FAUST: Design and implementation of a pipelined RISC-V vector floating-point unit

被引:3
|
作者
Kovac, Mate [1 ]
Dragic, Leon [1 ]
Malnar, Branimir [1 ]
Minervini, Francesco [2 ]
Palomar, Oscar [2 ]
Rojas, Carlos [2 ]
Olivieri, Mauro [2 ,3 ]
Knezovic, Josip [1 ]
Kovac, Mario [1 ]
机构
[1] Comp Univ Zagreb, Fac Elect Engn, Zagreb, Croatia
[2] Barcelona Supercomp Ctr BSC, Barcelona, Spain
[3] Sapienza Univ Rome, Rome, Italy
关键词
Faust; FPU-V; RISC-V; FPU; Vector processor; Chip; European processor initiative; HPC; Exascale computing;
D O I
10.1016/j.micpro.2023.104762
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we present Faust, a pipelined FPU for vector processing-capable RISC-V core developed within the European Processor Initiative (EPI) project. Faust is based on the open-source multi-format floating-point ar-chitecture FPnew that was extended and redesigned to support the RISC-V Vector extension specification (RVV) 1.0 and the most recent IEEE 754-2019 FP standard. Faust is extensively tested, mature and configurable, enabling ease of integration, as will be demonstrated in the paper. Faust can produce two binary32 operations or one binary64 operation per clock cycle. We have also developed FPU-V, an update of the SoftFloat-based reference model as a critical part of the UVM-based universal and extensible FPU verification environment. Faust was integrated and taped out as part of Vitruvius, a RISC-V Vector Processing unit of the EPAC1.0, the first EPI Accelerator Test Chip in GlobalFoundries 22FDX technology, and was shown fully operational at a target frequency of 1 GHz.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Design and Implementation of Floating-Point Transcendental Function Processor Based on RISC-V Architecture
    Qin, Bochen
    Cai, Gang
    Huang, Zhihong
    2024 13TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS, ICCCAS 2024, 2024, : 59 - 63
  • [2] Design and implementation of pipelined floating-point reciprocal approximation operation unit
    He J.
    Wang L.
    Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology, 2020, 42 (02): : 41 - 46
  • [3] IndiRA: Design and Implementation of a Pipelined RISC-V Processor
    Tiwari, Ankita
    Guha, Prithwijit
    Trivedi, Gaurav
    Gupta, Nitesh
    Jayaraj, Navneeth
    Pidanic, Jan
    2023 33RD INTERNATIONAL CONFERENCE RADIOELEKTRONIKA, RADIOELEKTRONIKA, 2023,
  • [4] Study of floating-point architectures for pipelined RISC processors
    Reyes, Joy Alinda P.
    Alarcon, Louis P.
    Alarilla, Luis, Jr.
    2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS, 2006, : 2713 - +
  • [5] Design of the IBM RISC System/6000 floating-point execution unit
    Montoye, R.K.
    Hokenek, E.
    Runyon, S.L.
    IBM Journal of Research and Development, 1990, 34 (01): : 59 - 70
  • [6] Design and verification of a VHDL model of a floating-point unit for a RISC microprocessor
    Brunelli, Claudio
    Nurmi, Jari
    2006 INTERNATIONAL SYMPOSIUM ON SYSTEM-ON-CHIP PROCEEDINGS, 2006, : 87 - +
  • [7] A Pluggable Vector Unit for RISC-V Vector Extension
    Maisto, Vincenzo
    Cilardo, Alessandro
    PROCEEDINGS OF THE 2022 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2022), 2022, : 1143 - 1148
  • [8] Design of a fully pipelined single-precision floating-point unit
    Li, Zhaolin
    Zhang, Xinyue
    Li, Gongqiong
    Zhou, Runde
    ASICON 2007: 2007 7TH INTERNATIONAL CONFERENCE ON ASIC, VOLS 1 AND 2, PROCEEDINGS, 2007, : 60 - 63
  • [9] Manticore: A 4096-Core RISC-V Chiplet Architecture for Ultraefficient Floating-Point Computing
    Zaruba, Florian
    Schuiki, Fabian
    Benini, Luca
    IEEE MICRO, 2021, 41 (02) : 36 - 42
  • [10] THE SUPRENUM VECTOR FLOATING-POINT UNIT
    KAMMER, H
    PARALLEL COMPUTING, 1988, 7 (03) : 315 - 323