diff options
| author | Lawrence Benson <github@lawben.com> | 2023-03-29 15:26:28 +0100 |
|---|---|---|
| committer | David Green <david.green@arm.com> | 2023-03-29 15:26:28 +0100 |
| commit | 267d6d665cf2379ebfcc65fa385a35529c83a7d0 (patch) | |
| tree | d3320b24f6ca908456594bab63dfd1423810dac5 /llvm/lib/CodeGen/AssignmentTrackingAnalysis.cpp | |
| parent | 0b57d47bfab9d12d749d96627716eebdd4a9d636 (diff) | |
| download | llvm-267d6d665cf2379ebfcc65fa385a35529c83a7d0.zip llvm-267d6d665cf2379ebfcc65fa385a35529c83a7d0.tar.gz llvm-267d6d665cf2379ebfcc65fa385a35529c83a7d0.tar.bz2 | |
[AArch64] Use NEON's tbl1 for 16xi8 and 8xi8 build vector with mask.
When using Clang's __builtin_shufflevector with a 16xi8 or 8xi8 source and
runtime mask on an AArch64 target, LLVM currently generates 16 or 8
extract+and+insert operations. This patch replaces these inserts with (a vector
AND +) NEON's tbl1 intruction.
Issue: https://github.com/llvm/llvm-project/issues/60515
Differential Revision: https://reviews.llvm.org/D146212
Diffstat (limited to 'llvm/lib/CodeGen/AssignmentTrackingAnalysis.cpp')
0 files changed, 0 insertions, 0 deletions