maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Analysis/CostModel/AArch64
History
David Sherwood e7b89c2fc3 Add BasicTTIImpl cost model for llvm.get.active.lane.mask intrinsic 
The vectoriser sometimes generates predicated vector loops using
the llvm.get.active.lane.mask intrinsic so it's important that we
are able to calculate a valid cost for the call instruction. When
SVE is enabled we are able to use a single whilelo instruction
for some vector types - in such cases I've marked the cost as 1.
For all other cases I've set the cost according to how the intrinsic
will be expanded.

Tests added here:

  Analysis/CostModel/AArch64/sve-intrinsics.ll
  Analysis/CostModel/ARM/active_lane_mask.ll
  Analysis/CostModel/RISCV/active_lane_mask.ll

Differential Revision: https://reviews.llvm.org/D121109
 		2022-03-14 09:35:05 +00:00
..
abs.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
aggregates.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
arith-fp-sve.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
arith-fp.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
arith-overflow.ll [AArch64] Vector shifts cost 1 2022-03-03 10:42:57 +00:00
arith-ssat.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
arith-usat.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
arith.ll [AArch64] Use NPM for cost model tests. NFC 2022-03-07 08:57:50 +00:00
bitreverse.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
bswap.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
cast.ll [AArch64] Improve costs for some conversions to fp16. 2022-03-11 10:27:39 +00:00
cmp.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
cost-scalable-vector-gep.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
ctlz.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
ctpop.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
cttz.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
div.ll [AArch64] Vector shifts cost 1 2022-03-03 10:42:57 +00:00
div_cte.ll [AArch64] Vector shifts cost 1 2022-03-03 10:42:57 +00:00
free-widening-casts.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
gep.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
getIntrinsicInstrCost-vector-reverse.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
kryo-inseltpoison.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
kryo.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
lit.local.cfg
…
load-to-trunc.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
logicalop.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
masked_ldst.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
masked_ldst_vls.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
mem-op-cost-model.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
min-max.ll [AArch64] Use NPM for cost model tests. NFC 2022-03-07 08:57:50 +00:00
mul.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
neon-stepvector.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-add.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-and.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-fadd.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-minmax.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-or.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
reduce-xor.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
rem.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
select.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
shuffle-broadcast.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
shuffle-other.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
shuffle-reverse.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
shuffle-select.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
shuffle-transpose.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
splice.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
store.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-bitcast.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-cmpsel.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-fixed-length.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-fpext.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-fptoi.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-fptrunc.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-gather.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-illegal-types.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-insert-extract.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-intrinsics.ll Add BasicTTIImpl cost model for llvm.get.active.lane.mask intrinsic 2022-03-14 09:35:05 +00:00
sve-ldst.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-math.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-remainder.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-scatter.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-shuffle-broadcast.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-stepvector.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-trunc.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
sve-widening-instruction.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
vector-reduce.ll [test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>' 2022-02-09 15:42:16 -08:00
vector-select.ll [SchedModels][CortexA55] Add ASIMD integer instructions 2022-02-17 13:41:57 +03:00