[llvm] e6a7e3b - [X86][SSE] matchShuffleWithSHUFPD - add support for unary shuffles.

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2020-03-10T15:42:36Z
New Revision: e6a7e3b5e3e779a3bfb617c8d9ed4302edab2cef

URL: https://github.com/llvm/llvm-project/commit/e6a7e3b5e3e779a3bfb617c8d9ed4302edab2cef
DIFF: https://github.com/llvm/llvm-project/commit/e6a7e3b5e3e779a3bfb617c8d9ed4302edab2cef.diff

LOG: [X86][SSE] matchShuffleWithSHUFPD - add support for unary shuffles.

This causes one minor test change but is mainly necessary for an upcoming patch.

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86ISelLowering.cpp
    llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index e4533e0d37d0..8297935d7ebf 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -15942,6 +15942,7 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
   // Mask for V8F64: 0/1,  8/9,  2/3,  10/11, 4/5, ..
   // Mask for V4F64; 0/1,  4/5,  2/3,  6/7..
   ShuffleImm = 0;
+  bool UnaryMask = isUndefOrZeroOrInRange(Mask, 0, NumElts);
   bool ShufpdMask = true;
   bool CommutableMask = true;
   for (int i = 0; i < NumElts; ++i) {
@@ -15949,7 +15950,7 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
       continue;
     if (Mask[i] < 0)
       return false;
-    int Val = (i & 6) + NumElts * (i & 1);
+    int Val = (i & 6) + (UnaryMask ? 0 : (NumElts * (i & 1)));
     int CommutVal = (i & 0xe) + NumElts * ((i & 1) ^ 1);
     if (Mask[i] < Val || Mask[i] > Val + 1)
       ShufpdMask = false;
@@ -15961,7 +15962,9 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
   if (!ShufpdMask && !CommutableMask)
     return false;
 
-  if (!ShufpdMask && CommutableMask)
+  if (UnaryMask)
+    V2 = V1;
+  else if (!ShufpdMask && CommutableMask)
     std::swap(V1, V2);
 
   ForceV1Zero = ZeroLane[0];

diff  --git a/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll b/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
index 85400656e2e5..5f9dbdf888a3 100644
--- a/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
+++ b/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
@@ -2791,7 +2791,7 @@ define void @test_mm_storeh_pi(x86_mmx *%a0, <4 x float> %a1) nounwind {
 ;
 ; X64-SSE2-LABEL: test_mm_storeh_pi:
 ; X64-SSE2:       # %bb.0:
-; X64-SSE2-NEXT:    pshufd $78, %xmm0, %xmm0 # encoding: [0x66,0x0f,0x70,0xc0,0x4e]
+; X64-SSE2-NEXT:    shufps $78, %xmm0, %xmm0 # encoding: [0x0f,0xc6,0xc0,0x4e]
 ; X64-SSE2-NEXT:    # xmm0 = xmm0[2,3,0,1]
 ; X64-SSE2-NEXT:    movq %xmm0, %rax # encoding: [0x66,0x48,0x0f,0x7e,0xc0]
 ; X64-SSE2-NEXT:    movq %rax, (%rdi) # encoding: [0x48,0x89,0x07]