OPENCL BENCHMARK SOFTWAREIn Proceedings of IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2017. Hwu.Ĭhai: Collaborative Heterogeneous Applications for Integrated-architectures. Please cite the following paper if you find our benchmark suite useful: OPENCL BENCHMARK HOW TOThe versions suffixed with -Sim run on the gem5-gpu simulator.Ĭheck out our Getting Started page for instructions on how to download and use the benchmarks. The versions suffixed with -U use unified memory and system-wide atomics while the versions suffixed with -D use the traditional communication techniques of discrete architectures. The Chai benchmarks are designed to use the latest features of heterogeneous architectures such as shared virtual memory and system-wide atomics to achieve efficient simultaneous collaboration between host and accelerator devices.Įach benchmark has multiple implementations: OpenCL-U, OpenCL-D, CUDA-U, CUDA-D, CUDA-U-Sim, CUDA-D-Sim, and C++AMP.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |