Skip to content

Fix bf16 move_ker bug #29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 27, 2020
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions torch_ipex/csrc/cpu/bf16/vec/bf16_vec_kernel.h
Original file line number Diff line number Diff line change
Expand Up @@ -166,9 +166,9 @@ static inline void move_ker(at::BFloat16 *out, at::BFloat16 *in, int64_t len) {
int64_t i = 0;
for (; i < len - 63; i += 64) {
auto in0 = _mm512_loadu_si512(in + i);
auto in1 = _mm512_loadu_si512(in + i + 16);
auto in1 = _mm512_loadu_si512(in + i + 32);
_mm512_storeu_si512(out + i, in0);
_mm512_storeu_si512(out + i + 16, in1);
_mm512_storeu_si512(out + i + 32, in1);
}

if (i < len - 31) {
Expand Down