While parallel architectures based on clusters of Processing Elements (PEs) sharing L1 memory are widespread, there is no consensus on how lean their PE should be. Architecting PEs as vector processors holds the promise to greatly reduce their instruction fetch bandwidth, mitigating the Von Neumann Bottleneck (VNB). However, due to their historical association with supercomputers, classical vector machines include micro-architectural tricks to improve the Instruction Level Parallelism (ILP), which increases their instruction fetch and decode energy overhead. In this paper, we explore for the first time vector processing as an option to build small and efficient PEs for large-scale shared-L1 clusters. We propose Spatz, a compact, modular 32-bit vector processing unit based on the integer embedded subset of the RISC-V Vector Extension version 1.0. A Spatz-based cluster with four Multiply-Accumulate Units (MACUs) needs only 7.9 pJ per 32-bit integer multiply-accumulate operation, 40% less energy than an equivalent cluster built with four Snitch scalar cores. We analyzed Spatz' performance by integrating it within MemPool, a large-scale many-core shared-L1 cluster. The Spatz-based MemPool system achieves up to 285 GOPS when running a 256x256 32-bit integer matrix multiplication, 70% more than the equivalent Snitch-based MemPool system. In terms of energy efficiency, the Spatz-based MemPool system achieves up to 266 GOPS/W when running the same kernel, more than twice the energy efficiency of the Snitch-based MemPool system, which reaches 128 GOPS/W. Those results show the viability of lean vector processors as high-performance and energy-efficient PEs for large-scale clusters with tightly-coupled L1 memory.
翻译:虽然基于共享 L1 内存的处理元素组群的平行结构十分广泛, 但对于如何精细的 PE 仍缺乏共识。 当矢量处理器时, 建筑 PE 有望大幅降低教学带宽, 减缓 Von Neumann Bottleneck (VNB) 。 但是, 由于它们与超级计算机的历史关联, 古典矢量机器包括微结构构造技巧, 以改善教学级平行单位( ILP), 从而增加他们的教学取回和解码能源管理。 在本文中, 我们首次探索矢量处理作为为大型共享的 大型共享的 共享 共享的 PEE1 。 我们建议 Spatz, 一个基于整数组的模块32位矢量处理器, 一个基于四种多维的多维能度组( MACU), 一个基于32 比基于32 位整数的元数级的递增计算器操作, 40%的能量处理, 一个与4个Snitch 等量的 等量的多的 共振量的 Gloal- mus- musal 等量系统 。 我们通过Sloess- pol- pol- pol- pol- sload- sal- pus- sal- sal- sal- sal- sal- sal- sal- smalmal- sal- sal- sal- sal- sal- sal- sal- sal- smald- supal- sal- sal- smald- sal- smald- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- smald- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal-