Conversation
jharlow-intel
commented
Apr 2, 2026
jharlow-intel
commented
- Have you provided a meaningful PR description?
- Have you added a test, reproducer or referred to an issue with a reproducer?
- Have you tested your changes locally for CPU and GPU devices?
- Have you made sure that new changes do not introduce compiler warnings?
- Have you checked performance impact of proposed changes?
- Have you added documentation for your changes, if necessary?
- Have you added your changes to the changelog?
- If this PR is a work in progress, are you opening the PR as a draft?
|
View rendered docs @ https://intelpython.github.io/dpctl/pulls/2273/index.html |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_50 ran successfully. |
dpctl/_sycl_queue.pyx
Outdated
| """ | ||
| cdef DPCTLSyclEventRef ERef = NULL | ||
|
|
||
| ERef = _memcpy_impl(<SyclQueue>self, dest, src, count, NULL, 0) |
There was a problem hiding this comment.
Since this calls _memcpy_impl it is actually wrapping memcpy, not copy, i.e., https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html#api:queue-copy
The goal here should be to wrap the copy call from sycl::queue, which may seem redundant but, may have use (there have been cases in the past where memcpy breaks, for example). Users may want access to this specific API for some specific reason.
This means that the copy implementations will need to be added to the C API, probably libsyclinterface/source/dpctl_sycl_queue_interface.cpp and the respective libsyclinterface/include/syclinterface/dpctl_sycl_queue_interface.h.
There was a problem hiding this comment.
Yeah, Codex really dropping the ball and editing functions and comment it shouldn't, I'm leaving this PR a draft for now as I pick through it more finely, don't bother reviewing this until I know it's un-slopified and remove the draft tag and in-progress label.
Only opened the PR this early because I wanted the internal CI GPU testing
jharlow-intel
force-pushed
the
task/SyclQueue
branch
from
1e48eb4 to
ae492b5
Compare
| #include <stdexcept> | ||
| #include <sycl/sycl.hpp> /* SYCL headers */ | ||
| #include <utility> | ||
| #include <vector> |
There was a problem hiding this comment.
seems like the LLM picked up that this should have been included in the first place for this file
jharlow-intel
force-pushed
the
task/SyclQueue
branch
from
16cfb22 to
36cddbc
Compare
jharlow-intel
force-pushed
the
task/SyclQueue
branch
from
36cddbc to
4a0516d
Compare
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_51 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_52 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_53 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_50 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_51 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_52 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_50 ran successfully. |
|
Array API standard conformance tests for dpctl=0.22.0dev1=py310h93fe807_51 ran successfully. |
3 participants
