11 citations · 32 across the 10 of their papers we have counts for
11 papers
A Flexible Instruction Set Architecture for Efficient GEMMs
Alexandre de Limas Santana, Adrià Armejach, Francesc Martinez +2
GEneral Matrix Multiplications (GEMMs) are recurrent in high-performance computing and deep learning workloads. Typically, high-end CPUs accelerate GEMM workloads with Single-Instr…
Compressed Real Numbers for AI: a case-study using a RISC-V CPU
Federico Rossi, Marco Cococcioni, Roger Ferrer Ibàñez +5
As recently demonstrated, Deep Neural Networks (DNN), usually trained using single precision IEEE 754 floating point numbers (binary32), can also work using lower precision. Theref…
Open-Source GEMM Hardware Kernels Generator: Toward Numerically-Tailored Computations
Louis Ledoux, Marc Casas
Many scientific computing problems can be reduced to Matrix-Matrix Multiplications (MMM), making the General Matrix Multiply (GEMM) kernels in the Basic Linear Algebra Subroutine (…
Characterizing the impact of last-level cache replacement policies on big-data workloads
Alexandre Valentin Jamet, Lluc Alvarez, Marc Casas
In recent years, graph-processing has become an essential class of workloads with applications in a rapidly growing number of fields. Graph-processing typically uses large input se…
Optimization of SpGEMM with Risc-V vector instructions
Valentin Le Fèvre, Marc Casas
The Sparse GEneral Matrix-Matrix multiplication (SpGEMM) is a fundamental routine extensively used in domains like machine learning or graph analytics. Despite its…
Optimization of the Sparse Multi-Threaded Cholesky Factorization for A64FX
Valentin Le Fèvre, Tetsuzo Usui, Marc Casas
Sparse linear algebra routines are fundamental building blocks of a large variety of scientific applications. Direct solvers, which are methods for solving linear systems via the f…
Generating Efficient DNN-Ensembles with Evolutionary Computation
Marc Ortiz, Florian Scheidegger, Marc Casas +2
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models. We demonstrate that we can jointly optimize for a…
Reducing Data Motion to Accelerate the Training of Deep Neural Networks
Sicong Zhuang, Cristiano Malossi, Marc Casas
This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices. In par…
Memory Vulnerability: A Case for Delaying Error Reporting
Luc Jaulmes, Miquel Moretó, Mateo Valero +1
To face future reliability challenges, it is necessary to quantify the risk of error in any part of a computing system. To this goal, the Architectural Vulnerability Factor (AVF) h…
Low-Precision Floating-Point Schemes for Neural Network Training
Marc Ortiz, Adrián Cristal, Eduard Ayguadé +1
The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to…
Adaptive and application dependent runtime guided hardware prefetcher reconfiguration on the IBM POWER7
David Prat, Cristobal Ortega, Marc Casas +2
Hardware data prefetcher engines have been extensively used to reduce the impact of memory latency. However, microprocessors' hardware prefetcher engines do not include any automat…