diff options
| author | Changpeng Fang <changpeng.fang@gmail.com> | 2020-02-07 11:06:33 -0800 |
|---|---|---|
| committer | Changpeng Fang <changpeng.fang@gmail.com> | 2020-02-07 11:06:33 -0800 |
| commit | 6370c7c13e6d7cfa70197e9a45033e2b845e1b9e (patch) | |
| tree | 05a3a978c7fd9102ec2cfa7b95dc3a87b4dc114e /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 4a1a0690ad6813a4c8cdb8dc20ea6337aa1f61e0 (diff) | |
| download | llvm-6370c7c13e6d7cfa70197e9a45033e2b845e1b9e.zip llvm-6370c7c13e6d7cfa70197e9a45033e2b845e1b9e.tar.gz llvm-6370c7c13e6d7cfa70197e9a45033e2b845e1b9e.tar.bz2 | |
AMDGPU: Limit the search in finding the instruction pattern for v_swap generation.
Summary:
Current implementation of matchSwap in SIShrinkInstructions searches the entire
use_nodbg_operands set to find the possible pattern to generate v_swap instruction.
This approach will lead to a O(N^3) in compile time for SIShrinkInstructions.
But in reality, the matching pattern only exists within nearby instructions in the
same basic block. This work limits the search to a maximum of 16 instructions, and has
a linear compile time comsumption.
Reviewers:
rampitec, arsenm
Differential Revision: https://reviews.llvm.org/D74180
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions