Portable mapping of data parallel programs to OpenCL for heterogeneous systems

General purpose GPU based systems are highly attractive as they give potentially massive performance at little cost. Re-alizing such potential is challenging due to the complexity of programming. This paper presents a compiler based approach to automatically generate optimized OpenCL code from data-...

Full description

Saved in:
Bibliographic Details
Main Authors: O'Boyle, Michael F. P., Wang, Zheng, Grewe, Dominik
Format: Conference Proceeding
Language:English
Subjects:
Arrays
Benchmark testing
Feature extraction
GPU
Graphics processing units
Indexes
Kernel
Learning Mapping
Machine
OpenCL
Predictive models
Software and its engineering > Software notations and tools > Compilers
Software and its engineering > Software notations and tools > General programming languages > Language features
Theory of computation > Models of computation > Concurrency
Theory of computation > Models of computation > Concurrency > Parallel computing models
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:General purpose GPU based systems are highly attractive as they give potentially massive performance at little cost. Re-alizing such potential is challenging due to the complexity of programming. This paper presents a compiler based approach to automatically generate optimized OpenCL code from data-parallel OpenMP programs for GPUs. Such an approach brings together the benefits of a clear high levellanguage (OpenMP) and an emerging standard (OpenCL) for heterogeneous multi-cores. A key feature of our scheme is that it leverages existing transformations, especially data transformations, to improve performance on GPU architectures and uses predictive modeling to automatically determine if it is worthwhile running the OpenCL code on the GPU or OpenMP code on the multi-core host. We applied our approach to the entire NAS parallel benchmark suite and evaluated it on two distinct GPU based systems: Core i7/NVIDIA GeForce GTX 580 and Core 17/AMD Radeon 7970. We achieved average (up to) speedups of 4.51x and 4.20x (143x and 67x) respectively over a sequential baseline. This is, on average, a factor 1.63 and 1.56 times faster than a hand-coded, GPU-specific OpenCL implementation developed by independent expert programmers.
DOI:10.1109/CGO.2013.6494993