shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/X86
History
Florian Hahn eaf48dd9b0
[VPlan] Replace BranchOnCount with BranchOnCond if TC <= UF * VF. 
Try to simplify BranchOnCount to `BranchOnCond true` if TC <= UF * VF.

This is an alternative to D121899 which simplifies the VPlan directly
instead of doing so late in code-gen.

The potential benefit of doing this in VPlan is that this may help
cost-modeling in the future. The reason this is done in prepareToExecute
at the moment is that a single plan may be used for multiple VFs/UFs.

There are further simplifications that can be applied as follow ups:

1. Replace inductions with constants
2. Replace vector region with regular block.

Fixes #55354.

Depends on D126679.

Reviewed By: Ayal

Differential Revision: https://reviews.llvm.org/D126680
2022-06-06 09:38:53 +01:00
..
already-vectorized.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
avx1.ll
…
avx512.ll
…
consecutive-ptr-cg-bug.ll
…
consecutive-ptr-uniforms.ll
[VPlan] Model pre-header explicitly.
2022-04-09 14:19:47 +02:00
constant-fold.ll
[VPlan] Replace BranchOnCount with BranchOnCond if TC <= UF * VF.
2022-06-06 09:38:53 +01:00
constant-vector-operand.ll
…
conversion-cost.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
cost-model-assert.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
cost-model.ll
…
drop-poison-generating-flags.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
float-induction-x86.ll
[runtime-unroll] Use incrementing IVs instead of decrementing ones
2021-11-12 15:44:58 -08:00
fneg-cost.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
fp32_to_uint32-cost-model.ll
…
fp64_to_uint32-cost-model.ll
…
fp80-widest-type.ll
…
fp_to_sint8-cost-model.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
funclet.ll
[LoopVectorize][CostModel] Choose smaller VFs for in-loop reductions without loads/stores
2022-01-04 10:12:57 +00:00
gather_scatter.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
gather-cost.ll
…
gather-vs-interleave.ll
[FileCheck] Catch missspelled directives.
2022-05-26 11:37:19 +01:00
gcc-examples.ll
…
i1-reg-usage.ll
[LV] Improve register pressure estimate at high VFs
2022-05-23 07:57:45 +00:00
illegal-parallel-loop-uniform-write.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
imprecise-through-phis.ll
[CostModel][X86] Reduce cost of vector selects on SSE2/AVX1 targets
2022-05-01 09:32:14 +01:00
int128_no_gather.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
interleave_short_tc.ll
…
interleave-opaque-pointers.ll
[VPlan] VPInterleaveRecipe only uses first lane if op not stored.
2022-05-11 11:24:56 +01:00
interleaved-accesses-large-gap.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
interleaved-accesses-waw-dependency.ll
…
interleaving.ll
…
intrinsiccost.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
invariant-load-gather.ll
[VPlan] Model first exit values using VPLiveOut.
2022-05-21 16:01:38 +01:00
invariant-store-vectorization.ll
[LV] Do not LoopSimplify/LCSSA after generating main vector loop.
2022-05-20 09:58:40 +01:00
libm-vector-calls-finite.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
libm-vector-calls-VF2-VF8.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
libm-vector-calls.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
limit-vf-by-tripcount.ll
[LV] Do not LoopSimplify/LCSSA after generating main vector loop.
2022-05-20 09:58:40 +01:00
lit.local.cfg
…
load-deref-pred.ll
[LV] Create & use VPScalarIVSteps for all scalar users.
2022-03-13 17:15:24 +00:00
masked_load_store.ll
[LV] Do not LoopSimplify/LCSSA after generating main vector loop.
2022-05-20 09:58:40 +01:00
max-mstore.ll
…
metadata-enable.ll
[instcombine] Canonicalize constant index type to i64 for extractelement/insertelement
2021-12-13 16:56:22 -08:00
min-trip-count-switch.ll
…
mul_slm_16bit.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
no_fpmath_with_hotness.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
no_fpmath.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
no-vector.ll
…
nontemporal.ll
…
optsize.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
outer_loop_test1_no_explicit_vect_width.ll
[VPlan] Replace BranchOnCount with BranchOnCond if TC <= UF * VF.
2022-06-06 09:38:53 +01:00
parallel-loops-after-reg2mem.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
parallel-loops.ll
[instcombine] Canonicalize constant index type to i64 for extractelement/insertelement
2021-12-13 16:56:22 -08:00
pointer-runtime-checks-unprofitable.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
powof2div.ll
…
pr23997.ll
…
pr34438.ll
[VPlan] Replace BranchOnCount with BranchOnCond if TC <= UF * VF.
2022-06-06 09:38:53 +01:00
pr35432.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
pr36524.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
pr39160.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
pr42674.ll
[VPlan] Replace BranchOnCount with BranchOnCond if TC <= UF * VF.
2022-06-06 09:38:53 +01:00
pr47437.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
pr48340.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
pr51366-sunk-instruction-used-outside-of-loop.ll
[VPlan] Model first exit values using VPLiveOut.
2022-05-21 16:01:38 +01:00
pr54413-select-interleave-count-loop-with-cost-zero.ll
[LV] Handle zero cost loops in selectInterleaveCount.
2022-03-29 22:52:43 +01:00
pr54634.ll
[LV] Handle non-integral types when considering interleave widening legality
2022-04-03 20:16:20 -07:00
pr55096-scalarize-add.ll
[LV] Add crashing test from #55096.
2022-05-12 22:40:28 +01:00
propagate-metadata.ll
…
ptr-indvar-crash.ll
…
rauw-bug.ll
…
reduction-crash.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
reduction-fastmath.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
reduction-small-size.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
redundant-vf2-cost.ll
…
reg-usage-debug.ll
[NFC][LV] Use different braces in debug output
2022-03-07 19:32:37 +03:00
reg-usage.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
register-assumption.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
runtime-limit.ll
…
scatter_crash.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
slm-no-vectorize.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
small-size.ll
[VPlan] Model pre-header explicitly.
2022-04-09 14:19:47 +02:00
strided_load_cost.ll
…
struct-store.ll
…
svml-calls-finite.ll
…
svml-calls.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
tail_folding_and_assume_safety.ll
…
tail_loop_folding.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
tripcount.ll
…
uint64_to_fp64-cost-model.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
uniform_load.ll
…
uniform_mem_op.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
uniform-phi.ll
…
uniformshift.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
unroll_selection.ll
…
unroll-pm.ll
…
unroll-small-loops.ll
…
veclib-calls.ll
…
vect.omp.force.ll
…
vect.omp.force.small-tc.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
vector_max_bandwidth.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
vector_ptr_load_store.ll
[LV] Remove what seems like stale code in collectElementTypesForWidening.
2022-01-05 12:20:59 +00:00
vector-scalar-select-cost.ll
[CostModel][X86] Adjust 128-bit select costs to account for slow BLENDV op
2022-05-06 13:07:34 +01:00
vectorization-remarks-loopid-dbg.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
vectorization-remarks-missed.ll
[LAA] Add remarks for unbounded array access
2022-02-23 15:57:39 +00:00
vectorization-remarks-profitable.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
vectorization-remarks.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
vectorize-only-for-real.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
x86_fp80-interleaved-access.ll
Revert "[NFCI] Regenerate SROA/LoopVectorize test checks"
2022-04-04 01:15:30 +02:00
x86_fp80-vector-store.ll
…
x86-interleaved-accesses-masked-group.ll
[InstCombine] Fix inbounds preservation when swapping GEPs (PR44206)
2022-05-31 15:45:02 +02:00
x86-interleaved-store-accesses-with-gaps.ll
[InstCombine] Fix inbounds preservation when swapping GEPs (PR44206)
2022-05-31 15:45:02 +02:00
x86-pr39099.ll
[LV] Drop integer poison-generating flags from instructions that need predication
2021-11-22 10:57:29 +00:00
x86-predication.ll
…