[PATCH] D59777: [x86] improve AVX lowering of vector zext

[Sanjay Patel via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL357129: [x86] improve AVX lowering of vector zext (authored by spatel, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D59777?vs=192158&id=192529#toc

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59777/new/

https://reviews.llvm.org/D59777

Files:
  llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
  llvm/trunk/test/CodeGen/X86/vector-zext.ll


Index: llvm/trunk/test/CodeGen/X86/vector-zext.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/vector-zext.ll
+++ llvm/trunk/test/CodeGen/X86/vector-zext.ll
@@ -2594,10 +2594,8 @@
 ; AVX1-LABEL: splatshuf_zext_v4i64:
 ; AVX1:       # %bb.0:
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm1 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatshuf_zext_v4i64:
@@ -2649,11 +2647,8 @@
 ;
 ; AVX1-LABEL: splatshuf_zext_v8i32_matching_undefs:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,6,7,6,7,14,15,0,1,6,7,6,7,14,15]
-; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1],zero,zero,xmm0[6,7],zero,zero,xmm0[6,7],zero,zero,xmm0[14,15],zero,zero
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatshuf_zext_v8i32_matching_undefs:
@@ -2754,11 +2749,8 @@
 ;
 ; AVX1-LABEL: splatshuf_zext_v16i16:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14]
-; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm1 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
-; AVX1-NEXT:    vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14],zero,xmm0[14],zero,xmm0[14],zero,xmm0[14],zero,xmm0[14],zero,xmm0[14],zero,xmm0[14],zero,xmm0[14],zero
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatshuf_zext_v16i16:
Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -9883,6 +9883,20 @@
   return false;
 }
 
+/// Return true if a shuffle mask chooses elements identically in its top and
+/// bottom halves. For example, any splat mask has the same top and bottom
+/// halves. If an element is undefined in only one half of the mask, the halves
+/// are not considered identical.
+static bool hasIdenticalHalvesShuffleMask(ArrayRef<int> Mask) {
+  assert(Mask.size() % 2 == 0 && "Expecting even number of elements in mask");
+  unsigned HalfSize = Mask.size() / 2;
+  for (unsigned i = 0; i != HalfSize; ++i) {
+    if (Mask[i] != Mask[i + HalfSize])
+      return false;
+  }
+  return true;
+}
+
 /// Get a 4-lane 8-bit shuffle immediate for a mask.
 ///
 /// This helper function produces an 8-bit shuffle immediate corresponding to
@@ -18369,6 +18383,12 @@
 
   SDValue OpLo = DAG.getNode(ISD::ZERO_EXTEND_VECTOR_INREG, dl, HalfVT, In);
 
+  // Short-circuit if we can determine that each 128-bit half is the same value.
+  // Otherwise, this is difficult to match and optimize.
+  if (auto *Shuf = dyn_cast<ShuffleVectorSDNode>(In))
+    if (hasIdenticalHalvesShuffleMask(Shuf->getMask()))
+      return DAG.getNode(ISD::CONCAT_VECTORS, dl, VT, OpLo, OpLo);
+
   SDValue ZeroVec = DAG.getConstant(0, dl, InVT);
   SDValue Undef = DAG.getUNDEF(InVT);
   bool NeedZero = Op.getOpcode() == ISD::ZERO_EXTEND;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59777.192529.patch
Type: text/x-patch
Size: 3892 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190327/897af4a8/attachment.bin>