Y. C. Xu

Jinliang Shi, Shigang Li, Youxuan Xu et al.

Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior computing power, which is promising to boost the performance of matrix operators to a higher level. However, due to the irregularity of unstructured sparse data, it is difficult to deliver practical speedups on TCUs. To this end, we propose FlashSparse, a novel approach to bridge the gap between sparse workloads and the TCU architecture. Specifically, FlashSparse minimizes the sparse granularity for SpMM and SDDMM on TCUs through a novel swap-and-transpose matrix multiplication strategy. Benefiting from the minimum sparse granularity, the computation redundancy is remarkably reduced while the computing power of TCUs is fully utilized. Besides, FlashSparse is equipped with a memory-efficient thread mapping strategy for coalesced data access and a sparse matrix storage format to save memory footprint. Extensive experimental results on H100 and RTX 4090 GPUs show that FlashSparse sets a new state-of-the-art for sparse matrix multiplications (geometric mean 5.5x speedup over DTC-SpMM and 3.22x speedup over RoDe).

Yaodan Xu, Sheng Zhou, Zhisheng Niu

For servers incorporating parallel computing resources, batching is a pivotal technique for providing efficient and economical services at scale. Parallel computing resources exhibit heightened computational and energy efficiency when operating with larger batch sizes. However, in the realm of online services, the adoption of a larger batch size may lead to longer response times. This paper aims to provide a dynamic batching scheme that delicately balances latency and efficiency. The system is modeled as a batch service queue with size-dependent service times. Then, the design of dynamic batching is formulated as a semi-Markov decision process (SMDP) problem, with the objective of minimizing the weighted sum of average response time and average power consumption. A method is proposed to derive an approximate optimal SMDP solution, representing the chosen dynamic batching policy. By introducing an abstract cost to reflect the impact of "tail" states, the space complexity and the time complexity of the procedure can decrease by 63.5% and 98%, respectively. Numerical results showcase the superiority of SMDP-based batching policies across various parameter setups. Additionally, the proposed scheme exhibits noteworthy flexibility in balancing power consumption and latency.

Jinliang Shi, Shigang Li, Youxuan Xu et al.

Sparse matrix multiplication operators (i.e., SpMM and SDDMM) are widely used in deep learning and scientific computing. Modern accelerators are commonly equipped with Tensor cores and CUDA cores to accelerate sparse operators. The former brings superior computing power but only for structured matrix multiplication, while the latter has relatively lower performance but with higher programming flexibility. In this work, we discover that utilizing one resource alone leads to inferior performance for sparse matrix multiplication, due to their respective limitations. To this end, we propose Libra, a systematic approach that enables synergistic computation between CUDA and Tensor cores to achieve the best performance for sparse matrix multiplication. Specifically, we propose a 2D-aware workload distribution strategy to find out the sweet point of task mapping for different sparse operators, leveraging both the high performance of Tensor cores and the low computational redundancy on CUDA cores. In addition, Libra incorporates systematic optimizations for heterogeneous computing, including hybrid load-balancing, finely optimized kernel implementations, and GPU-accelerated preprocessing. Extensive experimental results on H100 and RTX 4090 GPUs show that Libra outperforms the state-of-the-art by on average 3.1x (up to 9.23x) over DTC-SpMM and 2.9x (up to 3.9x) for end-to-end GNN applications. Libra opens up a new perspective for sparse operator acceleration by fully exploiting the heterogeneous computing resources on GPUs.