Make numeric segmenter chunk size and head graph configurable (#603) - #603
Make numeric segmenter chunk size and head graph configurable (#603)#603Victor-C-Zhang wants to merge 2 commits into
Conversation
|
@Victor-C-Zhang has exported this pull request. If you are a Meta employee, you can view the originating Diff in D99729917. |
Summary: Add a segmenter to all XLDB numeric graphs (U8/U16/U32/U64/F32) that auto-chunks input at ~16MB boundaries, aligned to element width. This is implemented inside makeXldbGenericIntCGraphImpl so it applies to all int/float graph variants automatically. Fallback (ZSTD) and Store graphs are not segmented. There is an existing numeric segmenter standard graph, but we can't use it because it doesn't allow us to specify the chunk size or inner graph. The next diff in this stack will add support in the numeric segmenter. When a new OpenZL release is issued, we will migrate to the numeric segmenter. Differential Revision: D99729801
meta-codesync
Bot
changed the title
…ok#603) Summary: Make the numeric segmenter accept local params for the chunk byte size and head graph, replacing the previously hardcoded values. - Chunk size: read via ZL_Segmenter_getLocalIntParam() using ZL_SEGM_NUMERIC_CHUNK_BYTE_SIZE_MAX_PID. Falls back to 16MB default if not provided. - Head graph: read via ZL_Segmenter_getCustomGraphs(). Falls back to ZL_GRAPH_NUMERIC_COMPRESS if no custom graph is provided. Both changes are backward-compatible — existing callers that don't provide these params get identical behavior to before. Differential Revision: D99729917
2dd7410 to
2c3634c
Compare
…ok#603) Summary: Pull Request resolved: facebook#603 Make the numeric segmenter accept local params for the chunk byte size and head graph, replacing the previously hardcoded values. - Chunk size: read via ZL_Segmenter_getLocalIntParam() using ZL_SEGM_NUMERIC_CHUNK_BYTE_SIZE_MAX_PID. Falls back to 16MB default if not provided. - Head graph: read via ZL_Segmenter_getCustomGraphs(). Falls back to ZL_GRAPH_NUMERIC_COMPRESS if no custom graph is provided. Both changes are backward-compatible — existing callers that don't provide these params get identical behavior to before. Differential Revision: D99729917
2c3634c to
f84df91
Compare
|
Hi @Victor-C-Zhang! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
1 participant
Summary:
Make the numeric segmenter accept local params for the chunk byte size
and head graph, replacing the previously hardcoded values.
ZL_SEGM_NUMERIC_CHUNK_BYTE_SIZE_MAX_PID. Falls back to 16MB default
if not provided.
ZL_GRAPH_NUMERIC_COMPRESS if no custom graph is provided.
Both changes are backward-compatible — existing callers that don't
provide these params get identical behavior to before.
Differential Revision: D99729917