David Green fe04290482

[AArch64] Change the default vscale-for-tuning to 1. (#117174) ...

Most AArch64 cpus outside of Neoverse V1 (256) and A64FX (512) have an
SVE vector length of 128, and in environments like Android (where no
mcpu option is common) we would expect all cpus to match. This patch
changes the default vector length to 128 with -mcpu=generic, to match
the most common case.

2024-11-29 17:41:05 +00:00

..

abs.ll

…

aggregates.ll

…

arith-fp-sve.ll

[AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)

2024-08-09 14:25:07 +01:00

arith-fp.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

arith-overflow.ll

…

arith-ssat.ll

…

arith-usat.ll

…

arith-widening.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

arith.ll

…

bitreverse.ll

…

bswap.ll

…

cast.ll

[AArch64] NFC: Rename -force-streaming-compatible-sve to -force-streaming-compatible (#92774)

2024-05-22 07:58:54 +01:00

cmp.ll

[AArch64] Expand scmp/ucmp vector operations with sub (#108830)

2024-09-16 18:44:52 +01:00

cost-scalable-vector-gep.ll

…

ctlz.ll

…

ctpop.ll

…

cttz_elts.ll

[AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)

2024-08-09 14:25:07 +01:00

cttz.ll

…

div_cte.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

div.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

ext-rhadd.ll

[LLVM][test] Convert remaining instances of ConstantExpr based splats to use splat().

2024-02-27 13:37:23 +00:00

extract_float_streaming.ll

[AArch64] Guard against getRegisterBitWidth returning zero in vector instr cost. (#117749)

2024-11-29 04:01:03 +00:00

extract_float.ll

[CostModel][AArch64] Make extractelement, with fmul user, free whenev… (#111479)

2024-11-13 11:10:49 +05:30

fp-conversions-odd-vector-types.ll

[AArch64] Add more type combinations to vector fp conversion cost tests.

2024-09-06 14:49:45 +01:00

fptoi_sat.ll

[AArch64] Extend costs for fptoi.sat intrinsics.

2024-07-28 10:47:40 +01:00

free-widening-casts.ll

…

fshl.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

fshr.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

gep.ll

…

getIntrinsicInstrCost-vector-reverse.ll

Move several vector intrinsics out of experimental namespace (#88748)

2024-04-29 10:16:45 +01:00

insert-extract.ll

…

kryo-inseltpoison.ll

…

lit.local.cfg

…

load-to-trunc.ll

…

logicalop.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

masked_ldst_vls.ll

…

masked_ldst.ll

[LoopVectorize][AArch64] Add limited support for scalable vectorisation of i1 types (#95920)

2024-06-25 15:04:24 +01:00

mem-op-cost-model.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

min-max.ll

…

mul.ll

…

neon-stepvector.ll

Move stepvector intrinsic out of experimental namespace (#98043)

2024-08-28 12:48:20 +01:00

no-sve-no-neon.ll

[AArch64] Fix assertion failure in getCastInstrCost

2024-07-16 10:43:07 +00:00

reduce-add.ll

…

reduce-and.ll

…

reduce-fadd.ll

[AArch64][CostModel] Reduce the cost of fadd reduction with fast flag (#108791)

2024-09-24 14:35:01 +05:30

reduce-minmax.ll

[TTI]Fallback to SingleSrcPermute shuffle kind, if no direct estimation for

2024-02-12 07:09:49 -05:00

reduce-or.ll

…

reduce-xor.ll

…

rem.ll

[LLVM][IR] Use splat syntax when printing Constant[Data]Vector. (#112548)

2024-11-06 11:53:33 +00:00

select.ll

…

shuffle-broadcast.ll

…

shuffle-load.ll

[AArch64] Add costs for LD3/LD4 shuffles.

2024-04-21 13:53:22 +01:00

shuffle-other.ll

Revert "[AArch64] Remove special-case inserted shuffle cost."

2024-07-29 11:24:39 +00:00

shuffle-reverse.ll

…

shuffle-select.ll

…

shuffle-store.ll

[AArch64] Add ZIP and UZP shuffle costs. (#88150)

2024-04-11 08:45:28 +01:00

shuffle-transpose.ll

…

splice.ll

Move several vector intrinsics out of experimental namespace (#88748)

2024-04-29 10:16:45 +01:00

store-ptr.ll

…

store.ll

…

sve-arith.ll

[AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)

2024-08-09 14:25:07 +01:00

sve-bitcast.ll

…

sve-cmpsel.ll

…

sve-ext.ll

…

sve-fixed-length.ll

…

sve-fpext.ll

…

sve-fptoi.ll

[AArch64] Auto-generate check-lines in cost model test.

2024-09-06 22:38:02 +01:00

sve-fptrunc.ll

…

sve-gather.ll

[AArch64] Change the default vscale-for-tuning to 1. (#117174)

2024-11-29 17:41:05 +00:00

sve-illegal-types.ll

…

sve-insert-extract.ll

…

sve-intrinsics.ll

[AArch64] Change the default vscale-for-tuning to 1. (#117174)

2024-11-29 17:41:05 +00:00

sve-ldst.ll

[LoopVectorize][AArch64] Add limited support for scalable vectorisation of i1 types (#95920)

2024-06-25 15:04:24 +01:00

sve-math.ll

…

sve-min-max.ll

[AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)

2024-08-09 14:25:07 +01:00

sve-remainder.ll

…

sve-scatter.ll

[AArch64] Change the default vscale-for-tuning to 1. (#117174)

2024-11-29 17:41:05 +00:00

sve-shuffle-broadcast.ll

…

sve-stepvector.ll

Move stepvector intrinsic out of experimental namespace (#98043)

2024-08-28 12:48:20 +01:00

sve-trunc.ll

…

sve-vscale.ll

…

sve-widening-instruction.ll

…

vec3-ops.ll

[AArch64] Improve cost computations for odd vector mem ops. (#78181)

2024-01-17 21:32:06 +00:00

vector-reduce.ll

…

vector-select.ll

…