[llvm-commits] [llvm] r163018 - in /llvm/trunk: lib/Target/X86/X86ISelLowering.cpp test/CodeGen/X86/pr12359.ll

[Michael Liao]

Author: hliao
Date: Fri Aug 31 15:12:31 2012
New Revision: 163018

URL: http://llvm.org/viewvc/llvm-project?rev=163018&view=rev
Log:
Fix PR12359

- In addition to undefined, if V2 is zero vector, skip 2nd PSHUFB and POR as
  well as PSHUFB will zero elements with negative indices.

  Patch by Sriram Murali <sriram.murali at intel.com>


Added:
    llvm/trunk/test/CodeGen/X86/pr12359.ll
Modified:
    llvm/trunk/lib/Target/X86/X86ISelLowering.cpp

Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=163018&r1=163017&r2=163018&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Fri Aug 31 15:12:31 2012
@@ -5881,8 +5881,6 @@
   DebugLoc dl = SVOp->getDebugLoc();
   ArrayRef<int> MaskVals = SVOp->getMask();
 
-  bool V2IsUndef = V2.getOpcode() == ISD::UNDEF;
-
   // If we have SSSE3, case 1 is generated when all result bytes come from
   // one of  the inputs.  Otherwise, case 2 is generated.  If no SSSE3 is
   // present, fall back to case 3.
@@ -5906,7 +5904,11 @@
     V1 = DAG.getNode(X86ISD::PSHUFB, dl, MVT::v16i8, V1,
                      DAG.getNode(ISD::BUILD_VECTOR, dl,
                                  MVT::v16i8, &pshufbMask[0], 16));
-    if (V2IsUndef)
+
+    // As PSHUFB will zero elements with negative indices, it's safe to ignore
+    // the 2nd operand if it's undefined or zero.
+    if (V2.getOpcode() == ISD::UNDEF ||
+        ISD::isBuildVectorAllZeros(V2.getNode()))
       return V1;
 
     // Calculate the shuffle mask for the second input, shuffle it, and

Added: llvm/trunk/test/CodeGen/X86/pr12359.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/pr12359.ll?rev=163018&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/X86/pr12359.ll (added)
+++ llvm/trunk/test/CodeGen/X86/pr12359.ll Fri Aug 31 15:12:31 2012
@@ -0,0 +1,10 @@
+; RUN: llc -asm-verbose -mtriple=x86_64-unknown-unknown -mcpu=corei7 < %s | FileCheck %s
+define <16 x i8> @shuf(<16 x i8> %inval1) {
+entry:
+  %0 = shufflevector <16 x i8> %inval1, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 4, i32 3, i32 2, i32 16, i32 16, i32 3, i32 4, i32 0, i32 4, i32 3, i32 2, i32 16, i32 16, i32 3, i32 4>
+  ret <16 x i8> %0
+; CHECK: shuf
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: pshufb
+; CHECK-NEXT: ret
+}