Loading...
Please wait, while we are loading the content...
Meta-programming and auto-tuning in the search for high performance GPU code
| Content Provider | ACM Digital Library |
|---|---|
| Author | Svensson, Bo Joel Vollmer, Michael Holk, Eric Newton, Ryan R. |
| Abstract | Writing high performance GPGPU code is often difficult and time-consuming, potentially requiring laborious manual tuning of low-level details. Despite these challenges, the cost in ignoring GPUs in high performance computing is increasingly large. Auto-tuning is a potential solution to the problem of tedious manual tuning. We present a framework for auto-tuning GPU kernels which are expressed in an embedded DSL, and which expose compile-time parameters for tuning. Our framework allows for kernels to be polymorphic over what search strategy will tune them, and allows search strategies to be implemented in the same meta-language as the kernel-generation code (Haskell). Further, we show how to use functional programming abstractions to enforce regular (hyper-rectangular) search spaces. We also evaluate several common search strategies on a variety of kernels, and demonstrate that the framework can tune both EDSL and ordinary CUDA code. . |
| Starting Page | 1 |
| Ending Page | 11 |
| Page Count | 11 |
| File Format | |
| ISBN | 9781450338073 |
| DOI | 10.1145/2808091.2808092 |
| Language | English |
| Publisher | Association for Computing Machinery (ACM) |
| Publisher Date | 2015-08-30 |
| Publisher Place | New York |
| Access Restriction | Subscribed |
| Subject Keyword | Gpus Auto-tuning Meta-programming Parallelism |
| Content Type | Text |
| Resource Type | Article |
