David Green 233fb987fc [ARM] Improve bitwise reduction costs ...

This adds some basic and/or/xor reduction costs for NEON/MVE, handling them
like other reductions where vector operations are used to reduce to legal
sizes, followed by an optional VREV+VAND/VORR/VEOR step and scalarization from
there.

2023-09-04 16:22:52 +01:00

..

active_lane_mask.ll

…

add-cast-vect.ll

…

arith-overflow.ll

…

arith-ssat.ll

…

arith-usat.ll

…

arith.ll

…

cast_ldst.ll

…

cast.ll

…

cmps.ll

…

control-flow.ll

…

divrem.ll

…

fparith.ll

…

fptoi_sat.ll

…

freeshift.ll

…

gep.ll

…

immediates.ll

…

insertelement.ll

…

intrinsic-cost-kinds.ll

[ARM] Improve costs for FMin/Max reductions

2023-09-04 12:49:13 +01:00

lit.local.cfg

…

load_store.ll

…

load-to-trunc.ll

…

logicalop.ll

…

memcpy.ll

…

mul-cast-vect.ll

…

mve-abs.ll

…

mve-active_lane_mask.ll

…

mve-cmp.ll

…

mve-gather-scatter-cost.ll

[TTI] Use users of GEP to guess access type in getGEPCost

2023-06-29 13:44:37 +01:00

mve-minmax.ll

…

mve-vecreduce-add.ll

…

reduce-add.ll

…

reduce-and.ll

…

reduce-bit.ll

[ARM] Improve bitwise reduction costs

2023-09-04 16:22:52 +01:00

reduce-fminmax.ll

[ARM] Improve costs for FMin/Max reductions

2023-09-04 12:49:13 +01:00

reduce-fp.ll

[ARM] Improve reduction fadd/fmul costs

2023-09-04 11:37:14 +01:00

reduce-or.ll

…

reduce-smax.ll

[ARM] Improve reduction integer min/max costs

2023-09-04 15:47:06 +01:00

reduce-smin.ll

[ARM] Improve reduction integer min/max costs

2023-09-04 15:47:06 +01:00

reduce-umax.ll

[ARM] Improve reduction integer min/max costs

2023-09-04 15:47:06 +01:00

reduce-umin.ll

[ARM] Improve reduction integer min/max costs

2023-09-04 15:47:06 +01:00

select.ll

…

shl-cast-vect.ll

…

shuffle.ll

…

sub-cast-vect.ll

…

target-intrinsics.ll

…