Paper Info
Title
VAST: the illusion of a large memory space for GPUs
Abstract
Heterogeneous systems equipped with traditional processors (CPUs) and graphics processing units (GPUs) have enabled processing large data sets. With new programming models, such as OpenCL and CUDA, programmers are encouraged to offload data parallel workloads to GPUs as much as possible in order to fully utilize the available resources. Unfortunately, offloading work is strictly limited by the size of the physical memory on a specific GPU. In this paper, we present Virtual Address Space for Throughput processors (VAST), an automatic GPU memory management system that provides an OpenCL program with the illusion of a virtual memory space. Based on the available physical memory on the target GPU, VAST does the following: automatically partitions the data parallel workload into chunks; efficiently extracts the precise working set required for the divided workload; rearranges the working set in contiguous memory space; and, transforms the kernel to operate on the reorganized working set. With VAST, the programmer is responsible for developing a data parallel kernel in OpenCL without concern for physical memory space limitations of individual GPUs. VAST transparently handles code generation dealing with the constraints of the actual physical memory and improves the retargetability of the OpenCL with moderate overhead. Experiments demonstrate that a real GPU, NVIDIA GTX 760 with 2 GB of memory, can compute any size of data without program changes achieving 2.6x speedup over CPU exeuction, which is a realistic alternative for large data computation.
Year
DOI
Venue
2014
10.1145/2628071.2628075
PACT
Keywords
Field
DocType
gpu,code generation,run-time environments,virtual memory,optimization
Interleaved memory,Uniform memory access,Computer science,Virtual memory,Parallel computing,Distributed memory,Real-time computing,Memory management,Memory map,Flat memory model,CUDA Pinned memory
Conference
ISSN
ISBN
Citations 
1089-795X
978-1-5090-6607-0
15
PageRank 
References 
Authors
0.65
20
3
Name
Order
Citations
PageRank
Janghaeng Lee131611.34
Mehrzad Samadi242216.09
Scott Mahlke34811312.08