Sohan Lal presented his current research conducted in the context of the LPGPU2 project during the poster’s session at the “Fourteenth International Summer School on Advanced Computer Architecture and Compilation for High-Performance and Embedded Systems (ACACES 2018)” in Fiuggi, Italy. The research shows that GPUs have low effective compression ratio due to large memory access granularity (MAG) and proposes a novel MAG aware lossy compression for GPUs which significantly increases the performance gain at a very low loss in the accuracy. The summer school is organized annually by the HiPEAC Network of Excellence. The summer school is for computer architects and tool builders working in the field of high-performance computer architecture and compilation for computing systems. The school aims at the dissemination of advanced scientific knowledge and the promotion of international contacts among scientists from academia and industry. 
For more information about this year’s summer school, please visit:
http://acaces.hipeac.net/2018/index.php
Comments are closed.