Add a pass to optimize patterns of vectorized interleaved memory accesses for
X86. The pass optimizes as a unit the entire wide load + shuffles pattern
produced by interleaved vectorization. This initial patch optimizes one pattern
(64-bit elements interleaved by a factor of 4). Future patches will generalize
to additional patterns.
Patch by Farhana Aleen
Differential revision: http://reviews.llvm.org/D24681
llvm-svn: 284260
diff --git a/llvm/lib/Target/X86/X86TargetMachine.cpp b/llvm/lib/Target/X86/X86TargetMachine.cpp
index 5dfa87b..773438d 100644
--- a/llvm/lib/Target/X86/X86TargetMachine.cpp
+++ b/llvm/lib/Target/X86/X86TargetMachine.cpp
@@ -269,6 +269,9 @@
addPass(createAtomicExpandPass(&getX86TargetMachine()));
TargetPassConfig::addIRPasses();
+
+ if (TM->getOptLevel() != CodeGenOpt::None)
+ addPass(createInterleavedAccessPass(TM));
}
bool X86PassConfig::addInstSelector() {