[InstCombine] Fold a shifty implementation of clamp-to-allones.

Summary:
Fold
or(ashr(subNSW(Y, X), ScalarSizeInBits(Y)-1), X)
into
X s> Y ? -1 : X

https://rise4fun.com/Alive/d8Ab

clamp255 is a common operator in image processing, can be implemented
in a shifty way "(255 - X) >> 31 | X & 255". Fold shift into select
enables more optimization, e.g., vmin generation for ARM target.

Reviewers: lebedev.ri, efriedma, spatel, kparzysz, bcahoon

Reviewed By: lebedev.ri

Subscribers: kristof.beyls, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67800

llvm-svn: 372678

1 files changed, 15 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
index 490faddaefb..cde4cc1e842 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
@@ -2677,6 +2677,21 @@ Instruction *InstCombiner::visitOr(BinaryOperator &I) {
     }
   }
 
+  // or(ashr(subNSW(Y, X), ScalarSizeInBits(Y)-1), X)  --> X s> Y ? -1 : X.
+  {
+    Value *X, *Y;
+    const APInt *ShAmt;
+    Type *Ty = I.getType();
+    if (match(&I, m_c_Or(m_OneUse(m_AShr(m_NSWSub(m_Value(Y), m_Value(X)),
+                                         m_APInt(ShAmt))),
+                         m_Deferred(X))) &&
+        *ShAmt == Ty->getScalarSizeInBits() - 1) {
+      Value *NewICmpInst = Builder.CreateICmpSGT(X, Y);
+      return SelectInst::Create(NewICmpInst, ConstantInt::getAllOnesValue(Ty),
+                                X);
+    }
+  }
+
   return nullptr;
 }