Squire: A General-Purpose Accelerator to Exploit Fine-Grain Parallelism on Dependency-Bound Kernels

TL;DR

Squire is a versatile accelerator designed to efficiently exploit fine-grain parallelism in dependency-bound kernels, significantly improving performance and energy efficiency with minimal hardware overhead.

Contribution

It introduces a general-purpose accelerator architecture that effectively handles complex dependency patterns in kernels, enhancing flexibility over traditional FPGA, ASIC, and GPGPU solutions.

Findings

Achieves up to 7.64× speedup on kernels

End-to-end application speedup of 3.66×

Reduces energy consumption by up to 56%

Abstract

Multiple HPC applications are often bottlenecked by compute-intensive kernels implementing complex dependency patterns (data-dependency bound). Traditional general-purpose accelerators struggle to effectively exploit fine-grain parallelism due to limitations in implementing convoluted data-dependency patterns (like SIMD) and overheads due to synchronization and data transfers (like GPGPUs). In contrast, custom FPGA and ASIC designs offer improved performance and energy efficiency at a high cost in hardware design and programming complexity and often lack the flexibility to process different workloads. We propose Squire, a general-purpose accelerator designed to exploit fine-grain parallelism effectively on dependency-bound kernels. Each Squire accelerator has a set of general-purpose low-power in-order cores that can rapidly communicate among themselves and directly access data from the L2 cache. Our proposal integrates one Squire accelerator per core in a typical multicore system, allowing the acceleration of dependency-bound kernels within parallel tasks with minimal software changes. As a case study, we evaluate Squire's effectiveness by accelerating five kernels that implement complex dependency patterns. We use three of these kernels to build an end-to-end read-mapping tool that will be used to evaluate Squire. Squire obtains speedups up to 7.64$\times$ in dynamic programming kernels. Overall, Squire provides an acceleration for an end-to-end application of 3.66$\times$. In addition, Squire reduces energy consumption by up to 56% with a minimal area overhead of 10.5% compared to a Neoverse-N1 baseline.