An official website of the United States government
Graph convolutional networks (GCNs) are fundamental in various scientific applications, ranging from biomedical protein-protein interactions (PPI) to large-scale recommendation systems. An essential component for modeling graph structures in GCNs is sparse general matrix-matrix multiplication (SpGEMM). As the size of graph data continues to scale up, SpGEMMs are often conducted in an out-of-core fashion due to limited GPU memory space in resource-constrained systems. Albeit recent efforts that aim to alleviate the memory constraints of out-of-core SpGEMM through either GPU feature caching, hybrid CPU-GPU memory layout, or performing the computation in sparse format, current systems suffer from both high I/O latency and GPU under-utilization issues. In this paper, we first identify the problems of existing systems, where sparse format data alignment and memory allocation are the main performance bottlenecks, and propose AIRES, a novel algorithm-system co-design solution to accelerate out-of-core SpGEMM computation for GCNs. Specifically, from the algorithm angle, AIRES proposes to alleviate the data alignment issues on the block level for matrices in sparse formats and develops a tiling algorithm to facilitate row block-wise alignment. On the system level, AIRES employs a three-phase dynamic scheduling that features a dual-way data transfer strategy utilizing a tiered memory system: integrating GPU memory, GPU Direct Storage (GDS), and host memory to reduce I/O latency and improve throughput. Evaluations show that AIRES significantly outperforms the state-of-the-art methods, achieving up to 1.8× lower latency in real-world graph processing benchmarks.
more »
« less
ASA: A ccelerating S parse A ccumulation in Column-wise SpGEMM
Sparse linear algebra is an important kernel in many different applications. Among various sparse general matrix-matrix multiplication (SpGEMM) algorithms, Gustavson’s column-wise SpGEMM has good locality when reading input matrix and can be easily parallelized by distributing the computation of different columns of an output matrix to different processors. However, the sparse accumulation (SPA) step in column-wise SpGEMM, which merges partial sums from each of the multiplications by the row indices, is still a performance bottleneck. The state-of-the-art software implementation uses a hash table for partial sum search in the SPA, which makes SPA the largest contributor to the execution time of SpGEMM. There are three reasons that cause the SPA to become the bottleneck: (1) hash probing requires data-dependent branches that are difficult for a branch predictor to predict correctly; (2) the accumulation of partial sum is dependent on the results of the hash probing, which makes it difficult to hide the hash probing latency; and (3) hash collision requires time-consuming linear search and optimizations to reduce these collisions require an accurate estimation of the number of non-zeros in each column of the output matrix. This work proposes ASA architecture to accelerate the SPA. ASA overcomes the challenges of SPA by (1) executing the partial sum search and accumulate with a single instruction through ISA extension to eliminate data-dependent branches in hash probing, (2) using a dedicated on-chip cache to perform the search and accumulation in a pipelined fashion, (3) relying on the parallel search capability of a set-associative cache to reduce search latency, and (4) delaying the merging of overflowed entries. As a result, ASA achieves an average of 2.25× and 5.05× speedup as compared to the state-of-the-art software implementation of a Markov clustering application and its SpGEMM kernel, respectively. As compared to a state-of-the-art hashing accelerator design, ASA achieves an average of 1.95× speedup in the SpGEMM kernel.
more »
« less
- Award ID(s):
- 1750826
- PAR ID:
- 10407645
- Date Published:
- Journal Name:
- ACM Transactions on Architecture and Code Optimization
- Volume:
- 19
- Issue:
- 4
- ISSN:
- 1544-3566
- Page Range / eLocation ID:
- 1 to 24
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We consider a sparse matrix-matrix multiplication (SpGEMM) setting where one matrix is square and the other is tall and skinny. This special variant, TS-SpGEMM, has important applications in multi-source breadth-first search, influence maximization, sparse graph embedding, and algebraic multigrid solvers. Unfortunately, popular distributed algorithms like sparse SUMMA deliver suboptimal performance for TS-SpGEMM. To address this limitation, we develop a novel distributed-memory algorithm tailored for TS SpGEMM. Our approach employs customized 1D partitioning for all matrices involved and leverages sparsity-aware tiling for efficient data transfers. In addition, it minimizes communication overhead by incorporating both local and remote computations. On average, our TSSpGEMM algorithm attains 5x performance gains over 2D and 3D SUMMA. Furthermore, we use our algorithm to implement multi-source breadth-first search and sparse graph embedding algorithms and demonstrate their scalability up to 512 Nodes (or 65,536 cores) on NERSC Perlmutter.more » « less
-
Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse kernel. Numerous methods have been developed to accelerate SpMV. However, no single method consistently gives the highest performance across a wide range of matrices. For this reason, a performance prediction model is needed to predict the best SpMV method for a given sparse matrix. Unfortunately, predicting SpMV’s performance is challenging due to the diversity of factors that impact it. In this work, we develop a machine learning framework called WISE that accurately predicts the magnitude of the speedups of different SpMV methods over a baseline method for a given sparse matrix. WISE relies on a novel feature set that summarizes a matrix’s size, skew, and locality traits. WISE can then select the best SpMV method for each specific matrix. With a set of nearly 1,500 matrices, we show that using WISE delivers an average speedup of 2.4× over using Intel’s MKL in a 24-core server.more » « less
-
Breath-first search (BFS) is a fundamental building block in many graph-based applications. It is challenging to optimize due to its irregular memory-access pattern. Prior work, based on hardware description languages (HDLs) and high-level synthesis (HLS), address the memory-access bottleneck by using techniques such as edge-centric traversal, data alignment, and compute-unit (CU) replication. While these optimizations work well for dense graph datasets, optimizing BFS on sparse graphs remains a significant challenge due to the kernel launch overhead and poor workload distribution across processing elements. As a complement to the prior work, we present and evaluate optimizations in OpenCL for BFS on sparse graphs. Specifically, we explore application-specific and architecture-aware optimizations aimed at mitigating the irregular global-memory access bottleneck in sparse graphs. In our kernel design, we consider factors such as choice of data structure between queue and array, number of memory banks, and kernel launch configuration. We evaluate the impact of proposed optimizations on a diverse set of sparse graphs. In comparison with the state-of-the-art OpenCL implementation for FPGA, we achieve 5.7x-22.3x speedup on Stratix 10 SX 2800 FPGA for the graphs that are most sensitive to our optimization scheme.more » « less
-
This work addresses the 2019 Sparse Deep Neural Network Graph Challenge with an implementation of this challenge using the GraphBLAS programming model. We demonstrate our solution to this challenge with GraphBLAST, a GraphBLAS implementation on the GPU, and compare it to SuiteSparse, a GraphBLAS implementation on the CPU. The GraphBLAST implementation is 1.94× faster than Suite-Sparse; the primary opportunity to increase performance on the GPU is a higher-performance sparse-matrix-times-sparse-matrix (SpGEMM) kernel.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3543068
