Implement dpctl.tensor.sum reduction operation#1210
Implement dpctl.tensor.sum reduction operation#1210oleksandr-pavlyk merged 10 commits intomasterfrom
dpctl.tensor.sum reduction operation#1210Conversation
|
View rendered docs @ https://intelpython.github.io/dpctl/pulls/1210/index.html |
|
Array API standard conformance tests failed to run for dpctl=0.14.3dev1=py310h76be34b_116. |
3cf142e to
62f2d46
Compare
2b69338 to
55711fd
Compare
|
Array API standard conformance tests failed to run for dpctl=0.14.3dev1=py310h76be34b_117. |
|
Array API standard conformance tests failed to run for dpctl=0.14.3dev1=py310h76be34b_117. |
|
Array API standard conformance tests for dpctl=0.14.3dev1=py310h76be34b_120 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.3dev1=py310h76be34b_121 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.3dev1=py310h76be34b_132 ran successfully. |
Added MemoryOverap check, and the array range check per FIXME note and PR review feedback. Also consolidated transfer of iteration/reduction metadata into a single operation to improve test stability on CPU and improve overall host submission overhead time.
|
Array API standard conformance tests for dpctl=0.14.3dev2=py310h7bf5fec_15 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.3dev2=py310h7bf5fec_17 ran successfully. |
|
Deleted rendered PR docs from intelpython.github.com/dpctl, latest should be updated shortly. 🤞 |
|
Array API standard conformance tests for dpctl=0.14.3dev2=py310h7bf5fec_20 ran successfully. |
This PR adds implementation of sum-reduction over an axis of
dpctl.tensor.usm_ndarray.