Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/141525
Title: Accelerating BLAS and LAPACK via efficient floating point architecture design
Authors: Merchant, Farhad
Chattopadhyay, Anupam
Raha, Soumyendu
Nandy, S. K.
Narayan, Ranjani
Keywords: Engineering::Computer science and engineering
Issue Date: 2017
Source: Merchant, F., Chattopadhyay, A., Raha, S., Nandy, S. K., & Narayan, R. (2017). Accelerating BLAS and LAPACK via efficient floating point architecture design. Parallel Processing Letters, 27(3&4), 1750006-. doi:10.1142/S0129626417500062
Journal: Parallel Processing Letters
Abstract: Basic Linear Algebra Subprograms (BLAS) and Linear Algebra Package (LAPACK) form basic building blocks for several High Performance Computing (HPC) applications and hence dictate performance of the HPC applications. Performance in such tuned packages is attained through tuning of several algorithmic and architectural parameters such as number of parallel operations in the Directed Acyclic Graph of the BLAS/LAPACK routines, sizes of the memories in the memory hierarchy of the underlying platform, bandwidth of the memory, and structure of the compute resources in the underlying platform. In this paper, we closely investigate the impact of the Floating Point Unit (FPU) micro-architecture for performance tuning of BLAS and LAPACK. We present theoretical analysis for pipeline depth of different floating point operations like multiplier, adder, square root, and divider followed by characterization of BLAS and LAPACK to determine several parameters required in the theoretical framework for deciding optimum pipeline depth of the floating operations. A simple design of a Processing Element (PE) is presented and shown that the PE outperforms the most recent custom realizations of BLAS and LAPACK by 1.1X to 1.5X in GFlops/W, and 1.9X to 2.1X in Gflops/mm2. Compared to multicore, General Purpose Graphics Processing Unit (GPGPU), Field Programmable Gate Array (FPGA), and ClearSpeed CSX700, performance improvement of 1.8-80x is reported in PE.
URI: https://hdl.handle.net/10356/141525
ISSN: 0129-6264
DOI: 10.1142/S0129626417500062
Rights: © 2017 World Scientific Publishing Company. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations

4
checked on Sep 3, 2020

WEB OF SCIENCETM
Citations 50

3
checked on Oct 14, 2020

Page view(s) 50

10
checked on Oct 21, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.