The GPU Computing Era
John R. Nickolls, W.J. Dally · IEEE Micro · 2010
GPU computing is at a tipping point, becoming more widely used in demanding consumer applications and high-performance computing. This article describes the rapid evolution of GPU architectures-from graphics processors to massively parallel many-core multiprocessors, recent developments in GPU computing architectures, and how the enthusiastic adoption of CPU+GPU coprocessing is accelerating parallel applications.
Cited by 980 works. doi:10.1109/mm.2010.41
Authors
References
- Computer Organization and Design: the Hardware/Software Interface
- Scalable parallel programming with CUDA
- Scalable Parallel Programming with CUDA
- NVIDIA Tesla: A Unified Graphics and Computing Architecture
- Programming Massively Parallel Processors: A Hands-on Approach
- Cg
- The OpenCL specification
- Programming Massively Parallel Processors. A Hands-on Approach
- Parallel Computing Experiences with CUDA
- Accelerating molecular dynamic simulation on graphics processing units