Efficient Execution of Graph Algorithms on CPU with SIMD Extensions

Abstract

Existing state-of-the-art CPU graph frameworks take advantage of multiple cores, but not the SIMD capability within each core. In this work, we retarget an existing GPU graph algorithm compiler to obtain the first graph framework that uses SIMD extensions on CPUs to efficiently execute graph algorithms. We evaluate this compiler on 10 benchmarks and 3 graphs on 3 different CPUs and also compare to the GPU. Evaluation results show that on a 8-core machine, enabling SIMD on a naive multi-core implementation achieves an additional 7.48x speedup, averaged across 10 benchmarks and 3 inputs. Applying our SIMD-targeted optimizations improves the plain SIMD implementation by 1.67x, outperforming a serial implementation by 12.46x. On average, the optimized multi-core SIMD version also outperforms the state-of-the-art graph framework, GraphIt, by 1.53x, averaged across 5 (common) benchmarks. SIMD execution on CPUs closes the gap between the CPU and GPU to 1.76x, but the CPU virtual memory performs better when graphs are much bigger than available physical memory.