By: Ireland (boh.delete@this.outlook.ie), February 3, 2017 9:02 am
Room: Moderated Discussions
RichardC (tich.delete@this.pobox.com) on February 3, 2017 6:04 am wrote:
> >
>
> And it doesn't have much to do with flooding either, except inasmuch as the high costs of
> unpredicted extreme weather may be pushing the government to give the Met
> Office more funding to improve the speed and accuracy of forecasting.
>
> Evidently some people in the Met Office think ARM+GPGPU may be a superior approach for their
> particular problems; and evidently Cray agrees with them enough to be at least willing to devote
> scarce development effort to giving it a try.
>
Got it Richard, understood. Going down this avenue of thinking about the project and it's technology however did encourage me at least to look at the kinds of markets that Cray is working in nowadays, and what ideas it has got to offer.
It surprised me, that no one got around to make mention of Cray even, in the whole debate. I have to remark however, that after listening to some of their production explanations, product presentations - that the thing of making disciplines, and disciplinary models come together a little more - is what's driving some of the growth in their industry now of HPC.
One of the things that they underlined, was the need to match the increased resolution of data getting captured nowadays, with something on the computation end, that is able to match it. Again, it's an issue that I know that you've mentioned also, in the business intelligence.
Good analysis anyhow, I enjoyed reading it.
> >
>
> And it doesn't have much to do with flooding either, except inasmuch as the high costs of
> unpredicted extreme weather may be pushing the government to give the Met
> Office more funding to improve the speed and accuracy of forecasting.
>
> Evidently some people in the Met Office think ARM+GPGPU may be a superior approach for their
> particular problems; and evidently Cray agrees with them enough to be at least willing to devote
> scarce development effort to giving it a try.
>
Got it Richard, understood. Going down this avenue of thinking about the project and it's technology however did encourage me at least to look at the kinds of markets that Cray is working in nowadays, and what ideas it has got to offer.
It surprised me, that no one got around to make mention of Cray even, in the whole debate. I have to remark however, that after listening to some of their production explanations, product presentations - that the thing of making disciplines, and disciplinary models come together a little more - is what's driving some of the growth in their industry now of HPC.
One of the things that they underlined, was the need to match the increased resolution of data getting captured nowadays, with something on the computation end, that is able to match it. Again, it's an issue that I know that you've mentioned also, in the business intelligence.
Good analysis anyhow, I enjoyed reading it.