Open
Conversation
Signed-off-by: Onur Satici <onur@spiraldb.com>
github-actions
bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Previous Runs (1)
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingSummary
Detailed Results Table
|
Contributor
Benchmarks: TPC-H SF=1 on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: FineWeb NVMeSummary
Detailed Results Table
|
Contributor
Benchmarks: TPC-H SF=1 on S3Summary
Detailed Results Table
|
Contributor
🚨🚨🚨❌❌❌ SQL BENCHMARK FAILED ❌❌❌🚨🚨🚨Benchmark |
Contributor
Benchmarks: TPC-DS SF=1 on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: FineWeb S3Summary
Detailed Results Table
|
Contributor
Benchmarks: Statistical and Population GeneticsSummary
Detailed Results Table
|
Contributor
Benchmarks: Random AccessSummary
Detailed Results Table
|
Contributor
Benchmarks: TPC-H SF=10 on S3Summary
Detailed Results Table
|
Contributor
Benchmarks: Clickbench on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: CompressionSummary
Detailed Results Table
|
gatesn
reviewed
Feb 23, 2026
Contributor
There was a problem hiding this comment.
This seems to draw some weird boundaries?
What's the goal here? To move Vortex towards a buffer pool? Or to allow I/O to read into both host and device buffers?
Feels like the sort of thing we should have a discussion / rfc for! But don't want to stall your experiments on this
Contributor
Author
|
yes we could use a discussion here, the goal is to have control on how the buffer handles are created during a scan. I want to use a vortex read at implementation, but I also want to control the allocations |
Contributor
Author
Contributor
|
How would for example CUDA host mem malloc fit into this? |
a10y
reviewed
Feb 23, 2026
| /// A destination for I/O reads that can be finalized into a [`BufferHandle`]. | ||
| pub trait WriteTarget: Send + 'static { | ||
| /// Returns the buffer as a mutable slice. | ||
| fn as_mut_slice(&mut self) -> &mut [u8]; |
Contributor
There was a problem hiding this comment.
would it make more sense to return an uninit slice? that way we can avoid zero-initializing all the memory. maybe that's too much of a microoptimization
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
4 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.
Summary
Add buffer allocator trait and a simple cpu buffer pool.
VortexReadAtnow can own a buffer pool through a lower level traitReadInto, and AllocatingReader will bridge them.This PR adds the types, but doesn't wire the buffer pool in yet. The existing ReadAt implementors currently use the default allocator, which allocates a fresh new BufferMut per call