diff options
| author | Philip Reames <preames@rivosinc.com> | 2024-08-24 10:47:57 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-08-24 10:47:57 -0700 |
| commit | 2cb25d5608453655a2ed39d8177034ab7773aac2 (patch) | |
| tree | 4337a7a991cc58625b8b60d8fac3406cc2749a2d /llvm/lib/Support/VirtualFileSystem.cpp | |
| parent | 31b4bf938b46001abbf2a58875047bf13ba083dd (diff) | |
| download | llvm-2cb25d5608453655a2ed39d8177034ab7773aac2.zip llvm-2cb25d5608453655a2ed39d8177034ab7773aac2.tar.gz llvm-2cb25d5608453655a2ed39d8177034ab7773aac2.tar.bz2 | |
[DAG][RISCV] Use vp_reduce_fadd/fmul when widening types for FP reductions (#105840)
This is a follow up to #105455 which updates the VPIntrinsic mappings
for the fadd and fmul cases, and supports both ordered and unordered
reductions. This allows the use a single wider operation with a
restricted EVL instead of padding the vector with the neutral element.
This has all the same tradeoffs as the previous patch.
Diffstat (limited to 'llvm/lib/Support/VirtualFileSystem.cpp')
0 files changed, 0 insertions, 0 deletions