LLM-synthesized GPU query kernels outperform engineered engines by 7.4x, but a portable SYCL engine with lifted optimizations closes the gap to 1.27x, suggesting engineering remains preferable on GPUs.
Black or white? how to develop an autotuner for memory- based analytics
5 Pith papers cite this work, alongside 60 external citations. Polarity classification is still indexing.
5
Pith papers citing it
60
external citations · external index
years
2026 5representative citing papers
PerfEvolve equips LLM agents with executable skills from expert methods to enable dynamic, version-consistent, workload-specific tuning in PostgreSQL, outperforming documentation baselines by up to 35.2% on TPC-C and TPC-H.
FliX flips the indexing paradigm by mapping GPU compute to data buckets and using batch binary search, delivering up to 6.5x lower query latency and 4x better throughput per memory than leading GPU B-trees and LSM-trees.
GS-NFS accelerates dynamic 3DGS encoding and decoding by 1-2 orders of magnitude on GPU while maintaining competitive compression ratios and rendering quality.
Presto is extended to GPU-aware execution using cuDF experiments on TPC-H, delivering up to 6x cost/performance gains over CPU Presto via optimized data paths and inter-operator communication.
citing papers explorer
-
From Custom-Fit to Portable: Bridging the Gap Between Synthesized and Engineered GPU Query Execution
LLM-synthesized GPU query kernels outperform engineered engines by 7.4x, but a portable SYCL engine with lifted optimizations closes the gap to 1.27x, suggesting engineering remains preferable on GPUs.
-
A Case for Agentic Tuning: From Documentation to Action in PostgreSQL
PerfEvolve equips LLM agents with executable skills from expert methods to enable dynamic, version-consistent, workload-specific tuning in PostgreSQL, outperforming documentation baselines by up to 35.2% on TPC-C and TPC-H.
-
FliX: Flipped-Indexing for Scalable GPU Queries and Updates
FliX flips the indexing paradigm by mapping GPU compute to data buckets and using batch binary search, delivering up to 6.5x lower query latency and 4x better throughput per memory than leading GPU B-trees and LSM-trees.
-
GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds
GS-NFS accelerates dynamic 3DGS encoding and decoding by 1-2 orders of magnitude on GPU while maintaining competitive compression ratios and rendering quality.
-
Accelerating Presto with GPUs
Presto is extended to GPU-aware execution using cuDF experiments on TPC-H, delivering up to 6x cost/performance gains over CPU Presto via optimized data paths and inter-operator communication.