Blogs (2) >>
ISMM 2017
Sun 18 Jun 2017 Barcelona, Spain
co-located with PLDI 2017
Sun 18 Jun 2017 14:00 - 14:30 at Aula Master - Session 3: Hybrid Memory Systems Chair(s): Ben L. Titzer

Heterogeneous systems that integrate a multicore CPU and a GPU on the same die are ubiquitous. On these systems, both the CPU and GPU share the same physical memory as opposed to using separate memory dies. Although integration eliminates the need to copy data between the CPU and the GPU, arranging transparent memory sharing between the two devices can carry large overheads. Memory on CPU/GPU systems is typically managed by a software framework such as OpenCL or CUDA, a runtime library, and a GPU driver. These frameworks offer a range of memory management methods that vary in ease of use, consistency guarantees and performance. In this study, we analyze some of the common memory management methods of the most widely used software frameworks for heterogeneous systems: CUDA, OpenCL 1.2, OpenCL 2.0, and HSA, on NVIDIA and AMD hardware. We focus on performance/functionality trade-offs, with the goal of exposing their performance impact and simplifying the choice of memory management methods for programmers.

Sun 18 Jun

14:00 - 15:30: ISMM 2017 - Session 3: Hybrid Memory Systems at Aula Master
Chair(s): Ben L. TitzerGoogle
ismm-2017-papers14:00 - 14:30
Mohammad DashtiUniversity of British Columbia, Alexandra (Sasha) FedorovaSimon Fraser University
ismm-2017-papers14:30 - 15:00
Ellis GilesRice University, Kshitij DoshiIntel Corporation, Peter VarmanRice University
ismm-2017-papers15:00 - 15:30
Ivy Bo PengKTH Royal Institute of Technology, Roberto GioiosaPacific Northwest National Laboratory, Gokcen KestorPacific Northwest National Laboratory, Stefano MarkidisKTH Royal Institute of Technology, Pietro CicottiSan Diego Supercomputer Center, Erwin LaureKTH Royal Institute of Technology