MASKED_STRIDED-LABEL: 'test'
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %0, i16* %arrayidx6, align 2
+;
+; ENABLED_MASKED_STRIDED-LABEL: 'test'
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, i16* %arrayidx6, align 2
+; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %0, i16* %arrayidx6, align 2
+;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll
index 8ccdde4686b6..96f7dd3ba5b8 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-load-i16.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 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
+; 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
@@ -13,51 +14,39 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] 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.loaded = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; SSE42: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+define void @test([1024 x i16]* %B) {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; SSE: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX2: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
-; AVX512: LV: Found an estimated cost of 2 for VF 64 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
+; AVX512: LV: Found an estimated cost of 2 for VF 64 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB.loaded = load i16, i16* %inB, align 2
-define void @test([1024 x i16]* %B) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll
index 36b0d8396a54..ec7523e71e62 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-load-i32.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
+; 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
@@ -13,51 +14,39 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] 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
-;
-; 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 3 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 4 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX1: LV: Found an estimated cost of 8 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+define void @test([1024 x i32]* %B) {
+; 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
;
-; 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 3 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 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 3 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 4 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX1: LV: Found an estimated cost of 8 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 3 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2: LV: Found an estimated cost of 4 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX2: LV: Found an estimated cost of 8 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 2 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 2 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 4 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 2 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 2 for VF 32 For instruction: %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 4 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([1024 x i32]* %B) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll
index 8a61c126d283..25a5cac597e0 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-load-i64.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
+; 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
@@ -13,51 +14,39 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] 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
-;
-; 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 2 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 4 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 8 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX1: LV: Found an estimated cost of 16 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+define void @test([1024 x i64]* %B) {
+; 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
;
-; 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 2 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 4 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 8 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX1: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 16 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2: LV: Found an estimated cost of 4 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2: LV: Found an estimated cost of 8 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX2: LV: Found an estimated cost of 16 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 1 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 4 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 8 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 1 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 4 for VF 32 For instruction: %valB.loaded = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 8 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([1024 x i64]* %B) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll
index 07de875935a5..add91483d05b 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-load-i8.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 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=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
+; 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
@@ -13,51 +14,39 @@ target triple = "x86_64-unknown-linux-gnu"
@A = 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.loaded = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-;
-; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; SSE42: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-;
-; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+define void @test([1024 x i8]* %B) {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; SSE: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; SSE: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; SSE: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; SSE: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
;
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1-LABEL: 'test'
+; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
;
-; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2-LABEL: 'test'
+; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX2: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
;
-; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
-; AVX512: LV: Found an estimated cost of 1 for VF 64 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512-LABEL: 'test'
+; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: %valB.loaded = load i8, i8* %inB, align 1
+; AVX512: LV: Found an estimated cost of 1 for VF 64 For instruction: %valB.loaded = load i8, i8* %inB, align 1
;
-; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB.loaded = load i8, i8* %inB, align 1
-define void @test([1024 x i8]* %B) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll
index 3edbab730911..01eaa41f5d37 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-store-i16.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=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
+; 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
@@ -13,51 +14,39 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] zeroinitializer, align 128
@B = 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; SSE2: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; SSE42: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX1: LV: Found an estimated cost of 40 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+define void @test([1024 x i16]* %C) {
+; SSE-LABEL: 'test'
+; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2
+; SSE: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; SSE: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; SSE: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; SSE: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX1: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX2-FASTGATHER: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 4 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX2: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
-; AVX512: LV: Found an estimated cost of 2 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 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: store i16 %valB, i16* %out, align 2
+; AVX512: LV: Found an estimated cost of 2 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([1024 x i16]* %C) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll
index 467679e3f95c..3dc452d8c319 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-store-i32.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
@@ -13,51 +14,46 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] zeroinitializer, align 128
@B = 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([1024 x i32]* %C) {
+; 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 9 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 16 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX1: LV: Found an estimated cost of 32 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 9 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-SLOWGATHER: 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 32 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 9 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 16 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX1: LV: Found an estimated cost of 32 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 9 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 16 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX2-FASTGATHER: LV: Found an estimated cost of 32 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 9 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 8 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 16 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX2: LV: Found an estimated cost of 32 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 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 2 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 4 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 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 2 for VF 32 For instruction: store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 4 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([1024 x i32]* %C) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll
index 1494e6999a3c..a58b7debfa23 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-store-i64.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
@@ -13,51 +14,46 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] zeroinitializer, align 128
@B = 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([1024 x i64]* %C) {
+; 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 8 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 8 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 16 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 32 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX1: LV: Found an estimated cost of 64 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 8 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 32 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 64 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 8 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 8 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 16 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 32 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX1: LV: Found an estimated cost of 64 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 8 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 16 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 32 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX2-FASTGATHER: LV: Found an estimated cost of 64 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 8 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 16 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 32 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX2: LV: Found an estimated cost of 64 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 1 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 4 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 8 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 1 for VF 2 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 4 for VF 32 For instruction: store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 8 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([1024 x i64]* %C) {
entry:
br label %for.body
diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll
index 33e6c7c67dc6..6c1dbf3e738b 100644
--- a/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll
+++ b/llvm/test/Analysis/CostModel/X86/masked-store-i8.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
@@ -13,51 +14,46 @@ target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] zeroinitializer, align 128
@B = 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 11 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; SSE2: LV: Found an estimated cost of 23 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 5 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 11 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; SSE42: LV: Found an estimated cost of 23 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+define void @test([1024 x i8]* %C) {
+; 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 11 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; SSE2: LV: Found an estimated cost of 23 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 16 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX1: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; SSE42: LV: Found an estimated cost of 16 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 16 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-SLOWGATHER: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 16 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX1: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 16 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX2-FASTGATHER: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 4 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 8 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 16 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX2: LV: Found an estimated cost of 40 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
-; AVX512: LV: Found an estimated cost of 1 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 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: store i8 %valB, i8* %out, align 1
+; AVX512: LV: Found an estimated cost of 1 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([1024 x i8]* %C) {
entry:
br label %for.body
More information about the llvm-commits
mailing list