Write a Blog >>
Wed 26 Feb 2020 09:35 - 10:00 - Concurrency and GPU (Mediterranean Ballroom) Chair(s): Ang Li

In this paper,we propose a runtime, called HUM, which hides host-to-device memory copy time without any code modification. It overlaps the host-to-device memory copy with host computation or CUDA kernel computation by exploiting Unified Memory and fault mechanisms. HUM provides wrapper functions of CUDA commands and executes host-to-device memory copy commands in an asynchronous manner. We also propose two runtime techniques. One checks if it is correct to make the synchronous host-to-device memory copy command asynchronous. If not, HUM makes the host computation or the kernel computation waits until the memory copy completes. The other subdivides consecutive host-to-device memory copy commands into smaller memory copy requests and schedules the requests from different commands in a round-robin manner. As a result, the kernel execution can be scheduled as early as possible to maximize the overlap. We evaluate HUM using 51 applications from Parboil, Rodinia, and CUDA Code Samples and compare their performance under HUM with that of hand-optimized implementations. The evaluation result shows that executing the applications under HUM is, on average, 1.21 times faster than executing them under original CUDA. The speedup is comparable to the average speedup 1.22 of the hand-optimized implementations for Unified Memory.

Wed 26 Feb
Times are displayed in time zone: (GMT-07:00) Tijuana, Baja California change

PPoPP-2020-papers
09:35 - 10:50: Main Conference - Concurrency and GPU (Mediterranean Ballroom)
Chair(s): Ang LiPacific Northwest National Laboratory
PPoPP-2020-papers09:35 - 10:00
Talk
Jaehoon JungSeoul National University, Daeyoung ParkSeoul National University, Youngdong DoSeoul National University, Jungho ParkSeoul National University, Jaejin LeeSeoul National University
PPoPP-2020-papers10:00 - 10:25
Talk
KHALED HAMIDOUCHEAdvanced Micro Devices (AMD), Michael LeBeaneAdvanced Micro Devices (AMD)
PPoPP-2020-papers10:25 - 10:50
Talk
Nian LiuShanghai Jiao Tong University, Binyu ZangShanghai Jiao Tong University, Haibo ChenShanghai Jiao Tong University