Skip to content

[SYCL][L0] Use immediate commandlists. #5833

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 33 commits into from
Apr 15, 2022
Merged

[SYCL][L0] Use immediate commandlists. #5833

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
33 commits
Select commit Hold shift + click to select a range
1179d9c
[SYCL] Use immediate commandlist.
rdeodhar Mar 17, 2022
0982a5c
Formatting change.
rdeodhar Mar 18, 2022
cd76f9c
Formatting change.
rdeodhar Mar 18, 2022
3042253
Merge branch 'sycl' of https://github.com/intel/llvm into cmdlist
rdeodhar Mar 18, 2022
9a8a9f6
Disable use of device-only events when immediate commandlists are bei…
rdeodhar Mar 18, 2022
2ad8746
Changed scheme for destroying immediate commandlists.
rdeodhar Mar 19, 2022
04418ef
Formatting change.
rdeodhar Mar 19, 2022
0581dca
Use device-only events in on-demand mode.
rdeodhar Mar 21, 2022
4b8ebce
Merge branch 'sycl' of https://github.com/intel/llvm into cmdlist
rdeodhar Mar 21, 2022
d2e4e80
Disable extended ZE_DEBUG trace.
rdeodhar Mar 22, 2022
9deda92
Remove debug code, some cleanup.
rdeodhar Mar 22, 2022
fe7fd06
Immediate commandlist usage is default OFF.
rdeodhar Mar 22, 2022
020764d
Code restructuring.
rdeodhar Mar 23, 2022
954e35b
Restructured code to remove dispatch layer.
rdeodhar Mar 23, 2022
2e5b5f9
Added documentation of environment variable control.
rdeodhar Mar 23, 2022
fc6ed53
Modified comments.
rdeodhar Mar 23, 2022
2aded1d
Addressed review comments.
rdeodhar Mar 25, 2022
73a5349
Restructuring to fix indirect access tracking.
rdeodhar Mar 25, 2022
350c85a
Changes to properly implement SYCL queue.wait().
rdeodhar Mar 30, 2022
7b3f783
Minor changes.
rdeodhar Mar 31, 2022
32058e5
Restructuring of getZeQueue.
rdeodhar Apr 1, 2022
01a5c5a
Fixes to internal plugin queue indices and L0 indices.
rdeodhar Apr 5, 2022
4c00577
Bug fix in queue group selection.
rdeodhar Apr 5, 2022
e238505
Cleanup after review.
rdeodhar Apr 6, 2022
3f98e8f
Merge branch 'sycl' of https://github.com/intel/llvm into cmdlist
rdeodhar Apr 6, 2022
381050e
Formatting change.
rdeodhar Apr 6, 2022
c653e39
When using immediate commandlists, use only copy engine index 0 by de…
rdeodhar Apr 6, 2022
0965479
Fixed a leak in event pools.
rdeodhar Apr 7, 2022
4441ea3
Updated some comments and added a TODO around Event release.
rdeodhar Apr 8, 2022
29cf917
Changed convention for InUse flag for immediate commandlists.
rdeodhar Apr 8, 2022
fd2935b
Merge branch 'sycl' of https://github.com/intel/llvm into cmdlist
rdeodhar Apr 11, 2022
28b40dd
Fixed bug in setting last command event.
rdeodhar Apr 12, 2022
5d9fb0d
Merge branch 'sycl' of https://github.com/intel/llvm into cmdlist
rdeodhar Apr 13, 2022
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
3 changes: 2 additions & 1 deletion sycl/doc/EnvironmentVariables.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,8 @@ variables in production code.</span>
| `SYCL_PI_LEVEL_ZERO_USE_COPY_ENGINE` | Any(\*) | This environment variable enables users to control use of copy engines for copy operations. If the value is an integer, it will allow the use of copy engines, if available in the device, in Level Zero plugin to transfer SYCL buffer or image data between the host and/or device(s) and to fill SYCL buffer or image data in device or shared memory. The value of this environment variable can also be a pair of the form "lower_index:upper_index" where the indices point to copy engines in a list of all available copy engines. The default is 1. |
| `SYCL_PI_LEVEL_ZERO_USE_COMPUTE_ENGINE` | Integer | It can be set to an integer (>=0) in which case all compute commands will be submitted to the command-queue with the given index in the compute command group. If it is instead set to a negative value then all available compute engines may be used. The default value is "0" |
| `SYCL_PI_LEVEL_ZERO_USE_COPY_ENGINE_FOR_D2D_COPY` (experimental) | Integer | Allows the use of copy engine, if available in the device, in Level Zero plugin for device to device copy operations. The default is 0. This option is experimental and will be removed once heuristics are added to make a decision about use of copy engine for device to device copy operations. |
| `SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS` | Any(\*) | Enable support of device-scope events whose state is not visible to the host. If enabled mode is SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS=1 the Level Zero plugin would create all events having device-scope only and create proxy host-visible events for them when their status is needed (wait/query) on the host. If enabled mode is SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS=2 the Level Zero plugin would create all events having device-scope and add proxy host-visible event at the end of each command-list submission. The default is 0, meaning all events are host-visible. |
| `SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS` | Any(\*) | Enable support of device-scope events whose state is not visible to the host. If enabled mode is SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS=1 the Level Zero plugin would create all events having device-scope only and create proxy host-visible events for them when their status is needed (wait/query) on the host. If enabled mode is SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS=2 the Level Zero plugin would create all events having device-scope and add proxy host-visible event at the end of each command-list submission. The default is 2, meaning only the last event in a batch is host-visible. |
| `SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS` | Integer | When set to a positive value enables use of Level Zero immediate commandlists, which means there is no batching and all commands are immediately submitted for execution. Default is 0. Note: When immediate commandlist usage is enabled it is necessary to also set SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS to either 0 or 1. |

## Debugging variables for CUDA Plugin

Expand Down
Loading