[X86][AVX] Added support for lowering to VBROADCASTF128/VBROADCASTI128 with generic IR

As discussed on D22460, I've updated the vbroadcastf128 pd256/ps256 builtins to map directly to generic IR - load+splat a 128-bit vector to both lanes of a 256-bit vector.

Fix for PR28657.

llvm-svn: 276417

2 files changed, 31 insertions, 2 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index c74e53ea84e..fb3240b2522 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -6619,6 +6619,26 @@ static Value *EmitX86MaskedLoad(CodeGenFunction &CGF,
   return CGF.Builder.CreateMaskedLoad(Ops[0], Align, MaskVec, Ops[1]);
 }
 
+static Value *EmitX86SubVectorBroadcast(CodeGenFunction &CGF,
+                                        SmallVectorImpl<Value *> &Ops,
+                                        llvm::Type *DstTy,
+                                        unsigned SrcSizeInBits,
+                                        unsigned Align) {
+  // Load the subvector.
+  Ops[0] = CGF.Builder.CreateAlignedLoad(Ops[0], Align);
+
+  // Create broadcast mask.
+  unsigned NumDstElts = DstTy->getVectorNumElements();
+  unsigned NumSrcElts = SrcSizeInBits / DstTy->getScalarSizeInBits();
+
+  SmallVector<uint32_t, 8> Mask;
+  for (unsigned i = 0; i != NumDstElts; i += NumSrcElts)
+    for (unsigned j = 0; j != NumSrcElts; ++j)
+      Mask.push_back(j);
+
+  return CGF.Builder.CreateShuffleVector(Ops[0], Ops[0], Mask, "subvecbcst");
+}
+
 static Value *EmitX86Select(CodeGenFunction &CGF,
                             Value *Mask, Value *Op0, Value *Op1) {
 
@@ -6995,6 +7015,13 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
       getContext().getTypeAlignInChars(E->getArg(1)->getType()).getQuantity();
     return EmitX86MaskedLoad(*this, Ops, Align);
   }
+
+  case X86::BI__builtin_ia32_vbroadcastf128_pd256:
+  case X86::BI__builtin_ia32_vbroadcastf128_ps256: {
+    llvm::Type *DstTy = ConvertType(E->getType());
+    return EmitX86SubVectorBroadcast(*this, Ops, DstTy, 128, 16);
+  }
+
   case X86::BI__builtin_ia32_storehps:
   case X86::BI__builtin_ia32_storelps: {
     llvm::Type *PtrTy = llvm::PointerType::getUnqual(Int64Ty);
diff --git a/clang/test/CodeGen/avx-builtins.c b/clang/test/CodeGen/avx-builtins.c
index 650e4d280ec..4abeacd17ca 100644
--- a/clang/test/CodeGen/avx-builtins.c
+++ b/clang/test/CodeGen/avx-builtins.c
@@ -84,13 +84,15 @@ __m256 test_mm256_blendv_ps(__m256 V1, __m256 V2, __m256 V3) {
 
 __m256d test_mm256_broadcast_pd(__m128d* A) {
   // CHECK-LABEL: test_mm256_broadcast_pd
-  // CHECK: call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %{{.*}})
+  // CHECK: load <2 x double>, <2 x double>* %{{.*}}, align 16
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
   return _mm256_broadcast_pd(A);
 }
 
 __m256 test_mm256_broadcast_ps(__m128* A) {
   // CHECK-LABEL: test_mm256_broadcast_ps
-  // CHECK: call <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8* %{{.*}})
+  // CHECK: load <4 x float>, <4 x float>* %{{.*}}, align 16
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
   return _mm256_broadcast_ps(A);
 }