[LV, X86] Be more optimistic about vectorizing shifts.

Shifts with a uniform but non-constant count were considered very expensive to
vectorize, because the splat of the uniform count and the shift would tend to
appear in different blocks. That made the splat invisible to ISel, and we'd
scalarize the shift at codegen time.

Since r201655, CodeGenPrepare sinks those splats to be next to their use, and we
are able to select the appropriate vector shifts. This updates the cost model to
to take this into account by making shifts by a uniform cheap again.

Differential Revision: https://reviews.llvm.org/D23049

llvm-svn: 277782

1 files changed, 8 insertions, 1 deletions

diff --git a/llvm/lib/Analysis/CostModel.cpp b/llvm/lib/Analysis/CostModel.cpp
index 68a4bea96ba..5dd54cd4d19 100644
--- a/llvm/lib/Analysis/CostModel.cpp
+++ b/llvm/lib/Analysis/CostModel.cpp
@@ -20,6 +20,7 @@
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Analysis/Passes.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Analysis/VectorUtils.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
@@ -123,7 +124,7 @@ static bool isAlternateVectorMask(SmallVectorImpl<int> &Mask) {
 
 static TargetTransformInfo::OperandValueKind getOperandInfo(Value *V) {
   TargetTransformInfo::OperandValueKind OpInfo =
-    TargetTransformInfo::OK_AnyValue;
+      TargetTransformInfo::OK_AnyValue;
 
   // Check for a splat of a constant or for a non uniform vector of constants.
   if (isa<ConstantVector>(V) || isa<ConstantDataVector>(V)) {
@@ -132,6 +133,12 @@ static TargetTransformInfo::OperandValueKind getOperandInfo(Value *V) {
       OpInfo = TargetTransformInfo::OK_UniformConstantValue;
   }
 
+  // Check for a splat of a uniform value. This is not loop aware, so return
+  // true only for the obviously uniform cases (argument, globalvalue)
+  const Value *Splat = getSplatValue(V);
+  if (Splat && (isa<Argument>(Splat) || isa<GlobalValue>(Splat)))
+    OpInfo = TargetTransformInfo::OK_UniformValue;
+
   return OpInfo;
 }