ASUS, EVGA and ZOTAC GeForce GTX 960 pictured

ASUS STRIX GeForce GTX 960 OC (STRIX-GTX960-DC2OC-2GD5)

ASUS STRIX GTX 960 is an overclocked card equipped with DirectCU II cooler. The GTX 960 will feature 0 dB technology, the same technology that is available in all STRIX graphics cards. The card itself is a rather tiny, probably best fitted for mini-ITX builds. It does look like STRIX GTX 750 Ti, except it has more display connectors.

EVGA GeForce GTX 960 Superclocked

For the fans of ACX 2.0 cooling (there are any here?) EVGA brings new Superclocked GTX 960 (and some other models no one cares about).

The GTX 960 Superclocked is powered with through single 8-pin power connector. It has a full cover base plate, two heat sinks connected to each other with three copper heat pipes.  The ACX 2.0 has two 80mm 11-blade fans. I don’t know how what are the clocks yet, but I will keep you updated.

 

ZOTAC GeForce GTX 960

ZOTAC has four GTX 960 cards in the making. These cards only feature two designs and optional factory-overclocking. The first card is simply called ZOTAC GTX 960. You can actually get the same cooler with GTX 970, but I suppose it’s more suitable for this card anyway. ZOTAC’s GTX 970 features one 6-pin connector. The PCB is actually shorter than the dual-fan cooler itself.

The overclocked model based on this design will ship with 1177 / 1240 MHz clocks.

ZOTAC GeForce GTX 960 AMP!

Here is my favorite model so far. The dual-fan AMP! edition. More powerful cards like 970 and 980 are available with triple-fan edition of the same cooling system. The GTX 960 however, is not as demanding as GM204-powered cards, thus only 2 fans are required.

While it does look nice, it only has one 6-pin power connector, so I’m not sure if it can live up to the expectation of overclockers. It does however have a backplate, so if you’re into those kind of things, this could be the perfect card for you. The AMP! model has GPU clocks of 1266 / 1329 MHz.

Source: http://videocardz.com/54374/asus-evga-and-zotac-geforce-gtx-960-pictured

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

Nvidia unveils Tesla K80: dual-GPU accelerator with 24GB of GDDR5 memory

Nvidia Corp. on Monday unveiled what it claims to be the most powerful compute accelerator on the planet. The Tesla K80 dual-GPU solution sports 4992 stream processors as well as 24GB GDDR5 memory in a bid to offer unprecedented performance for difficult computational challenges, ranging from astrophysics, genomics and quantum chemistry to data analytics.

Nvidia Tesla K80 accelerator carries two brand-new GK210 processors developed specifically for high-performance computing market. Just like the GK110 graphics chips, the GK210 features up to 2880 stream processors (and up to 15 streaming multiprocessor clusters) as well as 384-bit memory bus. However, in a bid to offer better performance in compute applications, Nvidia increased the size of L1 cache of every SM cluster to 128KB (up from 64KB) and enlarged register file of every SM cluster to 512KB (up from 256KB). The new caching sub-system should significantly improve performance in numerous memory-bound applications.

The Tesla K80 accelerator is based on two GK210 processors with 2496 stream processors enabled (4992 stream processors in total). The GPUs operate at clock-rates between 562MHz and 875MHz thanks to GPU Boost technology. 24GB of GDDR5 memory function at 5.0GHz. effective frequency. The Tesla K80 delivers up to 8.74TFLOPS single-precision and up to 2.91TFLOPS double precision peak floating point performance.

“Nvidia GPUs have become the de facto computing platform for the deep learning community,” said Yann LeCun, director of AI research at Facebook, and silver professor of computer science and neural science at New York University. “Because the accuracy of deep learning systems improves as the models and datasets get larger, we always look for the fastest hardware we can find. The Tesla K80 accelerator, with its dual-GPU architecture and large memory, gives us more teraflops and more GB than ever before from a single server, allowing us to make faster progress in deep learning.”

The Tesla K80 compute accelerators are available inside HPC servers and as compute cards. Each card costs $5000.

Source: http://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-unveils-tesla-k80-dual-gpu-accelerator-with-24gb-of-gddr5-memory/

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

GeForce GTX 970 2-way SLI

GeForce GTX 970 2-way SLI

We review that lovely GeForce GTX 970 but this time in a 2-way SLI setup. In this review we'll run the standard benchmarks, but we will also have a good look at Ultra HD gaming performance as well as a micro stuttering analysis with the help of FCAT. In this article we'll be looking at 2-way SLI performance from a single monitor point of view, so ideally with so much horsepower a WQHD resolution (2560x1440/1600) is the monitor you need to have to be able to compare to what SLI would do for you on your setup, preferably even Ultra HD of course. You will notice great performance increases with 2-way SLI as the cards scale nicely with so much horsepower.

With that in the back of our mind we created a second segment in this article. For the second part of this article we'll take it up a notch and look into Ultra High-resolution gaming as we hook up an Ultra High Definition monitor. While Full HD (1920x1080/1200) and WHQL (2560x1440) have become the industry standard within the display industry, enthusiasts will never settle for just standard and are always looking for the next big innovation in technology. Ultra HD gaming is the next evolution in immersion that gamers have been waiting for. Commonly addressed as Ultra HD, UHD or 4K, this new resolution refers to the ultra-high resolutions with approximately 4000 horizontal pixels. Ultra HD resolution also has four times the number of pixels of a typical 1920x1080 resolution. It will be interesting to find out how the GeForce GTX 970 cards will handle such extreme resolutions. Considering its nice 4 GB framebuffer but  slightly dimmed memory bandwidth yet hefty GPU clocks, it's looking quite alright I'd say! With UHD (Ultra High Definition Gaming) becoming rapidly popular we'll test multiple multi-GPU setups on such a monitor. Next to that we'll perform FCAT tests to see where AMD is in Autumn anno 2014 in terms of micro-stuttering and frame pacing.

Join us in this review where we'll once again look at everything. As if you figured just one card would be interesting, you have no idea what's coming at you with two cards. 

Read More here: http://www.guru3d.com/articles-pages/geforce-gtx-970-sli-review,1.html

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

Nvidia ‘Big Daddy’ Maxwell GM200 GPU Alleged Specs Leaked – GTX 980 Ti or GTX Titan X?

[Rumor] Wow that took absolutely no time at all. Barely a few days have passed and the first rumblings of the Mysterious GM200 GPU are already upon us. The Chinese tech publication PCTuning.com, the first site to leak the GTX 980 specs I might add, has just released the GM200 GPU’s (namely GTX 980 Ti and/or maybe the new Titan) technical specifications citing insider sources. Keep in mind though, that this is still just a rumor since I cannot personally verify the authenticity of the information, although this is isn’t pure speculation either.

Nvidia Geforce GTX 980 Ti / GTX Titan X ‘GM200′ Specs Allegedly Leaked

First of all, I would like to apologize in advance for the heading. I do not know what the GM200 GPU will be called, but since I have to name the article something appropriate, 980 Ti and Titan X will have to do. Anyways here are the specs as mentioned byPCTuning:

• Die Size: 551mm^2
• SMMs/CUDA Cores: 20-22/ 2560-2816
• Memory Bus: 384 Bit
• Performance: ~50% Boost over GTX Titan Black
• Launch: Q4 2014

Now, the publication mentions that the professional and gaming equivalents will release together and there is a chance that Nvidia will keep the GM200 GPU for the professional space only. In such a case a “Geforce GTX 990″ is expected rocking two GM204 Cores. This is where the actual leak from PCTuning ends and I take the reigns on conjecture, so if speculation isn’t your cup of tea you might want to skip this part.

Basically, we already know that the GM200 chip/GTX 980 Ti/TitanX is completely ready. Its customer samples were tested a few weeks back and if it follows the same trend as the Gm204 then it should be out and about within 2 months at most. This is confirmed by data from the shipping portal zauba.com. Before the first ‘CS’ entry which appeared on 12th August 2014, there had only been entries using the nomenclature ‘INT’ which means the core is meant for Internal Testing. Because green follows the same pattern we knew that once the INT chips were spotted the CS chips wouldn’t be that far behind and  chips with the name GM200-CS0-A1 and GM200-CS1-A1 were soon spotted, indicating that the GPU is now ready. This core will have double the performance per watt of the GK110 core (as can be seen from the research paper) and we should see an amazing leap in gaming performance from 204 to 200.

Now while the GM204-A1 die is based on the 28nm process, and as I have previously mentioned before sources inside the industry tell me Nvidia is thinking about porting the circuit to 20nm in 2015. There is also one more path Nvidia can choose. I believe that Nvidia is keeping the Gm200 GPU as the ultimate checkmate against AMD. If AMD rolls out a competing flagship on the 28nm node, by my estimates the GM200 should have the performance crown. Either way, the leak scene is starting again.

Source: http://wccftech.com/nvidia-geforce-gtx-980-ti-gtx-titan-x-coming/#ixzz3EI9qQS1t

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

Quadro Cards are Here!

The Leadtek Quadro K4200 Workstation card features 4GB 256-bit DDR3 memory, DVI-I, 2x DisplayPort, OpenGL 4.3, Shader Model 5.0, DirectX 11, NVIDIA 3D Vision Pro and more. Designed and built specifically for professional workstations.

The Leadtek Quadro K5200 Workstation Card features 8GB 256-bit DDR3 memory, PCI-E 3.0, 2304 CUDA cores, 2x DVI, 2x DisplayPort 1.2, OpenGL 4.3, Shader Model 5.0, DirectX 11, NVIDIA 3D Vision Pro and more. Designed and built specifically for professional workstations.

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

EKWB R9 295X2 Installation Part 1

Check out RDT's new installation video on the R9 295X2.

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

Gigabyte GTX 980 Australian Pricing

The Gigabyte GeForce GTX 980 graphics card features a 1126MHz core clock with a 1216MHz boost clock, 4GB 256-bit GDDR5 memory, PCI-E 3.0, Open GL 4.4 support, DirectX 12 support, DVI, HDMI and 3x DisplayPort. Backed by a 3 year Gigabyte warranty.

If you are wanting to pay the Australia premium of $799 feel free. I for one will stick to my GTX 780's. For the price I would prefer to get a GTX 780Ti.

Full features, specifications and images coming soon!



If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

EVEN more GeForce GTX 980 and GTX 970 cards pictured

Inno3d iChill GTX 980

Earlier today Inno3D posted a new teaser of its iChill GTX 980. This is the fastest GTX980 Inno3D will offer.

If you thought that putting three fans on GM204 board is way too much, then what do you think of four? Quite interesting approach has been revealed by Inno3D. There’s a separate 40mm fan on the site.

At least this card boosts up to 1329 MHz. That’s quite a jump.

  

 

Inno3D GTX 970

This cute little fellow is the GTX 970 from Inno3D. It has rather large efficient fans, factory-overclocked BIOS and it’s bundled with 3DMark11.

    

Gigabyte GTX 970 and GTX 980 G1 Gaming

At last, you can see the first G1 Gaming cards (both 970 and 980 look the same). G1 Gaming series feature new WindForce cooling. Both cards will be available with a backplate. What’s cool about Gigabyte’s cards is that they offer more display connectors than any other custom 900 series card on the market. Open air cooling solution does not require any perforation on the IO bracket, thus Gigabyte put another DVI there, now there are 3 DisplayPorts, 1 HDMI, 1 DVI-D and 1 DVI-I.

  

ASUS GTX 980

Rather than launching new DirectCU III cooling system, ASUS decided to stick to reference designs and its newest STRIX series. I cannot wait to see GTX 980 MATRIX…

Bonus: MSI GTX 760

I think you should guys know that MSI has also cheaper version of Twin Frozr V cooling being made. This particular card is GTX 760, but since 760  is pretty much the backbone of 970, we should see it under 900 series sooner or later (GTX 960?)

Source: http://videocardz.com/52495/even-more-geforce-gtx-980-and-gtx-970-cards-pictured

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

EK Liquid Cooling Solution for AMD FirePro W9100

EK Water Blocks, Ljubljana based premium liquid cooling gear manufacturer, is proud to introduce the first dedicated liquid cooling solution for the latest AMD FirePro W9100 series CAD/CAM graphics cards.

EK-FCW9100 is a Full-Cover water block which directly cools the GPU, RAM as well as VRM (voltage regulation module) as water flows directly over these critical areas thus allowing the graphics card and it's VRM to remain 100% stable under any given workload. This cooler features high-flow design therefore it can be easily used in liquid cooling systems using weaker water pumps.

Base is made of C110 grade electrolytic copper while the top is made of laser cut stainless steel metal plate, which also serves as a I/O bracket. The sealing is performed by quality NBR rubber washers while the screw-in standoffs ensure safe and trouble-free installation procedure.

This water block features a very slim design therefore up to seven EK-FCW9100 water blocks can be used on a single ATX form factor motherboard. Contact us for custom multiple-port FC Terminal built per your demands.

A single-slot design also means it is possible to simply double the computing power per unit compared to factory heatsink fan (HSF) cooling solution. Same footprint - twice the power!

"Our solution is opening possibilities for vendors to build more powerful GPGPU powered workstations within the same convenient PC form factor", says Niko Tivadar, Product Manager at EK Water Blocks. "A single OpenCL 2.0 supported workstation offering over 18 TFLOPS of peak dual-precision performance is now a reality."

The product comes with a MSRP of 124.95€ (incl. VAT) and is readily available for purchase through EK Webshop.

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

ASUS STRIX GeForce GTX 970 smiles for camera

Here it is, the first ASUS graphics card from GeForce 900 series.

In terms of design, not much has changed since GTX 780 and R9 280X. By comparing these cards we notice less heat pipes near PCI-E interface, which is probably due to lower thermal requirements.

The cooler shroud is exactly the same. DirectCU II cooling features two fans, which only start working when GPU temperature exceeds 65 C. From that point fans start to spin slowly (500 RPM) until finding the sweat spot between temperature and generated noise. There are some concerns though, that letting GPU heat up so quickly may reduce the lifespan of the processor.

The packaging reveals that STRIX GTX 970 has DIGI+ VRM, 4GB GDDR5 memory and it’s a factory-overclocked solution. Clock speeds were not revealed.

GeForce GTX 970 has 1664 CUDA cores, which in connection with 256-bit interface make a reasonable Kepler GK104 replacement.

Judging from rumored information, this card should cost around $400 – $450. ASUS STRIX GTX 970 will launch on September 19th.

Lets hope that we don't get stuck with a drip feed down in Australia.

 If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

NVIDIA GeForce GTX 980 has 2048 CUDA cores

Not 1920, not 2560, but 2048 CUDAs are powering the new flagship card from NVIDIA.

GeForce GTX 980 has 16 Streaming Multiprocessors Maxwell (SMM), which give us 2048 CUDA cores in total. For comparison, GTX 970 has only 13 SMMs (1664 CUDAs), so there’s a 384 CUDA difference between these two cards.

GeForce GTX 980 is advertised as GK104 replacement, it is much more power efficient and much more powerful than first Kepler processor.

We will cover 2nd Generation Maxwell in detail very soon. Maxwell GM204 has some very neat features for gamers.

This post was only meant to confirm there are 2048 CUDAs in 980, hence not the most detailed table below.

Stay tunned.

NVIDIA GeForce GTX 900
	GeForce GTX 980	GeForce GTX 970	GeForce GTX 770	GeForce GTX 780Ti	Radeon R9 290X
GPU Codename	GM204-400	GM204-200	GK104-425	GK110-425	Hawaii XT
Unified Cores	2048	1664	1536	2880	2816
Memory	4GB GDDR5	4GB GDDR5	2GB GDDR5	3GB GDDR5	4GB GDDR5
Memory Bus	256-bit	256-bit	256-bit	384-bit	512-bit
Bandwidth	224 GB/s	224 GB/s	224 GB/s	288 GB/s	320 GB/s
Power Connectors	6pin + 6pin	6pin + 6pin	6pin + 8pin	6pin + 8pin	6pin + 8pin
TDP	~175W	148W	230W	250W	290W
Launch Date	Sep 19th, 2014	Sep 19th, 2014	May 30th, 2013	Nov 7th, 2013	Oct 24h, 2013

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus

NVIDIA GeForce GTX 980 pictured

 What you’re looking at is the new GeForce GTX 980. Today we are solely looking at the design. Specifications will be covered in our next post.

NVIDIA GeForce GTX 980 has been a mystery until now. The new flagship will adopt GeForce GTX TITAN/780/780Ti cooling solution. It is a blower type cooler capable of dissipating 250W of power. This time it will only have to deal with 180 Watts, leaving plenty of headroom for overclocking.

Now let’s take closer look at the card. First up, there are some cosmetic changes, like the one below.

However the biggest improvement can be seen on the back. NVIDIA has adopted TITAN Z backplate for its new flagship.
There is a removable part over power connectors. We do not know why yet.

GeForce GTX 980 has two 6pin power connectors. There is a space for another 8pin connector, but we are more than sure it is not necessary. It is said that GeForce GTX 980 will require only 180W, so PCI-E interface and two 6-pin connectors are more than enough.

The memory layout has of course changed, as we have modules with higher capacity. This particular sample is using Samsung K4G41325FC-HC28 4Gb (128Mx32) modules.

What pictures do not show is the new display output configuration. NVIDIA GeForce GTX 980 has five display outputs: DVI, HDMI, and three DisplayPorts. We heard that GTX 980 and 970 may feature HDMI 2.0 support, but we were unable to confirm it.

The power section has been redesigned. GTX 980 has 5 GPU phases (780 Ti had 6), but the VRM has been greatly improved.

Anyway, it’s late, so enough talking, have a look at the PCB, you can also see the new bracket (which looks similar to TITAN Z).

 

Source: http://videocardz.com/52321/nvidia-geforce-gtx-980-pictured

If you want to contact RDT please feel free to call between the hours of 9am-8pm AEST. deon@robertsondt.com Ph: 0426279566 or visit https://www.facebook.com/rdtaus