Thanks to visit codestin.com
Credit goes to github.com

Skip to content

BUG: Fix non-contiguous 32-bit memory load when ARM/Neon is enabled #25243

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.

Sign up for GitHub

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
Dec 1, 2023
Merged

BUG: Fix non-contiguous 32-bit memory load when ARM/Neon is enabled #25243

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
21 changes: 6 additions & 15 deletions numpy/_core/src/common/simd/neon/memory.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,21 +52,12 @@ NPYV_IMPL_NEON_MEM(f64, double)
***************************/
NPY_FINLINE npyv_s32 npyv_loadn_s32(const npy_int32 *ptr, npy_intp stride)
{
switch (stride) {
case 2:
return vld2q_s32((const int32_t*)ptr).val[0];
case 3:
return vld3q_s32((const int32_t*)ptr).val[0];
case 4:
return vld4q_s32((const int32_t*)ptr).val[0];
default:;
int32x2_t ax = vcreate_s32(*ptr);
int32x4_t a = vcombine_s32(ax, ax);
a = vld1q_lane_s32((const int32_t*)ptr + stride, a, 1);
a = vld1q_lane_s32((const int32_t*)ptr + stride*2, a, 2);
a = vld1q_lane_s32((const int32_t*)ptr + stride*3, a, 3);
return a;
}
int32x4_t a;
a = vld1q_lane_s32((const int32_t*)ptr, a, 0);
a = vld1q_lane_s32((const int32_t*)ptr + stride, a, 1);
a = vld1q_lane_s32((const int32_t*)ptr + stride*2, a, 2);
a = vld1q_lane_s32((const int32_t*)ptr + stride*3, a, 3);
return a;
}

NPY_FINLINE npyv_u32 npyv_loadn_u32(const npy_uint32 *ptr, npy_intp stride)
Expand Down