Ara: A 1 GHz+ Scalable and Energy-Efficient RISC-V Vector Processor with Multi-Precision Floating Point Support in 22 nm FD-SOI

06/02/2019
by   Matheus Cavalcante, et al.
0

In this paper, we present Ara, a 64-bit vector processor based on the version 0.5 draft of RISC-V's vector extension, implemented in GlobalFoundries 22FDX FD-SOI technology. Ara's microarchitecture is scalable, as it is composed of a set of identical lanes, each containing part of the processor's vector register file and functional units. It achieves up to 97 256 x 256 double precision matrix multiplication on sixteen lanes. Ara runs at 1.2 GHz in the typical corner (TT/0.80 V/25 oC), achieving a performance up to 34 DP-GFLOPS. In terms of energy efficiency, Ara achieves up to 67 DP-GFLOPS/W under the same conditions, which is 56 found in literature. An analysis on several vectorizable linear algebra computation kernels for a range of different matrix and vector sizes gives insight into performance limitations and bottlenecks for vector processors and outlines directions to maintain high energy efficiency even for small matrix sizes where the vector architecture achieves suboptimal utilization of the available FPUs.

READ FULL TEXT

page 2

page 3

page 4

page 6

page 8

page 9

page 10

page 12

research
09/18/2023

Spatz: Clustering Compact RISC-V-Based Vector Units to Maximize Computing Efficiency

The ever-increasing computational and storage requirements of modern app...
research
02/24/2020

Snitch: A 10 kGE Pseudo Dual-Issue Processor for Area and Energy Efficient Execution of Floating-Point Intensive Workloads

Data-parallel applications, such as data analytics, machine learning, an...
research
11/17/2020

Audience Creation for Consumables – Simple and Scalable Precision Merchandising for a Growing Marketplace

Consumable categories, such as grocery and fast-moving consumer goods, a...
research
06/24/2016

FPMax: a 106GFLOPS/W at 217GFLOPS/mm2 Single-Precision FPU, and a 43.7GFLOPS/W at 74.6GFLOPS/mm2 Double-Precision FPU, in 28nm UTBB FDSOI

FPMax implements four FPUs optimized for latency or throughput workloads...
research
07/27/2022

Performance of an Astrophysical Radiation Hydrodynamics Code under Scalable Vector Extension Optimization

We present results of a performance study of an astrophysical radiation ...
research
07/26/2023

On Singleton Self-Loop Removal for Termination of LCTRSs with Bit-Vector Arithmetic

As for term rewrite systems, the dependency pair (DP, for short) framewo...
research
11/09/2021

Adaptable Register File Organization for Vector Processors

Modern scientific applications are getting more diverse, and the vector ...

Please sign up or login with your details

Forgot password? Click here to reset