Lucene: Investigate performance of concurrent CAGRA search with batch size of 1
Nobody has claimed this yet.
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
Given the lack of support in Lucene for batched queries, it should still be possible to improve GPU utilization by running search queries from multiple host threads. After a concurrency bug fix in cuVS (https://github.com/rapidsai/cuvs/pull/1771/), we can now run multiple CAGRA search queries concurrently. However, the impact of any overhead in cuvs-lucene remains to be assessed.
Proposed evaluation grid:
- Workload: 5M vectors, 64 dimesions, FP16
- Hardware: AWS g6e.16xlarge (1xL40S GPU, 64 vCPU, 512 GB RAM)
- Software: cuVS C++ (baseline) vs. cuvs-lucene (test)
- Search config: k = 1000, batch_size = 1, n_threads up to 64
- Recall targets: 80%, 90%, 95%, 99%
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the proposed evaluation for 5M FP16 vectors on an AWS g6e.16xlarge, comparing cuVS C++ with cuvs-lucene at batch_size=1 and up to 64 host threads. Measure utilization, throughput, overhead, and recall at 80%, 90%, 95%, and 99%; done means a clear comparison of results and conclusions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- performance, search
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100