Wenju He a271d07488

[libclc] Implement erf/erfc vector function with loop since scalar function is large (#157055) ...

This PR reduces amdgcn--amdhsa.bc size by 1.8% and nvptx64--nvidiacl.bc
size by 4%.
Loop trip count is constant and backend can decide whether to unroll.

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

2025-09-05 19:58:24 +08:00

..

include/clc

[libclc] Implement erf/erfc vector function with loop since scalar function is large (#157055)

2025-09-05 19:58:24 +08:00

lib

[libclc] Implement erf/erfc vector function with loop since scalar function is large (#157055)

2025-09-05 19:58:24 +08:00