| | |
Summary: Dynamically Managed Data for CPU-GPU Architectures
Thomas B. Jablin James A. Jablin
Prakash Prabhu Feng Liu David I. August
Princeton University, Princeton, New Jersey, USA
Brown University, Providence, Rhode Island, USA
ABSTRACT
GPUs are flexible parallel processors capable of accelerating
real applications. To exploit them, programmers must ensure
a consistent program state between the CPU and GPU mem-
ories by managing data. Manually managing data is tedious
and error-prone. In prior work on automatic CPU-GPU data
management, alias analysis quality limits performance, and
type-inference quality limits applicability. This paper presents
Dynamically Managed Data (DyManD), the first automatic sys-
tem to manage complex and recursive data-structures without
static analyses. By replacing static analyses with a dynamic
run-time system, DyManD overcomes the performance limita-
tions of alias analysis and enables management for complex
and recursive data-structures. DyManD-enabled GPU paral-
|
