Turn avx insert intrinsic calls into INSERT_SUBVECTOR DAG nodes and remove duplicate patterns for selecting the intrinsics

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151342 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 63 insertions, 9 deletions

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 048fc6ff08..c7d676e05e 100644
--- a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4831,6 +4831,21 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
     setValue(&I, Res);
     return 0;
   }
+  case Intrinsic::x86_avx_vinsertf128_pd_256:
+  case Intrinsic::x86_avx_vinsertf128_ps_256:
+  case Intrinsic::x86_avx_vinsertf128_si_256: {
+    DebugLoc dl = getCurDebugLoc();
+    EVT DestVT = TLI.getValueType(I.getType());
+    EVT ElVT = TLI.getValueType(I.getArgOperand(1)->getType());
+    uint64_t Idx = (cast<ConstantInt>(I.getArgOperand(2))->getZExtValue() & 1) *
+                   ElVT.getVectorNumElements();
+    Res = DAG.getNode(ISD::INSERT_SUBVECTOR, dl, DestVT,
+                      getValue(I.getArgOperand(0)),
+                      getValue(I.getArgOperand(1)),
+                      DAG.getConstant(Idx, MVT::i32));
+    setValue(&I, Res);
+    return 0;
+  }
   case Intrinsic::convertff:
   case Intrinsic::convertfsi:
   case Intrinsic::convertfui:
diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index 4a670817d3..56e997c1fb 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -6606,15 +6606,6 @@ def VINSERTF128rm : AVXAIi8<0x18, MRMSrcMem, (outs VR256:$dst),
           []>, VEX_4V;
 }
 
-let Predicates = [HasAVX] in {
-def : Pat<(int_x86_avx_vinsertf128_pd_256 VR256:$src1, VR128:$src2, imm:$src3),
-          (VINSERTF128rr VR256:$src1, VR128:$src2, imm:$src3)>;
-def : Pat<(int_x86_avx_vinsertf128_ps_256 VR256:$src1, VR128:$src2, imm:$src3),
-          (VINSERTF128rr VR256:$src1, VR128:$src2, imm:$src3)>;
-def : Pat<(int_x86_avx_vinsertf128_si_256 VR256:$src1, VR128:$src2, imm:$src3),
-          (VINSERTF128rr VR256:$src1, VR128:$src2, imm:$src3)>;
-}
-
 //===----------------------------------------------------------------------===//
 // VEXTRACTF128 - Extract packed floating-point values
 //
diff --git a/test/CodeGen/X86/avx-vinsertf128.ll b/test/CodeGen/X86/avx-vinsertf128.ll
index cda1331da3..def2212db9 100644
--- a/test/CodeGen/X86/avx-vinsertf128.ll
+++ b/test/CodeGen/X86/avx-vinsertf128.ll
@@ -56,3 +56,51 @@ define <8 x i32> @DAGCombineB(<8 x i32> %v1, <8 x i32> %v2) nounwind readonly {
   %2 = add <8 x i32> %1, %v1
   ret <8 x i32> %2
 }
+
+; CHECK: insert_pd
+define <4 x double> @insert_pd(<4 x double> %a0, <2 x double> %a1) {
+; CHECK: vinsertf128
+%res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> %a0, <2 x double> %a1, i8 0)
+ret <4 x double> %res
+}
+
+; CHECK: insert_undef_pd
+define <4 x double> @insert_undef_pd(<4 x double> %a0, <2 x double> %a1) {
+; CHECK: vmovaps	%ymm1, %ymm0
+%res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> undef, <2 x double> %a1, i8 0)
+ret <4 x double> %res
+}
+declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
+
+
+; CHECK: insert_ps
+define <8 x float> @insert_ps(<8 x float> %a0, <4 x float> %a1) {
+; CHECK: vinsertf128
+%res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> %a0, <4 x float> %a1, i8 0)
+ret <8 x float> %res
+}
+
+; CHECK: insert_undef_ps
+define <8 x float> @insert_undef_ps(<8 x float> %a0, <4 x float> %a1) {
+; CHECK: vmovaps	%ymm1, %ymm0
+%res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %a1, i8 0)
+ret <8 x float> %res
+}
+declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
+
+
+; CHECK: insert_si
+define <8 x i32> @insert_si(<8 x i32> %a0, <4 x i32> %a1) {
+; CHECK: vinsertf128
+%res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> %a0, <4 x i32> %a1, i8 0)
+ret <8 x i32> %res
+}
+
+; CHECK: insert_undef_si
+define <8 x i32> @insert_undef_si(<8 x i32> %a0, <4 x i32> %a1) {
+; CHECK: vmovaps	%ymm1, %ymm0
+%res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> undef, <4 x i32> %a1, i8 0)
+ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
+