“Accelerating Simulations of Agent Based Models on Heterogeneous Architectures” presented by Jin Wang at GPGPU6
A paper “Accelerating Simulations of Agent Based Models on Heterogeneous Architectures” was presented by Jin Wang on Sixth Workshop on General-Purpose Computation on Graphics Processing Units (GPGPU-6), held with ASPLOS-2013 on March 16, 2013.
“Relational Algorithms for Multi-Bulk-Synchronous Processors” presented by Haicheng Wu at PPoPP-2013
A poster “Relational Algorithms for Multi-Bulk-Synchronous Processors” was presented by Haicheng Wu at PPoPP-2013 on February 24, 2013. See poster.
LCL Tutorial at CGO 2013
A joint tutorial showcasing the use of Light-weight Computing Language Framework (LCL) and GPUOcelot was presented on CGO 2013 conference on Feb 24, 2013. For more details, see the tutorial page here.
GPU Lynx 1.0.0 released!
Official version v1.0.0 of GPU Lynx has been released!
GPU Lynx is a dynamic instrumentation framework intended to facilitate the creation and insertion of PTX instrumentation procedures in CUDA applications. This project was developed by Naila Farooqui.
For more information, please check the main GPU Lynx project website:
http://code.google.com/p/gpulynx/
The release can be downloaded from here:
http://code.google.com/p/gpulynx/downloads/list
Some documentation that walks through an example instrumentation (with code included) can be found here:
Eiger version 1.2 released!
Version 1.2 of the Eiger Performance Modeling Framework has been released! It contains a significant overhaul to the model generation process, along with greater flexibility. Go get it here.
“Software Reliability Enhancements for GPU Applications” presented by Si Li at MULTIPROG-2013
A peer-reviewed paper “Software Reliability Enhancements for GPU Applications” was presented by Si Li on the Sixth Workshop on Programmability Issues for Heterogeneous Multicores (MULTIPROG-2013), held in conjunction with the 8th International Conference on High-Performance and Embedded Architectures and Compilers (HiPEAC) in Berlin, Germany on January 21, 2013. See paper.
“Architectural Alternatives for Energy Efficient Performance Scaling” presented by Prof. Yalamanchili at VLSID 2013
The talk “Architectural Alternatives for Energy Efficient Performance Scaling” was presented by Prof. Sudhakar Yalamnchili in the special session on “Low Power Computing – Reducing the gap between the Physical and Practical Limits” at 26th IEEE International Conference on VLSI Design in Pune, India on January 8, 2013. See the presentation here.
“Energy-efficient Adaptive Circuits and Systems” Tutorial at VLSID 2013
The tutorial “Energy-efficient Adaptive Circuits and Systems” was presented at the 26th IEEE International Conference on VLSI Design in Pune, India on January 6, 2013. See the tutorial page here.
Haicheng Wu selected as a 2012-2013 NVIDIA Graduate Research Fellow
Congratulations to Haicheng Wu for being selected as a 2012-2013 NVIDIA Graduate Research Fellow! See more information here.
