Evaluating Multi-GPU Sorting with Modern Interconnects

Summary: Evaluates multi-GPU sorting across PCIe/NVLink/NVSwitch; proposes a P2P GPU-only sort and a heterogeneous sort, benchmarked on three modern platforms. Reports up to 35x higher P2P throughput with NVSwitch, up to 14x CPU radix-sort speedup (P2P) and 9x (HET); on fast interconnects P2P beats HET by ~1.65x, and copy/compute overlap does not hide transfer bottlenecks. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6295
Venue: SIGMOD
Year: 2022
Pagerank: 4.810361e-05
Overall Rank: 7,155 | 50.28%
DOI: 10.1145/3514221.3517842

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
5,251	Triton Join: Efficiently Scaling to a Large Join State on GPUs with Fast Interconnects	2022	SIGMOD	5.6003972e-05
6,068	GPU Database Systems Characterization and Optimization	2024	VLDB	5.2240241e-05
6,451	Vortex: Overcoming Memory Capacity Limitations in GPU-Accelerated Large-Scale Data Analytics	2025	VLDB	5.0522576e-05
7,324	BOSS - An Architecture for Database Kernel Composition	2024	VLDB	4.7565238e-05
7,917	Terabyte-Scale Analytics in the Blink of an Eye	2026	VLDB	4.6129625e-05
8,476	Analyzing Vectorized Hash Tables Across CPU Architectures	2023	VLDB	4.4972784e-05
9,458	DPDPU: Data Processing with DPUs	2025	CIDR	4.3344018e-05
9,837	Efficiently Joining Large Relations on Multi-GPU Systems	2025	VLDB	4.269939e-05
10,293	GPU Acceleration of SQL Analytics on Compressed Data	2026	VLDB	4.1905499e-05

Outgoing Citations (Sorted by Pagerank)

Showing 18 of 18 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
307	SIMD-Scan: Ultra Fast in-Memory Table Scan using on-Chip Vector Processing Units	2009	VLDB	0.00028226342
395	One Trillion Edges: Graph Processing at Facebook-Scale	2015	VLDB	0.00024440144
403	Multi-Core, Main-Memory Joins: Sort vs. Hash Revisited	2014	VLDB	0.00024176677
424	Amazon Redshift and the Case for Simpler Data Warehouses	2015	SIGMOD	0.00023604384
584	Massively Parallel Sort-Merge Joins in Main Memory Multi-Core Database Systems	2012	VLDB	0.00019700451
594	HYRISE—A Main Memory Hybrid Storage Engine	2011	VLDB	0.00019515008
857	Efficient Transaction Processing in SAP HANA Database – The End of a Column Store Myth	2012	SIGMOD	0.00015840492
932	Fast Sort on CPUs and GPUs: A Case for Bandwidth Oblivious SIMD Sort	2010	SIGMOD	0.00015227954
1,610	A Comprehensive Study of Main-Memory Partitioning and its Application to Large-Scale Comparison- and Radix-Sort	2014	SIGMOD	0.00011155922
2,044	A Study of the Fundamental Performance Characteristics of GPUs and CPUs for Database Analytics	2020	SIGMOD	9.6963999e-05
2,167	Self-Tuning, GPU-Accelerated Kernel Density Models for Multidimensional Selectivity Estimation	2015	SIGMOD	9.3879598e-05
3,161	A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs	2017	SIGMOD	7.4648665e-05
3,328	Pump Up the Volume: Processing Large Data on GPUs with Fast Interconnects	2020	SIGMOD	7.2136181e-05
3,899	Efficient Join Algorithms For Large Database Tables in a Multi-GPU Environment	2021	VLDB	6.6513982e-05
4,000	MG-Join: A Scalable Join for Massively Parallel Multi-GPU Architectures	2021	SIGMOD	6.5419402e-05
4,048	PARADIS: An Efficient Parallel Algorithm for In-place Radix Sort	2015	VLDB	6.4970736e-05
4,649	SIMD- and Cache-Friendly Algorithm for Sorting an Array of Structures	2015	VLDB	6.0171025e-05
7,209	GPU-accelerated data management under the test of time	2020	CIDR	4.7949787e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
3,899	Efficient Join Algorithms For Large Database Tables in a Multi-GPU Environment	2021	VLDB	6.6513982e-05
236	High-Performance Sorting on Networks of Workstations	1997	SIGMOD	0.00031790391
944	Efficient Implementation of Sorting on Multi-Core SIMD CPU Architecture	2008	VLDB	0.0001512998
7,550	Efficient Top-K Query Processing on Massively Parallel Hardware	2018	SIGMOD	4.7089541e-05
7,209	GPU-accelerated data management under the test of time	2020	CIDR	4.7949787e-05
238	GPUTeraSort: High Performance Graphics Co-processor Sorting for Large Database Management	2006	SIGMOD	0.00031596093
932	Fast Sort on CPUs and GPUs: A Case for Bandwidth Oblivious SIMD Sort	2010	SIGMOD	0.00015227954
3,328	Pump Up the Volume: Processing Large Data on GPUs with Fast Interconnects	2020	SIGMOD	7.2136181e-05
9,837	Efficiently Joining Large Relations on Multi-GPU Systems	2025	VLDB	4.269939e-05
3,161	A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs	2017	SIGMOD	7.4648665e-05