mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
091d315f5e
For the power9 CPU, vector operations consume a pair of execution units rather than one execution unit like a scalar operation. Update the target transform cost functions to reflect the higher cost of vector operations when targeting Power9. Patch by RolandF. Differential revision: https://reviews.llvm.org/D55461 llvm-svn: 352261 |
||
---|---|---|
.. | ||
AliasSet | ||
AssumptionCache | ||
BasicAA | ||
BlockFrequencyInfo | ||
BranchProbabilityInfo | ||
CallGraph | ||
CFLAliasAnalysis | ||
ConstantFolding | ||
CostModel | ||
Delinearization | ||
DemandedBits | ||
DependenceAnalysis | ||
DivergenceAnalysis | ||
DominanceFrontier | ||
Dominators | ||
GlobalsModRef | ||
IVUsers | ||
LazyCallGraph | ||
LazyValueAnalysis | ||
LegacyDivergenceAnalysis | ||
Lint | ||
LoopAccessAnalysis | ||
LoopInfo | ||
MemoryDependenceAnalysis | ||
MemorySSA | ||
MustExecute | ||
PhiValues | ||
PostDominators | ||
ProfileSummary | ||
RegionInfo | ||
ScalarEvolution | ||
ScopedNoAliasAA | ||
StackSafetyAnalysis | ||
TypeBasedAliasAnalysis | ||
ValueTracking | ||
alias-analysis-uses.ll |