diff options
| author | Igor Kirillov <igor.kirillov@arm.com> | 2023-10-30 18:40:48 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-10-30 18:40:48 +0000 |
| commit | 849f963e3139d79eba9989554a299ec6a1a16b10 (patch) | |
| tree | 03d10fbdf6132b46d766035b70549da5cc704cd6 /lldb/source/Commands/CommandObjectGUI.cpp | |
| parent | 89564f0b69ac935dc3b865e4d627f3a0610b4abd (diff) | |
| download | llvm-849f963e3139d79eba9989554a299ec6a1a16b10.zip llvm-849f963e3139d79eba9989554a299ec6a1a16b10.tar.gz llvm-849f963e3139d79eba9989554a299ec6a1a16b10.tar.bz2 | |
[CodeGen] Improve ExpandMemCmp for more efficient non-register aligned sizes handling (#70469)
* Enhanced the logic of ExpandMemCmp pass to merge contiguous
subsequences
in LoadSequence, based on sizes allowed in `AllowedTailExpansions`.
* This enhancement seeks to minimize the number of basic blocks and
produce
optimized code when using memcmp with non-register aligned sizes.
* Enable this feature for AArch64 with memcmp sizes modulo 8 equal to
3, 5, and 6.
Reapplication of #69942 after fixing a bug
Diffstat (limited to 'lldb/source/Commands/CommandObjectGUI.cpp')
0 files changed, 0 insertions, 0 deletions