llvm-project/llvm/test/Transforms/LoopVectorize/ARM
Philip Reames e6ad9ef4e7 [instcombine] Canonicalize constant index type to i64 for extractelement/insertelement
The basic idea to this is that a) having a single canonical type makes CSE easier, and b) many of our transforms are inconsistent about which types we end up with based on visit order.

I'm restricting this to constants as for non-constants, we'd have to decide whether the simplicity was worth extra instructions. For constants, there are no extra instructions.

We chose the canonical type as i64 arbitrarily.  We might consider changing this to something else in the future if we have cause.

Differential Revision: https://reviews.llvm.org/D115387
2021-12-13 16:56:22 -08:00
..
arm-ieee-vectorize.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
arm-unroll.ll
gather-cost.ll
gcc-examples.ll
interleaved_cost.ll
lit.local.cfg
mve-gather-scatter-tailpred.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
mve-icmpcost.ll [ARM] Make MVE v2i1 predicates legal 2021-12-03 14:05:41 +00:00
mve-interleaved-cost.ll
mve-known-trip-count.ll [LV] Account for tripcount when calculation vectorization profitability 2021-05-06 12:36:46 +01:00
mve-maskedldst.ll
mve-predstorecost.ll
mve-qabs.ll [LV] Mark increment of main vector loop induction variable as NUW. 2021-06-07 10:47:52 +01:00
mve-reduction-predselect.ll [SVE] Add support for folding for select + masked loads 2021-07-26 11:58:41 +01:00
mve-reduction-types.ll [LV] Mark increment of main vector loop induction variable as NUW. 2021-06-07 10:47:52 +01:00
mve-reductions.ll [LV][ARM] Improve reduction costmodel for mismatching extension types. 2021-12-10 15:40:58 +00:00
mve-saddsatcost.ll [instcombine] Canonicalize constant index type to i64 for extractelement/insertelement 2021-12-13 16:56:22 -08:00
mve-selectandorcost.ll [ARM] Make MVE v2i1 predicates legal 2021-12-03 14:05:41 +00:00
mve-shiftcost.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
mve-vldn.ll
pointer_iv.ll [instcombine] Canonicalize constant index type to i64 for extractelement/insertelement 2021-12-13 16:56:22 -08:00
prefer-tail-loop-folding.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
scalar-block-cost.ll
sphinx.ll [LV] Mark increment of main vector loop induction variable as NUW. 2021-06-07 10:47:52 +01:00
tail-fold-multiple-icmps.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-allowed.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-counting-down.ll
tail-folding-loop-hint.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-not-allowed.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-prefer-flag.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-reduces-vf.ll
tail-folding-reductions-allowed.ll [ARM] Add datalayout to costmodel tests. NFC 2021-11-16 09:49:42 +00:00
tail-folding-scalar-epilogue-fallback.ll Revert "[IR] `IRBuilderBase::CreateAdd()`: short-circuit `x + 0` --> `x`" 2021-10-27 22:21:37 +03:00
vector_cast.ll
width-detect.ll