Segin: Synergistically Enabling Fine-Grained Multi-Tenant and Resource Optimized SpMV

Helya Hosseini, Ubaid Bakhtiar, Donghyeon Joo, Bahar Asgari

Abstract: Sparse matrix-vector multiplication (SpMV) is a critical operation across numerous application domains. As a memory-bound kernel, SpMV does not require a complex compute engine but still needs efficient use of available compute units to achieve peak performance efficiently. However, sparsity causes resource underutilization. To efficiently run SpMV, we propose Segin that leverages a novel fine-grained multi-tenancy, allowing multiple SpMV operations to be executed simultaneously on a single hardware with minimal modifications, which in turn improves throughput. To achieve this, Segin employs hierarchical bitmaps, hence a lightweight logical circuit, to quickly and efficiently identify optimal pairs of sparse matrices to overlap. Our evaluations demonstrate that Segin can improve throughput by 1.92×, while enhancing resource utilization.

External IDs:dblp:journals/cal/HosseiniBJA25