[X86] Drop single use check for freeze(undef) in LowerAVXCONCAT_VECTORS

Ignoring freeze(undef) if it has multiple uses in LowerAVXCONCAT_VECTORS
causes the custom INSERT_SUBVECTOR for vector widening to be ignored.

Differential Revision: https://reviews.llvm.org/D144903

diff --git a/clang/test/CodeGen/X86/avx-cast-builtins.c b/clang/test/CodeGen/X86/avx-cast-builtins.c
new file mode 100644 (file)
index 0000000..edf64b8
--- /dev/null
+++ b/clang/test/CodeGen/X86/avx-cast-builtins.c
@@ -0,0 +1,100 @@
+// RUN: %clang_cc1 -O3 -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-unknown -target-feature +avx -target-feature +avx512f  -target-feature +avx512fp16 -S -o - | FileCheck %s
+
+
+#include <immintrin.h>
+
+__m256d test_mm256_castpd128_pd256(__m128d A) {
+  // CHECK-LABEL: test_mm256_castpd128_pd256
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm256_castpd128_pd256(A);
+}
+
+__m256 test_mm256_castps128_ps256(__m128 A) {
+  // CHECK-LABEL: test_mm256_castps128_ps256
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm256_castps128_ps256(A);
+}
+
+__m256i test_mm256_castsi128_si256(__m128i A) {
+  // CHECK-LABEL: test_mm256_castsi128_si256
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm256_castsi128_si256(A);
+}
+
+__m256h test_mm256_castph128_ph256(__m128h A) {
+  // CHECK-LABEL: test_mm256_castph128_ph256
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm256_castph128_ph256(A);
+}
+
+__m512h test_mm512_castph128_ph512(__m128h A) {
+  // CHECK-LABEL: test_mm512_castph128_ph512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castph128_ph512(A);
+}
+
+__m512h test_mm512_castph256_ph512(__m256h A) {
+  // CHECK-LABEL: test_mm512_castph256_ph512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castph256_ph512(A);
+}
+
+__m512d test_mm512_castpd256_pd512(__m256d A){
+  // CHECK-LABEL: test_mm512_castpd256_pd512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castpd256_pd512(A);
+}
+
+__m512 test_mm512_castps256_ps512(__m256 A){
+  // CHECK-LABEL: test_mm512_castps256_ps512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castps256_ps512(A);
+}
+
+__m512d test_mm512_castpd128_pd512(__m128d A){
+  // CHECK-LABEL: test_mm512_castpd128_pd512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castpd128_pd512(A);
+}
+
+__m512 test_mm512_castps128_ps512(__m128 A){
+  // CHECK-LABEL: test_mm512_castps128_ps512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castps128_ps512(A);
+}
+
+__m512i test_mm512_castsi128_si512(__m128i A){
+  // CHECK-LABEL: test_mm512_castsi128_si512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castsi128_si512(A);
+}
+
+__m512i test_mm512_castsi256_si512(__m256i A){
+  // CHECK-LABEL: test_mm512_castsi256_si512
+  // CHECK:         # %bb.0:
+  // CHECK-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+  // CHECK-NEXT:    ret{{[l|q]}}
+  return _mm512_castsi256_si512(A);
+}

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 4a59bba..355c5be 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -11656,7 +11656,7 @@ static SDValue LowerAVXCONCAT_VECTORS(SDValue Op, SelectionDAG &DAG,
     SDValue SubVec = Op.getOperand(i);
     if (SubVec.isUndef())
       continue;
-    if (ISD::isFreezeUndef(SubVec.getNode()) && SubVec.hasOneUse())
+    if (ISD::isFreezeUndef(SubVec.getNode()))
       ++NumFreezeUndef;
     else if (ISD::isBuildVectorAllZeros(SubVec.getNode()))
       ++NumZero;

diff --git a/llvm/test/CodeGen/X86/avx512-intrinsics.ll b/llvm/test/CodeGen/X86/avx512-intrinsics.ll
index 591256d..5d545d8 100644 (file)
--- a/llvm/test/CodeGen/X86/avx512-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx512-intrinsics.ll
@@ -7495,10 +7495,7 @@ declare <8 x i64> @llvm.x86.avx512.psrlv.q.512(<8 x i64>, <8 x i64>) nounwind re
 define <8 x double> @test_mm256_castpd128_pd256_freeze(<2 x double> %a0) nounwind {
 ; CHECK-LABEL: test_mm256_castpd128_pd256_freeze:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm1
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; CHECK-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
 ; CHECK-NEXT:    ret{{[l|q]}}
   %a1 = freeze <2 x double> poison
   %res = shufflevector <2 x double> %a0, <2 x double> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
@@ -7520,10 +7517,7 @@ define <8 x double> @test_mm256_castpd256_pd256_freeze(<4 x double> %a0) nounwin
 define <16 x float> @test_mm256_castps128_ps512_freeze(<4 x float> %a0) nounwind {
 ; CHECK-LABEL: test_mm256_castps128_ps512_freeze:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm1
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; CHECK-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
 ; CHECK-NEXT:    ret{{[l|q]}}
   %a1 = freeze <4 x float> poison
   %res = shufflevector <4 x float> %a0, <4 x float> %a1, <16x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
@@ -7545,10 +7539,7 @@ define <16 x float> @test_mm256_castps256_ps512_freeze(<8 x float> %a0) nounwind
 define <8 x i64> @test_mm512_castsi128_si512_freeze(<2 x i64> %a0) nounwind {
 ; CHECK-LABEL: test_mm512_castsi128_si512_freeze:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm1
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; CHECK-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
 ; CHECK-NEXT:    ret{{[l|q]}}
   %a1 = freeze <2 x i64> poison
   %res = shufflevector <2 x i64> %a0, <2 x i64> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>

diff --git a/llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll b/llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll
index 8ea5023..394270b 100644 (file)
--- a/llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll
@@ -1231,10 +1231,7 @@ define <16 x half> @test_mm256_castph128_ph256_freeze(<8 x half> %a0) nounwind {
 define <32 x half> @test_mm512_castph128_ph512_freeze(<8 x half> %a0) nounwind {
 ; CHECK-LABEL: test_mm512_castph128_ph512_freeze:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm1
-; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; CHECK-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
+; CHECK-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
 ; CHECK-NEXT:    retq
   %a1 = freeze <8 x half> poison
   %res = shufflevector <8 x half> %a0, <8 x half> %a1, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>