oneDNN v3.7 release notes #2481
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
documentation
vgvozdeva
force-pushed
the
vgvozdeva/release-notes
branch
from
17acd19 to
23e00b1
Compare
mgouicem
reviewed
Jan 23, 2025
Comment on lines
+18
to
+20
| * [experimental] Extended microkernel API: | ||
| Introduced int4 quantization support. | ||
| Fpmath mode API |
There was a problem hiding this comment.
I don't think we did that in external microkernel API (and cannot find the related commits).
However we did add a new query for B matrix packing type.
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
sgeor255
approved these changes
Jan 23, 2025
TaoLv
approved these changes
Jan 23, 2025
vpirogov
reviewed
Jan 23, 2025
vpirogov
reviewed
Jan 23, 2025
| # Usability | ||
| * With SYCL runtime, memory objects on CPU engine are now reference-counted and no more need to be explicitly kept alive by user for the duration of the primitive execution. This align memory object lifetime behavior on CPU and GPU engines. | ||
| * Improve verbose diagnostic to better identify issues during dispatching, primitive and kernel creation for CPU primitive and GPU (in case of OpenCL implementation) primitive implementations. | ||
| * Improve verbose diagnostic to simplify debugging of nGEN fallbacks. |
There was a problem hiding this comment.
nGEN is an implementation detail. I would suggest calling out specific situations when new diagnostics is triggered.
Suggested change
| * Improve verbose diagnostic to simplify debugging of nGEN fallbacks. | |
| * Improved verbose diagnostics for Intel GPU driver compatibility issues. |
vpirogov
reviewed
Jan 23, 2025
| @@ -0,0 +1,44 @@ | |||
| # Performance Optimizations | |||
| ## Intel Architecture Processors | |||
There was a problem hiding this comment.
@tprimak, I think we had a bit more improvements for x64. Please review and update this section.
vpirogov
reviewed
Jan 23, 2025
| * Improved fp16/bf16 softmax performance with relaxed [accumulation mode](https://oneapi-src.github.io/oneDNN/dev_guide_attributes_accumulation_mode.html#doxid-dev-guide-attributes-accumulation-mode). | ||
| * Added support and improved perfomance for fp8 matmul with bf16/fp16. | ||
|
|
||
| ## Intel Graphics Products |
There was a problem hiding this comment.
@karturov, please review and update this section.
vpirogov
reviewed
Jan 23, 2025
vpirogov
reviewed
Jan 23, 2025
| * Improved performance of the following subgraphs with Graph API | ||
| * Scaled dot-product Attention (SDPA) [with causal mask](https://oneapi-src.github.io/oneDNN/dev_guide_graph_sdpa.html#doxid-dev-guide-graph-sdpa) | ||
| * Scaled dot-product Attention (SDPA) [with compressed key and value](https://oneapi-src.github.io/oneDNN/dev_guide_graph_sdpa_compressed_kv.html#doxid-dev-guide-graph-sdpa-compressed-kv) | ||
| ## AArch64-based Processors |
There was a problem hiding this comment.
@jondea, @theComputeKid, could you please help summarizing AArch64 improvements?
Co-authored-by: Mourad Gouicem <mourad.gouicem@intel.com>
Co-authored-by: Tao Lv <tao.a.lv@intel.com>
Co-authored-by: Vadim Pirogov <vadim.o.pirogov@intel.com>
Co-authored-by: Tao Lv <tao.a.lv@intel.com>
Co-authored-by: Tao Lv <tao.a.lv@intel.com>
Co-authored-by: Tao Lv <tao.a.lv@intel.com>
Co-authored-by: Vadim Pirogov <vadim.o.pirogov@intel.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR includes a release notes draft based on the information from the PRs for the contributors to review. Your additions and corrections are highly appreciated.