FractalSync: Lightweight Scalable Global Synchronization of Massive Bulk Synchronous Parallel AI Accelerators

Abstract: The slow-down of technology scaling and the emergence of AI workloads have led computer architects to increasingly exploit parallelization coupled with hardware acceleration to keep pushing the performance envelope. However, this solution comes with the challenge of synchronization of processing elements (PEs) in massive heterogeneous many-core platforms. To address this challenge, we propose FractalSync, a hardware accelerated synchronization mechanism for Bulk Synchronous Parallel (BSP) systems. We integrate FractalSync in MAGIA, a scalable tile-based AI accelerator, with each tile featuring a RISC-V-coupled matrix-multiplication (MatMul) accelerator, scratchpad memory (SPM), and a DMA connected to a global mesh Network-on-Chip (NoC). We study the scalability of the proposed barrier synchronization scheme on tile meshes ranging from 2x2 PEs to 16x16 PEs to evaluate its design boundaries. Compared to a synchronization scheme based on software atomic memory operations (AMOs), the proposed solution achieves up to 43x speedup on synchronization, introducing a negligible area overhead (<0.01%). FractalSync closes timing at MAGIA's target 1GHz frequency.