[X86][NFC] Update ternlog comments #119343
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-backend-x86 Author: Phoebe Wang (phoebewang) ChangesFull diff: https://github.com/llvm/llvm-project/pull/119343.diff 2 Files Affected:
diff --git a/llvm/test/CodeGen/X86/avx512-insert-extract.ll b/llvm/test/CodeGen/X86/avx512-insert-extract.ll
index 1c4bfa8422d810..085581d27c62fb 100644
--- a/llvm/test/CodeGen/X86/avx512-insert-extract.ll
+++ b/llvm/test/CodeGen/X86/avx512-insert-extract.ll
@@ -672,7 +672,7 @@ define <32 x i16> @insert_v32i16(<32 x i16> %x, i16 %y, ptr %ptr) nounwind {
; KNL-NEXT: vinserti32x4 $0, %xmm1, %zmm0, %zmm1
; KNL-NEXT: vmovd %edi, %xmm0
; KNL-NEXT: vpbroadcastw %xmm0, %ymm0
-; KNL-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm1, %zmm0
+; KNL-NEXT: vpternlogq {{.*#+}} zmm0 = zmm0 ^ (mem & (zmm0 ^ zmm1))
; KNL-NEXT: retq
;
; SKX-LABEL: insert_v32i16:
@@ -1466,7 +1466,7 @@ define zeroext i8 @test_extractelement_varible_v2i1(<2 x i64> %a, <2 x i64> %b,
; KNL-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; KNL-NEXT: vpcmpnleuq %zmm1, %zmm0, %k1
-; KNL-NEXT: vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; KNL-NEXT: vpternlogq {{.*#+}} zmm0 {%k1} {z} = -1
; KNL-NEXT: vmovdqa %xmm0, -{{[0-9]+}}(%rsp)
; KNL-NEXT: andl $1, %edi
; KNL-NEXT: movzbl -24(%rsp,%rdi,8), %eax
@@ -1497,7 +1497,7 @@ define zeroext i8 @test_extractelement_varible_v4i1(<4 x i32> %a, <4 x i32> %b,
; KNL-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; KNL-NEXT: vpcmpnleud %zmm1, %zmm0, %k1
-; KNL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; KNL-NEXT: vpternlogd {{.*#+}} zmm0 {%k1} {z} = -1
; KNL-NEXT: vmovdqa %xmm0, -{{[0-9]+}}(%rsp)
; KNL-NEXT: andl $3, %edi
; KNL-NEXT: movzbl -24(%rsp,%rdi,4), %eax
@@ -1528,7 +1528,7 @@ define zeroext i8 @test_extractelement_varible_v8i1(<8 x i32> %a, <8 x i32> %b,
; KNL-NEXT: ## kill: def $ymm1 killed $ymm1 def $zmm1
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
; KNL-NEXT: vpcmpnleud %zmm1, %zmm0, %k1
-; KNL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; KNL-NEXT: vpternlogd {{.*#+}} zmm0 {%k1} {z} = -1
; KNL-NEXT: vpmovdw %zmm0, %ymm0
; KNL-NEXT: vmovdqa %xmm0, -{{[0-9]+}}(%rsp)
; KNL-NEXT: andl $7, %edi
@@ -1559,7 +1559,7 @@ define zeroext i8 @test_extractelement_varible_v16i1(<16 x i32> %a, <16 x i32> %
; KNL: ## %bb.0:
; KNL-NEXT: ## kill: def $edi killed $edi def $rdi
; KNL-NEXT: vpcmpnleud %zmm1, %zmm0, %k1
-; KNL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; KNL-NEXT: vpternlogd {{.*#+}} zmm0 {%k1} {z} = -1
; KNL-NEXT: vpmovdb %zmm0, -{{[0-9]+}}(%rsp)
; KNL-NEXT: andl $15, %edi
; KNL-NEXT: movzbl -24(%rsp,%rdi), %eax
@@ -1641,7 +1641,7 @@ define i32 @test_insertelement_variable_v32i1(<32 x i8> %a, i8 %b, i32 %index) n
; KNL-NEXT: ## kill: def $esi killed $esi def $rsi
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpcmpeqb %ymm1, %ymm0, %ymm0
-; KNL-NEXT: vpternlogq $15, %zmm0, %zmm0, %zmm0
+; KNL-NEXT: vpternlogq {{.*#+}} zmm0 = ~zmm0
; KNL-NEXT: andl $31, %esi
; KNL-NEXT: testb %dil, %dil
; KNL-NEXT: vmovdqa %ymm0, (%rsp)
@@ -1695,7 +1695,7 @@ define i64 @test_insertelement_variable_v64i1(<64 x i8> %a, i8 %b, i32 %index) n
; KNL-NEXT: vpcmpeqb %ymm2, %ymm1, %ymm1
; KNL-NEXT: vpcmpeqb %ymm2, %ymm0, %ymm0
; KNL-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
-; KNL-NEXT: vpternlogq $15, %zmm0, %zmm0, %zmm0
+; KNL-NEXT: vpternlogq {{.*#+}} zmm0 = ~zmm0
; KNL-NEXT: andl $63, %esi
; KNL-NEXT: testb %dil, %dil
; KNL-NEXT: vmovdqa64 %zmm0, (%rsp)
@@ -1827,7 +1827,7 @@ define i96 @test_insertelement_variable_v96i1(<96 x i8> %a, i8 %b, i32 %index) n
; KNL-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; KNL-NEXT: vpcmpeqb %ymm0, %ymm2, %ymm2
; KNL-NEXT: vinserti64x4 $1, %ymm1, %zmm2, %zmm1
-; KNL-NEXT: vpternlogq $15, %zmm1, %zmm1, %zmm1
+; KNL-NEXT: vpternlogq {{.*#+}} zmm1 = ~zmm1
; KNL-NEXT: vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; KNL-NEXT: vpinsrb $1, 488(%rbp), %xmm2, %xmm2
; KNL-NEXT: vpinsrb $2, 496(%rbp), %xmm2, %xmm2
@@ -1862,7 +1862,7 @@ define i96 @test_insertelement_variable_v96i1(<96 x i8> %a, i8 %b, i32 %index) n
; KNL-NEXT: vpinsrb $15, 728(%rbp), %xmm3, %xmm3
; KNL-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; KNL-NEXT: vpcmpeqb %ymm0, %ymm2, %ymm2
-; KNL-NEXT: vpternlogq $15, %zmm2, %zmm2, %zmm2
+; KNL-NEXT: vpternlogq {{.*#+}} zmm2 = ~zmm2
; KNL-NEXT: cmpb $0, 736(%rbp)
; KNL-NEXT: vmovdqa %ymm0, {{[0-9]+}}(%rsp)
; KNL-NEXT: vmovdqa %ymm2, {{[0-9]+}}(%rsp)
@@ -2063,12 +2063,12 @@ define i128 @test_insertelement_variable_v128i1(<128 x i8> %a, i8 %b, i32 %index
; KNL-NEXT: vpcmpeqb %ymm3, %ymm2, %ymm2
; KNL-NEXT: vpcmpeqb %ymm3, %ymm0, %ymm0
; KNL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
-; KNL-NEXT: vpternlogq $15, %zmm0, %zmm0, %zmm0
+; KNL-NEXT: vpternlogq {{.*#+}} zmm0 = ~zmm0
; KNL-NEXT: vextracti64x4 $1, %zmm1, %ymm2
; KNL-NEXT: vpcmpeqb %ymm3, %ymm2, %ymm2
; KNL-NEXT: vpcmpeqb %ymm3, %ymm1, %ymm1
; KNL-NEXT: vinserti64x4 $1, %ymm2, %zmm1, %zmm1
-; KNL-NEXT: vpternlogq $15, %zmm1, %zmm1, %zmm1
+; KNL-NEXT: vpternlogq {{.*#+}} zmm1 = ~zmm1
; KNL-NEXT: andl $127, %esi
; KNL-NEXT: testb %dil, %dil
; KNL-NEXT: vmovdqa64 %zmm1, {{[0-9]+}}(%rsp)
@@ -2166,7 +2166,7 @@ define void @test_concat_v2i1(ptr %arg, ptr %arg1, ptr %arg2) nounwind {
; KNL-NEXT: vcmpltps %zmm0, %zmm1, %k1
; KNL-NEXT: kandw %k1, %k0, %k1
; KNL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
-; KNL-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z}
+; KNL-NEXT: vpternlogd {{.*#+}} zmm1 {%k1} {z} = -1
; KNL-NEXT: vpmovdw %zmm1, %ymm1
; KNL-NEXT: vpand %xmm0, %xmm1, %xmm0
; KNL-NEXT: vmovd %xmm0, (%rdx)
diff --git a/llvm/test/CodeGen/X86/fminimum-fmaximum.ll b/llvm/test/CodeGen/X86/fminimum-fmaximum.ll
index 07701f082b0e22..77d7cdb3ac879f 100644
--- a/llvm/test/CodeGen/X86/fminimum-fmaximum.ll
+++ b/llvm/test/CodeGen/X86/fminimum-fmaximum.ll
@@ -207,7 +207,7 @@ define float @test_fmaximum_nnan(float %x, float %y) nounwind {
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vaddss %xmm1, %xmm0, %xmm2
; AVX512DQ-NEXT: vsubss %xmm1, %xmm0, %xmm0
-; AVX512DQ-NEXT: vfpclassss $3, %xmm0, %k0
+; AVX512DQ-NEXT: vfpclassss $3, %xmm0, %k0 # k0 = isQuietNaN(xmm0) | isPositiveZero(xmm0)
; AVX512DQ-NEXT: kmovw %k0, %k1
; AVX512DQ-NEXT: vmovaps %xmm2, %xmm1
; AVX512DQ-NEXT: vmovss %xmm0, %xmm1, %xmm1 {%k1}
@@ -466,7 +466,7 @@ define float @test_fmaximum_combine_cmps(float %x, float %y) nounwind {
; AVX512DQ-LABEL: test_fmaximum_combine_cmps:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vdivss %xmm0, %xmm1, %xmm1
-; AVX512DQ-NEXT: vfpclassss $3, %xmm0, %k0
+; AVX512DQ-NEXT: vfpclassss $3, %xmm0, %k0 # k0 = isQuietNaN(xmm0) | isPositiveZero(xmm0)
; AVX512DQ-NEXT: kmovw %k0, %k1
; AVX512DQ-NEXT: vmovaps %xmm1, %xmm2
; AVX512DQ-NEXT: vmovss %xmm0, %xmm2, %xmm2 {%k1}
@@ -687,7 +687,7 @@ define double @test_fminimum_nnan(double %x, double %y) "no-nans-fp-math"="true"
;
; AVX512DQ-LABEL: test_fminimum_nnan:
; AVX512DQ: # %bb.0:
-; AVX512DQ-NEXT: vfpclasssd $5, %xmm1, %k0
+; AVX512DQ-NEXT: vfpclasssd $5, %xmm1, %k0 # k0 = isQuietNaN(xmm1) | isNegativeZero(xmm1)
; AVX512DQ-NEXT: kmovw %k0, %k1
; AVX512DQ-NEXT: vmovapd %xmm0, %xmm2
; AVX512DQ-NEXT: vmovsd %xmm1, %xmm2, %xmm2 {%k1}
@@ -940,7 +940,7 @@ define float @test_fminimum_combine_cmps(float %x, float %y) nounwind {
; AVX512DQ-LABEL: test_fminimum_combine_cmps:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vdivss %xmm0, %xmm1, %xmm1
-; AVX512DQ-NEXT: vfpclassss $5, %xmm0, %k0
+; AVX512DQ-NEXT: vfpclassss $5, %xmm0, %k0 # k0 = isQuietNaN(xmm0) | isNegativeZero(xmm0)
; AVX512DQ-NEXT: kmovw %k0, %k1
; AVX512DQ-NEXT: vmovaps %xmm1, %xmm2
; AVX512DQ-NEXT: vmovss %xmm0, %xmm2, %xmm2 {%k1}
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.