diff options
| author | Sushant Gokhale <sgokhale@nvidia.com> | 2025-10-20 17:36:44 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-10-20 17:36:44 -0700 |
| commit | 005ec78b71c8790a58cb1124e8ca2fcf47a880a0 (patch) | |
| tree | b62cc43293088c399cc8ca1e0c89d694583369b4 /clang/lib/AST/ByteCode/Program.cpp | |
| parent | de21b0d62ebf072675ec8fe178db0d4ebd0da10d (diff) | |
| download | llvm-005ec78b71c8790a58cb1124e8ca2fcf47a880a0.zip llvm-005ec78b71c8790a58cb1124e8ca2fcf47a880a0.tar.gz llvm-005ec78b71c8790a58cb1124e8ca2fcf47a880a0.tar.bz2 | |
[AArch64][CostModel] Add constraints on which partial reductions are (#163728)
natively supported on Neon and SVE
PR #158641 refined and refactored the cost model for partial reductions.
While doing so, it missed out on certain constraints. Specifically,
cases like i32 -> i64 partial reduce are not natively supported. This
patch adds back the condition/constraint that was present before PR
#158641
Diffstat (limited to 'clang/lib/AST/ByteCode/Program.cpp')
0 files changed, 0 insertions, 0 deletions