[llvm-commits] [llvm] r151342 - in /llvm/trunk: lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp lib/Target/X86/X86InstrSSE.td test/CodeGen/X86/avx-vinsertf128.ll

Pete Cooper peter_cooper at apple.com
Thu Feb 23 19:51:49 PST 2012


Author: pete
Date: Thu Feb 23 21:51:49 2012
New Revision: 151342

URL: http://llvm.org/viewvc/llvm-project?rev=151342&view=rev
Log:
Turn avx insert intrinsic calls into INSERT_SUBVECTOR DAG nodes and remove duplicate patterns for selecting the intrinsics

Modified:
    llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
    llvm/trunk/lib/Target/X86/X86InstrSSE.td
    llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll

Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp?rev=151342&r1=151341&r2=151342&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Thu Feb 23 21:51:49 2012
@@ -4831,6 +4831,21 @@
     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:

Modified: llvm/trunk/lib/Target/X86/X86InstrSSE.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrSSE.td?rev=151342&r1=151341&r2=151342&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrSSE.td (original)
+++ llvm/trunk/lib/Target/X86/X86InstrSSE.td Thu Feb 23 21:51:49 2012
@@ -6606,15 +6606,6 @@
           []>, 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
 //

Modified: llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll?rev=151342&r1=151341&r2=151342&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll Thu Feb 23 21:51:49 2012
@@ -56,3 +56,51 @@
   %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
+





More information about the llvm-commits mailing list