An accelerator for double precision floating point operations

被引：2

作者：

Danese, G ^{[1
]}

De Lotto, I ^{[1
]}

Leporati, F ^{[1
]}

Scaricabarozzi, M ^{[1
]}

Spelgatti, A ^{[1
]}

机构：

[1] Univ Pavia, Dipartimento Informat & Sistemist, INFM, I-27100 Pavia, Italy

来源：

ELEVENTH EUROMICRO CONFERENCE ON PARALLEL, DISTRIBUTED AND NETWORK-BASED PROCESSING, PROCEEDINGS | 2003年

关键词：

D O I：

10.1109/EMPDP.2003.1183566

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We describe DPFPA (Double Precision Floating Point Accelerator) an FPGA based coprocessor interfaced to the CPU through the PCI bus; it is conceived to accelerate the evaluation of double precision floating point operations. This coprocessor is based on two double precision floating point units: a pipelined adder and a pipelined multiplier. The work is part of a global project aimed to design and build a parallel system made up by a cluster of accelerated workstations. First estimations of performance have been obtained, using a similar board developed at Fermilab (Batavia, IL) with less recent components and working at half the frequency with respect to DPFPA. Even in this case, a substantial acceleration with respect to the execution on Intel's CPU based mother-board was observed.

引用

页码：57 / 63

页数：7

共 50 条

[41] DLX gold: Design and implementation of a DLX microprocessor with single precision Floating-Point operations
Aguilar, John Edrian H.
Reas, Rosario M.
Villangca, John Benedict B.
Villangca, B.
Ballesil, Anastacia P.
Reyes, Joy Alinda P.
TENCON 2007 - 2007 IEEE REGION 10 CONFERENCE, VOLS 1-3, 2007, : 1272 - 1275
[42] Neural network based edge detection with pulse mode operations and floating point format precision
Damak, Alima
Krid, Mohamed
Masmoudi, Dorra Sellami
2008 INTERNATIONAL CONFERENCE ON DESIGN & TECHNOLOGY OF INTEGRATED SYSTEMS IN NANOSCALE, 2008, : 37 - 41
[43] An FPGA implementation of a fully verified double precision IEEE floating-point adder
Kikkeri, Nikhil
Seidel, Peter-Michael
2007 IEEE INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES, AND PROCESSORS, 2007, : 83 - 88
[44] Unified Architecture for Double/Two-Parallel Single Precision Floating Point Adder
Jaiswal, Manish Kumar
Cheung, Ray C. C.
Balakrishnan, M.
Paul, Kolin
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2014, 61 (07) : 521 - 525
[45] Low-Latency Double-Precision Floating-Point Division for FPGAs
Liebig, Bjoern
Koch, Andreas
PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (FPT), 2014, : 107 - 114
[46] Configurable Architecture for Double/Two-Parallel Single Precision Floating Point Division
Jaiswal, Manish Kumar
Cheung, Ray C. C.
Balakrishnan, M.
Paul, Kolin
2014 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI), 2014, : 333 - 338
[47] Verilog Implementation of Double Precision Floating Point Division Using Vedic Paravartya Sutra
Rajani, Molleti
Murty, Narayana P.
2015 IEEE INTERNATIONAL CONFERENCE ON RESEARCH IN COMPUTATIONAL INTELLIGENCE AND COMMUNICATION NETWORKS (ICRCICN), 2015, : 253 - 256
[48] A design of high speed double precision floating point adder using macro modules
Huang, Chi
Wu, Xinyu
Lai, Jimnei
Sun, Chengshou
Li, Gang
ASP-DAC 2005: PROCEEDINGS OF THE ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE, VOLS 1 AND 2, 2005, : D11 - D12
[49] Dual-Mode Double Precision/Two-Parallel Single Precision Floating Point Multiplier Architecture
Jaiswal, Manish Kumar
So, Hayden K. -H
2015 IFIP/IEEE INTERNATIONAL CONFERENCE ON VERY LARGE SCALE INTEGRATION (VLSI-SOC), 2015, : 213 - 218
[50] Hybrid Precision Floating-Point (HPFP) Selection to Optimize Hardware-Constrained Accelerator for CNN Training
Junaid, Muhammad
Aliev, Hayotjon
Park, Sangbo
Kim, Hyungwon
Yoo, Hoyoung
Sim, Sanghoon
SENSORS, 2024, 24 (07)

← 1 2 3 4 5 →