… We engineer a GPU implementation of a B-Tree that supports concurrent queries (point, …
Our B-tree outperforms the state of the art, a GPU log-structured merge tree (LSM) and a GPU …

… a high performance GPU concurrent B+tree… GPU show that our GPU concurrent B+tree
is efficient with a throughput of 1.23 billion per second. Compared to a state-of-the-art GPU B+tree …

… We introduce a GPU B-Tree that supports snapshots and offers … Our work builds on this
GPU B-Tree [3] which uses cache-line… high performance. However, one consequence of this …

… In this paper, we first identify the gaps between B+tree and GPUs. Concurrent B+tree … have
occupied about 80% of the accelerator market share in the high-performance computing (HPC…

… GPUs requiring careful engineering of a host of issues. Therefore, the current best parallelizations
of R-tree on GPU has … a new root will be created, like B-tree [21], its counterpart for one …

… novel B+tree structure, to bridge the gaps between B+tree and … the queries on GPU and
updates on CPU, and B+tree will be … Sadayappan, “High-performance code generation for stencil …

… GPU, which becomes the bottlenecks of many applications and limits the benefits brought by
using high-performance GPUs [… They designed a GPU B-Tree for batch search and update …

… a novel design for a B+-tree based on the heterogeneous computing platform and the hybrid
memory architecture found in GPUs. We propose a hybrid CPU-GPU B+-tree, – HB+-tree, – …

… [41] improve the query throughput of B+tree on GPUs using several … strategy for STM on
B+tree to minimize the possible fallback … Engineering a High-performance GPU B-Tree. In …

… To address these challenges, we will introduce a GPU B-Tree design that scales to … These
device-wide primitives achieve high performance only when the GPU is fully utilized. Our fully-…