Simon Pilgrim 1e564504bb [SLPVectorizer] Relax alternate opcodes to accept any BinaryOperator pair ...

SLP currently only accepts (F)Add/(F)Sub alternate counterpart ops to be merged into an alternate shuffle.

This patch relaxes this to accept any pair of BinaryOperator opcodes instead, assuming the target's cost model accepts the vectorization+shuffle.

Differential Revision: https://reviews.llvm.org/D48477

llvm-svn: 335349

2018-06-22 14:04:06 +00:00

..

64-bit-vector.ll

…

commute.ll

…

ext-trunc.ll

[SLP] Use getExtractWithExtendCost() to compute the scalar cost of extractelement/ext pair

2018-04-16 18:09:49 +00:00

gather-cost.ll

[SLP] Stop counting cost of gather sequences with multiple uses

2018-03-23 14:18:27 +00:00

gather-reduce.ll

…

gather-root.ll

…

getelementptr.ll

…

horizontal.ll

[AArch64] Implement getArithmeticReductionCost

2018-03-16 11:34:15 +00:00

lit.local.cfg

…

load-store-q.ll

…

matmul.ll

[AArch64] fix IR names to not be 'tmp' because that gives the CHECK script problems

2018-02-21 20:48:14 +00:00

minimum-sizes.ll

…

mismatched-intrinsics.ll

…

nontemporal.ll

…

remarks.ll

[DebugInfo] Add DILabel metadata and intrinsic llvm.dbg.label.

2018-05-09 02:40:45 +00:00

sdiv-pow2.ll

…

spillcost-di.ll

[DebugInfo] Add DILabel metadata and intrinsic llvm.dbg.label.

2018-05-09 02:40:45 +00:00

transpose.ll

[SLPVectorizer] Relax alternate opcodes to accept any BinaryOperator pair

2018-06-22 14:04:06 +00:00

tsc-s352.ll

[AArch64] add SLP test based on TSVC; NFC

2018-02-27 18:06:15 +00:00