PEGPUM 2018

Sixth International Workshop on
Power-Efficient GPU and Many-core Computing
Manchester, United Kingdom, 22 January 2018

The recent success of advanced mobile platforms coincides with the rising challenge of ensuring a long battery life, and accompanies a larger trend away from increasing processor clock speeds in favor of increasing parallelism. That high performance computing (HPC) is also strongly motivated in this area, as witnessed by the recent Green500 List project, illustrates the timeliness and ubiquity of topics relating to low-power computing. In the last years we have seen the introduction of new computing platforms that  include multicore CPUs, manycore GPUs and application-specific accelerators, some of them specially addressing low-power mobile applications. The design of applications, architectures, and supporting programming tools for low-power parallel computing systems is an open and very active research field. This workshop in conjunction with HiPEAC18 on low-power computing intends to foster dialogue and interaction among researchers from academia and industry addressing contemporary challenges in low-power parallel software and hardware design.

PEGPUM 2018 will be held in conjunction with HiPEAC 2018 at Manchester Central Convention Center, United Kingdom

Affiliation

The full-day PEGPUM 2018 workshop is administered within the auspices of the H2020 IA project (lpgpu.org).

Programme

8:45-9:45 HiPEAC Keynote

10:00-10:05 Welcome. Georgios Keramidas. Think Silicon S.A.

10:05-10:30 “Reasons for low power GPU analysis in automotive functional safety“. Callum Fare and Thales Sabino. Codeplay Software Ltd.

10:30-11:00 “Towards Cross-Platform GPGPU: Enabling Vulkan to Gain Prominence over CUDA & OpenCL”. Nadjib Mammeri. TU Berlin.

11:00-11:30 Coffee Break

11:30-12:00 “H.265 Media Player for Ultra High Definition Applications: 4K, 8K, and beyond”. Mauricio Alvarez Mesa. Spin Digital Video Technologies GmbH.

12:00-12:30 “Data Dependent GPU Power Consumption” Jan Lucas, TU Berlin

12:30-13:00 “Pareto-Optimal Silicon Allocation for Energy Efficiency and Throughput in a Deep Learning Processor“. Giulia Santoro, Mario R. Casu, Valentino Peluso, Andrea Calimera, Massimo Alioto. Politecnico di Torino, Italy and National University of Singapore.

13:00-14:00 Lunch

14:00-15:00 “Demonstration: Analyzing GPU Software using the LPGPU2 CodeXL Toolchain“. Samsung UK, TU Berlin.

15:00-15:30 “The Nema GPU Software Ecosystem”. Georgios Keramidas, Think Silicon S.A.

15:30-16:00 Coffee break

16:00-16:30 “Beyond GPUs: Reusing an LPGPU2 energy framework for FPGA design space exploration“. Matthias Goebel. TU Berlin.

Organizers and their Affiliations

Ben Juurlink, TU Berlin, Germany
Jan Lucas, TU Berlin, Germany
Martyn Bliss, Samsung Research UK, UK
Georgios Keramidas, Think Silicon S.A., Greece
Paul Keir, University of the West of Scotland, UK
Henk Corporaal, TU Eindhoven, Netherlands
Ana Lucia Varbanescu, Univ. of Amsterdam, The Netherlands

Contact

Georgios Keramidas, Think Silicon S.A., Greece

Tel: +30.2610.911-543
Fax: +30.2610.911-544
email: g.keramidas (AT) think-silicon.com

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close