LONDON – The HSA Foundation, an industry body formed in 2012 to create standards for heterogeneous computing, is close to setting hardware specifications that will determine what programmers and API creators can expect to work with in HSA-compliant systems.
"We're in the last gasps of setting the hardware specification," Jem Davies, vice president of technology at the media processing division of ARM, told EE Times. HSA hardware specifications are expected to accompany software and run time standards including HSAIL [HSA intermediate language].
The HSA Foundation was initiated by Advanced Micro Devices Inc. and launched in June 2012 with ARM, Imagination, MediaTek, Qualcomm, Samsung and Texas Instruments as founder members. The initiative is pledged to be CPU-, GPU- and DSP-agnostic and looks forward to a time when processing elements on a piece of silicon could be multitudinous and varied. The broad backing achieved means that specifications from the HSA – which stands for Heterogeneous Systems Architecture - could have wide-reaching implications.
HSA is about a mix of hardware, software, runtime systems and performance, Davies explained. "But the hardware is the furthest upstream. We have to set the specifications so the RTL can get written, licensed out and eventually get manufactured in chips," Davies said. It also explains why he feels that it will be a couple of years before true HSA demonstrations can occur.
However, AMD is eager to push forward with its heterogeneous approach as quickly as possible. It already describes one of its established processors, which combines a quad-core CPU and GPU, as an HSA accelerated processing unit.
Davies explained the HSA Foundation is working on a number of fronts. "That the caches are fully coherent is one of the truths we hold to be self-evident. You can manage the memory without but it is less easy and less efficient," Davies told EE Times. So the hardware specifications would likely include mechanisms for sharing of page tables between processors. "I don't want to copy data I want to share pointers," said Davies pointing out that copying memory is costly in terms of power consumption and especially so when memory fetches have to go off chip.
The first work is likely to be supporting CPU-GPU exchange of compute data, Davies said. The specific nature of that exchange is an advantage but the HSA does want to produce solutions that are scalable both in terms of numbers cores but also in terms of varieties of cores. So these could also include DSPs and application-specific instruction processors.
Click on image to enlarge.
HSA feature roadmap. Source: ARM and HSA Foundation