| 1 |
On Thu, 10 Sep 2015 12:20:39 +0000 (UTC) james <wireless@×××××××××××.com> wrote: |
| 2 |
|
| 3 |
> Fernando Rodriguez <frodriguez.developer <at> outlook.com> writes: |
| 4 |
> |
| 5 |
> > > albeit in it's infancy. Naturally it's going to take a while to |
| 6 |
> > > become mainstream useful; but that more like a year or 2, at most. |
| 7 |
> > |
| 8 |
> > The value I see on that technology for desktop computing is that we |
| 9 |
> > get the GPUs for what they're made (graphics processing) but their |
| 10 |
> > resources go unused by most applications, not in buying powerful |
| 11 |
> > GPUs for the purpose of offloading general purpose code, if that's |
| 12 |
> > the goal you're better off investing in more general purpose cores |
| 13 |
> > that are more suited for the task. |
| 14 |
|
| 15 |
It is true. |
| 16 |
|
| 17 |
> I think most folks when purchasing a workstation include a graphics |
| 18 |
> card on the list of items to include. So my suggestions where geared |
| 19 |
> towards informing folks about some of the new features of gcc that |
| 20 |
> may intice them to consider the graphics card resources in an |
| 21 |
> expanded vision of general resources for their workstation. |
| 22 |
> |
| 23 |
> > To trully take advantage of the GPU the actual algorithms need to be |
| 24 |
> > rewritten to use features like SIMD and other advanced parallelization |
| 25 |
> > features, most desktop workloads don't lend themselves for that kind |
| 26 |
> > of parallelization. |
| 27 |
|
| 28 |
And it is also true. |
| 29 |
|
| 30 |
> Not true if what openacc hopes to achived indeed does become a reality. |
| 31 |
|
| 32 |
Hopes almost never becomes a reality. |
| 33 |
|
| 34 |
> Currently, you are most correct. |
| 35 |
|
| 36 |
Absolutely correct. |
| 37 |
|
| 38 |
... |
| 39 |
|
| 40 |
> |
| 41 |
> When folks buy new hardware, it is often a good time to look at what |
| 42 |
> is on the horizon for computers they use. |
| 43 |
|
| 44 |
I also considered "what is on the horizon" when bought a brand new |
| 45 |
ATI Radeon R4770 graphic card about 6 years ago for computing purposes. |
| 46 |
|
| 47 |
In half a year it was discovered that it has much worse performance than |
| 48 |
ATI guys hoped for and, to improve it, they have to rewrite their proprietary |
| 49 |
drive for this graphic card. |
| 50 |
|
| 51 |
Instead of doing it, they just shamelessly dropped the support of the parallel |
| 52 |
computing feature of this graphic card in all subsequent versions of their drive. |
| 53 |
|
| 54 |
And as far as I know, no open source drive have ever supported the parallel |
| 55 |
computing feature of this graphic card as well. |
| 56 |
|
| 57 |
So, it was just a waste of money. Even more: I almost never worked at my assembled |
| 58 |
almost 7 year-old 4-core AMD computer with this graphic card as for all other |
| 59 |
purposes I prefer to work at my 10 year-old 2-core AMD computer with a very cheap |
| 60 |
on-board video card. Just to avoid extra heating and aircraft noise produced by R4770. |
| 61 |
|
| 62 |
So, Rich Freeman was absolutely right when he wrote in reply to your words above that |
| 63 |
|
| 64 |
> If all you need today is a $30 graphics card, then you probably should |
| 65 |
> just spend $30. If you think that software will be able to use all |
| 66 |
> kinds of fancy features on a $300 graphics card in two years, you |
| 67 |
> should just spend $30 today, and then wait two years and buy the fancy |
| 68 |
> graphics card on clearance for $10. |
| 69 |
|
| 70 |
> It is pretty rare that it is a wise move to spend money today on |
| 71 |
> computer hardware that you don't have immediate plans to use. |
Archives