Mint
Didem Unat, Xing Hui Cai, Scott B. Baden · International Conference on Supercomputing · 2011
We present Mint, a programming model that enables the non-expert to enjoy the performance benefits of hand coded CUDA without becoming entangled in the details. Mint targets stencil methods, which are an important class of scientific applications. We have implemented the Mint programming model with a source-to-source translator that generates optimized CUDA C from traditional C source. The translator relies on annotations to guide translation at a high level. The set of pragmas is small, and the model is compact and simple. Yet, Mint is able to deliver performance competitive with painstakingly hand-optimized CUDA. We show that, for a set of widely used stencil kernels, Mint realized 80% of the performance obtained from aggressively optimized CUDA on the 200 series NVIDIA GPUs. Our optimizations target three dimensional kernels, which present a daunting array of optimizations.
Cited by 149 works. doi:10.1145/1995896.1995932
Authors
References
- Scalable parallel programming with CUDA
- Finite difference schemes and partial differential equations
- Digital Image Processing
- Introduction to the Cell multiprocessor
- Benchmarking GPUs to tune dense linear algebra
- Implementing sparse matrix-vector multiplication on throughput-oriented processors
- Digital Image Processing 3rd Edition
- The FFT on a GPU
- Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures
- 3D finite difference computation on GPUs using CUDA