Philip Reames 536095a27c [RISCV] Refine costs for i1 reductions ... Our actual lowering for i1 reductions uses ctpop combined with possibly a vector negate and possibly a logic op afterwards. I believe ctpop to be low cost on all reasonable hardware. The default costing implementation here was returning quite inconsistent costs. and/or were returning very high costs (because we seem to think moving into scalar registers is very expensive?) and others were returning lower but still too high (because of the assumed tree reduce strategy). While we should probably improve the generic costing strategy for i1 vectors, let's start by fixing the immediate problem. Differential Revision: https://reviews.llvm.org/D127511		2022-06-10 13:21:52 -07:00
..
AliasSet	…
AssumptionCache	…
BasicAA	Reapply "[Intrinsics] Add `nocallback` to the default intrinsic attributes"	2022-03-25 09:36:50 -05:00
BlockFrequencyInfo	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
BranchProbabilityInfo	[BPI] Look-up tables for non-loop branches. NFC.	2021-11-22 10:30:42 +00:00
CFLAliasAnalysis	[AAEval] Make compatible with opaque pointers	2022-03-16 10:02:11 +01:00
CallGraph	[Statepoint] Update gc.statepoint calls in tests with elementtype (NFC)	2022-02-04 14:15:41 +01:00
CostModel	[RISCV] Refine costs for i1 reductions	2022-06-10 13:21:52 -07:00
CycleInfo	[test] Replace/remove some 'opt -analyze' RUN lines	2022-02-09 15:49:53 -08:00
DDG	…
Delinearization	[test] Remove one more unnecessary -analyze RUN line	2022-02-09 16:05:43 -08:00
DemandedBits	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
DependenceAnalysis	Recommit "[SCEV] Look through single value PHIs." (take 3)	2022-06-09 15:20:10 +01:00
DivergenceAnalysis	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
DominanceFrontier	…
Dominators	Introduce NewPM .dot printers for DomTree	2022-01-05 23:25:40 +00:00
FunctionPropertiesAnalysis	…
GlobalsModRef	[GlobalsModRef][FIX] Ensure we honor synchronizing effects of intrinsics	2022-04-12 16:42:50 -05:00
IRSimilarityIdentifier	[IRSim] Ignore debug instructions when creating canonical numbering	2022-04-19 13:18:28 -05:00
IVUsers	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
LazyCallGraph	[Statepoint] Update gc.statepoint calls in tests with elementtype (NFC)	2022-02-04 14:15:41 +01:00
LazyValueAnalysis	…
LegacyDivergenceAnalysis	[test] Replace `-analyze -divergence` with `-passes='print<divergence>'`	2022-02-09 16:09:14 -08:00
Lint	[test] Modify some tests to remove implicit -basic-aa in legacy PM RUN lines	2022-03-08 14:35:06 -08:00
LoopAccessAnalysis	Revert "[LAA] Initial support for runtime checks with pointer selects."	2022-06-01 15:24:27 +02:00
LoopCacheAnalysis/PowerPC	[NFC][LoopCacheAnalysis] Update test cases to make sure the outputs follow the right order	2022-05-25 23:32:00 -04:00
LoopInfo	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
LoopNestAnalysis	…
MemoryDependenceAnalysis	[test] Modify some tests to remove implicit -basic-aa in legacy PM RUN lines	2022-03-08 14:35:06 -08:00
MemorySSA	[FileCheck] Catch missspelled directives.	2022-05-26 11:37:19 +01:00
MustExecute	…
PhiValues	…
PostDominators	[test][NewPM] Remove RUN lines using -analyze	2021-09-02 11:38:14 -07:00
ProfileSummary	…
RegionInfo	[FileCheck] Catch missspelled directives.	2022-05-26 11:37:19 +01:00
ScalarEvolution	Recommit "[SCEV] Look through single value PHIs." (take 3)	2022-06-09 15:20:10 +01:00
ScopedNoAliasAA	[test] Modify some tests to remove implicit -basic-aa in legacy PM RUN lines	2022-03-08 14:35:06 -08:00
StackSafetyAnalysis	LTO: Decide upfront whether to use opaque/non-opaque pointer types	2022-06-01 18:05:53 -07:00
TypeBasedAliasAnalysis	Reapply "[Intrinsics] Add `nocallback` to the default intrinsic attributes"	2022-03-25 09:36:50 -05:00
ValueTracking	[ValueTracking] Add support to deduce a PHI node being a power of 2 if each incoming value is a power of 2.	2022-06-07 18:52:31 +00:00
alias-analysis-uses.ll	…