SimplifyDemandedVectorElts for all intrinsics

The point is that this simplifies integration of new intrinsics into SimplifiedDemandedVectorElts, and ensures we don't miss any existing ones.

This is intended to be NFC-ish, but as seen from the diffs, can produce slightly different output.  This is due to order of transforms w/in instcombine resulting in two slightly different fixed points.  That's something we should fix, but isn't a problem w/this patch per se.

Differential Revision: https://reviews.llvm.org/D57398

llvm-svn: 352653

1 files changed, 8 insertions, 8 deletions

diff --git a/llvm/test/Transforms/InstCombine/X86/x86-avx512.ll b/llvm/test/Transforms/InstCombine/X86/x86-avx512.ll
index 21e2e216bed..9c5080c7792 100644
--- a/llvm/test/Transforms/InstCombine/X86/x86-avx512.ll
+++ b/llvm/test/Transforms/InstCombine/X86/x86-avx512.ll
@@ -7,7 +7,7 @@ declare <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>, <4 x float>,
 define <4 x float> @test_add_ss(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @test_add_ss(
 ; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = fadd float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP4]]
@@ -38,7 +38,7 @@ define <4 x float> @test_add_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fadd float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP8]]
@@ -149,7 +149,7 @@ declare <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float>, <4 x float>,
 define <4 x float> @test_sub_ss(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @test_sub_ss(
 ; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = fsub float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP4]]
@@ -180,7 +180,7 @@ define <4 x float> @test_sub_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fsub float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP8]]
@@ -291,7 +291,7 @@ declare <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float>, <4 x float>,
 define <4 x float> @test_mul_ss(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @test_mul_ss(
 ; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = fmul float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP4]]
@@ -322,7 +322,7 @@ define <4 x float> @test_mul_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fmul float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP8]]
@@ -433,7 +433,7 @@ declare <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float>, <4 x float>,
 define <4 x float> @test_div_ss(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @test_div_ss(
 ; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = fdiv float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP4]]
@@ -464,7 +464,7 @@ define <4 x float> @test_div_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fdiv float [[TMP1]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
 ; CHECK-NEXT:    ret <4 x float> [[TMP8]]