diff options
| author | Wenju He <wenju.he@intel.com> | 2025-09-18 07:47:35 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-18 07:47:35 +0800 |
| commit | 7f3661128b1e5dda69586afcff99a8f662e4126f (patch) | |
| tree | 18cb4c8a3ad0691d4abeb6b72394609f213d5c06 /llvm/lib/CodeGen/MachineOperand.cpp | |
| parent | 5cc41936f22da6edd4a85927774df17b1e7c945e (diff) | |
| download | llvm-7f3661128b1e5dda69586afcff99a8f662e4126f.zip llvm-7f3661128b1e5dda69586afcff99a8f662e4126f.tar.gz llvm-7f3661128b1e5dda69586afcff99a8f662e4126f.tar.bz2 | |
[libclc] Remove __attribute__((always_inline)) (#158791)
always_inline doesn't guarantee performance improvement.
Target-specific optimizations decide whether inlining is profitable.
Changes to amdgcn--amdhsa.bc:
* _Z9__clc_logDv16_f and _Z15__clc_remainderDv16_fS_ are not inlined.
* sincos vector function code size has doubled due to apparent
duplication.
Also replace typo _CLC_DECL with _CLC_DEF for function definition.
Diffstat (limited to 'llvm/lib/CodeGen/MachineOperand.cpp')
0 files changed, 0 insertions, 0 deletions