Abstract | ||
---|---|---|
The advent of FPGA acceleration platforms with direct coherent access to processor memory creates an opportunity for accelerating applications with irregular parallelism governed by large in-memory pointer-based data structures. This paper uses the simple reference behavior of a linked-list traversal as a proxy to study the performance potentials of accelerating these applications on shared-memory processor-FPGA systems. The linked-list traversal is parameterized by node layout in memory, per-node data payload size, payload dependence, and traversal concurrency to capture the main performance effects of different pointer-based data structures and algorithms. The paper explores the trade-offs over a wide range of implementation options available on shared-memory processor-FPGA architectures, including using tightly-coupled processor assistance. We make observations of the key effects on currently available systems including the Xilinx Zynq, the Intel QuickAssist QPI FPGA Platform, and the Convey HC-2. The key results show: (1) the FPGA fabric is least efficient when traversing a single list with non-sequential node layout and a small payload size; (2) processor assistance can help alleviate this shortcoming; and (3) when appropriate, a fabric only approach that interleaves multiple linked list traversals is an effective way to maximize traversal performance. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2847263.2847269 | ACM/SIGDA International Symposium on Field-Programmable Gate Arrays |
Field | DocType | Citations |
Pointer (computer programming),Data structure,Tree traversal,Linked list,Shared memory,Computer science,Parallel computing,Real-time computing,Payload (computing),Embedded system,Payload,Cache coherence | Conference | 12 |
PageRank | References | Authors |
0.60 | 9 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriel Weisz | 1 | 144 | 8.30 |
Joseph Melber | 2 | 12 | 0.60 |
Yu Wang | 3 | 57 | 2.44 |
Kermin E. Fleming | 4 | 190 | 15.12 |
Eriko Nurvitadhi | 5 | 399 | 33.08 |
James C. Hoe | 6 | 2048 | 141.34 |