News Posts matching #GPU

Return to Keyword Browsing

Seasonic FOCUS PLUS PSUs Encounter GPU Compatibility Issues

It has been confirmed by Seasonic that their FOCUS PLUS power supplies are experiencing potential conflict with a select number of graphics cards. In regards to NVIDIA, the compatibility issue is currently limited to the ASUS GeForce GTX 970 STRIX. In limited instances, this particular graphics card can encounter a black screen under heavy load. Testing by Seasonic has determined that the issue is caused by higher than normal ripple when the GPU is heavily stressed. They also determined that solving the problem simply required using modified PCIe cables that feature enhanced shielding.

When it comes to AMD GPUs things are a bit more problematic. Both of AMD's Vega 56 and Vega 64 series of graphics cards with serial numbers before January 2018, can experience system shutdowns when paired with a FOCUS PLUS power supply. The issue is caused by higher than normal peak current being emitted by these graphics cards when under heavy load. This results in the power supply's internal protection safety being triggered. Considering Seasonic's popularity the fact these power supplies are encountering problems is likely going to be a hit to their brand image. At least they are stepping up to the plate having admitted to the problem while also investigating the root causes. They are also encouraging anyone that is encountering issues to contact them for assistance.

Bad Times for Motherboard and GPU Makers: Oversupply and High Prices in 1H19

The "sustained chill in the crypto mining sector" is, according to Taiwan-based sources cited at DigiTimes, one of the leading reasons motherboard and graphics cards makers will face a bleak scenario in the next few months. According to those sources, other factors such as the US-China trade war doesn't help a situation on which NVIDIA new RTX family hasn't helped due to the high price of those GPUs. ASUSTeK Computer and Gigabyte Technology have seen their inventory levels drive up, "causing their revenues for the peak season to fall under expectations".

These problems now join the ones Intel is facing with its shortage of processors, and according to DigiTimes, revenue prospects for the fourth quarter are further dimmed by lingering sluggish demand from the DIY market among other things. To counteract these problems those companies could actually be could be further adversely affected: "Nvidia and Intel likely to raise their chip prices to maintain profitability", a move that could lead to a bleak profitability period starting in 2019.

ASUS Republic of Gamers Announces ROG Strix Radeon RX 590 Graphics Card

ASUS Republic of Gamers (ROG) today announced the ROG Strix Radeon RX 590, an all-new gaming graphics card powered by the latest AMD Radeon RX 590 GPU and engineered with advanced cooling, reliability, performance, and customizable lighting.

ROG Strix cards take cooling to the next level, keeping temperatures low and dB levels quiet. It starts with MaxContact technology, which uses precision machining to create a heat spreader surface that makes up to 2X more contact with the GPU chip, helping to improve thermal transfer. As heat passes into the heatsink, three powerful Wing-blade fans spin up when GPU temperatures exceed 55 Celsius. Wingblade fans are a patented design that offers 105% more static pressure than traditional axial designs, ensuring air is dispersed through the entire cooling array.

MSI GeForce RTX 2070 AERO ITX Makes Its Debut

MSI's most recent addition to their NVIDIA GeForce based line up has appeared. The newly minted RTX 2070 AERO ITX is as you may have guessed a graphics card that targets the mini-ITX market. It is currently the smallest RTX series graphics card to be spotted thus far, with it being perfect for this form factor as it lacks a few features seen on the higher end RTX 2080 and 2080 Ti that add complexity. Essentially the lack of NVlink on all RTX 2070 offerings allows for a simpler PCB design that is better suited for this design. There is also the fact anyone wanting SLI would not be looking at ITX focused cards anyway.

The other feature removed likely for cost savings is the VirtualLink (USB-C) connector that delivers power, video, and data for virtual reality headsets. While not entirely a deal breaker it still makes using it for a small form factor VR system a bit more difficult going forward. That said, considering the slow adoption of VR its removal is still a relatively safe bet for MSI for now. Taking a closer look at the packaging shows no indication of a pre-applied overclock, meaning MSI's RTX 2070 AERO ITX should come with NVIDIA reference clock speeds of 1410 MHz base / 1620 MHz boost on the core. The 8 GB of GDDR6 memory should have clocks of 1750 MHz (14000 MHz effective). As for the graphics card's TDP, it should also keep to the reference specification of 175-watts. Currently, pricing and availability are still unknown.

Sapphire Radeon RX 590 NITRO+ Special Edition Spotted

As the expected November 15th release date for AMD's Radeon RX 590 inches closer, more leaks of AIB cards have started trickling in. Sapphire's Radeon RX 590 NITRO+ is just the latest to appear. Much like the ASUS ROG STRIX version leaked earlier, Sapphire design is using a hefty cooler for what amounts to a mid-range graphics card. The design looks to be the exact same as their RX 580 NITRO+ with just a fresh coat of paint to spruce things up. They are using the same shroud, dual fans, large aluminum heatsink, and full cover backplate on both graphics cards. That said, the change to a bright blue shroud gives the RX 590 NITRO+ a unique appearance that should at the very least help it stand out against its more mundane black and white designs of the competition.

In regards to actual specifications, the RX 590 features the same 2304 Stream processors, 144 TMUs (texture mapping units), and 32 ROPS (render output units) as the RX 580. This is because the Polaris 30 design used in the RX 590 is just a die shrink of Polaris 20 used in the RX 580. Obviously with a die shrink typically comes improved performance, usually via higher clock speeds. Currently, the final clock speeds for Sapphire's Radeon RX 590 NITRO+ are not known. However, if the rumored reference boost clock of 1545 MHz is correct, an overclock pushing that a step further is likely. Meaning performance should be improved compared to what we have seen in various leaks thus far.

Intel Announces "Forward-Looking" Architecture Event to be Held December 11th

Intel today announced to press that they've scheduled an event for December 11th. The scheduled event should take the form of a small gathering of both Intel and press professionals, where Intel will be giving insights into its thought process and technologies with some in-depth presentations for technicians and engineers from the blue giant. Intel has become more and more secluded when it comes to the workings and architecture details of its technology advances, with the company even going so far as to cancel the (previously annual) Intel Developer Forums.

The event is apparently focusing on "architecture" considerations for future Intel products, so information shared could be strung with NDAs, and could fall under any product family Intel is working on (CPU, GPU, FPGA, AI...). We'll see what Intel has to share, and what kind of details (or watercolor ideas) can be painted on any future Intel products.

Darren McPhee, Former Radeon Marketing Executive, Joins Intel's Discrete Graphics Division

Darren McPhee worked 12 years for ATI and AMD. When he left AMD in 2015, he was one of the company's top marketing managers. For the last three years he has worked for various companies, but the surprise has come with Intel recruiting him to occupy the position of Product Marketing Manager in its 'Discrete Graphics' group, one of the most interesting initiatives in the recent times.

This division is working hard to develop a new family of discrete graphics cards that will theoretically compete with AMD and NVIDIA solutions. Intel has been steadily growing, and in fact Intel already signed Raja Koduri, AMD GPU architect, in November 2017. This firm has been attracting more and more talent from an AMD: Koduri was followed by Jim Keller, Ryzen Architect, and Chris Hook, who led AMD's Radeon Technologies Group Marketing Departmen prior to his move to Intel. These hires certainly make it clear that Intel is taking an increasingly promising project very seriously. We will have to be patient, however, because the firm already indicated in SIGGRAPH 18 that it will have its first models ready in 2020.

AMD Vega 20 Possible Performance Spotted in Final Fantasy XV Benchmark

It would appear AMD's 7nm Vega 20 has been benchmarked in Final Fantasy XV. While the details are scarce, what we do know is the hardware device ID 66AF:C1 can be linked to Vega 20 via the Linux patches back in April. Now considering AMD has not confirmed any 7nm Vega graphics cards for consumers, It is more likely this version is an engineering sample for the new Radeon Instinct or Pro series cards.

AMD Share Price Falls ~28% via Weak GPU Sales; Revenue Share from GPUs Only 30%

Following the release of the Q3 financial results by AMD, the stock market was quick to respond to less-than-expected operating income and market share numbers with a ~9.2% drop in share price before the markets closed. This was then followed by fervent after-hours trading resulting an even bigger drop to a share price of $17.88 at the time of this post, compared to the starting value of $25.04 earlier today. The small hike and drop after-hours also indicates some enterprising parties made use of the lower share values to their profit.

AMD held a teleconference for their investors to go along with the report, and attempted to better explain what was going on. In particular, they attribute the decreased client GPU sales to a big decrease in the blockchain GPU sales market (read GPU mining) relative to the first half of 2018. The lack of competing products to take on NVIDIA Pascal-, and then Turing-based, GPU solutions also does not help. As it stands, AMD shared news that GPUs now contribute to only ~30% of their revenue with the other 70% coming from the Ryzen-based processor division instead. They hinted strongly at new products coming from both segments, including an on-track path for a 7 nm datacenter GPU later this year and new Ryzen+Vega-powered notebooks, but it appears that more needs to be done to appease their investors at this point.

Distributed GPU Rendering on the Blockchain is The New Normal, and It's Much Cheaper Than AWS

Otoy, based in Los Angeles, announced a few months ago the launch of RNDR, a cloud rendering platform that is based on the same blockchain used on the Ethereum platform. The idea is simple: it leverages a distributed network of idle GPUs to render graphics more quickly and efficiently.

The solution takes advantage of the unused power of our GPUs, and allows those who need to render images at full speed to do so through this platform. RNDR distributes the revenue through its own blockchain in a decentralized fashion, and in a recent survey of 1,200 of its contributors Otoy said it has the world's largest cloud rendering platform. One that has even been praised by Hollywood director and producer J.J. Abrams, founder of Brave and Basic Attention Token Brendan Eich, and famed talent agent Ari Emanuel.

MSI Talks about NVIDIA Supply Issues, US Trade War and RTX 2080 Ti Lightning

Back on September 27th, MSI talked candidly with PConline at the MSI Gaming New Appreciation Conference, in Shanghai. Multiple MSI executives were available to answer questions regarding products, launches, and potential issues. The first question asked was about the brewing US-Chinese trade war and if it will affect prices of graphics cards and CPUs. To which, Liao Wei, Deputy General Manager of MSI Global Multimedia Business Unit, and MSI Headquarters Graphics Card Products gave an actual answer. Stating that the since NVIDIA's GPU core is handled by a TSMC in Taiwan and memory is handled by Samsung and Hynix in South Korea and the United States respectively, there is little chance of further graphics card price hikes. However CPU side prices may increase on the Intel side, however, AMD is expected to be unaffected.

VUDA is a CUDA-Like Programming Interface for GPU Compute on Vulkan (Open-Source)

GitHub developer jgbit has started an open-source project called VUDA, which takes inspiration from NVIDIA's CUDA API to bring an easily accessible GPU compute interface to the open-source world. VUDA is implemented as wrapper on top of the highly popular next-gen graphics API Vulkan, which provides low-level access to hardware. VUDA comes as header-only C++ library, which means it's compatible with all platforms that have a C++ compiler and that support Vulkan.

While the project is still young, its potential is enormous, especially due to the open source nature (using the MIT license). The page on GitHub comes with a (very basic) sample, that could be a good start for using the library.

Intel is Adding Vulkan Support to Their OpenCV Library, First Signs of Discrete GPU?

Intel has submitted the first patches with Vulkan support to their open-source OpenCV library, which is designed to accelerate Computer Vision. The library is widely used for real-time applications as it comes with 1st-class optimizations for Intel processors and multi-core x86 in general. With Vulkan support, existing users can immediately move their neural network workloads to the GPU compute space without having to rewrite their code base.

At this point in time, the Vulkan backend supports Convolution, Concat, ReLU, LRN, PriorBox, Softmax, MaxPooling, AvePooling, and Permute. According to the source code changes, this is just "a beginning work for Vulkan in OpenCV DNN, more layer types will be supported and performance tuning is on the way."

It seems that now, with their own GPU development underway, Intel has found new love for the GPU-accelerated compute space. The choice of Vulkan is also interesting as the API is available on a wide range of platforms, which could mean that Intel is trying to turn Vulkan into a CUDA killer. Of course there's still a lot of work needed to achieve that goal, since NVIDIA has had almost a decade of head start.

New NVFlash Released With Turing Support

With the latest release of NVIDIA's NVFlash, version 5.513.0, users can now read and write the BIOS on Turing based graphics cards. This includes the RTX 2080 Ti, 2080, and 2070. While this may seem mundane at first, due to the different power limits between graphics cards, there is some hope that cross flashing of the BIOS could result in tangible performance gains.

DOWNLOAD: NVIDIA NVFlash v5.513.0

MSI and ESL Partnering For The MSI Gaming Arena 2018 World Championships, Sponsors ESL One 2018

MSI, a world leader in gaming hardware, has partnered with ESL for its MSI Gaming Arena (MGA) 2018 World Championship and as the exclusive gaming sponsor of the ESL One 2018 Grand Finals at the Barclays Center in New York on September 29 and 30.
MGA 2018 World Championship
Before the Grand Final, MSI Gaming Arena (MGA) 2018 will host the world's top Counter-Strike: Global Offensive teams fighting for the coveted MGA Trophy and $60,000 prize pool on September 30 at the Barclays Center in New York. After the regional qualifiers, the four remaining teams will secure their spot in the MGA 2018 CS:GO Grand Finals.

GALAX Starts Selling OC Lab Edition GPU Pot for Extreme LN2 Overclocking

GALAX has announced availability of their OC Lab Edition GPU Pot, a non-plant-based solution for users to cool their graphics cards with. The OC Lab Edition GPU Pot is fully made of 99.9% purity copper, which allows it to withstand up to -196 ºC. Not many more details are available for now, except pricing, and it's something to definitely not smile about: the OC Lab Edition GPU Pot will cost users $229.99.

GALAX, however, being a customer-friendly brand, are suggesting users put down an order for three of these OC Lab Edition GPU Pot alongside three of their own Galax HOF OC Lab WC cards, which go for $1,799... netting you a $600 discount on the pots. So, yeah. There's that. If you want it.

NVIDIA Stock Falls 2.1% After Turing GPU Reviews Fail to Impress Morgan Stanley

NVIDIA's embargo on their Turing-based RTX 2080 and RTX 2080 Ti ended Wednesday, September 19 and it appears that enthusiasts were not the only ones left wanting more from these graphics cards. In particular, Morgan Stanley analyst Joseph Moore shared a note today (Thursday, September 20) with company clients saying "As review embargos broke for the new gaming products, performance improvements in older games is not the leap we had initially hoped for. Performance boost on older games that do not incorporate advanced features is somewhat below our initial expectations, and review recommendations are mixed given higher price points." The NVIDIA Corporation share value on the NASDAQ exchange had closed at $271.98 (USD) Wednesday and immediately tumbled down to a low of $264.10 opening today before recovering to close at $266.28, down 2.1% over the previous closure.

The Morgan Stanley report further mentioned that "We are surprised that the 2080 is only slightly better than the 1080ti, which has been available for over a year and is slightly less expensive. With higher clock speeds, higher core count, and 40% higher memory bandwidth, we had expected a bigger boost." Accordingly, the market analyst expects a slower adoption of these new GPUs as well as no expectation of "much upside" from NVIDIA's gaming business unit for the next two quarters. Despite all this, Morgan Stanley remains bullish on NVIDIA and expects a $273 price point in the long term.

AMD Fast-tracks 7nm "Navi" GPU to Late-2018 Alongside "Zen 2" CPU

AMD is unique in the world of computing as the only company with both high-performance CPU and GPU products. For the past several years we have been executing our multi-generational leadership product and architectural roadmap. Just in the last 18 months, we successfully introduced and ramped our strongest set of products in more than a decade and our business has grown dramatically as we gained market share across the PC, gaming and datacenter markets.

The industry is at a significant inflection point as the pace of Moore's Law slows while the demand for computing and graphics performance continues to grow. This trend is fueling significant shifts throughout the industry and creating new opportunities for companies that can successfully bring together architectural, packaging, system and software innovations with leading-edge process technologies. That is why at AMD we have invested heavily in our architecture and product roadmaps, while also making the strategic decision to bet big on the 7nm process node. While it is still too early to provide more details on the architectural and product advances we have in store with our next wave of products, it is the right time to provide more detail on the flexible foundry sourcing strategy we put in place several years ago.

AMD Chip Manufacturing to Lay Solely With TSMC On, After 7 nm - And Why It's not a Decision, but a Necessity

It's been a tumultuous few days for AMD, as the company has seen Jim Anderson, Computing and Graphics Group leader after the departure of Raja Koduri, leave the company, at a time of soaring share value for the company (hitting $25.26 and leaving short positions well, short, by $2.67 billion.) However, there's one particular piece of news that is most relevant for the company: Globalfoundries' announcement to stop all ongoing development on the 7 nm node.

This is particularly important for a variety of reasons. The most important one is this: Globalfoundries' inability to execute on the 7 nm node leaves AMD fully free to procure chips and technology from competing foundries. If you remember, AMD's spin-off of GlobalFoundries left the former with the short end of the stick, having to cater to GlobalFoundries' special pricing, and paying for the privilege of accessing other foundries' inventories. Of course, the Wafer Supply Agreement (WSA) that is in place will have to be amended - again - but the fact is this: AMD wants 7 nm products, and GlobalFoundries can't provide.
To the forumites: this piece is marked as an editorial

Intel and Philips Accelerate Deep Learning Inference on CPUs in Medical Imaging

Using Intel Xeon Scalable processors and the OpenVINO toolkit, Intel and Philips tested two healthcare use cases for deep learning inference models: one on X-rays of bones for bone-age-prediction modeling, the other on CT scans of lungs for lung segmentation. In these tests, Intel and Philips achieved a speed improvement of 188 times for the bone-age-prediction model, and a 38 times speed improvement for the lung-segmentation model over the baseline measurements.

Intel Xeon Scalable processors appear to be the right solution for this type of AI workload. Our customers can use their existing hardware to its maximum potential, while still aiming to achieve quality output resolution at exceptional speeds," said Vijayananda J., chief architect and fellow, Data Science and AI at Philips HealthSuite Insights.

NVIDIA Announces Turing-based Quadro RTX 8000, Quadro RTX 6000 and Quadro RTX 5000

NVIDIA today reinvented computer graphics with the launch of the NVIDIA Turing GPU architecture. The greatest leap since the invention of the CUDA GPU in 2006, Turing features new RT Cores to accelerate ray tracing and new Tensor Cores for AI inferencing which, together for the first time, make real-time ray tracing possible.

These two engines - along with more powerful compute for simulation and enhanced rasterization - usher in a new generation of hybrid rendering to address the $250 billion visual effects industry. Hybrid rendering enables cinematic-quality interactive experiences, amazing new effects powered by neural networks and fluid interactivity on highly complex models.

Google Cloud Introduces NVIDIA Tesla P4 GPUs, for $430 per Month

Today, we are excited to announce a new addition to the Google Cloud Platform (GCP) GPU family that's optimized for graphics-intensive applications and machine learning inference: the NVIDIA Tesla P4 GPU.

We've come a long way since we introduced our first-generation compute accelerator, the K80 GPU, adding along the way P100 and V100 GPUs that are optimized for machine learning and HPC workloads. The new P4 accelerators, now in beta, provide a good balance of price/performance for remote display applications and real-time machine learning inference.

Due to Reduced Demand, Graphics Cards Prices to Decline 20% in July - NVIDIA Postponing Next Gen Launch?

DigiTimes, citing "sources from the upstream supply chain", is reporting an expected decrease in graphics card pricing for July. This move comes as a way for suppliers to reduce the inventory previously piled in expectation of continued demand from cryptocurrency miners and gamers in general. It's the economic system at work, with its strengths and weaknesses: now that demand has waned, somewhat speculative price increases of yore are being axed by suppliers to spur demand. This also acts as a countermeasure to an eventual flow of graphics cards from ceasing-to-be miners to the second-hand market, which would further place a negative stress on retailers' products.

Alongside this expected 20% retail price drop for graphics cards, revenue estimates for major semiconductor manufacturer TSMC and its partners is being revised towards lower than previously-projected values, as demand for graphics and ASIC chips is further reduced. DigiTimes' sources say that the worldwide graphics card market now has an inventory of several million units that is being found hard to move (perhaps because the products are already ancient in the usual hardware tech timeframes), and that Nvidia has around a million GPUs still pending logistical distribution. Almost as an afterthought, DigiTimes also adds that NVIDIA has decided to postpone launch of their next-gen products (both 12 nm and then, forcibly, 7 nm) until supply returns to safe levels.

Upcoming Windows 10 Task Manager Update to Show Power Usage, Power Usage Trend per Process

One nifty new feature currently being deployed to Windows 10 Fast Ring users is the ability to see exactly how much power a given process is consuming in your system's hardware (CPU, GPU & Disk). The new feature, which appears as two additional Task Manager tabs, showcases the instantaneous power usage of a given process, but also features a trend calculator that covers a two-minute interval. This should be pretty handy, if the measurement process is close enough to the real power consumption. This could even be used as another flag for cryptomining malware or scripts in a given webpage. You can check the source for the additional updates that have been brought to build 17704 of the Windows Insider Program.
Return to Keyword Browsing