More Bang For Your Buck(et): Fast and Space-efficient Hardware-accelerated Coarse-granular Indexing on GPUs

TL;DR

This paper introduces cgRX, a GPU-based coarse-granular index that significantly improves memory efficiency, range-lookup speed, and updateability by indexing buckets of keys instead of individual keys, leveraging hardware-accelerated raytracing cores.

Contribution

It generalizes the RTIndeX approach to reduce memory overhead and enable fast range-lookups and updates through bucket-based indexing on GPUs.

Findings

cgRX achieves 1.5-3x higher throughput per memory footprint compared to baselines.

Range-lookup performance is improved by up to 2x over RTIndeX.

Updateability is up to 5.6x faster than rebuilding from scratch.

Abstract

In recent work, we have shown that NVIDIA's raytracing cores on RTX video cards can be exploited to realize hardware-accelerated lookups for GPU-resident database indexes. On a high level, the concept materializes all keys as triangles in a 3D scene and indexes them. Lookups are performed by firing rays into the scene and utilizing the index structure to detect hits in a hardware-accelerated fashion. While this approach called RTIndeX (or short RX) is indeed promising, it currently suffers from three limitations: (1) significant memory overhead per key, (2) slow range-lookups, and (3) poor updateability. In this work, we show that all three problems can be tackled by a single design change: Generalizing RX to become a coarse-granular index cgRX. Instead of indexing individual keys, cgRX indexes buckets of keys which are post-filtered after retrieval. This drastically reduces the memory overhead, leads to the generation of a smaller and more efficient index structure, and enables fast range-lookups as well as updates. We will see that representing the buckets in the 3D space such that the lookup of a key is performed both correctly and efficiently requires the careful orchestration of firing rays in a specific sequence. Our experimental evaluation shows that cgRX offers the most bang for the buck(et) by providing a throughput in relation to the memory footprint that is 1.5-3x higher than for the comparable range-lookup supporting baselines. At the same time, cgRX improves the range-lookup performance over RX by up to 2x and offers practical updateability that is up to 5.6x faster than rebuilding from scratch.