Quadro | KitGuru https://www.kitguru.net KitGuru.net - Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards Thu, 30 Mar 2023 15:46:05 +0000 en-US hourly 1 https://wordpress.org/?v=6.4.3 https://www.kitguru.net/wp-content/uploads/2021/06/cropped-KITGURU-Light-Background-SQUARE2-32x32.png Quadro | KitGuru https://www.kitguru.net 32 32 PNY NVIDIA RTX A4500 Professional Graphics Card Review https://www.kitguru.net/components/james-morris/pny-nvidia-rtx-a4500-professional-graphics-card-review/ https://www.kitguru.net/components/james-morris/pny-nvidia-rtx-a4500-professional-graphics-card-review/#respond Mon, 19 Dec 2022 13:00:47 +0000 https://www.kitguru.net/?p=585137 Looking for a pro GPU? We check out the RTX A4500

The post PNY NVIDIA RTX A4500 Professional Graphics Card Review first appeared on KitGuru.]]>
Although AMD has made huge inroads into the workstation CPU market, it still hasn't had the same success where graphics acceleration is concerned. NVIDIA continues to rule the workstation GPU roost. Since the release of the Ampere-generation RTX Ax000 series, NVIDIA has launched Ax500 models that widen the range. We took at a look at the mainstream NVIDIA RTX A4500 from PNY and ask the question: should you upgrade from the A4000?

The first thing we should mention is that NVIDIA has dropped the Quadro branding with the Ampere professional GPUs. There's an Ada generation just emerging, too, but that is only available with the top-end 6000 model so far. As its number suggests, the A4500 sits between the A4000 and A5000. However, where the A4000 uses NVIDIA's GA104 GPU, the A4500 uses the GA102 like the A5000. That means the GPU is related to the NVIDIA GeForce RTX 3080, where the A4000 is related to the GeForce RTX 3070 Ti.

In terms of specification, the A4500 unsurprisingly sits between the A4000 and A5000. However, it's a little more like the A5000, with a faster base and boost GPU clock, faster memory, and a wider bus width. The memory allocation also sits precisely in between the two other models.

The key thing, however, is that while the A5000 is almost £1,000 more than the A4000, the A4500 is only £300 more. That means it could be exactly what you need if the A4000 is just that little bit underpowered but you don't have an extra grand in your budget. So exactly how much more performance do you get for the extra £300? We ran the A4500 against the A4000 with a suite of professional workloads. Read on to discover what we learned.

GPU PNY NVIDIA RTX A4000
PNY NVIDIA RTX A4500 PNY NVIDIA RTX A5000
RT Cores
48 56 64
Tensor Cores
192 224 256
CUDA Cores
6,144 7,168 8,192
GPU Architecture / Variant GA104 GA102 GA102
Base Clock 735 MHz 1,170 MHz 1,170 MHz
GPU Boost Clock 1,560 MHz 1,695 MHz 1,695 MHz
Total Video memory 16 GB GDDR6 20 GB GDDR6 24 GB GDDR6
Memory Clock (Effective)
1,750 (14,000) MHz 2,000 (16,000) MHz 2,000 (16,000) MHz
Memory Bandwidth 448 GB/sec 640 GB/sec 768 GB/sec
Bus Width 256-bit 320-bit 384-bit
Manufacturing Process 8nm 8nm 8nm
TDP 140 W 200 W 230 W
Display Outputs 4 x DisplayPort 1.4 4 x DisplayPort 1.4 4 x DisplayPort 1.4
Display Resolution
4 @ 1920×1080
4 @ 3840×2160
4 @ 5120×2880
1 @ 7680×4320
(all at 60Hz)
4 @ 1920×1080
4 @ 3840×2160
4 @ 5120×2880
1 @ 7680×4320
(all at 60Hz)
4 @ 1920×1080
4 @ 3840×2160
4 @ 5120×2880
1 @ 7680×4320

(all at 60Hz)
Software API Support DirectX 12, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3 DirectX 12, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3 DirectX 12, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3

PNY NVIDIA RTX A4500 Retail Price: £1,439.99

Be sure to check out our sponsors store EKWB here

The post PNY NVIDIA RTX A4500 Professional Graphics Card Review first appeared on KitGuru.]]>
https://www.kitguru.net/components/james-morris/pny-nvidia-rtx-a4500-professional-graphics-card-review/feed/ 0
Modders unlock GPU virtualisation on GeForce and Quadro graphics cards https://www.kitguru.net/components/graphic-cards/joao-silva/modders-unlock-gpu-virtualisation-on-geforce-and-quadro-graphics-cards/ https://www.kitguru.net/components/graphic-cards/joao-silva/modders-unlock-gpu-virtualisation-on-geforce-and-quadro-graphics-cards/#respond Mon, 12 Apr 2021 14:06:24 +0000 https://www.kitguru.net/?p=511389 GPU virtualisation is officially exclusive to some Nvidia data centre and professional graphics cards, but a group of modders have been working on changing that. Through some tweaking, developers have managed to enable GPU virtualisation on GeForce and Quadro graphics cards.  Nvidia GeForce gaming graphics cards have always had the hardware requirements for GPU virtualisation, …

The post Modders unlock GPU virtualisation on GeForce and Quadro graphics cards first appeared on KitGuru.]]>
GPU virtualisation is officially exclusive to some Nvidia data centre and professional graphics cards, but a group of modders have been working on changing that. Through some tweaking, developers have managed to enable GPU virtualisation on GeForce and Quadro graphics cards. 

Nvidia GeForce gaming graphics cards have always had the hardware requirements for GPU virtualisation, but Nvidia has kept the feature locked down to specific units through its driver software. Modders have now found a way to get around this, enabling GPU virtualisation on GeForce and Quadro GPUs.

For those unaware of GPU virtualisation, it's the ability to divide a GPU into multiple virtual parts (vGPUs), allowing various users to use the GPU simultaneously. This feature comes in handy in situations where someone has a workstation equipped with, for example, an RTX A8000. Instead of assigning that workstation to a single user, GPU virtualisation would allow better use of resources by virtualising into multiple vGPUs for distinct users.

Broadly explained, for GPU virtualisation to work on GeForce graphics cards, you just have to replace the device ID with another that natively supports the feature. There are a few requirements for the bypass to work, including having python 3 installed with the “frida” package, DKMS, and the Nvidia GRID GPU driver. As for the supported graphics cards, any card sharing the same physical chip as a Tesla works. Those interested can find the project on Github.

Discuss on our Facebook page, HERE.

KitGuru says: Most consumers won't need this type of feature, but this is still an interesting development regardless. Have any of you used GPU virtualisation before? Are you interested in trying it out on a GeForce GPU for the first time? 

The post Modders unlock GPU virtualisation on GeForce and Quadro graphics cards first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/joao-silva/modders-unlock-gpu-virtualisation-on-geforce-and-quadro-graphics-cards/feed/ 0
EKWB introduce new enterprise grade GPU water blocks https://www.kitguru.net/components/graphic-cards/james-dawson/ek-water-blocks-introduce-new-enterprise-grade-gpu-water-blocks/ https://www.kitguru.net/components/graphic-cards/james-dawson/ek-water-blocks-introduce-new-enterprise-grade-gpu-water-blocks/#respond Sun, 21 Jun 2020 11:09:18 +0000 https://www.kitguru.net/?p=473008 EK Water Blocks has expanded its professional range this week with a host of new workstation/server-grade water blocks for powerful workstation graphics cards from both Nvidia and AMD, including Quadro, Tesla and Radeon Pro WX GPUs. The company claims that this is just the beginning of its push into the enterprise market, with more product …

The post EKWB introduce new enterprise grade GPU water blocks first appeared on KitGuru.]]>
EK Water Blocks has expanded its professional range this week with a host of new workstation/server-grade water blocks for powerful workstation graphics cards from both Nvidia and AMD, including Quadro, Tesla and Radeon Pro WX GPUs.

The company claims that this is just the beginning of its push into the enterprise market, with more product releases expected to follow in the coming months. In the first batch of enterprise-grade water blocks comes the EK-Pro GPU WB series designed to directly cool the GPU, VRM and VRAM of these workstation/server graphics cards, with liquid channelled directly across critical components.

EK-Pro GPU water blocks utilise an Open Split-Flow design that EK has proved to be a superior solution for GPU cooling. The water blocks feature a low hydraulic flow restriction, perfect for use with a low speed or a weaker pump setup, while still maintaining high thermal performance. Both the jet plate and fin structure are optimised for even flow distribution and optimal performance in reversed liquid flow situations.

At the base of the EK-Pro GPU WB is a CNC machined nickel-plated copper thermal transfer plate, with a top cover manufactured from a durable industrial-grade stainless steel. EPDM rubber O-rings are used to ensure the block is perfectly sealed, while brass standoffs come pre-installed for simple assembly. Compared with consumer EKWB GPU blocks, the thermal transfer plate has been made thicker and more durable, a G1/4” port terminal is milled directly into the thermal transfer plate for increased reliability.

EK-Pro GPU WB RTX water blocks are compatible with Nvidia Quadro RTX 8000, 6000 and 4000 GPUs. An EK-Pro GPU WB RTX 2080 Ti-Ni + Inox is also available for Nvidia RTX 2080 Ti graphics cards and the EK-Pro GPU WB WX9100 is designed specifically for the AMD Radeon Pro WX 9100. Additionally, EKWB has a new line of EK-Pro GPU backplates to complement this new series of enterprise GPU water blocks.

The new EK-Pro water blocks and backplates are available to order via the EK Webshop, backplates are on pre-order status and expected to ship on 23rd June 2020. The EK-Pro GPU WB blocks are priced starting from €191.50 and the backplates from €40.24.

Discuss on our Facebook page HERE.

KitGuru says: With its reputation for producing high-quality consumer liquid cooling products, its no surprise that EKWB is expanding its enterprise range with some durable and high-performance products. What do you guys think of these new workstation/server-grade GPU blocks from EKWB?  

The post EKWB introduce new enterprise grade GPU water blocks first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/james-dawson/ek-water-blocks-introduce-new-enterprise-grade-gpu-water-blocks/feed/ 0
IFA 2019: Razer shows off new Blade and Studio laptops https://www.kitguru.net/lifestyle/mobile/laptops/matthew-wilson/ifa-2019-razer-shows-off-new-blade-and-studio-laptops/ https://www.kitguru.net/lifestyle/mobile/laptops/matthew-wilson/ifa-2019-razer-shows-off-new-blade-and-studio-laptops/#respond Mon, 09 Sep 2019 10:00:55 +0000 https://www.kitguru.net/?p=424983 IFA 2019 has had a big focus on new gear for professionals, particularly where displays and laptops are concerned. Razer's booth was no different this year with the European debut of the Razer Blade Studio Edition, although there were also some interesting updates to the gaming-focused Blade laptops too.  The 13-inch Razer Blade Stealth has …

The post IFA 2019: Razer shows off new Blade and Studio laptops first appeared on KitGuru.]]>
IFA 2019 has had a big focus on new gear for professionals, particularly where displays and laptops are concerned. Razer's booth was no different this year with the European debut of the Razer Blade Studio Edition, although there were also some interesting updates to the gaming-focused Blade laptops too. 

The 13-inch Razer Blade Stealth has been upgraded and is now considered to be the world's first gaming UltraBook. Razer has made the jump to an Intel 10th Gen Core i7-1065G7 processor and swapped out Nvidia MX-series graphics for a GTX 1650.

The Blade 15 Base Model has also received an upgrade to an Intel Core i7-9750H and RTX 2060 graphics with a 1080p/144Hz display. The Blade 15 Advanced will soon be available with either a 4K OLED panel or a 240Hz display and up to RTX 2080 Max-Q graphics.

The Razer Blade 15 Studio Edition was first announced at Computex to coincide with NVIDIA's RTX Studio initiative. We're hearing that this one will cost around £4,000 and will sport an Intel Core i7-9750H, 32GB of DDR4 RAM and a Quadro RTX 5000 Max-Q GPU.

KitGuru Says: There are plenty of Razer Blade upgrades coming up this year. Is there anything in particular that has caught your eye?

The post IFA 2019: Razer shows off new Blade and Studio laptops first appeared on KitGuru.]]>
https://www.kitguru.net/lifestyle/mobile/laptops/matthew-wilson/ifa-2019-razer-shows-off-new-blade-and-studio-laptops/feed/ 0
Nvidia Quadro P6000 can’t run four VR simulations at once https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-quadro-p6000-cant-run-four-vr-simulations-at-once/ https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-quadro-p6000-cant-run-four-vr-simulations-at-once/#comments Wed, 07 Dec 2016 09:48:35 +0000 http://www.kitguru.net/?p=313981 At the end of last month we reported on a Nvidia blog entry which claimed that a single Quadro P6000 was capable of powering four VR simulations on Oculus Rifts and HTC Vives at the same time. However it turns out this was based on a mistake in the original Nvidia blog entry, so to …

The post Nvidia Quadro P6000 can’t run four VR simulations at once first appeared on KitGuru.]]>
At the end of last month we reported on a Nvidia blog entry which claimed that a single Quadro P6000 was capable of powering four VR simulations on Oculus Rifts and HTC Vives at the same time. However it turns out this was based on a mistake in the original Nvidia blog entry, so to correct the record, we're updating the original story and releasing this one so everyone is aware.

The blog entry in question can still be found on the Nvidia site, though it has now been updated to reflect the reality of the situation. Far from being capable of delivering four separate VR experiences on a single GPU, the Quadro P6000 is capable of running just one VR simulation. To achieve the quad-VR aspect of the server, Nvidia suggests that it actually takes four Quadro P6000s.

quadro

It seems to be a case of whoever wrote the blog getting the wrong end of the stick and suggesting it was a single GPU, rather than a single server with four cards in. Unfortunately that makes the original story rather redundant, since it's not impressive to run four VR simulations on four cards when they cost $5000 (£4000) a piece.

While we don't doubt that the military training demos are intensive, we'd imagine that some high-end consumer cards could achieve a similar effect. Especially considering the Quadro P6000s are only a little more powerful than the much cheaper Pascal Titan X cards anyway.

Discuss on our Facebook page, HERE.

KitGuru Says: Apologies for this one guys, but the source material lead us astray. We've updated the original story to link here, so hopefully no one else gets the wrong end of the stick. 

The post Nvidia Quadro P6000 can’t run four VR simulations at once first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-quadro-p6000-cant-run-four-vr-simulations-at-once/feed/ 7
Update: Nvidia Quadro P6000 not as capable as we thought https://www.kitguru.net/components/vr/jon-martindale/nvidia-quadro-p6000-can-run-four-military-grade-vr-demos-at-once/ https://www.kitguru.net/components/vr/jon-martindale/nvidia-quadro-p6000-can-run-four-military-grade-vr-demos-at-once/#comments Mon, 28 Nov 2016 11:05:24 +0000 http://www.kitguru.net/?p=313216 Update 07/12/16: This story has now been shown to be false, after Nvidia updated its information. For a full retraction and explanation, have a read of the new story here. Original Story: If we thought early consumer grade virtual reality was pretty, wait until the military grade experiences and AAA games start filtering through to …

The post Update: Nvidia Quadro P6000 not as capable as we thought first appeared on KitGuru.]]>
Update 07/12/16: This story has now been shown to be false, after Nvidia updated its information. For a full retraction and explanation, have a read of the new story here.

Original Story: If we thought early consumer grade virtual reality was pretty, wait until the military grade experiences and AAA games start filtering through to the public. We may need some relatively hefty equipment to run them, but that's no problem for a system fitted with Nvidia's top-end enterprise card, the Quadro P6000. It's capable of running up to four VR simulations on a Rift or Vive simultaneously.

Although virtual reality might have been teased in the consumer space for a few decades and has finally made its mark in 2016, various militaries around the world have been using it just as long to help train soldiers. From tank driving, to piloting F-18s, soldiers have been in VR longer than any of us ever have. When it comes to the latest developments too, they're way ahead of the curve on visual immersion too.

quadro

Many of the demos used by the U.S. military are built by Mass Virtual, a specialist in VR simulations. It helped pioneer the 360 degree projector systems which we've seen used before VR became a big deal. Now though it creates stunning looking VR environments in its own engine, Virtual Attain, which it recently made freely available to the U.S. government.

With that it's able to create stunningly realistic environments and scenarios that allow for virtual training missions for engineering, clearing buildings, piloting ships, planes and more. Powering such experiences isn't easy though, which is why Nvidia has been throwing Quadros at it to showcase how stupendously powerful they are. At the upcoming I/ITSEC show, running between the 28th of November and 2nd December, a single Quadro P6000 will be used to power as many as four different VR experiences on four separate HTC Vives and Oculus Rifts, as per the Nvidia blog.

[yframe url='http://www.youtube.com/watch?v=fXOSWuLnPSM']

The idea is that Quadro equipped systems can be installed either at the network level, for mass VR deployment, or in confined spaces such as ships of submarines, to help train large scale movements, or to refine important skills to prevent them from getting rusty during down time.

Discuss on our Facebook page, HERE.

KitGuru Says: Even if the Quadros are usually ungodly expensive, it won't be long until that sort of power becomes available for consumer grade GPUs. When it does, the idea of whether our cards can run VR is laughable. Even low end should be able to handle it by that point. 

The post Update: Nvidia Quadro P6000 not as capable as we thought first appeared on KitGuru.]]>
https://www.kitguru.net/components/vr/jon-martindale/nvidia-quadro-p6000-can-run-four-military-grade-vr-demos-at-once/feed/ 2
Nvidia launches Pascal Quadro Cards, with GTX 1080 beating power https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-launches-pascal-quadro-cards-with-gtx-1080-beating-power/ https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-launches-pascal-quadro-cards-with-gtx-1080-beating-power/#comments Tue, 26 Jul 2016 14:01:40 +0000 http://www.kitguru.net/?p=300579 Nvidia has debuted a new pair of graphics cards as part of its Pascal line up, but these ones aren't designed to give you ungodly frame rates in the latest and greatest games, these ones are for the business users. Workstations, renderers and situations that require more power than a GTX Titan X can put …

The post Nvidia launches Pascal Quadro Cards, with GTX 1080 beating power first appeared on KitGuru.]]>
Nvidia has debuted a new pair of graphics cards as part of its Pascal line up, but these ones aren't designed to give you ungodly frame rates in the latest and greatest games, these ones are for the business users. Workstations, renderers and situations that require more power than a GTX Titan X can put out, could all benefit from teaming up with the new Quadro P5000 and P6000.

These cards are being shown off by Nvidia for the first time at this year's SIGGRAPH conference, where visitors will get a chance to see both cards up close, with live demos of 4K videos being stitched together in real time, to create seamless 360 degree movies.

The former of the two cards is, as you might expect, the smaller one – but that doesn't mean it's weak. Able to output just shy of nine teraflops of power, the P5000 is no push over. It comes equipped with 2,560 CUDA cores and 16GB of GDDR5X.

quadrop6000-03

Nvidia didn't give us any details on what the clock speeds for both the memory and core are, but we do know that the P5000 draws 180w of power, which isn't too hectic.

Its bigger brother the P6000 though, draws a much heftier 250w, because it puts out as much as 12 teraflops of floating point performance. That's thanks to its monstrous 3,840 CUDA cores, combined with 24GB of GDDR5X memory.

Both of these GPUs are compatible with Nvidia's VR works, and they're being pitched as good hardware for use in making new 360 degree video, as well as developing virtual reality games. The P6000 and P5000 also support Nvidia Opitx 4, Nvidia's Ray Tracing engine.

KitGuru Says: Complete overkill for any gamer and certainly not optimised for the tasks within your average game, but it's hard not to salivate at those specifications. 

The post Nvidia launches Pascal Quadro Cards, with GTX 1080 beating power first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/jon-martindale/nvidia-launches-pascal-quadro-cards-with-gtx-1080-beating-power/feed/ 3
Boxx unveils tiny mini-ITX workstation with 18-core Intel Xeon https://www.kitguru.net/desktop-pc/anton-shilov/boxx-technologies-unveils-tiny-mini-itx-workstation-with-18-core-intel-xeon/ https://www.kitguru.net/desktop-pc/anton-shilov/boxx-technologies-unveils-tiny-mini-itx-workstation-with-18-core-intel-xeon/#comments Wed, 30 Sep 2015 22:03:20 +0000 http://www.kitguru.net/?p=270135 Boxx Technologies, a well-known maker of workstations from the U.S., has introduced its new Apexx 1 mini-ITX workstation that can integrate an Intel Xeon microprocessor with up to 18 cores or a factory-overclocked Intel Core i7 chip with up to eight cores. The system comes with a specially-designed cooling solution and can offer unbeatable performance …

The post Boxx unveils tiny mini-ITX workstation with 18-core Intel Xeon first appeared on KitGuru.]]>
Boxx Technologies, a well-known maker of workstations from the U.S., has introduced its new Apexx 1 mini-ITX workstation that can integrate an Intel Xeon microprocessor with up to 18 cores or a factory-overclocked Intel Core i7 chip with up to eight cores. The system comes with a specially-designed cooling solution and can offer unbeatable performance for professionals, who need a lot of general-purpose horsepower. Still, the Apexx 1 has a number of compromises.

The Boxx Apexx 1 is based on the Asrock X99E-ITX/ac motherboard, which is equipped with a modified LGA2011-3 socket with additional pins (also known as the O.C. socket) that is designed to provide enhanced overclocking potential and which supports Intel’s latest Core i7 high-end desktop chips with up to eight cores as well as Intel Xeon E5 v3 central processing units with up to 18 cores and up to 45MB of cache. The Core i7-5960X “extreme” processor can be factory-overclocked by Boxx to 4.0GHz.

boxx_apexx_3

The Apexx 1 system can be equipped with up to 64GB of ECC memory, one high-end solid-state drive in M.2 form-factor (with PCIe 3.0 x4 interface), two 2.5” HDDs or SSDs. Due to size constraints, the system is only compatible with small form-factor professional graphics cards from AMD and Nvidia. The fastest adapter that Boxx offers is Nvidia’s Quadro K1200 with 4GB of memory. All Apexx 1 configurations include USB 3.0 ports, Gigabit Ethernet, and Wi-Fi 802.11ac wireless connectivity.

boxx_apexx_1

The Asrock X99E-ITX/ac mainboard only supports two DDR4 memory modules and thus cannot take advantage of quad-channel memory controllers of advanced CPUs. As a result, performance of multi-core microprocessors in applications that require memory bandwidth may be limited. Moreover, the workstation requires a special Boxx server-grade liquid-cooling system in order to cool-down chips with thermal design pwoer of 145W or higher, which may be rather noisy. Since at present the Asrock X99E-ITX/ac is the only mini-ITX platform for LGA2011-3 processors, the limitations is not something that can be avoided.

boxx_apexx_4

Boxx claims that the Apexx 1 was designed for such applications as Autodesk 3ds Max, Autocad, Maya, Revit, Cinema4D, SolidWorks, Catia and others.

The unique Boxx Apexx 1 workstations start at $5180 when equipped with an eight-core chip, Nvidia Quadro K1200, and so on. Top-of-the-range configuration with 18-core Intel Xeon E5-2699 v3 with 45MB cache, 64GB of DDR4 memory, 512GB M.2 SSD, two 1.2TB Serial ATA-6Gb/s SSDs and so on will cost around $15600.

boxx_apexx_2

Discuss on our Facebook page, HERE.

KitGuru Says: The Boxx Apexx 1 is the most powerful mini-ITX workstation ever. However, how balanced it is? If one needs a system for rendering, then it makes sense to install 18-core CPUs and sacrifice GPU performance. However, those, who need small form-factor, great graphics performance and decent CPU for rendering, should consider Apple Mac Pro, which packs two AMD FirePro graphics processors as well as Intel Xeon microprocessors with up to 12 cores.

The post Boxx unveils tiny mini-ITX workstation with 18-core Intel Xeon first appeared on KitGuru.]]>
https://www.kitguru.net/desktop-pc/anton-shilov/boxx-technologies-unveils-tiny-mini-itx-workstation-with-18-core-intel-xeon/feed/ 7
Nvidia’s next-gen ‘Pascal’ graphics cards will get 16GB of HBM2 memory https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-next-gen-high-end-graphics-cards-will-get-16gb-of-hbm2-memory/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-next-gen-high-end-graphics-cards-will-get-16gb-of-hbm2-memory/#comments Thu, 24 Sep 2015 01:57:48 +0000 http://www.kitguru.net/?p=269090 At the GPU Technology Conference in Japan, Nvidia Corp. once again revealed key features of its next-generation graphics processing architecture code-named “Pascal”. As a it appears, the company has slightly changed its plans concerning memory capacity supported by its upcoming GPUs. As expected, Nvidia’s high-end graphics processor that belongs to the “Pascal” family will feature an …

The post Nvidia’s next-gen ‘Pascal’ graphics cards will get 16GB of HBM2 memory first appeared on KitGuru.]]>
At the GPU Technology Conference in Japan, Nvidia Corp. once again revealed key features of its next-generation graphics processing architecture code-named “Pascal”. As a it appears, the company has slightly changed its plans concerning memory capacity supported by its upcoming GPUs.

As expected, Nvidia’s high-end graphics processor that belongs to the “Pascal” family will feature an all-new architecture with a number of exclusive innovations, including mixed precision (for the first time Nvidia’s stream processors will support FP16, FP32 and FP64 precision), NVLink interconnection technology for supercomputers and multi-GPU configurations, unified memory addressing as well as support for second-generation high-bandwidth memory (HBM generation 2).

Based on a slide that Nvidia demonstrated at the GTC Japan 2015, next-generation high-end graphics cards with “Pascal” GPUs will sport up to 16GB of HBM2 with up to 1TB/s bandwidth. Previously Nvidia expected select solutions with “Pascal” graphics processors to feature up to 32GB of HBM2.

nvidia_pascal_expectations_gtc_2015_japan
Nvidia “Pascal” highlights. Image by WccfTech

Given the fact that Nvidia does not produce high-bandwidth memory itself, but relies on supplies from companies like Samsung Electronics and SK Hynix, changes of their roadmaps can affect Nvidia’s plans. In order to install 32GB of HBM2 memory on a graphics processor with a 4096-bit memory bus, 8GB memory chips are used. While the HBM2 specification allows to build such ICs [integrated circuits], it is not easy to manufacture packages with eight vertically stacked 8Gb memory dies. As a result, such chips may be delayed from 2016 to a later date.

16GB of HBM2 memory should be enough for gaming and professional graphics cards, but high-performance computing applications could take advantage of 32GB of onboard memory even now.

Discuss on our Facebook page, HERE.

KitGuru Says: If Nvidia is not able to get 8GB HBM2 chips next year, AMD will not be able to get them as well. Therefore, expect graphics cards with up to 16GB of high-bandwidth memory from both companies.

The post Nvidia’s next-gen ‘Pascal’ graphics cards will get 16GB of HBM2 memory first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-next-gen-high-end-graphics-cards-will-get-16gb-of-hbm2-memory/feed/ 44
Nvidia gets first samples of GP100 from TSMC, begins internal tests https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-receives-first-samples-of-gp100-chips-from-tsmc-begins-to-test-them/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-receives-first-samples-of-gp100-chips-from-tsmc-begins-to-test-them/#comments Wed, 23 Sep 2015 00:18:13 +0000 http://www.kitguru.net/?p=268782 Taiwan Semiconductor Manufacturing Co. has successfully produced the first samples of Nvidia Corp.’s code-named GP100 graphics processing unit. Nvidia has already started to test the chip internally and should be on-track to release the GPU commercially in mid-2016. 3DCenter reports that Nvidia has sent the first graphics cards based on the GP100 graphics processor to its …

The post Nvidia gets first samples of GP100 from TSMC, begins internal tests first appeared on KitGuru.]]>
Taiwan Semiconductor Manufacturing Co. has successfully produced the first samples of Nvidia Corp.’s code-named GP100 graphics processing unit. Nvidia has already started to test the chip internally and should be on-track to release the GPU commercially in mid-2016.

3DCenter reports that Nvidia has sent the first graphics cards based on the GP100 graphics processor to its subsidiary in India, where it has a lot of hardware and software developers. No actual details about the chip or graphics cards on its base are known, but it is about time for the graphics giant to start testing its GP100.

Nvidia taped out the GP100 in June, 2015. Production cycle of TSMC’s 16nm FinFET process technology is about 90 days, therefore Nvidia got its GP100 from TSMC very recently. Right now the company is testing the chip and its drivers internally.

nvidia_artwork_iron

Nvidia’s GP100 graphics processing unit is based on the “Pascal” architecture and is made using 16nm FinFET+ process technology. The chip is expected to integrate up to 6000 stream processors and contain around 17 billion transistors. Graphics cards featuring the GP100 will carry up to 32GB of HBM2 memory.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It is about time for Nvidia to start testing its GP100 now. What remains to be seen is when exactly the company plans to formally introduce its next-generation GPUs. If the first revision of the chip is fully functional, the company may move in introduction of the GP100 to the first quarter of the year.

The post Nvidia gets first samples of GP100 from TSMC, begins internal tests first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-receives-first-samples-of-gp100-chips-from-tsmc-begins-to-test-them/feed/ 20
Scan 3XS GW-HTX35 Workstation (w/ Quadro M6000) Review https://www.kitguru.net/desktop-pc/james-morris/scan-3xs-gw-htx35-workstation-w-quadro-m6000-review/ https://www.kitguru.net/desktop-pc/james-morris/scan-3xs-gw-htx35-workstation-w-quadro-m6000-review/#comments Tue, 22 Sep 2015 08:23:04 +0000 http://www.kitguru.net/?p=262359 Scan will be well-known to KitGuru readers for its huge and comprehensive component supply business. But the company has also been building professional workstations for many years. The 3XS range includes both enthusiast systems for gamers as well as rack-mount servers and high-performance computing nodes. The 3XS GW-HTX35 is a high-end graphics system that brings …

The post Scan 3XS GW-HTX35 Workstation (w/ Quadro M6000) Review first appeared on KitGuru.]]>
Scan will be well-known to KitGuru readers for its huge and comprehensive component supply business. But the company has also been building professional workstations for many years. The 3XS range includes both enthusiast systems for gamers as well as rack-mount servers and high-performance computing nodes. The 3XS GW-HTX35 is a high-end graphics system that brings together the best possible components in most areas, and won't give you much change out of £10,000 as a result.

Central to the GW-HTX35 is a pair of ten-core Xeon processors, giving this system huge potential with parallel-processing tasks like 3D rendering. These are backed by a healthy 64GB of RAM. But 3D modelling performance will be excellent, too, because this is the first system we have seen with the super-expensive NVIDIA Quadro M6000 professional graphics card, which costs around £3,000 on its own and sports a whopping 12GB of frame buffer. So this is a system with potential to reign supreme across the board. Read on to see how it does in our suite of professional tests.

Here are some detailed shots of the system, internal and external.


Scan-10k-Review-KitGuru-Front
 Scan-10k-Review-KitGuru-Front-and-Back Scan-10k-Review-KitGuru-Top-Panel Scan-10k-Review-KitGuru-Internal-Panel
Scan-10k-Review-KitGuru-Mainboard-Connections Scan-10k-Review-KitGuru-PSU Scan-10k-Review-KitGuru-PSU-Internal Scan-10k-Review-KitGuru-HDD-Bays
Scan-10k-Review-KitGuru-Internals-Built Scan-10k-Review-KitGuru-Internals-Cooling Scan-10k-Review-KitGuru-heat-Sink Scan-10k-Review-KitGuru-Heatsinks
Scan-10k-Review-KitGuru-Board-Sockets Scan-10k-Review-KitGuru-Dual-CPU-Cooling Scan-10k-Review-KitGuru-memory-Sockets Scan-10k-Review-KitGuru-Quadro-M6000
Scan-10k-Review-KitGuru-Ethernet

Scan 3XS GW-HT35 Specifications:

  • 2x Intel Xeon E5-2687W V3 @ 3.1GHz
  • 64GB Crucial ECC Registered DDR4 SDRAM @ 2,133MHz
  • ASUS Z10PE-D8 WS Motherboard
  • 512GB Samsung 850 Pro SATA III 6Gb/s SSD
  • 2TB Seagate Barracuda 7200.14 SATA III 6Gb/s 7,200rpm HDD
  • 12GB GDDR5 NVIDIA Quadro M6000 Graphics
  • 2x 3XS customised Corsair H80 water cooling
  • 1,000W Corsair RM PSU
  • Fractal Design Define XL Titanium Grey chassis
  • Windows 7 Professional 64bit
  • 3 Years warranty, 1 Year Onsite, 2 Years RTB

Price: £9,179 inc VAT & Delivery (Buy from SCAN HERE)

The post Scan 3XS GW-HTX35 Workstation (w/ Quadro M6000) Review first appeared on KitGuru.]]>
https://www.kitguru.net/desktop-pc/james-morris/scan-3xs-gw-htx35-workstation-w-quadro-m6000-review/feed/ 3
Nvidia changes roadmap: ‘Volta’ is now due in 2018 https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-changes-roadmap-volta-is-now-due-in-2018/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-changes-roadmap-volta-is-now-due-in-2018/#comments Tue, 22 Sep 2015 01:14:41 +0000 http://www.kitguru.net/?p=268590 Nvidia Corp. has slightly changed its roadmap concerning GPU architectures. As it appear, its next-gen GPUs code-named “Pascal” are now due in 2016, whereas their successors will be released only in 2018. Based on a new roadmap that Nvidia showcased at a tech conference in Japan, the company will release its code-named “Pascal” GPUs in 2016 …

The post Nvidia changes roadmap: ‘Volta’ is now due in 2018 first appeared on KitGuru.]]>
Nvidia Corp. has slightly changed its roadmap concerning GPU architectures. As it appear, its next-gen GPUs code-named “Pascal” are now due in 2016, whereas their successors will be released only in 2018.

Based on a new roadmap that Nvidia showcased at a tech conference in Japan, the company will release its code-named “Pascal” GPUs in 2016 and will follow on with “Volta” graphics processors in 2018. The “Pascal” chips will be made using 16nm FinFET process technology and will be available in 2016, reports WccfTech. Previously “Volta” was expected in 2017.

NVIDIA-Pascal-GPU_Roadmap

Not a lot is known about the first “Pascal” GPU. Nvidia has reportedly taped out its GP100 graphics processor back in June. Given the timeframe of the tape-out, it is highly likely that Nvidia uses TSMC’s advanced 16nm FinFET+ (CLN16FF+) manufacturing technology. Nvidia has changed its approach to roll-out of new architectures. Instead of starting from simple GPUs and introducing biggest processors quarters after the initial chips, Nvidia will begin to roll-out 16nm “Pascal” GPUs with the largest chip in the family.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It looks like Nvidia is pulling in “Pascal”, but slightly delays “Volta”. The reason for this is simple: 10nm process technology. At TSMC it will only be available for Nvidia in 2018.

The post Nvidia changes roadmap: ‘Volta’ is now due in 2018 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-changes-roadmap-volta-is-now-due-in-2018/feed/ 32
Sales of desktop graphics cards hit 10-year low in Q2 2015 https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-desktop-graphics-cards-hit-10-year-low-in-q2-2015/ https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-desktop-graphics-cards-hit-10-year-low-in-q2-2015/#comments Mon, 24 Aug 2015 21:20:49 +0000 http://www.kitguru.net/?p=264714 Sales of graphics cards for desktop PCs decreased once again in the second quarter of 2015, according to data from Jon Peddie Research. Market share of Advanced Micro Devices also hit a new low during the quarter. Shipments of discrete graphics adapters for desktops dropped to 9.4 million units in Q2 2015, which is minimum …

The post Sales of desktop graphics cards hit 10-year low in Q2 2015 first appeared on KitGuru.]]>
Sales of graphics cards for desktop PCs decreased once again in the second quarter of 2015, according to data from Jon Peddie Research. Market share of Advanced Micro Devices also hit a new low during the quarter.

Shipments of discrete graphics adapters for desktops dropped to 9.4 million units in Q2 2015, which is minimum amount in more than ten years. According to JPR, sales of graphics cards dropped 16.81 per cent compared to the previous quarter, whereas sales of desktop PCs decreased 14.77 per cent. The attach rate of add-in graphics boards (AIBs) to desktop PCs has declined from a high of 63 per cent in Q1 2008 to 37 per cent this quarter. Average sales of graphics cards have been around 15 million units per quarter in the recent years, but declined sharply in 2014.

nvidia_geforce_gtx_980_1

Nvidia continued its dominance in the market of desktop discrete graphics cards. Market share of the company increased to 81.9 per cent, an all-time high. By contrast, sales of AMD Radeon graphics adapters decreased to a minimum in more than 10 years. The share of AMD dropped to 18 per cent in Q2 2015, which is the lowest share that AMD had in history. The highest share of desktop discrete market that AMD ever had was 55.5 per cent back in Q3 2004, according to Jon Peddie Research. AMD shipped around 35 per cent or desktop discrete graphics processing units in the last four years. AMD’s share began to contract sharply after Nvidia introduced its GeForce GTX 970 and 980 graphics cards in Q3 2014. In about a year AMD lost 20 per cent of market share it controls.

jpr_aib_q2_2015

 

Note: Some numbers are estimates.

JPR claims that while the market of desktop AIBs is shrinking, sales of expensive graphics cards used by gamers are increasing.

“However, in spite of the overall decline, somewhat due to tablets and embedded graphics, the PC gaming momentum continues to build and is the bright spot in the AIB market,” said Jon Peddie, the head of JPR.

jpr_aib_q2_2015_shares

AMD’s quarter-to-quarter total desktop graphics cards unit shipments decreased 33.3 per cent. Nvidia’s quarter-to-quarter unit shipments decreased 12 per cent.

Discuss on our Facebook page, HERE.

KitGuru Says: It is noteworthy that AMD is losing market share despite the fact that it has rather competitive graphics processing units. Further improvements of integrated graphics processors will decrease sales of add-in graphics boards.

The post Sales of desktop graphics cards hit 10-year low in Q2 2015 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-desktop-graphics-cards-hit-10-year-low-in-q2-2015/feed/ 24
Samsung expects graphics cards with 6144-bit bus, 48GB of HBM memory onboard https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-expects-graphics-cards-with-6144-bit-bus-48gb-of-hbm-memory-onboard/ https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-expects-graphics-cards-with-6144-bit-bus-48gb-of-hbm-memory-onboard/#comments Fri, 21 Aug 2015 15:56:38 +0000 http://www.kitguru.net/?p=264471 Samsung Electronics indicated that it plans to start volume production of high-bandwidth memory (HBM) next year at the Intel Developer Forum this week. At the trade-show, the company revealed its current vision and expectations concerning HBM. Samsung foresees that eventually high-performance applications (such as GPUs) could feature up to six HBM devices to enable unprecedented …

The post Samsung expects graphics cards with 6144-bit bus, 48GB of HBM memory onboard first appeared on KitGuru.]]>
Samsung Electronics indicated that it plans to start volume production of high-bandwidth memory (HBM) next year at the Intel Developer Forum this week. At the trade-show, the company revealed its current vision and expectations concerning HBM. Samsung foresees that eventually high-performance applications (such as GPUs) could feature up to six HBM devices to enable unprecedented capacities and bandwidth.

As it appears, Samsung plans to skip the first-generation HBM memory and will only manufacture products compliant with the second-generation HBM specification, which offers higher densities and clock-rates. Such approach will let Samsung to address broader market segments with its HBM offerings. Right now HBM can only be used on consumer graphics cards and certain highly-custom products, but HBM2 will enable professional and high-performance computing GPU-based solutions, which require a lot of memory onboard.

Samsung is currently working on multiple HBM packages featuring two (2Hi stack), four (4Hi) and eight (8Hi) 8Gb memory devices on a base logic die with 1024-bit interface, according to a slide that the company demonstrated at the IDF (which was published by ComputerBase.de). Maximum data-rates of Samsung’s HBM products will be 2Gb/s, which will support up to 256GB/s of bandwidth per chip.

samsung_hbm_plans

Samsung believes that HBM memory will enable it to create a variety of chip offerings targeting different market segments. Designers of logic chips (GPUs, APUs, network processors, etc.) will be able to integrate the right amount of HBM controllers into their chips in order to target different applications. At present AMD’s “Fiji” graphics processing unit supports up to four HBM stacks over its 4096-bit interface. Eventually, logic chips could accommodate more HBM controllers and expand interface width to unprecedented 6144-bit, according to Samsung Electronics.

For example, a mainstream graphics card could use just one 2Hi HBM chip to accommodate a 2GB frame-buffer with 256GB/s bandwidth. More advanced graphics adapters for consumers and creative professionals could feature four 2Hi or four 4Hi HBM stacks that provide up to 1TB/s of bandwidth as well as 8GB, 16GB or 32GB of memory. Accelerators for high-performance computing as well as ultra-high-end GPU offerings will support six HBM stacks, thus enabling cards with 12GB, 24GB or 48GB of onboard memory with 1.5TB/s bandwidth.

amd_radeon_fiji_gpu

So far, neither AMD nor Nvidia have demonstrated even hypothetical product implementations (which are used to showcase potential future uses of technologies) of GPU-based solutions featuring six HBM memory chips. Intel Corp.’s Xeon Phi co-processors use HMC [hybrid memory cube] DRAMs as “near memory” and are not expected to support HBM any time soon.

nvidia_pascal_module

Samsung expects HBM memory to be used for consumer graphics cards and high-performance computing accelerators based on AMD “Arctic Islands” and Nvidia “Pascal” graphics processors next year. Sometimes in 2017, network products will also take advantage of the new memory type. Three years from now other applications could employ HBM, according to Samsung.

The world’s largest maker of dynamic random access memory (DRAM) did not unveil any details about its actual HBM chips (capacities, clock-rates, etc.), but expect a family of products with different densities and frequencies.

Samsung did not disclose which process technology it will use to manufacture HBM.

Discuss on our Facebook page, HERE.

KitGuru Says: Samsung is definitely not the first to offer HBM, but it is pretty clear that the company takes the new type of memory very seriously. What is interesting is that the company decided not to give a glimpse into the future of HBM, which indicates that the third-generation HBM is still a work in progress.

The post Samsung expects graphics cards with 6144-bit bus, 48GB of HBM memory onboard first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-expects-graphics-cards-with-6144-bit-bus-48gb-of-hbm-memory-onboard/feed/ 31
Nvidia unveils Quadro M4000, M5000 professional graphics cards https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-quietly-unveils-quadro-m4000-m5000-professional-graphics-solutions/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-quietly-unveils-quadro-m4000-m5000-professional-graphics-solutions/#comments Wed, 12 Aug 2015 09:52:42 +0000 http://www.kitguru.net/?p=263188 Nvidia Corp. has quietly introduced two new professional graphics cards. The new Quadro M4000 and Quadro M5000 adapters are powered by the highly-successful “Maxwell” architecture. The novelties promise to deliver strong performance in graphics applications, but when it comes to computing, the new GPUs will be slower than some of their predecessors because of architectural …

The post Nvidia unveils Quadro M4000, M5000 professional graphics cards first appeared on KitGuru.]]>
Nvidia Corp. has quietly introduced two new professional graphics cards. The new Quadro M4000 and Quadro M5000 adapters are powered by the highly-successful “Maxwell” architecture. The novelties promise to deliver strong performance in graphics applications, but when it comes to computing, the new GPUs will be slower than some of their predecessors because of architectural peculiarities.

The new Quadro M4000 and M5000 graphics cards are powered by the GM204 graphics processing units with 1664 and 2048 stream processors, respectively. Both graphics adapters feature 256-bit memory bus and carry 8GB of GDDR5 memory. The more advanced Quadro M5000 features ECC memory and dual-slot cooling system. The more energy-efficient Quadro M4000 sports single-slot cooler.

quadro-m6000-header

The new Quadro graphics cards fully support all modern technologies and application programming interfaces, including OpenGL 4.5, OpenCL 1.2, DirectX 12, 3D Vision Pro, Quadro Sync, SLI and so on.

nvidia_quadro_specs_2015

Since Nvidia’s “Maxwell” architecture does not include FP64 arithmetic logic units (ALUs), performance of GPUs based on Nvidia’s latest technology in applications that require double precision computing is very low. Typically, professional graphics applications do not need FP64, but scientific applications used by creative professionals usually do. As a result, for many people previous-generation “Kepler” based Quadro graphics adapters may be a better choice.

Discuss on our Facebook page, HERE.

KitGuru Says: It is rather surprising that it took Nvidia almost a year to develop two professional graphics cards based on the GM204 graphics processing unit.

The post Nvidia unveils Quadro M4000, M5000 professional graphics cards first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-quietly-unveils-quadro-m4000-m5000-professional-graphics-solutions/feed/ 2
Lenovo’s new laptops come with Xeon CPUs and Quadro graphics https://www.kitguru.net/lifestyle/mobile/notebook/matthew-wilson/lenovos-new-laptops-come-with-xeon-cpus-and-quadro-graphics/ https://www.kitguru.net/lifestyle/mobile/notebook/matthew-wilson/lenovos-new-laptops-come-with-xeon-cpus-and-quadro-graphics/#respond Tue, 11 Aug 2015 15:31:43 +0000 http://www.kitguru.net/?p=263036 It looks like Lenovo is getting serious about portable workstations as its new Thinkpad P50 and P70 laptops come equipped with Intel Xeon processors and 4K panels. In addition to that, the systems are running Nvidia's professional Quadro graphics chips as well. Under the hood, you will find the Intel Xeon E3-1500M, one of Intel's …

The post Lenovo’s new laptops come with Xeon CPUs and Quadro graphics first appeared on KitGuru.]]>
It looks like Lenovo is getting serious about portable workstations as its new Thinkpad P50 and P70 laptops come equipped with Intel Xeon processors and 4K panels. In addition to that, the systems are running Nvidia's professional Quadro graphics chips as well.

Under the hood, you will find the Intel Xeon E3-1500M, one of Intel's first ever mobile Xeon processors, which should provide a performance boost for those needing to do video or 3D work on the go. In addition to that, the laptops support up to 64GB of RAM along with some Thunderbolt Ports, which can drive multiple 4K displays.

lenovo-thinkpad-p70

The Thinkpad P50 comes with a 15.6-inch display, with the P70 variant comes with a 17-inch screen. While these new portable workstation machines have been announced, they won't be available for a few months now, with availability currently scheduled for some time in the fourth quarter.

The Thinkpad P50 will start at $1,599 with the base model coming with a 1080p display for those who don't necessarily want 4K. The P70 on the other hand is a bit more expensive, starting at $1999 and going up depending on upgrades to RAM, screen and storage.

Discuss on our Facebook page, HERE.

KitGuru Says: These new ThinkPad laptops from Lenovo seem to be packing some serious power under the hood. What do you guys think of Intel's move to bring Xeon CPUs to laptops?

Via: Engadget

The post Lenovo’s new laptops come with Xeon CPUs and Quadro graphics first appeared on KitGuru.]]>
https://www.kitguru.net/lifestyle/mobile/notebook/matthew-wilson/lenovos-new-laptops-come-with-xeon-cpus-and-quadro-graphics/feed/ 0
Sales of Nvidia GeForce GTX rise as shipments of Tesla and Quadro drop https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-nvidia-geforce-gtx-rise-as-shipments-of-tesla-and-quadro-drop/ https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-nvidia-geforce-gtx-rise-as-shipments-of-tesla-and-quadro-drop/#comments Fri, 07 Aug 2015 01:29:44 +0000 http://www.kitguru.net/?p=262756 Nvidia Corp. on Thursday said that sales of its GeForce GTX graphics processing units used inside gaming personal computers increased 51 per cent year-over-year thanks to the success of the latest “Maxwell” family of products. By contrast, sales of Tesla, Quadro and Tegra products dropped in the second quarter. Sales of graphics processing units of …

The post Sales of Nvidia GeForce GTX rise as shipments of Tesla and Quadro drop first appeared on KitGuru.]]>
Nvidia Corp. on Thursday said that sales of its GeForce GTX graphics processing units used inside gaming personal computers increased 51 per cent year-over-year thanks to the success of the latest “Maxwell” family of products. By contrast, sales of Tesla, Quadro and Tegra products dropped in the second quarter.

Sales of graphics processing units of Nvidia were $959 million in the second quarter of the company’s fiscal 2016, up 9 per cent year-over-year and a 2 per cent increase quarter-over-quarter. According to Nvidia, revenue from GeForce GPUs for gaming grew 51 percent to $661 million, thanks to success of the company’s GeForce GTX GPUs in the channel, which shipments increased significantly from year-ago levels. By contrast, shipments of GPUs to PC OEMs decreased during the quarter.

nvidia_geforce_gtx_art

“Our gaming platforms continue to be fueled by growth in multiple vectors – new technologies like 4K and VR, blockbuster games with amazing production values, and increasing worldwide fan engagement in e-sports,” said Jen-Hsun Huang, chief executive officer of Nvidia.

Revenue from Tesla GPUs for accelerated computing decreased to $62 million, because of variability in project purchasing. Nvidia expects Tesla to remain successful as GPU accelerateion in the datacenter becomes more important. Sales of Quadro GPUs declined to $187 million due to weakness in the overall workstation market.

“Our GPU-accelerated data center platform continues to make great strides in some of today's most important computing initiatives – cloud-based virtualization and high performance computing applications like deep learning,” added Mr. Huang.

Revenue from Nvidia Tegra application processors for mobile devices and cars dropped to $128 million, down 12 per cent sequentially and 19 per cent year over year. Sales of Nvidia Tegra for vehicles rose to $71 million, or by 76 per cent year-over-year, whereas sales of mobile Tegra SoCs dropped to $57 million.

nvidia_q2_fy2015_revenue

In the second quarter of fiscal 2016 Nvidia earned $1.153 billion, up 5 percent from $1.103 billion in the same period last year, and up marginally from $1.151 billion in the prior quarter. Gross margin of the company dropped to 55 per cent, which is still a record for a fabless company. The success of Nvidia’s GeForce was offset by the recall of its Shield tablet.

Discuss on our Facebook page, HERE.

KitGuru Says: Nvidia continues to be phenomenally successful, which is not really surprising as its main competitor is rather weak these days.

The post Sales of Nvidia GeForce GTX rise as shipments of Tesla and Quadro drop first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/sales-of-nvidia-geforce-gtx-rise-as-shipments-of-tesla-and-quadro-drop/feed/ 3
KitGuru Complete Guide to PC Workstations – Part 3 https://www.kitguru.net/components/james-morris/kitguru-complete-guide-to-pc-workstations-part-3/ https://www.kitguru.net/components/james-morris/kitguru-complete-guide-to-pc-workstations-part-3/#respond Thu, 06 Aug 2015 08:25:14 +0000 http://www.kitguru.net/?p=246247 In the second part of this series, we presented some initial tests to illustrate how CPU and graphics can affect different types of performance in a PC workstation. In this third part, we focus down on one particular, industry-standard benchmark that puts a workstation through a range of tests with popular 3D modelling and design …

The post KitGuru Complete Guide to PC Workstations – Part 3 first appeared on KitGuru.]]>
In the second part of this series, we presented some initial tests to illustrate how CPU and graphics can affect different types of performance in a PC workstation. In this third part, we focus down on one particular, industry-standard benchmark that puts a workstation through a range of tests with popular 3D modelling and design applications.

SPECviewperf from the Standard Performance Evaluation Corporation has been the most popular test of professional 3D graphics for many years. In this article, we put our smorgasbord of CPU and graphics combinations through every single test from SPECviewper 12.02. Some of the results may surprise you.

(see second article HERE).

Complete-Guide-to-Workstations-3-Cards-650
As with our previous article, we will be running our tests on three different workstation specifications using three different Intel processors, with four different NVIDIA Quadro professional 3D accelerators.

Complete-Guide-to-Workstations-PC-Specialist
All of the workstations and cards were kindly supplied by Wakefield-based PC Specialist.

The post KitGuru Complete Guide to PC Workstations – Part 3 first appeared on KitGuru.]]>
https://www.kitguru.net/components/james-morris/kitguru-complete-guide-to-pc-workstations-part-3/feed/ 0
Nvidia is developing new ‘Maxwell’-based Quadro, Tesla cards https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-is-developing-new-maxwell-based-quadro-tesla-cards/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-is-developing-new-maxwell-based-quadro-tesla-cards/#comments Mon, 29 Jun 2015 23:08:21 +0000 http://www.kitguru.net/?p=256655 Nvidia Corp. is developing three new cards for the professional markets: two new Quadro graphics adapters as well as a new Tesla accelerator for high-performance computing applications. The latest drivers from Nvidia add support for Nvidia Quadro M5000, Quadro M4000 as well as Tesla M60 boards, reports VideoCardz web-site. The new cards are based on …

The post Nvidia is developing new ‘Maxwell’-based Quadro, Tesla cards first appeared on KitGuru.]]>
Nvidia Corp. is developing three new cards for the professional markets: two new Quadro graphics adapters as well as a new Tesla accelerator for high-performance computing applications.

The latest drivers from Nvidia add support for Nvidia Quadro M5000, Quadro M4000 as well as Tesla M60 boards, reports VideoCardz web-site. The new cards are based on the GM204GL graphics processing unit, which is powered by “Maxwell” architecture. Specifications of the new cards are unknown, but it is clear that the new solutions will not address the high-end of the market.

quadro-m6000-header

Since GM204GL graphics processor demonstrates very high performance in video games thanks to 2048 stream processors, it is highly likely that the new Quadro graphics cards will also offer decent performance in professional graphics applications.

nvidia_tesla_k80_2

It is surprising that Nvidia plans to use its GM204GL graphics processor for an HPC accelerator. “Maxwell” hardware does not support double-precision FP64 computations natively and performance of GM204 in FP64 operations is very low. Perhaps, Nvidia will market the new Tesla card as a solution only for FP32 operations and will cost considerably less than other Tesla cards.

Nvidia’s new graphics cards will become available in the coming weeks.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It is not completely clear why Nvidia does not use its GM200 processor for Tesla cards. Given the fact that it features significantly higher performance than the GM204, it is more logical to use it instead of the GM204.

The post Nvidia is developing new ‘Maxwell’-based Quadro, Tesla cards first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-is-developing-new-maxwell-based-quadro-tesla-cards/feed/ 2
Nvidia and Samsung still cannot finalize chip manufacturing deal https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-and-samsung-still-cannot-finalize-chip-manufacturing-deal/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-and-samsung-still-cannot-finalize-chip-manufacturing-deal/#comments Sat, 20 Jun 2015 13:23:37 +0000 http://www.kitguru.net/?p=255534 Earlier this year Nvidia Corp. officially named Samsung Electronics its manufacturing partner. However, as it appears, the companies still have not signed any actual deals because negotiations are proceeding with difficulties. The consequence of prolonged negotiations could result in later-than-expected release of Samsung-made Nvidia chips. Nvidia wants Samsung Electronics to guarantee certain level of yield …

The post Nvidia and Samsung still cannot finalize chip manufacturing deal first appeared on KitGuru.]]>
Earlier this year Nvidia Corp. officially named Samsung Electronics its manufacturing partner. However, as it appears, the companies still have not signed any actual deals because negotiations are proceeding with difficulties. The consequence of prolonged negotiations could result in later-than-expected release of Samsung-made Nvidia chips.

Nvidia wants Samsung Electronics to guarantee certain level of yield rate at 14nm for its graphics processing units, reports BusinessKorea. The yield rate is as a condition of a provisional contract with Samsung Electronics, the web-site emphasizes. The negotiations are proceeding with difficulties because Samsung’s 14nm low-power plus (14LPP) fabrication process is still not really mature.

nvidia_tegra_x1_cut

Theoretically, engineering and business decision operations are isolated. Nvidia’s chip designers are working on chips to be made by Samsung, whereas other people are negotiating over pricing. If talks take too much time, then the start of volume production may be delayed, but since Nvidia will need Samsung’s production services only in 2016, it still has weeks or even months to negotiate a deal.

At present, Samsung Foundry is the only contract maker of semiconductors that produces chips using 14nm FinFET process technology in high volume. Taiwan Semiconductor Manufacturing Co. is expected to start mass production of chips using its 16nm FinFET process this month. Intel Corp.’s foundry division offers 14nm FinFET services to select companies and, based on rumours, not everyone is happy with the technology.

According to unofficial information, Nvidia recently taped out its first code-named GP100 graphics processing unit, which belongs to the “Pascal” family of products. The chip is set to be produced using TSMC’s 16nm FinFET+ (CLN16FF+) fabrication process.

samsung_semiconductor_foundry_chip_production_4

One analyst believes that Nvidia plans to use its contract with Samsung’s not only to get access to leading-edge fabrication processes and to ensure high-volume supply of chips, but also in order to cut-down its costs. In fact, a number of fabless semiconductor designers are believed to be using contracts with Samsung as a leverage in their negotiations with TSMC over pricing.

“We believe that Nvidia has a second source for foundry wafers in Samsung, outside of TSMC,” said Doug Freedman, an analyst with RBC Capital Markets, in a note to clients. “While it may be a small part of the wafer supply today, it should create a tailwind for [gross margin percentage] going forward as we believe that non-TSMC wafers can be purchased at as much as 10% below present cost levels.”

Nvidia and Samsung did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: In fact, chip designers and foundries are always negotiating over yields and costs, which is a normal process. No actual conclusions can be made because of prolonged talks.

The post Nvidia and Samsung still cannot finalize chip manufacturing deal first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-and-samsung-still-cannot-finalize-chip-manufacturing-deal/feed/ 20
Nvidia’s ‘Big Pascal’ GPU reportedly taped-out, on-track for 2016 launch – rumour https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-big-pascal-gpu-reportedly-taped-out-on-track-for-2016-launch-rumour/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-big-pascal-gpu-reportedly-taped-out-on-track-for-2016-launch-rumour/#comments Fri, 05 Jun 2015 22:33:26 +0000 http://www.kitguru.net/?p=253018 Nvidia Corp. has reportedly taped out its next-generation high-performance graphics processing unit that belongs to the “Pascal” family, according to a market rumour. If the information is correct, then Nvidia is on-track to release its new GPU around mid-2016. The company needs its “Big Pascal” graphics processor to build next-generation Tesla accelerators for high-performance computing applications …

The post Nvidia’s ‘Big Pascal’ GPU reportedly taped-out, on-track for 2016 launch – rumour first appeared on KitGuru.]]>
Nvidia Corp. has reportedly taped out its next-generation high-performance graphics processing unit that belongs to the “Pascal” family, according to a market rumour. If the information is correct, then Nvidia is on-track to release its new GPU around mid-2016. The company needs its “Big Pascal” graphics processor to build next-generation Tesla accelerators for high-performance computing applications and better compete against AMD on the market of consumer GPUs.

An anonymous person presumably with access to confidential information in the semiconductor industry revealed in a post over at Beyond3D forums that Nvidia had already taped out its next-generation code-named GP100 graphics processing unit. Nowadays, a tape-out means that the design of an integrated circuit has been finalized, but the first actual chips materialize only months after their tape-out.

Tape-out is the final stage of the design cycle of an integrated circuit, the point at which the artwork of the IC is sent to a maker of photomasks. Once the set of photolithographic masks is ready and verified, it is sent to a contract manufacturer of the chip, which produces the first working samples of the IC. Today’s mask sets contain 50 – 70 (up to 100) photomasks and it takes 15 – 20 hours to write a typical mask. It may take several weeks to prepare a mask-set. Production cycle of a complex FinFET processor is around 90 days from wafer start to chip delivery. As a result, it takes several months to prepare a set of photomasks and build an actual chip nowadays. Hence, if Nvidia taped-out of the GP100 in May, then the company will get the first samples of its GP100 in August. Nowadays high-volume production of chips starts between nine and twelve months after the initial tape-out.
nvidia_artworklatesteyeweb_mid
The world’s No. 1 producer of discrete graphics processors will reportedly use one of Taiwan Semiconductor Manufacturing Co.’s 16nm FinFET fabrication technology to make its “Big Pascal” GPU. Given the timeframe of the tape-out, it is highly likely that Nvidia uses TSMC’s advanced 16nm FinFET+ (CLN16FF+) manufacturing technology. According to the post, the BP100 is Nvidia’s first 16nm FinFET chip and the company has changed its approach to roll-out of new architectures. Instead of starting from simple GPUs and introducing biggest processors quarters after the initial chips, Nvidia will begin to roll-out “Pascal” with the largest chip in the family.

Nvidia’s “Pascal” architecture represents a big leap for the company. Thanks to all-new architecture, the Nvidia's next-gen GPUs will support many new features introduced by DirectX 12+, Vulkan and OpenCL application programming interfaces. The 16nm FinFET process technology will let Nvidia engineers to integrate considerably more stream processors and other execution units compared to today’s GPUs, significantly increasing overall performance. In addition, next-generation graphics processing units from Nvidia will support second-generation stacked high-bandwidth memory (HBM2). The HBM2 will let Nvidia and its partners build graphics boards with 16GB – 32GB of onboard memory and 820GB/s – 1TB/s of bandwidth. For high-performance computing (HPC) applications, the “Big Pascal” chip will integrate NVLink interconnection tech with 80GB/s or higher bandwidth, which will significantly increase performance of “Pascal”-based Tesla accelerators in supercomputers. Moreover, NVLink could bring major improvements to multi-GPU technologies thanks to massive bandwidth for inter-GPU communications. According to Nvidia's estimates, graphics adapters based on “Pascal” architecture should deliver two to ten times higher performance than comparable graphics processors today in peak scenarios.

NVIDIA_Tesla_K80_Dual-GPU_Accelerator_Front

Nvidia needs GP100 chip in order to build next-generation Tesla accelerators for supercomputers. Since “Maxwell” architecture (even the GM200) lacks native support for double precision (DP) FP64 computing, it cannot be used for Tesla cards. As a result, Nvidia currently offers Tesla accelerators featuring GK110 and GK210 chips, which are basically three years old. The release of the “Big Pascal” will help Nvidia to boost sales of Tesla cards for HPC applications.

The accuracy of predictions of the Beyond3D forum member could not be verified, but some of his previous posts indicate that he has access to information that is not yet public. The post in the forum on Friday was republished by 3DCenter, a web-site known for predictions in the field of graphics processing units.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: On the one hand, the rumour comes from one source without a track record and should be taken with a huge grain of salt. On the other hand, Nvidia needs “Big Pascal” to update Tesla accelerators as soon as possible. If Nvidia wants to release its GP100-based products in mid-2016, then the chip has been taped-out by now.

The post Nvidia’s ‘Big Pascal’ GPU reportedly taped-out, on-track for 2016 launch – rumour first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-big-pascal-gpu-reportedly-taped-out-on-track-for-2016-launch-rumour/feed/ 62
Gigabyte cosies up to Nvidia at Computex https://www.kitguru.net/components/graphic-cards/jon-martindale/gigabyte-cosies-up-to-nvidia-at-computex/ https://www.kitguru.net/components/graphic-cards/jon-martindale/gigabyte-cosies-up-to-nvidia-at-computex/#comments Tue, 02 Jun 2015 07:49:08 +0000 http://www.kitguru.net/?p=252236 Building relationships with other companies is one way to give yourself a boost in the technology game and big trade shows like the currently ongoing Computex in Taiwan, are a popular place to announce such alliances. While Gigabyte hasn't done anything quite so formal, it seems from our impressions of its stand and comments, that …

The post Gigabyte cosies up to Nvidia at Computex first appeared on KitGuru.]]>
Building relationships with other companies is one way to give yourself a boost in the technology game and big trade shows like the currently ongoing Computex in Taiwan, are a popular place to announce such alliances. While Gigabyte hasn't done anything quite so formal, it seems from our impressions of its stand and comments, that it's become much closer friends with Nvidia than it was before.

For starters, while it's Aorus laptops appear to be almost identical to their initial unveiling, it now appears that a number of them officially support Nvidia's G-Sync. While it's not clear if that will do anything to their pricing – since it's rather a costly tech – it is a nice addition for those that want to avoid any tearing in their gaming.

gigabyte04
 
gigabyte05 gigabyte03

gigabyte02 gigabyte01

There was also an area showing off Gigabyte's workstation developments, though once again, it was with a heavy Nvidia focus. Almost all of them featured Intel 750 NVMe storage, alongside Nvidia Quadro graphics cards.

gigabyte07 gigabyte08

We were also told in no uncertain words, that Gigabyte wasn't working much with AMD any more and had even dropped it from its workstation configurator.

Discuss on our Facebook page, HERE.

KitGuru Says: The Nvidia focus is an interesting one for Gigabyte, especially considering AMD's new HBM supporting 300 series is expected out within a month or so.

The post Gigabyte cosies up to Nvidia at Computex first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/jon-martindale/gigabyte-cosies-up-to-nvidia-at-computex/feed/ 6
Nvidia strengthens positions as market of graphics cards shrinks https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-strengthens-positions-as-market-of-graphics-cards-shrinks/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-strengthens-positions-as-market-of-graphics-cards-shrinks/#comments Wed, 27 May 2015 02:19:01 +0000 http://www.kitguru.net/?p=251306 Nvidia Corp. has managed to increase its share in the market of standalone graphics cards for personal computers, according to Jon Peddie Research. The market of graphics adapters for desktops in Q1 2015 decreased again to a new low in years, which is an alarming sign for developers of graphics processing units and makers of …

The post Nvidia strengthens positions as market of graphics cards shrinks first appeared on KitGuru.]]>
Nvidia Corp. has managed to increase its share in the market of standalone graphics cards for personal computers, according to Jon Peddie Research. The market of graphics adapters for desktops in Q1 2015 decreased again to a new low in years, which is an alarming sign for developers of graphics processing units and makers of graphics boards.

Shipments of graphics cards in the first quarter of 2015 decreased to 11.3 million units, an 8.79 per cent drop quarter over quarter. On a year-to-year basis, JPR found that total AIB shipments during the quarter fell 19.41 per cent, which is more than desktop PCs, which sales fell 6.52 per cent.

artwork_graphics_cards

As expected, sales and market share of Advanced Micro Devices’ Radeon graphics cards declined in the first quarter as the company and its partners were trying to sell-off inventory that had been shipped earlier. AMD’s quarter-to-quarter total desktop graphics cards shipments decreased by whopping 14.6 per cent. By contrast, Nvidia managed to increase its market share to 77.5 per cent in Q1 2015, a record high for the company in the recent years. Nonetheless, since the market was generally weak, sales of Nvidia GeForce graphics cards for desktops also dropped by 7 per cent sequentially.

jpr_q1_2015_aibs

According to analysts from Jon Peddie Research, shipments drop of add-in graphics cards is seasonally understandable and everything could have been worse. Still, the overall trend is not good for discrete desktop graphics adapters: the attach rate of graphics boards to desktop PCs has declined from a high of 63 per cent in Q1 2008 to 37 per cent in Q1 2015. Nevertheless, gamers continue to buy expensive graphics cards to enjoy the latest titles.

“However, in spite of the overall decline, somewhat due to tablets and embedded graphics, the PC gaming momentum continues to build and is the bright spot in the AIB market,” said Jon Peddie, the head of JPR.

Discuss on our Facebook page, HERE.

KitGuru Says: Given the lack of any announcements from AMD in the second quarter of 2015, do not expect many changes in shipments or rankings in Q2 as well. Nvidia will continue dominating the market of discrete desktop graphic cards this quarter and only sometimes in Q3 2013 AMD will finally be able to boost its sales.

The post Nvidia strengthens positions as market of graphics cards shrinks first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-strengthens-positions-as-market-of-graphics-cards-shrinks/feed/ 10
KitGuru Complete Guide to PC Workstations – Part 2 https://www.kitguru.net/components/graphic-cards/james-morris/kitguru-complete-guide-to-pc-workstations-part-2/ https://www.kitguru.net/components/graphic-cards/james-morris/kitguru-complete-guide-to-pc-workstations-part-2/#comments Fri, 22 May 2015 13:49:47 +0000 http://www.kitguru.net/?p=245560 As we explained in our introduction to this series, workstations are considerably more than just powerful PCs. Brute performance may be the basis of a system you intend to use for high-end desktop computing tasks like 3D animation, CAD/CAM, engineering and product design. But there is much more to a workstation than a high-end rig …

The post KitGuru Complete Guide to PC Workstations – Part 2 first appeared on KitGuru.]]>
As we explained in our introduction to this series, workstations are considerably more than just powerful PCs. Brute performance may be the basis of a system you intend to use for high-end desktop computing tasks like 3D animation, CAD/CAM, engineering and product design. But there is much more to a workstation than a high-end rig aimed at general work usage or gaming. There are many more variations within the Intel Xeon processor range than Core i7, and whilst the professional graphics cards have a family relationship with their consumer counterparts, the specification of these and driver accreditation make them very different beasts, too.

Read PART 1 first – over HERE.

Over the course of this new series, KitGuru will be guiding you through exactly what to look for in a workstation, depending on the kind of work you would like to perform. We will be using a gruelling suite of benchmarks to separate the wheat from the chaff, and running all of them on three different workstation specifications using three different Intel processors, with four different NVIDIA Quadro professional 3D accelerators.

All of the workstations and cards were kindly supplied by Wakefield-based PC Specialist. In this first article, we introduce the three specifications in detail and provide some initial test results with the Maxon Cinebench R15 benchmark.

The post KitGuru Complete Guide to PC Workstations – Part 2 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/james-morris/kitguru-complete-guide-to-pc-workstations-part-2/feed/ 5
Nvidia: AMD remains a strong competitor https://www.kitguru.net/components/anton-shilov/nvidia-amd-remains-a-strong-competitor/ https://www.kitguru.net/components/anton-shilov/nvidia-amd-remains-a-strong-competitor/#comments Tue, 12 May 2015 02:10:20 +0000 http://www.kitguru.net/?p=248973 Chief executive officer of Nvidia Corp. said last week that Advanced Micro Devices has always been a serious rival for his company and remains a tough competitor today. However, Nvidia believes that its new business approach greatly helps it to avoid competing directly with other suppliers. “[AMD has] been a strong competitor for as long …

The post Nvidia: AMD remains a strong competitor first appeared on KitGuru.]]>
Chief executive officer of Nvidia Corp. said last week that Advanced Micro Devices has always been a serious rival for his company and remains a tough competitor today. However, Nvidia believes that its new business approach greatly helps it to avoid competing directly with other suppliers.

“[AMD has] been a strong competitor for as long as I can remember, and they remain a strong competitor,” said Jen-Hsun Huang, chief executive officer of Nvidia, at the company’s conference call with investors and financial analysts. “It is just that our strategy is very different now. We used to be much more of a component supplier, competing directly with other component suppliers, but increasingly, we are really a differentiated platform supplier. The software investments that we have made over the years really, really increasingly define our product.”

nvidia_geforce_gtx_titan_z_huang

Products like Nvidia Quadro, Nvidia Tesla and Nvidia Grid are based on similar graphics processors that power GeForce graphics cards. However, thanks to state-of-the-art software, they gain exclusive capabilities and can be sold with huge profit margins. While AMD competes against Nvidia on the market of graphics cards for PCs and workstations, the company’s position on the markets of high-performance computing and datacenters are rather weak.

“When we think about our products and our platforms, it is really about the differentiated value that we have built on top of our GPUs, number one; and number two, I think the deep integration with the large ecosystems around the world, to the point where other companies' capabilities are really glommed onto this platform, making this platform more valuable to customers,” said Mr. Huang.

Discuss on our Facebook page, HERE.

KitGuru Says: When it comes to hardware, AMD can really compete against Nvidia very well with its powerful desktop GPUs. Unfortunately, when it comes to software and eco-systems, Nvidia is considerably ahead and it is unlikely that AMD will catch up with Nvidia any time soon.

The post Nvidia: AMD remains a strong competitor first appeared on KitGuru.]]>
https://www.kitguru.net/components/anton-shilov/nvidia-amd-remains-a-strong-competitor/feed/ 50
CEO of Nvidia: Can’t wait to tell you about future ‘Pascal’ products https://www.kitguru.net/components/graphic-cards/anton-shilov/ceo-of-nvidia-cant-wait-to-tell-you-about-future-pascal-products-in-the-pipeline/ https://www.kitguru.net/components/graphic-cards/anton-shilov/ceo-of-nvidia-cant-wait-to-tell-you-about-future-pascal-products-in-the-pipeline/#comments Sat, 09 May 2015 16:57:16 +0000 http://www.kitguru.net/?p=248807 Chief executive officer of Nvidia Corp. this week said that the company is designing a broad lineup of solutions for different applications powered by its next-generation “Pascal” graphics processor architecture and other technologies from the company. Jen-Hsun Huang seems to be impressed about the prospects of products that are in the company’s pipeline, but he …

The post CEO of Nvidia: Can’t wait to tell you about future ‘Pascal’ products first appeared on KitGuru.]]>
Chief executive officer of Nvidia Corp. this week said that the company is designing a broad lineup of solutions for different applications powered by its next-generation “Pascal” graphics processor architecture and other technologies from the company. Jen-Hsun Huang seems to be impressed about the prospects of products that are in the company’s pipeline, but he naturally reveals no details. The CEO advices to “wait a little longer” to find out more about them.

“I cannot wait to tell you about the products that we have in the pipeline,” said Jen-Hsun Huang, chief executive officer of Nvidia, at the company’s quarterly conference call with investors and financial analysts. “There are more engineers at Nvidia building the future of GPUs than just about anywhere else in the world. We are singularly focused on visual computing, as you guys know.”

In fact, Nvidia’s “Pascal” graphics processing architecture is ought to be impressive and there are many reasons why the chief exec of Nvidia is excited about it. Thanks to major architectural enhancements, the company’s next-gen GPUs will support numerous new features introduced by DirectX 12, Vulkan and OpenCL application programming interfaces. Moreover, having more GPU engineers than any other company in the world, Nvidia will probably add a lot of exclusive capabilities to future GPUs.

nvidia_pascal_module

The upcoming PK100 and PK104 graphics processing units will not only feature major architectural innovations, but they will also be made using either 14nm or 16nm manufacturing technology with fin-shaped field-effect transistors (FinFETs). “Pascal” GPUs will be the first graphics chips from Nvidia to be made using an all-new process technology since “Kepler” in 2012. Finer fabrication process is something that should permit Nvidia engineers to considerably increase the number of stream processors and other units inside the company’s future GPUs, dramatically increasing their performance.

In addition, next-generation graphics processing units from Nvidia will support second-generation stacked high-bandwidth memory (HBM2). The HBM2 will let Nvidia and its partners build graphics cards with up to 32GB of onboard memory and 820GB/s – 1TB/s bandwidth. Performance of such graphics adapters in ultra-high-definition (UHD) resolutions like 4K (3840*2160, 4096*2160) and 5K (5120*2880) should be extremely high.

For supercomputers, the “Big Pascal” chip will integrate NVLink interconnection tech with 80GB/s or higher bandwidth, which will significantly increase performance of “Pascal”-based Tesla accelerators in high-performance computing (HPC) applications. Moreover, NVLink could bring major improvements to multi-GPU technologies thanks to increased bandwidth for inter-GPU communications.

nvidia_geforce_gtx_card_art_1600

Graphics and compute cards based on “Pascal” will offer breakthrough performance, but the new architecture will be used not only for gaming and HPC markets. Nvidia will use its “Pascal” technology for a variety of solutions, including those for mobile and automotive applications.

“We have found over the years to be able to focus on just one thing, which is visual computing, and be able to leverage that one thing across PC, cloud, and mobile, and be able to address four very large markets with that one thing: gaming, enterprise, cloud, and automotive,” said Mr. Huang. “We can do this one thing and now be able to enjoy all and deliver the capabilities to the market in all three major computing platforms, and gain four vertical markets that are quite frankly very exciting.”

nvidia_geforce_gpu_maxwell_gm104_1600

While the chief exec of Nvidia is eager to reveal that his company’s next-generation GPU architecture will be big and will span from GeForce to Quadro Tesla and Tegra, bringing unique set of benefits to every platform and market, there are many things he will not elaborate on. The exact details and launch timeframes.

“I cannot wait to tell you all about it, you are just going to have to wait just a little longer,” teased Mr. Huang.

Discuss on our Facebook page, HERE.

KitGuru Says: Without any doubts, future graphics and multimedia processors based on the “Pascal” architecture will be able to offer dramatically higher performance compared to existing GPUs and SoCs, which will help to extend usage models of such chips. The main question that market observers, gamers and PC enthusiasts have these days is simple: when does Nvidia plan to release its first “Pascal”-based products.

The post CEO of Nvidia: Can’t wait to tell you about future ‘Pascal’ products first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/ceo-of-nvidia-cant-wait-to-tell-you-about-future-pascal-products-in-the-pipeline/feed/ 29
Nvidia: TSMC is our primary partner for 10nm and 16nm chips https://www.kitguru.net/components/anton-shilov/nvidia-tsmc-is-our-primary-partner-for-10nm-and-16nm-chips/ https://www.kitguru.net/components/anton-shilov/nvidia-tsmc-is-our-primary-partner-for-10nm-and-16nm-chips/#comments Fri, 08 May 2015 11:14:25 +0000 http://www.kitguru.net/?p=248571 Being one of the largest fabless designers of semiconductors in the world, Nvidia Corp. is a very special customer of Taiwan Semiconductor Manufacturing Co. For more than a decade, TSMC has been the primary producer of Nvidia graphics processing units and despite of Nvidia’s recent engagement with Samsung Foundry, TSMC will remain the company’s key …

The post Nvidia: TSMC is our primary partner for 10nm and 16nm chips first appeared on KitGuru.]]>
Being one of the largest fabless designers of semiconductors in the world, Nvidia Corp. is a very special customer of Taiwan Semiconductor Manufacturing Co. For more than a decade, TSMC has been the primary producer of Nvidia graphics processing units and despite of Nvidia’s recent engagement with Samsung Foundry, TSMC will remain the company’s key manufacturing partner.

“We are constantly evaluating foundry suppliers,” said Jen-Hsun Huang, chief executive officer of Nvidia, during the company’s quarterly conference call with investors and financial analysts. “We largely purchase from TSMC, the vast majority of our wafers we buy from TSMC. We are in 20nm, we are expecting to ramp 16nm. We are deeply engaged with TSMC for many, many nodes to come, including 10nm.”

semiconductor_wafer_cadence_4645_TSMC-Fab3inr008_78-sized

While TSMC remains the world’s largest contract maker of microelectronics, the company is behind Samsung Electronics with its 16nm manufacturing process that employs fin-shaped field-effect transistors (FinFET). Samsung is already producing chips using its 14nm FinFET (14LPE) fabrication technology in high volume, whereas TSMC plans to start making 16nm FinFET chips in Q3 with meaningful revenue contribution starting in the Q4 2015.

At present it is too late for Nvidia to jump ships from 16nm to 14nm (i.e., from TSMC to Samsung). In a bid to get a 14nm FinFET commercial chip from Samsung Electronics in late Q4 2015, Nvidia would have needed to form a design implementation team of around 100-200 engineers a couple of years ago and start to design its ASIC [application specific integrated circuit] in 2013 at the latest. Nvidia would tape out the chip in late 2014 or early 2015, nine to twelve months before the start of mass production. It is unknown when exactly Nvidia decided to use Samsung as a foundry, hence, the company’s 14nm FinFET roadmap and plans are completely unclear.

Officially, Nvidia claims that it does not necessarily need a bleeding-edge manufacturing process to deliver great products.

“There are just so many ways for us to deliver energy efficiency and performance,” said Mr. Huang. “I would not get too obsessed about the process technology all by itself.”.

tsmc_semiconductor_fab14_production

Nonetheless, process technologies are crucial for Nvidia. If Intel or AMD release their new products two or more quarters ahead of Nvidia, the company’s revenue and market share will decrease. Therefore, it makes a great sense for Nvidia to have two foundry partners. However, since it takes a long time to design a modern chip, decisions regarding manufacturing and process technologies have to be made years before such IC [integrated circuit] hits the market. At present Nvidia seems to be downplaying its relationship with Samsung, but no one knows what may happen in the future.

“But we are always looking at new foundry suppliers, and competition keeps everybody sharp,” said the CEO of Nvidia. “But for all intents and purposes, TSMC is our primary partner.”

Discuss on our Facebook page, HERE.

KitGuru Says: “Looking” at new foundry partners and listing one as a supplier in your filing with the Securities and Exchange Commission are two completely different things. In general, it seems that Nvidia is about to start using Samsung as a foundry partner, but it is completely unclear what exactly Samsung will produce for Nvidia. Perhaps, after learning about TSMC’s 20nm focus in late-2011 – early-2012, the company decided to diversify its wafer suppliers. If this is the case, then Nvidia’s next-gen “Pascal” GPUs as well as Tegra system-on-chips will be made by both Samsung and TSMC. Unfortunately, there are not a lot of facts to prove that theory.

The post Nvidia: TSMC is our primary partner for 10nm and 16nm chips first appeared on KitGuru.]]>
https://www.kitguru.net/components/anton-shilov/nvidia-tsmc-is-our-primary-partner-for-10nm-and-16nm-chips/feed/ 1
Samsung to make 14nm graphics processors for Nvidia https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-to-make-14nm-graphics-processors-for-nvidia/ https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-to-make-14nm-graphics-processors-for-nvidia/#comments Mon, 13 Apr 2015 22:59:37 +0000 http://www.kitguru.net/?p=244915 Nvidia Corp. will use Samsung Electronics’ manufacturing capacities to produce graphics processing units, according to a media report. The move will help Nvidia to increase performance of its GPUs without boosting their power consumption. When Nvidia revealed earlier this year that it will use Samsung’s services to build its chips, it was unclear whether the …

The post Samsung to make 14nm graphics processors for Nvidia first appeared on KitGuru.]]>
Nvidia Corp. will use Samsung Electronics’ manufacturing capacities to produce graphics processing units, according to a media report. The move will help Nvidia to increase performance of its GPUs without boosting their power consumption.

When Nvidia revealed earlier this year that it will use Samsung’s services to build its chips, it was unclear whether the company will order manufacturing of graphics processors or application processors. According to a report from KoreaTimes, Samsung will make GPUs for Nvidia using its 14nm FinFET manufacturing process.

Samsung’s 14nm fabrication technology will help Nvidia to pack significantly more execution units, such as stream processors, inside its GPUs, which will substantially increase their performance in games and other applications.

nvidia_artwork

Previously Nvidia planned to make its code-named “Pascal” graphics processing units using TSMC’s 16nm FinFET manufacturing technology. As it turns out, the company will also use Samsung’s 14nm FinFET process to make its future GPUs.

Samsung is in process of finding new revenue sources. Making chips for Nvidia will significantly increase earnings of the company’s foundry business unit.

“The latest agreement between Samsung and Nvidia is another positive factor lifting Samsung's logic chip business unit. The timing looks good as increased foundry customers justify the Korean chip giant's moves to find new revenue sources,” said a source familiar with the deal.

Nvidia and Samsung did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: What remains to be seen is whether Nvidia will alter its roadmap because of Samsung. The latter is already mass producing 14nm FinFET chips, whereas TSMC will only start making ICs [integrated circuits] using its 16nm FinFET process technology in Q3 2015. Perhaps, Nvidia will be able to roll-out its “Pascal” GPUs ahead of its original plan in 2016.

The post Samsung to make 14nm graphics processors for Nvidia first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/samsung-to-make-14nm-graphics-processors-for-nvidia/feed/ 2
Nvidia could outsource production of GPUs to Intel – analyst https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-could-outsource-production-of-gpus-to-intel-analyst/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-could-outsource-production-of-gpus-to-intel-analyst/#comments Wed, 25 Mar 2015 23:59:45 +0000 http://www.kitguru.net/?p=241943 After using Taiwan Semiconductor Manufacturing Corp. to make all of its chips almost exclusively for nearly a decade, Nvidia Corp. this year signed an agreement to produce a portion of its products at Samsung Foundry. But that could only be a part of Nvidia’s new strategy, according to a financial analyst. The multimedia chip desiger …

The post Nvidia could outsource production of GPUs to Intel – analyst first appeared on KitGuru.]]>
After using Taiwan Semiconductor Manufacturing Corp. to make all of its chips almost exclusively for nearly a decade, Nvidia Corp. this year signed an agreement to produce a portion of its products at Samsung Foundry. But that could only be a part of Nvidia’s new strategy, according to a financial analyst. The multimedia chip desiger could also outsource part of the production to Intel Custom Foundry.

“We also believe there is a potential for Nvidia to use Intel as a foundry,” wrote Doug Freedman, an analyst with RBC Capital Markets, in a note to clients, reports Tech Trader Daily. “While we continue to believe that TSMC has the majority of Nvidia’s wafers for CY2015 and probably CY2016 as well, we note that Nvidia could shift wafer supply quicker than other semiconductor companies because they have fewer products and end customer qualifications to contend with than peers that sell into industrial customers.”

Maxwell_GM204_DIE_3D_V17_Final

Last week Mr. Freedman expressed belief that Nvidia could use manufacturing at Samsung to boost its gross margins as Samsung charges less than TSMC. Some other market observers believe that certain fabless chip designers can use their contracts with Samsung or GlobalFoundries as a leverage to make TSMC to drop its prices.

While Samsung and GlobalFoundries charge less than TSMC, Intel charges 10 to 30 per cent more that the world’s No. 1 foundry, according to unofficial information. As a result, unless Nvidia wants to achieve certain goals using Intel’s unique manufacturing capabilities, it makes no sense for the company to work with the world’s largest maker of microprocessors. To do that efficiently, Nvidia would need to hire another design implementation team (preferably one that has experience of work with ICF) to develop chips using Intel’s libraries of elements and that is not an easy thing to do.

asml_semiconductor_art

Since Nvidia’s product lineups are not very broad, the company does not need to have multiple foundry partners. On the other hand, the company clearly needs access to leading-edge manufacturing processes. TSMC’s decision to make 20nm process technology a solution exclusively for mobile system-on-chips and then delay of 16nm FinFET fabrication process forced Nvidia to reconsider its plans. As a result, the chip designer could try to work with different foundries to ensure that it has access to the best technologies possible.

The financial analyst believes that Nvidia spends $1.7 billion on purchasing wafers from TSMC. Therefore, any savings means rather huge amounts of money for Nvidia and its new and old foundry partners.

Nvidia and Intel did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While two suppliers may make sense for Nvidia, three suppliers seem to be excessive. Therefore, unless Nvidia does not want to tangibly increase sales of various chips, it is unlikely to outsource to Intel. Moreover, Intel considers Nvidia a rival and the company indicated many times in the past that it is primarily interested in serving customers, who do not compete against it.

The post Nvidia could outsource production of GPUs to Intel – analyst first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-could-outsource-production-of-gpus-to-intel-analyst/feed/ 4
12GB of memory is not too much for Quadro M6000 https://www.kitguru.net/components/graphic-cards/anton-shilov/pny-12gb-of-memory-is-not-too-lot-for-quadro-m6000/ https://www.kitguru.net/components/graphic-cards/anton-shilov/pny-12gb-of-memory-is-not-too-lot-for-quadro-m6000/#respond Thu, 19 Mar 2015 04:20:39 +0000 http://www.kitguru.net/?p=240853 UPDATE: PNY said that the comments previously attributed to its representative were a result of misunderstanding between him and a journalist from a German web-site. The KitGuru news-story is altered to reflect this. Nvidia Corp.’s GeForce GTX Titan X overwhelmed many enthusiasts with 12GB of onboard memory. While for a gaming graphics card this looks …

The post 12GB of memory is not too much for Quadro M6000 first appeared on KitGuru.]]>
UPDATE: PNY said that the comments previously attributed to its representative were a result of misunderstanding between him and a journalist from a German web-site. The KitGuru news-story is altered to reflect this.

Nvidia Corp.’s GeForce GTX Titan X overwhelmed many enthusiasts with 12GB of onboard memory. While for a gaming graphics card this looks like an overkill, PNY believes that it may not be enough for a high-end professional graphics solutions.

PNY’s Quadro M6000 for professional digital content creators, which is going to hit the market in the coming weeks, is based on the GM200 “Big Maxwell” graphics processing unit with 3072 stream processors, 192 texture mapping units, 96 raster operations pipelines and 384-bit memory bus. Just like the GeForce GTX Titan X, it is equipped with 12GB of high-speed GDDR5 memory. But what is excessive for a consumer product may be not enough for a professional adapter that costs several thousands of dollars or pounds. In fact, some believe that even 12GB may not be enough for professionals working on extremely complex 3D models in ultra-high-definition resolutions.

A representative for PNY told ComputerBase web-site that 12GB of onboard memory is the maximum amount of memory that can currently be installed on a graphics card like the Quadro M6000. It is unknown whether PNY or Nvidia plan to create a GM200-based graphics solution featuring 24GB of memory, but keeping in mind that 8Gb GDDR5 memory chips are incoming, it should be technically possible provided that the GM200 supports high-capacity GDDR5 ICs.

pny_nvidia_quadro_m6000

Professional graphics adapters feature hardware capabilities disabled on consumer-grade graphics cards that better accelerate select things in professional applications. In addition, Quadro graphics cards feature special drivers optimized for professional programs and certified by developers of the latter.

Since Nvidia “Maxwell” architecture lacks double-precision floating point arithmetic units, the GM200 demonstrates dramatically low results in FP64 operations. As a result, while the Quadro M6000 will be appreciated by graphics professionals, engineers who need to run emulations that require FP64 precision will get better performance using a previous-generation Quadro K6000.

Discuss on our Facebook page, HERE.

KitGuru Says: Nvidia yet has to announce recommended price of its Quadro M6000 12GB graphics adapter. Without any doubts, the new card will cost a lot since even the Quadro K6000 costs around $4000. Now, imagine what kind of price tag would a Quadro M6000 24GB carry…

The post 12GB of memory is not too much for Quadro M6000 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/pny-12gb-of-memory-is-not-too-lot-for-quadro-m6000/feed/ 0