-
Notifications
You must be signed in to change notification settings - Fork 791
[SYCL][XPTI] Performance improvements for performance oriented toolchains #19953
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
Conversation
+ Improves the performance of collectors and downstream collectors by limiting the amount of metada that is attached to SYCL events + To get additional metadata, toolchains will have to also subscribe to the stream "sycl.debug" and the additional metadata will be sent in the orginal stream + Replaced all xptiMakeEvent() calls with the new xptiCreateTracepoint() function Signed-off-by: Vasanth Tovinkere <[email protected]>
Signed-off-by: Vasanth Tovinkere <[email protected]>
Signed-off-by: Vasanth Tovinkere <[email protected]>
unified-runtime/source/loader/layers/tracing/ur_tracing_layer.cpp
Outdated
Show resolved
Hide resolved
unified-runtime/source/loader/layers/tracing/ur_tracing_layer.cpp
Outdated
Show resolved
Hide resolved
unified-runtime/source/loader/layers/tracing/ur_tracing_layer.cpp
Outdated
Show resolved
Hide resolved
Signed-off-by: Vasanth Tovinkere <[email protected]>
These failures are unrelated:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
CUDA LGTM
Jenkins failure is unrelated, see #19929 (comment) |
|
||
- To support performance and debug streams, subscribing to the stream **"sycl.debug"** | ||
allows the default streams to contain additional metadata when keeping overheads | ||
to a minimum is not important |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
to a minimum is not important | |
to a minimum is not important. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
UR lgtm.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graph changes LGTM
@sergey-semenov Could you please review this PR on behalf of @intel/llvm-reviewers-runtime. @maarquitos14 and @KseniyaTikhomirova are both on vacation at the moment. |
Implementation of XPTI within SYCL combined debug and performance streams over time and this PR improves the performance by 15-20% for toolschains by separating the debug data from performance streams.