[llvm] r222635 - [X86] Fixes bug in build_vector v4x32 lowering

[Michael Kuperstein]

Author: mkuper
Date: Sun Nov 23 07:09:06 2014
New Revision: 222635

URL: http://llvm.org/viewvc/llvm-project?rev=222635&view=rev
Log:
[X86] Fixes bug in build_vector v4x32 lowering

r222375 made some improvements to build_vector lowering of v4x32 and v4xf32 into an insertps, but it missed a case where:

1. A single extracted element is used twice.
2. The lower of the two non-zero indexes should be preserved, and the higher should be used for the dest mask.

This caused a crash, since the source value for the insertps ends-up uninitialized.

Differential Revision: http://reviews.llvm.org/D6377

Modified:
    llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
    llvm/trunk/test/CodeGen/X86/sse41.ll

Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=222635&r1=222634&r2=222635&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Sun Nov 23 07:09:06 2014
@@ -5771,7 +5771,8 @@ static SDValue LowerBuildVectorv4x32(SDV
   // We only know how to deal with build_vector nodes where elements are either
   // zeroable or extract_vector_elt with constant index.
   SDValue FirstNonZero;
-  for (int i=0; i < 4; ++i) {
+  unsigned FirstNonZeroIdx;
+  for (unsigned i=0; i < 4; ++i) {
     if (Zeroable[i])
       continue;
     SDValue Elt = Op->getOperand(i);
@@ -5782,8 +5783,10 @@ static SDValue LowerBuildVectorv4x32(SDV
     MVT VT = Elt.getOperand(0).getSimpleValueType();
     if (!VT.is128BitVector())
       return SDValue();
-    if (!FirstNonZero.getNode())
+    if (!FirstNonZero.getNode()) {
       FirstNonZero = Elt;
+      FirstNonZeroIdx = i;
+    }
   }
 
   assert(FirstNonZero.getNode() && "Unexpected build vector of all zeros!");
@@ -5822,7 +5825,7 @@ static SDValue LowerBuildVectorv4x32(SDV
     return SDValue();
 
   SDValue V2 = Elt.getOperand(0);
-  if (Elt == FirstNonZero)
+  if (Elt == FirstNonZero && EltIdx == FirstNonZeroIdx)
     V1 = SDValue();
 
   bool CanFold = true;

Modified: llvm/trunk/test/CodeGen/X86/sse41.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/sse41.ll?rev=222635&r1=222634&r2=222635&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/sse41.ll (original)
+++ llvm/trunk/test/CodeGen/X86/sse41.ll Sun Nov 23 07:09:06 2014
@@ -1145,6 +1145,23 @@ entry:
   ret <4 x float> %vecinit3
 }
 
+define <4 x float> @insertps_10(<4 x float> %A)
+{
+; X32-LABEL: insertps_10:
+; X32:       ## BB#0:
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
+; X32-NEXT:    retl
+;
+; X64-LABEL: insertps_10:
+; X64:       ## BB#0:
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
+; X64-NEXT:    retq
+  %vecext = extractelement <4 x float> %A, i32 0
+  %vecbuild1 = insertelement <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %vecext, i32 0
+  %vecbuild2 = insertelement <4 x float> %vecbuild1, float %vecext, i32 2
+  ret <4 x float> %vecbuild2
+}
+
 define <4 x float> @build_vector_to_shuffle_1(<4 x float> %A) {
 ; X32-LABEL: build_vector_to_shuffle_1:
 ; X32:       ## BB#0: