projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8590e5a) | patch
[ARM] Add VADDV and VMLAV patterns for v16i16
authorDavid Green <david.green@arm.com>
Sun, 9 Aug 2020 10:09:49 +0000 (11:09 +0100)
committerDavid Green <david.green@arm.com>
Sun, 9 Aug 2020 10:09:49 +0000 (11:09 +0100)
commit186a7f81e813a59b68fadfe7ea90c348bb760c56
treeb18e3360713768b0be22d1d7bc3b47ed26e1a321tree | snapshot
parent8590e5abad51257fe9120313b37192f37aef8eeccommit | diff
[ARM] Add VADDV and VMLAV patterns for v16i16

This adds patterns for v16i16's vecreduce, using all the existing code
to go via an i32 VADDV/VMLAV and truncating the result.

Differential Revision: https://reviews.llvm.org/D85452
llvm/lib/Target/ARM/ARMISelLowering.cpp diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vecreduce-add.ll diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vecreduce-addpred.ll diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vecreduce-mla.ll diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vecreduce-mlapred.ll diff | blob | history
Domain: System / Toolchain;