Welcome, Unregistered.

If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below.

Showing results 1 to 25 of 500
Search took 0.20 seconds.
Search: Posts Made By: rpg.314
Forum: 3D Architectures & Chips 28-Mar-2014, 21:07
Replies: 16
Views: 2,187
Posted By rpg.314
How so? ROPs make them sort last, not sort...

How so? ROPs make them sort last, not sort middle.

You could make the argument that the triangle setup/raster parallelization introduced with Fermi makes them sort middle to a degree, but that is...
Forum: 3D Architectures & Chips 27-Mar-2014, 16:39
Replies: 27
Views: 3,284
Posted By rpg.314
I think high bw CPU mem access is not for x86...

I think high bw CPU mem access is not for x86 cpus', just power8 and derivatives.
Forum: 3D Architectures & Chips 27-Mar-2014, 16:36
Replies: 16
Views: 2,187
Posted By rpg.314
It *might* be enough for sort middle tiled...

It *might* be enough for sort middle tiled parallelization.

AMD/NV will never implement sort middle GPUs. Their current architectures are too optimized for sort last.

A more hopeful scenario...
Forum: 3D Hardware, Software & Output Devices 22-Mar-2014, 18:48
Replies: 1,683
Views: 160,741
Posted By rpg.314
True. Do you really think that if...

True.


Do you really think that if Khronos added new useful features and MS *refused* to adopt them, the tide wouldn't reverse?
Forum: 3D Architectures & Chips 22-Mar-2014, 18:48
Replies: 1,619
Views: 224,860
Posted By rpg.314
Interesting.

Interesting.
Forum: 3D Hardware, Software & Output Devices 22-Mar-2014, 00:25
Replies: 1,683
Views: 160,741
Posted By rpg.314
That assumes that Khronos will not match DX12....

That assumes that Khronos will not match DX12. They are legendery for their inaction in the DX10 era, but have cleaned up their act quite a bit since then. Although I won't be holding my breath for...
Forum: 3D Hardware, Software & Output Devices 21-Mar-2014, 02:42
Replies: 1,683
Views: 160,741
Posted By rpg.314
In that context, it's worth asking if ARB will...

In that context, it's worth asking if ARB will bring something like dx12 to opengl? Or was this presentation (http://www.slideshare.net/CassEveritt/approaching-zero-driver-overhead) a way to make...
Forum: 3D Technology & Algorithms 20-Mar-2014, 23:58
Replies: 101
Views: 18,395
Posted By rpg.314
Anybody know where the pdf, videos, code is?

Anybody know where the pdf, videos, code is?
Forum: Handheld Technology 20-Mar-2014, 23:52
Replies: 27
Views: 2,618
Posted By rpg.314
I am aware of that, but I am sceptical (but would...

I am aware of that, but I am sceptical (but would be delighted to be proven wrong) that this will come to consumer market. We'll see.
Forum: Handheld Technology 20-Mar-2014, 23:51
Replies: 27
Views: 2,618
Posted By rpg.314
GR6500 would be too slow for even the A8 SoC. I...

GR6500 would be too slow for even the A8 SoC. I am not sure if Apple would license it unless it was performance competitive with their pure rasterization IPs. Neccessary conditions for Apple's...
Forum: 3D Hardware, Software & Output Devices 20-Mar-2014, 00:49
Replies: 1,683
Views: 160,741
Posted By rpg.314
Still no public docs? WTH.

Still no public docs? WTH.
Forum: Handheld Technology 19-Mar-2014, 23:28
Replies: 27
Views: 2,618
Posted By rpg.314
Now all they need are licensees. If Apple...

Now all they need are licensees.

If Apple weren't developing their own GPU's, they might be interested. Sigh..
Forum: 3D Hardware, Software & Output Devices 06-Mar-2014, 13:40
Replies: 1,683
Views: 160,741
Posted By rpg.314
Of course it is. It's just a new sw abstraction,...

Of course it is. It's just a new sw abstraction, not new hw specs.
Forum: 3D Hardware, Software & Output Devices 06-Mar-2014, 13:40
Replies: 1,683
Views: 160,741
Posted By rpg.314
The way you put it, priceless...

The way you put it, priceless...
Forum: 3D Hardware, Software & Output Devices 06-Mar-2014, 03:51
Replies: 1,683
Views: 160,741
Posted By rpg.314
Look at the domain name.

Look at the domain name.
Forum: 3D Hardware, Software & Output Devices 28-Feb-2014, 01:24
Replies: 1,683
Views: 160,741
Posted By rpg.314
afaik, os x 10.9 has opengl 4.1

afaik, os x 10.9 has opengl 4.1
Forum: 3D Hardware, Software & Output Devices 27-Feb-2014, 02:56
Replies: 1,683
Views: 160,741
Posted By rpg.314
IMHO, it's because a different demographic uses...

IMHO, it's because a different demographic uses Macs.

They are completely absent from desktop/laptop gaming, for instance.``
Forum: 3D Architectures & Chips 23-Feb-2014, 23:38
Replies: 1,619
Views: 224,860
Posted By rpg.314
I don't know about the transient nature of L1,...

I don't know about the transient nature of L1, but moving all rw cachelines to L2 is interesting as it dramatically simplifies coherency at the cost of some latency. Latency hiding shouldn't be much...
Forum: 3D Architectures & Chips 23-Feb-2014, 23:33
Replies: 1,619
Views: 224,860
Posted By rpg.314
Working forwards, how do you know that? ...

Working forwards, how do you know that?

EDIT: should have read a bit more before posting. Thanks for the tuning guide links.
Forum: 3D Architectures & Chips 23-Feb-2014, 23:31
Replies: 1,619
Views: 224,860
Posted By rpg.314
I think the launch of GM107 @28nm makes a lot of...

I think the launch of GM107 @28nm makes a lot of sense. With rising wafer prices @20nm, it makes sense to launch the value card on an older process, gives you time to work out the kinks with the new...
Forum: 3D Architectures & Chips 23-Feb-2014, 15:01
Replies: 1,619
Views: 224,860
Posted By rpg.314
If L1 is a true rw cache, why wouldn't it hold...

If L1 is a true rw cache, why wouldn't it hold the spilled variables?
Forum: 3D & Semiconductor Industry 22-Feb-2014, 16:32
Replies: 91
Views: 7,669
Posted By rpg.314
I agree that a few small transistors don't prove...

I agree that a few small transistors don't prove viability of a multi-billion transistor SoC. But if a few transistors can be made with current tools, it's reasonable to assume that the rest of the...
Forum: 3D & Semiconductor Industry 22-Feb-2014, 16:29
Replies: 91
Views: 7,669
Posted By rpg.314
CNT has proven to be a deadend for logic. ...

CNT has proven to be a deadend for logic.

Graphene doesn't have a bandgap, so single layer graphene transistors are impossible.
Multi layer graphene has a bandgap, but that has alignment issues...
Forum: 3D & Semiconductor Industry 22-Feb-2014, 00:16
Replies: 91
Views: 7,669
Posted By rpg.314
The presentation only showed transistors, but I...

The presentation only showed transistors, but I don't see why making a CPU would be a problem.
Forum: 3D & Semiconductor Industry 21-Feb-2014, 02:34
Replies: 91
Views: 7,669
Posted By rpg.314
It was in one of Intel's process people in person...

It was in one of Intel's process people in person presentations. No link.
Showing results 1 to 25 of 500

 
Forum Jump

All times are GMT +1. The time now is 19:57.


Powered by vBulletin® Version 3.8.6
Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.