[X86] updating TTI costs for arithmetic instructions on X86\SLM arch.

updated instructions:
pmulld, pmullw, pmulhw, mulsd, mulps, mulpd, divss, divps, divsd, divpd, addpd and subpd.

special optimization case which replaces pmulld with pmullw\pmulhw\pshuf seq. 
In case if the real operands bitwidth <= 16.

Differential Revision: https://reviews.llvm.org/D28104 

llvm-svn: 291657

1 files changed, 4 insertions, 3 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index c9819a8e270..1b1f86f8efd 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -80,6 +80,7 @@
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/IR/Type.h"
+#include "llvm/IR/User.h"
 #include "llvm/IR/Value.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/IR/Verifier.h"
@@ -6949,9 +6950,9 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
     } else if (Legal->isUniform(Op2)) {
       Op2VK = TargetTransformInfo::OK_UniformValue;
     }
-
-    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, Op2VK,
-                                      Op1VP, Op2VP);
+    SmallVector<const Value *, 4> Operands(I->operand_values()); 
+    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
+                                      Op2VK, Op1VP, Op2VP, Operands);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);