summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/Hello/Hello.cpp
diff options
context:
space:
mode:
authorSanjay Patel <spatel@rotateright.com>2017-10-11 14:12:16 +0000
committerSanjay Patel <spatel@rotateright.com>2017-10-11 14:12:16 +0000
commit34fd5eaaf04cdfec3ee340a7b21c9316f3830470 (patch)
tree78bb5796359f75e49e4ad4093e43983977b75892 /llvm/lib/Transforms/Hello/Hello.cpp
parent3a4b7ec9deb6dc25d44b623af1e966bc5883a639 (diff)
downloadbcm5719-llvm-34fd5eaaf04cdfec3ee340a7b21c9316f3830470.tar.gz
bcm5719-llvm-34fd5eaaf04cdfec3ee340a7b21c9316f3830470.zip
[DAGCombiner] convert insertelement of bitcasted vector into shuffle
Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
Diffstat (limited to 'llvm/lib/Transforms/Hello/Hello.cpp')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud