Search results

I don't think it is not yields but business calculation. There should be coming yet an 'ultimate' Titan XXL with HBM2 memory and chip having slightlly more SMs than the Titan X which will help in product differentiation and justify terrifying price.

To me it has something to do with the loads and heat dissipation. P100 has lots of FP units and its TDP is 300 W for its die size and maximum load. TX has graphics computing units, has higher clock and TDP of 250 W achieved already at smaller die size. Since one can not have TDP more than...

Just wonder if the Xperia Z5 Premium would fit into one of those VR enclosures where smartphone can be put? I have Glyph, picture is absolutely perfect but FOV is limited and there are some ergonomic issues with it. To my mind, the best for VR would be miniature OLED displays like the ones used...

Thanks for the code. Not that I would not be able calculate this, I would ;), but I thought there might be a ready table somewhere. BTW, there is a convenient shortcut for calculating the width of the display which comes from a very good approximation to the equation (16x)^2 + (9x)^2 =...

Is there anywhere a table from which one can read precise dimensions in mm of the display area for different sizes? Like for 5.0", 5".1, 5.2".....6.0", 6.1", 6.2" etc. I am trying to figure out what would be the size of smartphones assuming no display borders and very thin bezel and comparing...

Expanding the scope: Will there every be processors wider than 64-bit., e.g. 128-bit and corresponding 128-bit operating systems? This of course would not be related to the addressable memory space as 64-bit is more than enough but rather to the width of data fetched and processed simultaneously.

Maybe there are nonoorganic TIMs ???

Are there oils which do not degrade with time? Are there TIMs not containing degradable oils?

True, it might be the TIM longevity is non-issue but people are reporting problems and some are doing repasting yearly or so. Fact is it is very difficult to collect reliable information on this.

Top TIMs are so close to each other that major question is which has best long-term stability. Kryonaut would be finest but its stability is not known yet.

To make the story short VESA compression standard principle is described here, see Fig.1. Details are in the standard document costing money but what is said in the document above Fig. 1 is that algorithm requires single line of pixel storage and a rate buffer. This, plus some other details...

I think it would be better for you not to try Glyph to avoid big disappointment :notworthy:. Glyph is NOT a VR device, it is a personal media player. Think about its viewing scenario as watching 60" TV in dark room from typical living room distance. Morever, Glyph is made by a startup funded by...

I am waiting for my kickstarted Glyph with clear understanding this is NOT a VR device and not a competitor to OR. I treat it as an experimental media player and I am interested in the potential of retinal projection. Reported picture quality of Glyph is very good though there were some...

There is very good reason to think there will be dual GPU Pascal cards. Nvidia has to make such cards for professional applications which are insatiable for computing power and Pascal has exquisite support for all kind of floating point arithmetics. A dual GPU Pascl card will have 8 Teraflops of...

Note lossless compression step is part of every compression in use. Sure lossless compression assumption is that bit patterns are not equally probable and in this sense it fails for pure noise and the like signals. Now tell me who is watching pure noise :wtf:?. For video signals with big...

This is lossless compression if you know what it means.

Success is guaranteed with juicy content and its not video games :jawdrop:.

Hoping for a good amount of time before the EOL there is a question which TIM is most resistant against aging:happy:? There are reports claiming TIM performance degrading over time with repasting being a cure. But if one wants to avoid the repasting as long as possible which TIM to choose?

Hmm, wonder what is then the actual screen size for normal use, could it be that by chance it is the same as the S7? Sounds Samsung is kind of misleading people about the screen size. Regarding the usefulness of edge, there are demos showing how column of messaging boxes open when sliding...

Do I see it correctly that the Edge screen is narrower? Which implies to me that the edge is included into the 5.5" overall size?? BTW, is the edge really useful in some way, adds nice functionality or it is thus esthetics/ownership statement???

Buying now you will regret in June or even in April when you see the specs :smuggrin:.

I told you so :kiss:.

Can somebody explain this: Samsung S7 Edge has screen size of 5.5" but some sources tell this includes the waterfalling edges. Is this true? What is then the size of the maximum rectangluar screen part for displaying photos or videos?

At stock speeds, there is assumption one can use the full power of all cores and threads, that is the software supports it. This is strongly depending on the particular software but often even the software claiming full support for parallelism rarely can make use of more than 8 cores...

Note that Pascal is optimized for computations in a branch of artificial intelligence known as deep machine learning, this is why it has extensive support for flexible floating point including FP16 which has no other use than deep learning. This is potential market hugely bigger than gaming and...

Wrong. There is even more important Nvidia GPU Technology Conference on April 7-10 where the Pascal anouncement would fit even better. Remember that Pascal is primarily positioned for the emerging artificial intelligence market a.k.a. deep machine learning.

Professionala cards were always 4-5x more expensive than comparable consumer cards /essentialy the same GPU/. The difference has been justificated by more advanced hardware (e.g. ECC RAM, components tested for 24/7 operation), drivers supporting high-end professional software, better support and...

Time and again it has been proved that Teslas/Quadro and Titans are of no real difference for workstation type of applications. NVidia tried to discourage professionals from Titans by saying that Tesla has drivers optimized for high-end professional software and offered better support which has...

What makes you believing in the 'correction' rumor?

There are many factors which limit the die size. As mentioned here the more elements packed on a die the lower the yield due to higher probability of defects. The bigger the die the less dies fit on one wafer which reduces economy of manufacturing. Bigger die equals bigger heat dissipation and...

There is definitely again an old problem for NV how to keep Tesla and top Titan ranges separate and discourage professionals from using Titan instead of much more expensive Tesla. Separation in time between launches is temporary solution. On the hardware side Tesla will support NV link which...

This is serious issue indeed but I am not sure if e.g. Titan Z power circuitry is substanially weaker than 2xTitan Black???

Dual GPU cards have to be the cream of the cream since they only make sense if doubling top of the range single GPU card. As such they are of interest only for those looking at and beyond top dual single GPU cards and among these folks there will be some fans ready to pay the premium. Companies...

It is exactly what you say which proves you wrong. HBM is just like another level of cache. Evidently the more cache the better but even the current levels are enough for most uses, the real bottleneck is between the RAM and mass storage. Having nonvolatile storage in RAM sockets will be...

Here you have the answer based on detail investigation of this issue: NVidia does release dual GPU cards. Traditionally they were mainly positioned for the professional graphics and HPC (High-Performance Computing) markets with consumer cards made as a side of it. That was leading into...

The real game changer might be coming in the form of 3D Xpoint Optane technology. Imagine nonvolatile memory which plugs in the RAM sockets and has RAM speed. In other words no difference between RAM and nonvolatile storage anymore. That would be total revolution and it may start happening from...

Here is the event calendar for the closest dates of potential anouncement of Pascal Monster cards (not equivalent to the cards shipping immediately): GDC 2016 (Game Developer Conference) March 14 GTC 2016 (GPU Technology Conference) April 7

Scaling problems in SLI are due to the ancient model how the CPU is cooperating with the GPUs. In this model single core in single thread is servicing GPUs which leads to bottlenecks when the number of GPUs grows. Solution for this problem is coming with the DX12 in which many cores in multiple...

Though very low, probability of devilish happenings is non-zero. This was very rare case maybe temperature inside the box was unusually high. Note the card was running overclocked which is outside normal operational mode and (I think) not covered by the manufacturer's responsibility. I, who...

Automatic shut down is definitely in the case of GPU itself. I am not so sure if this is also in the case of VRMs which was the reason of the card death here? VRMs are really fantastic in standing the power and temperature loads but they constantly operate in the heavy duty region, especially...