Publications related to Speedup

Full System Exploration of On-Chip Wireless Communication on Many-Core Architectures

David Atienza Alonso, Marina Zapater Sancho, Giovanni Ansaloni, Rafael Medina Morillas, Yasir Mahmood Qureshi, Joshua Alexander Harrison Klein

In order to develop sustainable and more powerful information technology (IT) infrastructures, the challenges posed by the "memory wall" are critical for the design of high-performance and high-efficiency many-core computing systems. In this context, recen ...

2022

High Performance Computing for gravitational lens modeling: Single vs double precision on GPUs and CPUs

Jean-Paul Richard Kneib, Markus Rexroth

Strong gravitational lensing is a powerful probe of cosmology and the dark matter distribution. Efficient lensing software is already a necessity to fully use its potential and the performance demands will only increase with the upcoming generation of tele ...

ELSEVIER2020

From a week to less than a day: Speedup and scaling of coordinate-scaled exact exchange calculations in plane waves

Ursula Röthlisberger, Martin Peter Bircher

Exact exchange is a primordial ingredient in Kohn–Sham Density Functional Theory based Molecular Dynamics (MD) simulations whenever thermodynamic properties, kinetics, barrier heights or excitation energies have to be predicted with high accuracy. However, ...

2020

Efficient Greedy Coordinate Descent for Composite Problems

Martin Jaggi, Sebastian Urban Stich, Anastasiia Koloskova, Sai Praneeth Reddy Karimireddy

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension ...

2019

Stop Crying Over Your Cache Miss Rate: Handling Efficiently Thousands of Outstanding Misses in FPGAs

Paolo Ienne, Mikhail Asiatici

FPGAs rely on massive datapath parallelism to accelerate applications even with a low clock frequency. However, applications such as sparse linear algebra and graph analytics have their throughput limited by irregular accesses to external memory for which ...

ASSOC COMPUTING MACHINERY2019

Efficient Greedy Coordinate Descent for Composite Problems

Martin Jaggi, Sebastian Urban Stich, Anastasiia Koloskova, Sai Praneeth Reddy Karimireddy

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension ...

MICROTOME PUBLISHING2019

Scaling and Resilience in Numerical Algorithms for Exascale Computing

Allan Svejstrup Nielsen

The first Petascale supercomputer, the IBM Roadrunner, went online in 2008. Ten years later, the community is now looking ahead to a new generation of Exascale machines. During the decade that has passed, several hundred Petascale capable machines have bee ...

EPFL2018

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

François Fleuret, Angelos Katharopoulos

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on "informative" examples ...

Idiap2018

Distributed Learning of CNNs on Heterogeneous CPU/GPU Architectures

José Pedro Rebelo Ferreira Marques, Gabriel Falcao Paiva Fernandes

The convolutional neural networks (CNNs) have proven to be powerful classification tools in tasks that range from check reading to medical diagnosis, reaching close to human perception, and in some cases surpassing it. However, the problems to solve are be ...

TAYLOR & FRANCIS INC2018

eQE: An open-source density functional embedding theory code for the condensed phase

Oliviero Andreussi

In this work, we present the main features and algorithmic details of a novel implementation of the frozen density embedding (FDE) formulation of subsystem density functional theory (DFT) that is specifically designed to enable ab initio molecular dynamics ...

Wiley2017

Speedup

Full System Exploration of On-Chip Wireless Communication on Many-Core Architectures

High Performance Computing for gravitational lens modeling: Single vs double precision on GPUs and CPUs

From a week to less than a day: Speedup and scaling of coordinate-scaled exact exchange calculations in plane waves

Efficient Greedy Coordinate Descent for Composite Problems

Stop Crying Over Your Cache Miss Rate: Handling Efficiently Thousands of Outstanding Misses in FPGAs

Efficient Greedy Coordinate Descent for Composite Problems

Scaling and Resilience in Numerical Algorithms for Exascale Computing

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

Distributed Learning of CNNs on Heterogeneous CPU/GPU Architectures

eQE: An open-source density functional embedding theory code for the condensed phase

Graph Chatbot

Chat with Graph Search

Full System Exploration of On-Chip Wireless Communication on Many-Core Architectures

High Performance Computing for gravitational lens modeling: Single vs double precision on GPUs and CPUs

From a week to less than a day: Speedup and scaling of coordinate-scaled exact exchange calculations in plane waves

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

eQE: An open-source density functional embedding theory code for the condensed phase

Efficient Greedy Coordinate Descent for Composite Problems

Stop Crying Over Your Cache Miss Rate: Handling Efficiently Thousands of Outstanding Misses in FPGAs

Efficient Greedy Coordinate Descent for Composite Problems

Scaling and Resilience in Numerical Algorithms for Exascale Computing

Distributed Learning of CNNs on Heterogeneous CPU/GPU Architectures