News Posts matching #GPU

Return to Keyword Browsing

INNO3D Announces Its GeForce RTX SUPER Series

INNO3D, a leading manufacturer of pioneering high-end multimedia components and various innovations, is excited to announce the new INNO3D GeForce RTX SUPER Series. With great power comes great responsibility, and with the INNO3D GeForce RTX 2080, 2070, 2060 SUPER graphics cards you will surely do your favourite games justice by powering them with the Turing architecture packed with more oomph thanks to additional cores and higher clocks.

Our R&D team have been burning the midnight oil in order to have every conceivable version of the SUPER series, from the iCHILL Frostbite, iCHILL Black, iCHILL X3 Ultra and X3 to the Gaming OC X2 and X3, and of course the INNO3D TWIN X2 OC and Compact.

AMD Patent Shines Raytraced Light on Post-Navi Plans

An AMD patent may have just shown the company's hand when it comes to its interpretation of raytracing implementation on graphics cards. The patent, titled "Texture Processor Based Ray Tracing Acceleration Method and System", describes a hybrid, software-hardware approach to raytracing. AMD says this approach improves upon solely hardware-based solutions:
"The hybrid approach (doing fixed function acceleration for a single node of the bounded volume hierarchy (BVH) tree and using a shader unit to schedule the processing) addresses the issues with solely hardware based and/or solely software based solutions. Flexibility is preserved since the shader unit can still control the overall calculation and can bypass the fixed function hardware where needed and still get the performance advantage of the fixed function hardware. In addition, by utilizing the texture processor infrastructure, large buffers for ray storage and BVH caching are eliminated that are typically required in a hardware raytracing solution as the existing vector general purpose register (VGPRs) and texture cache can be used in its place, which substantially saves area and complexity of the hardware solution."

AMD Patents a New Method for GPU Instruction Scheduling

With growing revenues coming from strong sales of Ryzen and Radeon products, AMD is more focused on innovation than ever. It is important for any company to re-invest its capital into R&D, to stay ahead. And that is exactly what AMD is doing by focusing on future technologies, while constantly improving existing solutions.

On June 13th, AMD published a new method for instruction scheduling of shader programs for a GPU. The method operates on fixed number of registers. It works in five stages:
  • Compute liveness-based register usage across all basic blocks
  • Computer range of numbers of waves for shader program
  • Assess the impact of available post-register allocation optimizations
  • Compute the scoring data based on number of waves of the plurality of registers
  • Compute optimal number of waves

NVIDIA to Unveil GeForce RTX SUPER Lineup on July 2nd

NVIDIA has confirmed that they will be launching a new RTX series of gaming graphics cards, called RTX Super, on July 2nd. According to info from VideoCardz, there will be three models of the new GPUs at launch - RTX 2060 SUPER, RTX 2070 SUPER and RTX 2080 SUPER. The review embargo will lift on the same day as launch day for RTX 2060 SUPER and RTX 2070 SUPER, but the embargo for RTX 2080 SUPER will prevail until "later in July".

The embargo for custom cards based on the new SUPER GPUs will be delayed until July 9th, when we will get the first wave of new cards. There is no apparent reason for the delay, so we will need to find out more about that. Pricing is yet to be announced, but according to the source, it will be "later this week". As a reminder, from previous leaks we have seen that Super series is supposed to bring about 10-13% more CUDA cores to the GPU models, more memory and higher memory speeds.

UL Releases PCI Express Feature Test For 3DMark Ahead of PCIe 4.0 Hardware

With PCI-Express 4.0 graphics cards and motherboards soon to arrive, UL has released their PCI Express feature test for 3DMark. This latest addition has been designed to verify the bandwidth available to the GPU over a computer's PCI Express interface. To accomplish this, the test will make bandwidth the limiting factor for performance and does so by uploading a large amount of vertex and texture data to the GPU for each frame. The end goal is to transfer enough data over the PCIe 4.0 interface to thoroughly saturate it. Once the test is complete, the end result will be a look at the average bandwidth achieved during the test.

Phanteks Prepares Glacier G2070 Strix Waterblock for Release

Phanteks today announces the new Glacier Series water-block designed specifically for ASUS RTX 2070/2060 cards. The new Glacier G2070 Strix is engineered to deliver high cooling performance for the Asus RTX 2070/2060 cards. Like all our Glacier Series products, the waterblock comes with anodized or chrome plated aluminum cover plates, polished acrylic surface, and high-quality nickel finish copper base.

The waterblock features minimalistic design that covers the entire PCB length and is compatible with the original ASUS Strix backplate to highlight your hardware. The integrated Digital-RGB lighting illuminates the whole waterblock evenly. The full cover waterblock directly cools the GPU, RAM and VRM (Voltage Regulator Module) thanks to the optimized high flow routing design. This ensures optimal performance and cooling to help keep the GPU stable even at high clock speeds or massive workloads. The Glacier Series Waterblocks will be available in Satin Black and Chrome color finishes and with Digital-RGB lighting. Available this month of June for $149.99.

Rumor: AMD Navi a Stopgap, Hybrid Design of RDNA and GraphicsCoreNext

The Wheel of Rumors turns, and assumptions come and pass, sometimes leaving unfulfilled hopes and dreams. In this case, the rumor mill, in what seems like a push from sweclockers, places Navi not as a "built from the ground-up" architecture, but rather as a highly customized iteration of GCN - iterated in the parts that it actually implements AMD's RDNA architecture, to be exact. And this makes sense from a number of reasons - it's certainly not anything to cry wolf about.

For one, AMD's GCN has been a mainstay in the graphics computing world since it was first introduced back in 2012, succeeding the company's TeraScale architecture. Game engines and assorted software have been well optimized already to take advantage of AMD's design - even with its two ISAs and assorted improvements over the years. One of the most important arguments is derived from this optimization effort: AMD's custom designs for the console market employ architectures that are GCN-based, and thus, any new architecture that would be used by both Microsoft and Sony for their next-generation consoles would have to be strictly backwards compatible.

Bitspower at COMPUTEX 2019: New CPU, GPU Blocks and Conceptual Products

Bitspower at COMPUTEX 2019 showcased new products and conceptual, advanced looks at products that are still being developed. The company showcased GPU waterblocks for both the NVIDIA RTX 20-series of graphics cards, as well as AMD's current top of the line Radeon VII. On the GPU waterblock side of things, they also showcased an in-development block with a rugged texture and design that carries Bitspower's logo, which would certainly look great on a vertically-mounted GPU.

BITFENIX at COMPUTEX 2019: Dawn TG, Nova Mesh 16, Saber PC Chassis Showcased

At COMPUTEX 2019, BITFENIX took the opportunity to showcase their latest case design built for the conscious enthusiast. Their Dawn TG is the company's take on the RGB market, with a stylized, ARGB front fascia that's eerily reminiscent of Oblivion's Tet (the movie, not the game). This case is available in both black and white, and features smoked tempered glass side mirrors for that premium feel.

The Nova Mesh TG Black brings slightly more gaudiness to its RGB design, which is clearly visible behind the tempered glass side mirrors. The panel's front fascia, as the name implies, is covered in mesh so as to maximize airflow for interior components.

EA Reveals Next-Generation Hair Rendering for Frostbite

In the gaming industry, everything is evolving around game graphics. GPUs are integrating new technologies such as ray tracing, there are tons of software dedicated to making in-game illustrations look as realistic as possible. Electronic Arts, one of the game publishing companies decided to release a state of the art AAA games, today revealed an update to DICE's Frostbite engine.

DICE's Frostbite engine is powering many of today's AAA titles such as Battlefield V, Anthem and Star Wars Battlefront. Today it got a big update. EA released new capabilities to render the hair of in-game characters with almost real-life realism. This is pretty impressive considering that hair is very difficult to model artificially. Being one of the most interesting topics for game developers, good hair animations are extremely important to achieving the lifelike look newer AAA titles are targeting.

AMD "Navi" Features 8 Streaming Engines, Possible ROP Count Doubling?

AMD's 7 nm "Navi 10" silicon may finally address two architectural shortcomings of its performance-segment GPUs, memory bandwidth, and render-backends (deficiency thereof). The GPU almost certainly features a 256-bit GDDR6 memory interface, bringing about a 50-75 percent increase in memory bandwidth over "Polaris 30." According to a sketch of the GPU's SIMD schematic put out by KOMACHI Ensaka, Navi's main number crunching machinery is spread across eight shader engines, each with five compute units (CUs).

Five CUs spread across eight shader engines, assuming each CU continues to pack 64 stream processors, works out to 2,560 stream processors on the silicon. This arrangement is in stark contrast to the "Hawaii" silicon from 2013, which crammed 10 CUs per shader engine across four shader engines to achieve the same 2,560 SP count on the Radeon R9 290. The "Fiji" silicon that followed "Hawaii" stuck to the 4-shader engine arrangement. Interestingly, both these chips featured four render-backends per shader engine, working out to 64 ROPs. AMD's decision to go with 8 shader engines raises hopes for the company doubling ROP counts over "Polaris," to 64, by packing two render backends per shader engine. AMD unveils Navi in its May 27 Computex keynote, followed by a possible early-July launch.

After a 4 Year Leave, AMD Rejoins the Fortune 500 List

The Fortune 500 lists the top 500 companies in the worold in terms of revenue. These are the most significant movers in the markets, be it of real estate, mining, hedge fund, or semiconductor nature (among others). AMD was "kicked" out of the Fortune 500 back in 2015, when the company was struggling with its Bulldozer-based processors and had an increasingly small marketshare - and thus revenue - that Zen came on to save. Now, thanks to the efforts of everyone involved in the company, they've been listed again on the #460 spot.

The company has been winning minds and wallets when it comes to their CPU solutions in both the mainstream and professional segments, with the company making very important forays into the HPC world mostly thanks to the strength of their CPU lineup - which, in some cases, like with the Frontier Supercomupter (expected to be the world's fastest), can bring wins in the GPU computing department as well. For comparison's sake, Intel stands at a commanding #43, while NVIDIA enjoys a comfortable #268 place.

AMD to Detail Zen 2, Navi Architectures Come Hot Chips in August

The Hot Chips conference is one of the leading-edge grounds for discussion of new silicon-bound technologies, and AMD will, as usual, take to its grounds in an effort to detail their efforts in their technology fields. The conference's organization has already confirmed a number of participants in its conference schedule, which includes the likes of Intel, Microsoft, Alibaba, NVIDIA, Tesla and of course, AMD.

AMD will be delivering two keynotes: the first, on August 19th, is simply titled "Zen 2", and will therefore deal with the underpinnings of the Zen 2 microarchitecture, which will be pervasive to all of AMD's CPU product lines. A second conference will be held on the same day by AMD's CEO Lisa Su herself, and is titled "Delivering the Future of High-Performance Computing with System, Software and Silicon Co-Optimization". On the next day, August 20th, another AMD keynote is simply titled "7 nm Navi GPU", and we expect it to follow in the footsteps of the Zen 2 conference. So, with AMD diving deep into both architectures come August... it's extremely likely the company will have launched both product lines by then. Fingers crossed. You can find the abstract on AMD's CEO Lisa Su's conference after the break.

AMD Confirms Launch of Next-gen Ryzen, EPYC and Navi for Q3

During AMD's annual shareholder meeting today, AMD president and CEO Dr. Lisa Su confirmed the launch of next-generation AMD Ryzen, EPYC CPUs and Navi GPUs for the third quarter of this year. The expected products are going to be manufactured on TSMC's 7 nm process and will be using new and improved architectures.

Ryzen 3000 series CPUs are rumored to have up to as much as 16 cores in Ryzen 9 SKUs, 12 cores in Ryzen 7 SKUs and 8 cores in Ryzen 5 SKUs. EPYC server CPUs will be available in models up to 64 cores. All of the new CPUs will be using AMD "Zen 2" architecture that will offer better IPC performance and, as rumors suggest for consumer models, are OC beasts. Navi GPUs are the new 7 nm GPUs that are expected to be very competitive both price and performance wise to NVIDIA's Turing series, hopefully integrating new technologies such as dedicated Ray Tracing cores for higher frame rates in Ray Tracing enabled games. No next generation ThreadRipper launch date was mentioned, so we don't yet know when and if that will that land.

AMD Readying Commemorative 50th Anniversary Editions of Radeon VII, Ryzen 7 2700X

AMD is going to celebrate their 50th anniversary in a big way, with commemorative editions of both its highest performance GPU and CPU in the form of the Radeon VII and Ryzen 7 2700X, respectively. This isn't so surprising - after all, if partners are readying their own special editions, it would be amiss for the red team not to do the same. It's a time to lavish their lineup with something that marks the fifty years of the company's existence - alongside its bright (and not so bright) spots.

The Radeon VII will apparently bring the red up to 11, with a red-colored shroud and LED lighting - and apart from that, we simply don't know. It's speculated the Ryzen 7 2700X will be packaged in a prettier box, with increased core clocks to boot - perhaps through core binning and a higher maximum boost threshold. It would make sense for AMD to do the same on their own Radeon VII - celebrating a 50th anniversary with increased performance across the board seems an easy conclusion to come to. We'll just have to wait a few more days, though - apparently, the company will be introducing these products next week, come April 29th. If you want a piece of AMD's history, this could be your chance - albeit a limited one when it comes to actual production numbers for these limited edition GPU and CPU.

Razer Supercharges Windows Laptops and MacBooks with the New Core X Chroma

Razer , the leading global lifestyle brand for gamers, announced today the latest external graphics enclosure (eGPU), the Razer Core X Chroma. The Razer Core X Chroma expands its features to now include a 700W power supply, USB and Gigabit Ethernet ports, and Razer Chroma lighting.

Designed to work with a wide array of Thunderbolt 3 Windows laptops and MacBooks, the Razer Core eGPU line will give mobile warriors the ability to tap into the massive graphics processing power of a desktop gaming machine with minimal hassle. This allows users to play the most demanding games and create world-class content at blazing speeds. The Razer Core X Chroma now includes a 700W power supply, USB and Gigabit Ethernet ports, and Razer Chroma lighting to meet the needs of the most hardcore gamers and creators.

NVIDIA Also Releases Tech Demos for RTX: Star Wars, Atomic Heart, Justice Available for Download

We've seen NVIDIA's move to provide RTX effects on older, non-RT capable hardware today being met with what the company was certainly expecting: a cry of dismay from users that now get to see exactly what their non-Turing NVIDIA hardware is capable of. The move from NVIDIA could be framed as a way to democratize access to RTX effects via Windows DXR, enabling users of its GTX 1600 and 1000 series of GPUs to take a look at the benefits of raytracing; but also as an upgrade incentive for those that now see how their performance is lacking without the new specialized Turing cores to handle the added burden.

Whatever your side of the fence on that issue, however, NVIDIA has provided users with one more raytraced joy today. Three of them, in fact, in the form of three previously-shown tech demos. The Star Wars tech demo (download) is the most well known, certainly, with its studies on reflections on Captain Phasma's breastplate. Atomic Heart (download) is another one that makes use of RTX for reflections and shadows, while Justice (download) adds caustics to that equation. If you have a Turing graphics card, you can test these demos in their full glory, with added DLSS for improved performance. If you're on Pascal, you won't have that performance-enhancing mode available, and will have to slog it through software computations. Follow the embedded links for our direct downloads of these tech demos.

Glued Die on ASUS ROG Strix GeForce RTX 2080 Ti Affects Some Aftermarket Cooling Solutions

Update April 4th: This post has been corrected based on new information provided by ASUS, EKWB, as well as other parties. The original story mentioned a silent change to the glue used on the PCB which, as we now believe, is no longer the case in that ASUS is not to blame.

Update April 5th: ASUS has confirmed to us that there has been no PCB change (in terms of components and their heights), it's only a problem of tolerances due to the glue being liquid during production.

ASUS has glued the GPU die to the PCB for many generations, which helps ensure contact and avoids microfractures in the solder balls from physical force or thermal expansion. The nature of this glue, typically an epoxy resin, means that aftermarket cooling solutions, such as full cover or die-only water blocks, have to accommodate for this around the holes around the die. Previous graphics cards had no issue here, because the mounting holes were far away from the GPU die. With RTX 2080 Ti and its super large GPU chip this has changed, and there's only a few millimeters of space left. If a waterblock uses wider standoffs than the design merits, or if the glue spreads out farther than intended, it can result in poor/inconsistent contact between waterblock and the GPU, which in turn can lead to worse thermal performance than ideal.

This time, EK Waterblocks alerted us that the ROG Strix GeForce RTX 2080 Ti had poor contact and fitting issues with their GPU water block for the same, as seen in images below provided by their customer T. Hilal, which interferes with the four standoffs surrounding the package. EK recommends removing these standoffs to ensure a good fit and thermal paste spread, and this does not affect water block performance much in their internal testing. In previous such occasions, EK and others have had to come up with a second version of the block for added compatibility, however it remains to be seen if the ROG Strix GeForce RTX 2080 Ti will merit a similar treatment this time round. As an external reference, Phanteks has separately confirmed to us that their water block remains compatible.

AMD President and CEO Dr. Lisa Su to Deliver COMPUTEX 2019 CEO Keynote

Taiwan External Trade Development Council (TAITRA) announced today that the 2019 COMPUTEX International Press Conference will be held with a Keynote by AMD President and CEO Dr. Lisa Su. The 2019 COMPUTEX International Press Conference & CEO Keynote is scheduled for Monday, May 27 at 10:00 AM in Room 201 of the Taipei International Convention Center (TICC) in Taipei, Taiwan with the keynote topic "The Next Generation of High-Performance Computing".

"COMPUTEX, as one of the global leading technology tradeshows, has continued to advance with the times for more than 30 years. This year, for the first time, a keynote speech will be held at the pre-show international press conference," said Mr. Walter Yeh, President & CEO, TAITRA, "Dr. Lisa Su received a special invitation to share insights about the next generation of high-performance computing. We look forward to her participation attracting more companies to participate in COMPUTEX, bringing the latest industry insights, and jointly sharing the infinite possibilities of the technology ecosystem on this global stage."

Intel Hires NVIDIA's Tom Petersen in Latest Move to Bolster GPU Division

Anyone remotely familiar with NVIDIA knows of their now erstwhile distinguished engineer Thomas A. Petersen, better known simply as Tom Petersen or TAP. He was a delight to work with as far as the tech media is concerned, including TechPowerUp, and was a source of technical information on NVIDIA microarchitectures as well as features targeting the general consumer and prosumer alike. The last few keynote presentations have had a visible lack of Tom on screen, and even in person to where we were discussing internally whether he had taken on a more "behind the scenes" approach at the company. As it turns out, Tom is the latest in line to have attracted the eyes of Intel as the latter gears up to the challenge of gaining marketing share in the discrete GPU business in the years to come.

Tom confirmed on his Facebook page this past Friday that he was indeed leaving NVIDIA, with March 29 being his last working day there. He was quick to note his unemployment status on his LinkedIn profile in a humorous manner as well, and this was surely not for long given news broke shortly from Hothardware, and then Gamers Nexus, who both independently verified from their contacts at Intel that Tom Petersen was headed to the blue team sooner than later. Aside from being a media liaison for technical marketing, he has been at the forefront for the development of tools to help benchmark render response and effectiveness (FCAT), contributed to NVIDIA's GPU BOOST technology directly, and no doubt will be an important contributor at Intel to complement the vast number of PR and media personnel joining their ranks in the recent few months. We are excited to see what Tom helps bring to the table, and wish him the best to help create a more open and competing dGPU market for us.

Without Silicon, Intel Scores First Exascale Computer Design Win for Xe Graphics - AURORA Supercomputer

This here is an interesting piece of tech news for sure, in that Intel has already scored a pretty massive design win for not one, but two upcoming products. Intel's "Future Xeon Scalable Processors" and the company's "Xe Compute Architecture" have been tapped by the U.S. Department of Energy for incorporation into the new AURORA Supercomputer - one that will deliver exascale performance. AURORA is to be developed in a partnership between Intel and Cray, using the later's Shasta systems and its "Slingshot" networking fabric. But these are not the only Intel elements in the supercomputer design: Intel's DC Optane persistent memory will also be employed (in an as-of-yet-unavailable version of it as well), making this a full win across the prow for Intel.

Samsung Electronics Introduces New Flashbolt HBM2E High Bandwidth Memory

Samsung Electronics Co., Ltd., the world leader in advanced semiconductor technology, today announced its new High Bandwidth Memory (HBM2E) product at NVIDIA's GPU Technology Conference (GTC) to deliver the highest DRAM performance levels for use in next-generation supercomputers, graphics systems, and artificial intelligence (AI).

The new solution, Flashbolt , is the industry's first HBM2E to deliver a 3.2 gigabits-per-second (Gbps) data transfer speed per pin, which is 33 percent faster than the previous-generation HBM2. Flashbolt has a density of 16Gb per die, double the capacity of the previous generation. With these improvements, a single Samsung HBM2E package will offer a 410 gigabytes-per-second (GBps) data bandwidth and 16 GB of memory.

NVIDIA GTC 2019 Kicks Off Later Today, New GPU Architecture Tease Expected

NVIDIA will kick off the 2019 GPU Technology Conference later today, at 2 PM Pacific time. The company is expected to either tease or unveil a new graphics architecture succeeding "Volta" and "Turing." Not much is known about this architecture, but it's highly likely to be NVIDIA's first to be designed for the 7 nm silicon fabrication process. This unveiling could be the earliest stage of the architecture's launch cycle, would could see market availability only by late-2019 or mid-2020, if not later, given that the company's RTX 20-series and GTX 16-series have only been unveiled recently. NVIDIA could leverage 7 nm to increase transistor densities, and bring its RTX technology to even more affordable price-points.

MSI Reveals New GeForce GTX 1660 Series Graphics Cards

As the world's most popular GAMING graphics card vendor, MSI is proud to announce its new graphics card line-up based on the new GeForce GTX 1660 GPU, the latest addition to the NVIDIA Turing GTX family.

The GeForce GTX 1660 utilizes the "TU116" Turing GPU that's been carefully architected to balance performance, power, and cost. TU116 includes all of the new Turing Shader innovations that improve performance and efficiency, including support for Concurrent Floating Point and Integer Operations, a Unified Cache Architecture with larger L1 cache, and Adaptive Shading.

JPR: GPU Shipments Down 2.65% From Last Quarter, 3.3% YoY

Jon Peddie Research, the market research firm for the computer graphics industry, has released its quarterly Market Watch report on worldwide GPU shipments used in PCs for Q4'18. Overall GPU shipments decreased -2.65% from last quarter, AMD shipments decreased -6.8% Nvidia decreased -7.6% and Intel's shipments, decreased -0.7%. AMD's market share from last quarter decreased -0.6%, Intel's increased 1.4%, and Nvidia's market share decreased -0.82%. Year-to-year total GPU shipments decreased -3.3%, desktop graphics decreased -20%, notebooks increased 8%.

Although overall GPU shipments declined PC sales saw an uptick of 1.61% which is a positive sign for the market overall. "The channel's demand for add-in boards (AIBs) in early 2018 was out of sync with what was happening in the market," said Dr. Jon Peddie, president and founder of Jon Peddie Research. "As a result, the channel was burdened with too much inventory. That has impacted sales of discrete GPUs in Q4, and will likely be evident in Q1, and Q2'19 as well."
Return to Keyword Browsing
Jul 15th, 2025 16:30 CDT change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts