- Re-enable population count loop idiom recognization
- fix a bug which cause sigfault.
- add two testing cases which was causing crash
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169687 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index af772ed..84e5677 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -17679,6 +17679,17 @@
return -1;
}
+ScalarTargetTransformInfo::PopcntHwSupport
+X86ScalarTargetTransformImpl::getPopcntHwSupport(unsigned TyWidth) const {
+ assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
+ const X86Subtarget &ST = TLI->getTargetMachine().getSubtarget<X86Subtarget>();
+
+ // TODO: Currently the __builtin_popcount() implementation using SSE3
+ // instructions is inefficient. Once the problem is fixed, we should
+ // call ST.hasSSE3() instead of ST.hasSSE4().
+ return ST.hasSSE41() ? Fast : None;
+}
+
unsigned
X86VectorTargetTransformInfo::getArithmeticInstrCost(unsigned Opcode,
Type *Ty) const {