aqjune created this revision.
aqjune added reviewers: efriedma, spatel, craig.topper, RKSimon.
Herald added a subscriber: pengfei.
aqjune requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
This fixes lowering of `mm*_undefined*` intrinsics to use `freeze poison`
instead of zeroinitializer.
(mentioned & discussed in D103874 <https://reviews.llvm.org/D103874>)
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D104790
Files:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/X86/avx-builtins.c
clang/test/CodeGen/X86/avx2-builtins.c
clang/test/CodeGen/X86/avx512f-builtins.c
clang/test/CodeGen/X86/sse-builtins.c
clang/test/CodeGen/X86/sse2-builtins.c
Index: clang/test/CodeGen/X86/sse2-builtins.c
===================================================================
--- clang/test/CodeGen/X86/sse2-builtins.c
+++ clang/test/CodeGen/X86/sse2-builtins.c
@@ -1630,13 +1630,16 @@
__m128d test_mm_undefined_pd() {
// CHECK-LABEL: test_mm_undefined_pd
- // CHECK: ret <2 x double> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: ret <2 x double> %[[FR]]
return _mm_undefined_pd();
}
__m128i test_mm_undefined_si128() {
// CHECK-LABEL: test_mm_undefined_si128
- // CHECK: ret <2 x i64> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <2 x i64>
+ // CHECK: ret <2 x i64> %[[FR_BC]]
return _mm_undefined_si128();
}
Index: clang/test/CodeGen/X86/sse-builtins.c
===================================================================
--- clang/test/CodeGen/X86/sse-builtins.c
+++ clang/test/CodeGen/X86/sse-builtins.c
@@ -786,7 +786,9 @@
__m128 test_mm_undefined_ps() {
// CHECK-LABEL: test_mm_undefined_ps
- // CHECK: ret <4 x float> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <4 x float>
+ // CHECK: ret <4 x float> %[[FR_BC]]
return _mm_undefined_ps();
}
Index: clang/test/CodeGen/X86/avx512f-builtins.c
===================================================================
--- clang/test/CodeGen/X86/avx512f-builtins.c
+++ clang/test/CodeGen/X86/avx512f-builtins.c
@@ -3780,25 +3780,32 @@
__m512 test_mm512_undefined() {
// CHECK-LABEL: @test_mm512_undefined
- // CHECK: ret <16 x float> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <8 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <8 x double> %[[FR]] to <16 x float>
+ // CHECK: ret <16 x float> %[[FR_BC]]
return _mm512_undefined();
}
__m512 test_mm512_undefined_ps() {
// CHECK-LABEL: @test_mm512_undefined_ps
- // CHECK: ret <16 x float> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <8 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <8 x double> %[[FR]] to <16 x float>
+ // CHECK: ret <16 x float> %[[FR_BC]]
return _mm512_undefined_ps();
}
__m512d test_mm512_undefined_pd() {
// CHECK-LABEL: @test_mm512_undefined_pd
- // CHECK: ret <8 x double> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <8 x double> poison
+ // CHECK: ret <8 x double> %[[FR]]
return _mm512_undefined_pd();
}
__m512i test_mm512_undefined_epi32() {
// CHECK-LABEL: @test_mm512_undefined_epi32
- // CHECK: ret <8 x i64> zeroinitializer
+ // CHECK: %[[FR:.*]] = freeze <8 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <8 x double> %[[FR]] to <8 x i64>
+ // CHECK: ret <8 x i64> %[[FR_BC]]
return _mm512_undefined_epi32();
}
Index: clang/test/CodeGen/X86/avx2-builtins.c
===================================================================
--- clang/test/CodeGen/X86/avx2-builtins.c
+++ clang/test/CodeGen/X86/avx2-builtins.c
@@ -455,7 +455,9 @@
__m128i test_mm_i32gather_epi64(long long const *b, __m128i c) {
// CHECK-LABEL: test_mm_i32gather_epi64
- // CHECK: call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <2 x i64>
+ // CHECK: call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> %[[FR_BC]], i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
return _mm_i32gather_epi64(b, c, 2);
}
@@ -467,7 +469,9 @@
__m256i test_mm256_i32gather_epi64(long long const *b, __m128i c) {
// CHECK-LABEL: test_mm256_i32gather_epi64
- // CHECK: call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
+ // CHECK: %[[FR:.*]] = freeze <4 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <4 x double> %[[FR]] to <4 x i64>
+ // CHECK: call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> %[[FR_BC]], i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
return _mm256_i32gather_epi64(b, c, 2);
}
@@ -479,10 +483,11 @@
__m128d test_mm_i32gather_pd(double const *b, __m128i c) {
// CHECK-LABEL: test_mm_i32gather_pd
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
// CHECK: [[CMP:%.*]] = fcmp oeq <2 x double>
// CHECK-NEXT: [[SEXT:%.*]] = sext <2 x i1> [[CMP]] to <2 x i64>
// CHECK-NEXT: [[BC:%.*]] = bitcast <2 x i64> [[SEXT]] to <2 x double>
- // CHECK: call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x double> %{{.*}}, i8 2)
+ // CHECK: call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> %[[FR]], i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x double> %{{.*}}, i8 2)
return _mm_i32gather_pd(b, c, 2);
}
@@ -494,10 +499,11 @@
__m256d test_mm256_i32gather_pd(double const *b, __m128i c) {
// CHECK-LABEL: test_mm256_i32gather_pd
+ // CHECK: %[[FR:.*]] = freeze <4 x double> poison
// CHECK: [[CMP:%.*]] = fcmp oeq <4 x double>
// CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i64>
// CHECK-NEXT: [[BC:%.*]] = bitcast <4 x i64> [[SEXT]] to <4 x double>
- // CHECK: call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x double> %{{.*}}, i8 2)
+ // CHECK: call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> %[[FR]], i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x double> %{{.*}}, i8 2)
return _mm256_i32gather_pd(b, c, 2);
}
@@ -509,10 +515,12 @@
__m128 test_mm_i32gather_ps(float const *b, __m128i c) {
// CHECK-LABEL: test_mm_i32gather_ps
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <4 x float>
// CHECK: [[CMP:%.*]] = fcmp oeq <4 x float>
// CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
// CHECK-NEXT: [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
- // CHECK: call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+ // CHECK: call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> %[[FR_BC]], i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x float> %{{.*}}, i8 2)
return _mm_i32gather_ps(b, c, 2);
}
@@ -524,10 +532,12 @@
__m256 test_mm256_i32gather_ps(float const *b, __m256i c) {
// CHECK-LABEL: test_mm256_i32gather_ps
+ // CHECK: %[[FR:.*]] = freeze <4 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <4 x double> %[[FR]] to <8 x float>
// CHECK: [[CMP:%.*]] = fcmp oeq <8 x float>
// CHECK-NEXT: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
// CHECK-NEXT: [[BC:%.*]] = bitcast <8 x i32> [[SEXT]] to <8 x float>
- // CHECK: call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> zeroinitializer, i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x float> %{{.*}}, i8 2)
+ // CHECK: call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %[[FR_BC]], i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x float> %{{.*}}, i8 2)
return _mm256_i32gather_ps(b, c, 2);
}
@@ -563,7 +573,9 @@
__m128i test_mm_i64gather_epi64(long long const *b, __m128i c) {
// CHECK-LABEL: test_mm_i64gather_epi64
- // CHECK: call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <2 x i64>
+ // CHECK: call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> %[[FR_BC]], i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
return _mm_i64gather_epi64(b, c, 2);
}
@@ -575,7 +587,9 @@
__m256i test_mm256_i64gather_epi64(long long const *b, __m256i c) {
// CHECK-LABEL: test_mm256_i64gather_epi64
- // CHECK: call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
+ // CHECK: %[[FR:.*]] = freeze <4 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <4 x double> %[[FR]] to <4 x i64>
+ // CHECK: call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> %[[FR_BC]], i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
return _mm256_i64gather_epi64(b, c, 2);
}
@@ -587,10 +601,11 @@
__m128d test_mm_i64gather_pd(double const *b, __m128i c) {
// CHECK-LABEL: test_mm_i64gather_pd
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
// CHECK: [[CMP:%.*]] = fcmp oeq <2 x double>
// CHECK-NEXT: [[SEXT:%.*]] = sext <2 x i1> [[CMP]] to <2 x i64>
// CHECK-NEXT: [[BC:%.*]] = bitcast <2 x i64> [[SEXT]] to <2 x double>
- // CHECK: call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x double> %{{.*}}, i8 2)
+ // CHECK: call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> %[[FR]], i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x double> %{{.*}}, i8 2)
return _mm_i64gather_pd(b, c, 2);
}
@@ -602,8 +617,9 @@
__m256d test_mm256_i64gather_pd(double const *b, __m256i c) {
// CHECK-LABEL: test_mm256_i64gather_pd
+ // CHECK: %[[FR:.*]] = freeze <4 x double> poison
// CHECK: fcmp oeq <4 x double> %{{.*}}, %{{.*}}
- // CHECK: call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x double> %{{.*}}, i8 2)
+ // CHECK: call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> %[[FR]], i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x double> %{{.*}}, i8 2)
return _mm256_i64gather_pd(b, c, 2);
}
@@ -615,10 +631,12 @@
__m128 test_mm_i64gather_ps(float const *b, __m128i c) {
// CHECK-LABEL: test_mm_i64gather_ps
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <4 x float>
// CHECK: [[CMP:%.*]] = fcmp oeq <4 x float>
// CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
// CHECK-NEXT: [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
- // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+ // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> %[[FR_BC]], i8* %{{.*}}, <2 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
return _mm_i64gather_ps(b, c, 2);
}
@@ -630,10 +648,12 @@
__m128 test_mm256_i64gather_ps(float const *b, __m256i c) {
// CHECK-LABEL: test_mm256_i64gather_ps
+ // CHECK: %[[FR:.*]] = freeze <2 x double> poison
+ // CHECK: %[[FR_BC:.*]] = bitcast <2 x double> %[[FR]] to <4 x float>
// CHECK: [[CMP:%.*]] = fcmp oeq <4 x float>
// CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
// CHECK-NEXT: [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
- // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+ // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> %[[FR_BC]], i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
return _mm256_i64gather_ps(b, c, 2);
}
Index: clang/test/CodeGen/X86/avx-builtins.c
===================================================================
--- clang/test/CodeGen/X86/avx-builtins.c
+++ clang/test/CodeGen/X86/avx-builtins.c
@@ -2063,19 +2063,24 @@
__m256 test_mm256_undefined_ps() {
// CHECK-LABEL: test_mm256_undefined_ps
- // CHECK: ret <8 x float> zeroinitializer
+ // CHECK: freeze <4 x double> poison
+ // CHECK: bitcast <4 x double> %{{.*}} to <8 x float>
+ // CHECK: ret <8 x float> %{{.*}}
return _mm256_undefined_ps();
}
__m256d test_mm256_undefined_pd() {
// CHECK-LABEL: test_mm256_undefined_pd
- // CHECK: ret <4 x double> zeroinitializer
+ // CHECK: freeze <4 x double> poison
+ // CHECK: ret <4 x double> %{{.*}}
return _mm256_undefined_pd();
}
__m256i test_mm256_undefined_si256() {
// CHECK-LABEL: test_mm256_undefined_si256
- // CHECK: ret <4 x i64> zeroinitializer
+ // CHECK: freeze <4 x double> poison
+ // CHECK: bitcast <4 x double> %{{.*}} to <4 x i64>
+ // CHECK: ret <4 x i64> %{{.*}}
return _mm256_undefined_si256();
}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -12491,12 +12491,9 @@
case X86::BI__builtin_ia32_undef128:
case X86::BI__builtin_ia32_undef256:
case X86::BI__builtin_ia32_undef512:
- // The x86 definition of "undef" is not the same as the LLVM definition
- // (PR32176). We leave optimizing away an unnecessary zero constant to the
- // IR optimizer and backend.
- // TODO: If we had a "freeze" IR instruction to generate a fixed undef
- // value, we should use that here instead of a zero.
- return llvm::Constant::getNullValue(ConvertType(E->getType()));
+ // The x86 definition of "undef" is equivalent to "freeze poison" in LLVM
+ // (PR32176).
+ return Builder.CreateFreeze(PoisonValue::get(ConvertType(E->getType())));
case X86::BI__builtin_ia32_vec_init_v8qi:
case X86::BI__builtin_ia32_vec_init_v4hi:
case X86::BI__builtin_ia32_vec_init_v2si:
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
