Rapid advancements in heterogeneous architectures have placed incremental challenges on programming productivity, portability, and performance on such systems. From high-end servers to mobile devices, from specialized accelerators to embedded SoCs, from single node multicore/manycore to distributed clusters in cloud, be it NVIDIA, ARM, Intel, AMD or Cray, there are a many complex low-level details needed to be managed and abstracted from the programmers. The PMHS workshop aims to bring together researchers and industrial practitioners both from computer architecture scientists and the software engineering community to present the latest ideas and findings in all aspects of heterogeneous system programming models, language design or extension, compilers design or optimization, runtime systems, and programming tools. The objective is to brainstorm ways to make programming heterogeneous systems less challenging and more interesting, and promote the synergies between hardware design and software design.
08月24日
2015
08月26日
2015
摘要截稿日期
注册截止日期
留言