-
Notifications
You must be signed in to change notification settings - Fork 160
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
[lapack][blas][cuda] Update host task impl to use enqueue_native_command #572
Commits on Sep 18, 2024
-
Implemented cusolver native_command.
See SYCL_EXT_ONEAPI_ENQUEUE_NATIVE_COMMAND for details. Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for e19072c - Browse repository at this point
Copy the full SHA e19072cView commit details
Commits on Sep 19, 2024
-
Impl native command for cublas
See SYCL_EXT_ONEAPI_ENQUEUE_NATIVE_COMMAND extension document for details. Generalize helpers funcs and use them for blas l1, l2, l3, batch Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for 44867dc - Browse repository at this point
Copy the full SHA 44867dcView commit details -
Update lapack tests to manage queue syncs
Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for a28cd4d - Browse repository at this point
Copy the full SHA a28cd4dView commit details -
cublas_native_named_func Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for b33b9e3 - Browse repository at this point
Copy the full SHA b33b9e3View commit details
Commits on Sep 20, 2024
-
Use cublas_native_named_func more
Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for 8fba319 - Browse repository at this point
Copy the full SHA 8fba319View commit details
Commits on Oct 1, 2024
-
this dep check is overzealous because it enforces that a dependent event cannot be submitted to run on the native device queue but not completed before a later event it is dependent upon has also been marked running on the device. This is not part of the sycl spec and unnecessarily slows down execution. Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for af4d1fd - Browse repository at this point
Copy the full SHA af4d1fdView commit details
Commits on Oct 2, 2024
-
Improve synchronous impl for scratchpad
These funcs are async in the cusolver backend. Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for c082d4a - Browse repository at this point
Copy the full SHA c082d4aView commit details -
Revert changes to lapack tests
Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Configuration menu - View commit details
-
Copy full SHA for ba20653 - Browse repository at this point
Copy the full SHA ba20653View commit details
Commits on Oct 4, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 61c9a53 - Browse repository at this point
Copy the full SHA 61c9a53View commit details
Commits on Oct 7, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 27b251f - Browse repository at this point
Copy the full SHA 27b251fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 94dcc7e - Browse repository at this point
Copy the full SHA 94dcc7eView commit details