Define AVX 128-bit pattern versions of SET0PS/PD.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110937 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index d3e2181d7c6a4f0dc5c5f7044639203a5b53f10e..8fc53c6fcb71e958d5bf0b95f7c5db61c52ce6fe 100644 (file)
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -2186,12 +2186,21 @@ def V_SET0PI : PDI<0xEF, MRMInitReg, (outs VR128:$dst), (ins), "",
                  [(set VR128:$dst, (v4i32 immAllZerosV))]>;
 }
 
+// The same as done above but for AVX. The 128-bit versions are the
+// same, but re-encoded. The 256-bit does not support PI version.
 let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
     isCodeGenOnly = 1, Predicates = [HasAVX] in {
-def V_SET0PSY : PSI<0x57, MRMInitReg, (outs VR256:$dst), (ins), "",
-                 [(set VR256:$dst, (v8f32 immAllZerosV))]>, VEX_4V;
-def V_SET0PDY : PDI<0x57, MRMInitReg, (outs VR256:$dst), (ins), "",
-                 [(set VR256:$dst, (v4f64 immAllZerosV))]>, VEX_4V;
+def AVX_SET0PS  : PSI<0x57, MRMInitReg, (outs VR128:$dst), (ins), "",
+                   [(set VR128:$dst, (v4f32 immAllZerosV))]>, VEX_4V;
+def AVX_SET0PD  : PDI<0x57, MRMInitReg, (outs VR128:$dst), (ins), "",
+                   [(set VR128:$dst, (v2f64 immAllZerosV))]>, VEX_4V;
+def AVX_SET0PSY : PSI<0x57, MRMInitReg, (outs VR256:$dst), (ins), "",
+                   [(set VR256:$dst, (v8f32 immAllZerosV))]>, VEX_4V;
+def AVX_SET0PDY : PDI<0x57, MRMInitReg, (outs VR256:$dst), (ins), "",
+                   [(set VR256:$dst, (v4f64 immAllZerosV))]>, VEX_4V;
+let ExeDomain = SSEPackedInt in
+def AVX_SET0PI : PDI<0xEF, MRMInitReg, (outs VR128:$dst), (ins), "",
+                 [(set VR128:$dst, (v4i32 immAllZerosV))]>;
 }
 
 def : Pat<(v2i64 immAllZerosV), (V_SET0PI)>;

diff --git a/lib/Target/X86/X86MCInstLower.cpp b/lib/Target/X86/X86MCInstLower.cpp
index e77c7c7e5750a1f06a20bd77641fe20bb792c84c..936ad163cf5cf87198e1e7c3c98da1d869eb4bf7 100644 (file)
--- a/lib/Target/X86/X86MCInstLower.cpp
+++ b/lib/Target/X86/X86MCInstLower.cpp
@@ -377,11 +377,14 @@ void X86MCInstLower::Lower(const MachineInstr *MI, MCInst &OutMI) const {
   case X86::FsFLD0SS:      LowerUnaryToTwoAddr(OutMI, X86::PXORrr); break;
   case X86::FsFLD0SD:      LowerUnaryToTwoAddr(OutMI, X86::PXORrr); break;
   case X86::V_SET0PS:      LowerUnaryToTwoAddr(OutMI, X86::XORPSrr); break;
-  case X86::V_SET0PSY:     LowerUnaryToTwoAddr(OutMI, X86::VXORPSYrr); break;
   case X86::V_SET0PD:      LowerUnaryToTwoAddr(OutMI, X86::XORPDrr); break;
-  case X86::V_SET0PDY:     LowerUnaryToTwoAddr(OutMI, X86::VXORPDYrr); break;
   case X86::V_SET0PI:      LowerUnaryToTwoAddr(OutMI, X86::PXORrr); break;
   case X86::V_SETALLONES:  LowerUnaryToTwoAddr(OutMI, X86::PCMPEQDrr); break;
+  case X86::AVX_SET0PS:    LowerUnaryToTwoAddr(OutMI, X86::VXORPSrr); break;
+  case X86::AVX_SET0PSY:   LowerUnaryToTwoAddr(OutMI, X86::VXORPSYrr); break;
+  case X86::AVX_SET0PD:    LowerUnaryToTwoAddr(OutMI, X86::VXORPDrr); break;
+  case X86::AVX_SET0PDY:   LowerUnaryToTwoAddr(OutMI, X86::VXORPDYrr); break;
+  case X86::AVX_SET0PI:    LowerUnaryToTwoAddr(OutMI, X86::VPXORrr); break;
 
   case X86::MOV16r0:
     LowerSubReg32_Op0(OutMI, X86::MOV32r0);   // MOV16r0 -> MOV32r0