DeepAI AI Chat
Log In Sign Up

FT-BLAS: A High Performance BLAS Implementation With Online Fault Tolerance

04/02/2021
by   Yujia Zhai, et al.
0

Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not only tolerates soft errors on the fly, but also provides comparable performance to modern state-of-the-art BLAS libraries on widely-used processors such as Intel Skylake and Cascade Lake. To accommodate the features of BLAS, which contains both memory-bound and computing-bound routines, we propose a hybrid strategy to incorporate fault tolerance into our brand-new BLAS implementation: duplicating computing instructions for memory-bound Level-1 and Level-2 BLAS routines and incorporating an Algorithm-Based Fault Tolerance mechanism for computing-bound Level-3 BLAS routines. Our high performance and low overhead are obtained from delicate assembly-level optimization and a kernel-fusion approach to the computing kernels. Experimental results demonstrate that FT-BLAS offers high reliability and high performance – faster than Intel MKL, OpenBLAS, and BLIS by up to 3.50 three levels of BLAS we benchmarked, even under hundreds of errors injected per minute.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/24/2016

Automating the Last-Mile for High Performance Dense Linear Algebra

High performance dense linear algebra (DLA) libraries often rely on a ge...
05/03/2021

A C++17 Thread Pool for High-Performance Scientific Computing

We present a modern C++17-compatible thread pool implementation, built f...
04/19/2021

Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs

Neural networks (NNs) are increasingly employed in domains that require ...
04/30/2018

Improving Performance of Iterative Methods by Lossy Checkponting

Iterative methods are commonly used approaches to solve large, sparse li...
03/27/2020

Algorithm-Based Fault Tolerance for Convolutional Neural Networks

Convolutional neural networks (CNNs) are becoming more and more importan...
08/04/2021

High-Performance Level-1 and Level-2 BLAS

The introduction of the Basic Linear Algebra Subroutine (BLAS) in the 19...