R600/SI: Try to keep i32 mul on SALU

[oota-llvm.git] / lib / Target / X86 / X86InstrInfo.cpp

diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp
index 36ee4a2d26b0107a77cf80ae09cb9cd93e17aaa5..f14179603eb6ecdff6bcf57686e3bbe8d3a4bf9a 100644 (file)
--- a/lib/Target/X86/X86InstrInfo.cpp
+++ b/lib/Target/X86/X86InstrInfo.cpp
@@ -26,6 +26,7 @@
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/StackMaps.h"
 #include "llvm/IR/DerivedTypes.h"
+#include "llvm/IR/Function.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCExpr.h"
@@ -377,7 +378,15 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     { X86::VMOVUPDYrr,  X86::VMOVUPDYmr,    TB_FOLDED_STORE },
     { X86::VMOVUPSYrr,  X86::VMOVUPSYmr,    TB_FOLDED_STORE },
     // AVX-512 foldable instructions
-    { X86::VMOVPDI2DIZrr,X86::VMOVPDI2DIZmr,  TB_FOLDED_STORE }
+    { X86::VMOVPDI2DIZrr,   X86::VMOVPDI2DIZmr, TB_FOLDED_STORE },
+    { X86::VMOVAPDZrr,      X86::VMOVAPDZmr,    TB_FOLDED_STORE | TB_ALIGN_64 },
+    { X86::VMOVAPSZrr,      X86::VMOVAPSZmr,    TB_FOLDED_STORE | TB_ALIGN_64 },
+    { X86::VMOVDQA32Zrr,    X86::VMOVDQA32Zmr,  TB_FOLDED_STORE | TB_ALIGN_64 },
+    { X86::VMOVDQA64Zrr,    X86::VMOVDQA64Zmr,  TB_FOLDED_STORE | TB_ALIGN_64 },
+    { X86::VMOVUPDZrr,      X86::VMOVUPDZmr,    TB_FOLDED_STORE },
+    { X86::VMOVUPSZrr,      X86::VMOVUPSZmr,    TB_FOLDED_STORE },
+    { X86::VMOVDQU32Zrr,    X86::VMOVDQU32Zmr,  TB_FOLDED_STORE },
+    { X86::VMOVDQU64Zrr,    X86::VMOVDQU64Zmr,  TB_FOLDED_STORE }
   };
 
   for (unsigned i = 0, e = array_lengthof(OpTbl0); i != e; ++i) {
@@ -601,10 +610,14 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     // AVX-512 foldable instructions
     { X86::VMOV64toPQIZrr,  X86::VMOVQI2PQIZrm,       0 },
     { X86::VMOVDI2SSZrr,    X86::VMOVDI2SSZrm,        0 },
+    { X86::VMOVAPDZrr,      X86::VMOVAPDZrm,          TB_ALIGN_64 },
+    { X86::VMOVAPSZrr,      X86::VMOVAPSZrm,          TB_ALIGN_64 },
     { X86::VMOVDQA32Zrr,    X86::VMOVDQA32Zrm,        TB_ALIGN_64 },
     { X86::VMOVDQA64Zrr,    X86::VMOVDQA64Zrm,        TB_ALIGN_64 },
     { X86::VMOVDQU32Zrr,    X86::VMOVDQU32Zrm,        0 },
     { X86::VMOVDQU64Zrr,    X86::VMOVDQU64Zrm,        0 },
+    { X86::VMOVUPDZrr,      X86::VMOVUPDZrm,          0 },
+    { X86::VMOVUPSZrr,      X86::VMOVUPSZrm,          0 },
     { X86::VPABSDZrr,       X86::VPABSDZrm,           0 },
     { X86::VPABSQZrr,       X86::VPABSQZrm,           0 },
 
@@ -612,7 +625,7 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     { X86::AESIMCrr,              X86::AESIMCrm,              TB_ALIGN_16 },
     { X86::AESKEYGENASSIST128rr,  X86::AESKEYGENASSIST128rm,  TB_ALIGN_16 },
     { X86::VAESIMCrr,             X86::VAESIMCrm,             TB_ALIGN_16 },
-    { X86::VAESKEYGENASSIST128rr, X86::VAESKEYGENASSIST128rm, TB_ALIGN_16 },
+    { X86::VAESKEYGENASSIST128rr, X86::VAESKEYGENASSIST128rm, TB_ALIGN_16 }
   };
 
   for (unsigned i = 0, e = array_lengthof(OpTbl1); i != e; ++i) {