On 2/17/24 01:33, Alexander Monakov wrote:
On Fri, 16 Feb 2024, Richard Henderson wrote:
Because non-embedded aarch64 is expected to have AdvSIMD enabled, merely
double-check with the compiler flags for __ARM_NEON and don't bother with
a runtime check. Otherwise, model the loop after the x86 SSE2 function,
and use VADDV to reduce the four vector comparisons.
Commit message will need a refresh (s/VADDV/UMAXV/, and there are no
vector comparisons anymore, "reduce the four vector components" perhaps).
Fixed, thanks.
r~
