aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Support/APFloat.cpp
diff options
context:
space:
mode:
authorSpenser Bauman <sbauman@mathworks.com>2023-03-24 19:42:12 +0000
committerRobert Suderman <suderman@google.com>2023-03-24 19:50:13 +0000
commit110c1b64a7b9984a604aa2809e0fb8c01278609d (patch)
tree4441733ccfe84374b1472796c546f92fe00a45c8 /llvm/lib/Support/APFloat.cpp
parent1fce1d341b17762bb45bdc89520b00820fd63337 (diff)
downloadllvm-110c1b64a7b9984a604aa2809e0fb8c01278609d.zip
llvm-110c1b64a7b9984a604aa2809e0fb8c01278609d.tar.gz
llvm-110c1b64a7b9984a604aa2809e0fb8c01278609d.tar.bz2
[mlir][tosa] Improve performance of tosa.transpose constant folding
Folding of the tosa.transpose operation is both time and memory intensive as the underlying ElementsAttr is processed as a sequence of Attributes. This change attempts operate on the underlying raw data of the ElementsAttr. In an example resnet50 network, this change reduces the time spent in folding transpose ops from 35s to 1.5s. Reviewed By: GeorgeARM, rsuderman, stellaraccident Differential Revision: https://reviews.llvm.org/D146526
Diffstat (limited to 'llvm/lib/Support/APFloat.cpp')
0 files changed, 0 insertions, 0 deletions