|
Holistic profiling of CPU and GPU for optimal vision applications on ARM Mali platforms
ARM
|
419 views |
|
|
| «Prev Next» |
| Keywords: ARM, Webinar, CPU, GPU, OpenCL |
| Description: Developers of sophisticated vision applications need all the processing power they can lay their hands on, and using OpenCL™ on More » |
| Description: Developers of sophisticated vision applications need all the processing power they can lay their hands on, and using OpenCL™ on a GPU can be a vital additional compute resource. But spreading the workload amongst processors and processor types brings its own problems and difficulties, and traditional application optimisation techniques are not always effective in this brave new heterogeneous world. The key to achieving performance is twofold: getting access to hardware counters for all the processors in your system, and then understanding what those numbers are telling you. In this talk I examine the tools and techniques available to profile these sorts of applications and use real case studies from vision applications. Using tools like DS-5 Streamline I show how to extract meaningful performance numbers and how to interpret them. « Less |
