Sciweavers

ASPLOS
2006
ACM

Accelerator: using data parallelism to program GPUs for general-purpose uses

13 years 9 months ago
Accelerator: using data parallelism to program GPUs for general-purpose uses
GPUs are difficult to program for general-purpose uses. Programmers can either learn graphics APIs and convert their applications to use graphics pipeline operations or they can use stream programtractions of GPUs. We describe Accelerator, a system that uses data parallelism to program GPUs for general-purpose uses instead. Programmers use a conventional imperative programming language and a library that provides only high-level data-parallel operations. No aspects of GPUs are exposed to programmers. The library implementation compiles the data-parallel operations on the fly to optimized GPU pixel shader code and API calls. We describe the compilation techniques used to do this. We evaluate the effectiveness of using data parallelism to program GPUs by providing results for a set of compute-intensive benchmarks. We compare the performance of Accelerator versions of the benchmarks against hand-written pixel shaders. The speeds of the Accelerator versions are typically within 50% of t...
David Tarditi, Sidd Puri, Jose Oglesby
Added 13 Jun 2010
Updated 13 Jun 2010
Type Conference
Year 2006
Where ASPLOS
Authors David Tarditi, Sidd Puri, Jose Oglesby
Comments (0)