[llvm-commits] [llvm] r137296 - in /llvm/trunk: lib/Target/X86/X86ISelLowering.cpp test/CodeGen/X86/avx-splat.ll

[Bruno Cardoso Lopes]

Author: bruno
Date: Wed Aug 10 21:49:44 2011
New Revision: 137296

URL: http://llvm.org/viewvc/llvm-project?rev=137296&view=rev
Log:
Splats for v8i32/v8f32 can be handled by VPERMILPSY. This was causing
infinite recursive calls in legalize. Fix PR10562

Modified:
    llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
    llvm/trunk/test/CodeGen/X86/avx-splat.ll

Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=137296&r1=137295&r2=137296&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Wed Aug 10 21:49:44 2011
@@ -4066,11 +4066,11 @@
   return DAG.getVectorShuffle(VT, dl, V1, V2, &Mask[0]);
 }
 
-// PromoteSplatv8v16 - All i16 and i8 vector types can't be used directly by
+// PromoteSplati8i16 - All i16 and i8 vector types can't be used directly by
 // a generic shuffle instruction because the target has no such instructions.
 // Generate shuffles which repeat i16 and i8 several times until they can be
 // represented by v4f32 and then be manipulated by target suported shuffles.
-static SDValue PromoteSplatv8v16(SDValue V, SelectionDAG &DAG, int &EltNo) {
+static SDValue PromoteSplati8i16(SDValue V, SelectionDAG &DAG, int &EltNo) {
   EVT VT = V.getValueType();
   int NumElems = VT.getVectorNumElements();
   DebugLoc dl = V.getDebugLoc();
@@ -4162,8 +4162,9 @@
   }
 
   // Make this 128-bit vector duplicate i8 and i16 elements
-  if (NumElems > 4)
-    V1 = PromoteSplatv8v16(V1, DAG, EltNo);
+  EVT EltVT = SrcVT.getVectorElementType();
+  if (NumElems > 4 && (EltVT == MVT::i8 || EltVT == MVT::i16))
+    V1 = PromoteSplati8i16(V1, DAG, EltNo);
 
   // Recreate the 256-bit vector and place the same 128-bit vector
   // into the low and high part. This is necessary because we want
@@ -6027,8 +6028,7 @@
       return PromoteVectorToScalarSplat(SVOp, DAG);
 
     // Handle splats by matching through known shuffle masks
-    if ((VT.is128BitVector() && NumElem <= 4) ||
-        (VT.is256BitVector() && NumElem <= 8))
+    if (VT.is128BitVector() && NumElem <= 4)
       return SDValue();
 
     // All i16 and i8 vector types can't be used directly by a generic shuffle

Modified: llvm/trunk/test/CodeGen/X86/avx-splat.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx-splat.ll?rev=137296&r1=137295&r2=137296&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx-splat.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx-splat.ll Wed Aug 10 21:49:44 2011
@@ -51,8 +51,9 @@
 ; To:
 ;   shuffle (vload ptr)), undef, <1, 1, 1, 1>
 ; CHECK: vmovaps
-; CHECK-NEXT: vpextrd
-define void @funcE() nounwind {
+; CHECK-NEXT: vinsertf128  $1
+; CHECK-NEXT: vpermilps $-1
+define <8 x float> @funcE() nounwind {
 allocas:
   %udx495 = alloca [18 x [18 x float]], align 32
   br label %for_test505.preheader
@@ -74,7 +75,7 @@
 
 __load_and_broadcast_32.exit1249:                 ; preds = %load.i1247, %for_exit499
   %load_broadcast12281250 = phi <8 x float> [ %phitmp, %load.i1247 ], [ undef, %for_exit499 ]
-  ret void
+  ret <8 x float> %load_broadcast12281250
 }
 
 ; CHECK: vpshufd  $0
@@ -87,3 +88,20 @@
   ret <8 x float> %tmp
 }
 
+; CHECK: vinsertf128  $1
+; CHECK-NEXT: vpermilps  $0
+define <8 x float> @funcG(<8 x float> %a) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
+  ret <8 x float> %shuffle
+}
+
+; CHECK: vextractf128  $1
+; CHECK-NEXT: vinsertf128  $1
+; CHECK-NEXT: vpermilps  $85
+define <8 x float> @funcH(<8 x float> %a) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+  ret <8 x float> %shuffle
+}
+