Add vectorized BinaryPacking int codec#72
Merged
Conversation
BinaryPacking using the Vector API pack/unpack kernels: each block is packed at its own maxbits with no exceptions. The maxbits computation is vectorized via an OR-reduction over the block. On Graviton4 (Neoverse V2, SVE2 128-bit), full codec round trip vs scalar BinaryPacking over 256K random ints: compress 2.5-3.0x faster across all bit widths; decompress 4.0x at low widths, tapering to 2.4x near width 31.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds VectorBinaryPacking, a BinaryPacking codec built on the existing Vector API pack/unpack kernels in the vector package. Each block is packed at its own maxbits with no exceptions, and the maxbits computation is vectorized with an OR-reduction over the block.
The codec is wired into BasicTest and SkippableBasicTest alongside VectorFastPFOR, with a dedicated round-trip test covering every lane width.
Benchmark on Graviton4 (Neoverse V2, SVE2 128-bit), full codec round trip vs scalar BinaryPacking over 256K random ints:
Requires --add-modules jdk.incubator.vector, same as VectorFastPFOR.