diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86ISelLowering.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index d1552cd512e..d8e72632b0c 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -17670,6 +17670,17 @@ FindInConvertTable(const X86TypeConversionCostTblEntry *Tbl, unsigned len, 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 { |
