Radeon Open Compute Platform 1.3 Closer To Boltzmann Initiative
Last year at SC AMD announced the Boltzmann Initiative. This initiative comprised of building an ecosystem that would rival that of Nvidia CUDA and would bridge the gap between the two companies. Going under the name of Radeon Open Compute Platform, AMD released the first version of the vision but it was far from the scope of the Boltzmann Initiative.
It did, however, show the potential that it had to offer and it made it clear what Boltzmann Initiative was all about. Now at SC16 AMD has updated the Radeon Open Compute Platform and the Boltzmann Initiative is closer to realization than before.
A year since the announcement AMD has now introduced OpenCL 1.2+ for the platform. Support for the new Polaris GPUs has also been added. Both the RX 400 series, as well as the Radeon Pro series, have been included.
AMD is using SC16 to reveal plans regarding Zen and that it is also going to be supporting ARMv8 AArch64 and IBM POWER8. This is interesting as this gives us an idea of where AMD might be headed for in the future and the grand scheme of things.
Although there is a lot of work that is still to be done, AMD has shown that the core of the Radeon Open Compute Platform is done and that it is closer to realization than ever. AMD will now be investing in frameworks and libraries to compliment this platform.
AMD Vega might also play a role in these plans somewhere down the road. AMD seems to mean business and with the Radeon Open Compute Platform, it might be able to compete with Nvidia better. CUDA has been successful until now but AMD could also be onto something here and the company might, in fact, close the gap.
What do you think about the Radeon Open Compute Platform?