diff options
Diffstat (limited to 'lib/Target/ARM/ARMTargetTransformInfo.cpp')
-rw-r--r-- | lib/Target/ARM/ARMTargetTransformInfo.cpp | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp index 79f56a4..5cc64de 100644 --- a/lib/Target/ARM/ARMTargetTransformInfo.cpp +++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp @@ -426,6 +426,15 @@ unsigned ARMTTI::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, } unsigned ARMTTI::getAddressComputationCost(Type *Ty, bool IsComplex) const { + // Address computations in vectorized code with non-consecutive addresses will + // likely result in more instructions compared to scalar code where the + // computation can more often be merged into the index mode. The resulting + // extra micro-ops can significantly decrease throughput. + unsigned NumVectorInstToHideOverhead = 10; + + if (Ty->isVectorTy() && IsComplex) + return NumVectorInstToHideOverhead; + // In many cases the address computation is not merged into the instruction // addressing mode. return 1; |