Imagination Technologies announces the tenth generation of its PowerVR graphics architecture, the IMG A-Series. The fastest GPU IP ever released, IMG A-Series evolves the PowerVR GPU architecture to fulfil the graphics and compute needs of the full spectrum of next-generation devices. Designed to be "The GPU of Everything" IMG A-Series is the ultimate solution for multiple markets, from automotive, AIoT, and computing through to DTV/STB/OTT, mobile and server.

The IMG A-Series' multi-dimensional approach to performance scalability ranges from 1 pixel per clock (PPC) parts for the entry-level market right up to 2 TFLOP cores for performance devices, and beyond that to multi-core solutions for cloud applications. Dr. Ron Black, CEO, Imagination Technologies, says: "IMG A-Series is our most important GPU launch since we delivered the first mobile PowerVR GPU 15 years ago and the best GPU IP for mobile ever made. It offers the best performance over sustained time periods and at low power budgets across all markets. It really is the GPU of everything."

Today Basemark releases version 1.1 of its multi-platform graphics hardware evaluation tool Basemark GPU. Basemark GPU has been made available for free to download and use for personal users. Additionally, Basemark has provided professional versions for Benchmark Development Program members, corporate and commercial users.

Basemark GPU 1.1 Benchmark offers unparalleled, objective comparisons between Vulkan, OpenGL, OpenGL ES and now DirectX 12 for graphics performance analysis across both mobile and desktop platforms. Our desktop Linux version of Basemark GPU 1.1 will be available in the next few days utilizing the easily installable universal Flatpak delivery format.

Basemark GPU is available for download now.

AMD recently announced the Radeon Instinct MI60, a GPU-based data-center compute processor with hardware virtualization features. It takes the crown for "the world's first 7 nm GPU." The company also put out specifications of the "Vega 20" GPU it's based on: 4,096 stream processors, 4096-bit HBM2 memory interface, 1800 MHz engine clock-speed, 1 TB/s memory bandwidth, 7.4 TFLOP/s peak double-precision (FP64) performance, and the works. Here's the kicker: the company isn't launching this accelerator with Windows support. At launch, AMD is only releasing x86-64 Linux drivers, with API support for OpenGL 4.6, Vulkan 1.0, and OpenCL 2.0, along with AMD's ROCm open ecosystem. The lack of display connector already disqualifies this card for most workstation applications, but with the lack of Windows support, it is also the most expensive graphics card that "can't run Crysis." AMD could release Radeon Pro branded graphics cards based on "Vega 20," which will ship with Windows and MacOS drivers.

NVIDIA released its first GeForce software suite since Windows 10 October 2018 went official. The new GeForce 416.16 WHQL drivers add full support for the new operating system, including WDDM 2.5, and DirectX Ray-Tracing (DXR), which are essential for NVIDIA RTX to work. The drivers also add SLI profiles for a large number of games, including "Battlefield V," "Basingstroke," "Divinity: Original Sin II," "Immortal: Unchained," "Jurassic World Evolution," "Phoenix Point," and "Seven: The Days Long Gone." 3DVision profiles are added for "The Elder Scrolls: Online."

A small number of bugs are also fixed with this release. "Pascal" GPUs running "Quake HD remix" no longer experience black square glitches. Temporal AA sharp drops in performance with GeForce GTX 1060 running "Rainbow 6: Siege" has been fixed. Driver errors on TITAN Xp when waking up from S4 sleep have been fixed. Lastly, an issue found with "Turing" GPUs not exposing Netflix 4K mode to displays connected over USB-C, has been fixed. Grab the driver from the link below.DOWNLOAD: NVIDIA GeForce 416.16 WHQL

The change-log follows.

NVIDIA debuted its R399 series of GeForce software, which could be its final sequence before GeForce RTX family of graphics cards are released to market, likely accompanied by a new series of GeForce software (likely R400 series?). Version 399.07 WHQL is "Game Ready" for "Battlefield V Open Beta," F1 2018, "Immortal: Unchained," Pro Evolution Soccer 2019, "Strange Brigade," and "Switchblade." The drivers also add SLI profiles for F1 2018 and "Immortal: Unchained."

GeForce 399.07 WHQL addresses a number of bugs, including blurry screen noticed on "Rainbow Six: Siege" with TAA dialed up to 100%; diagonal screen-tearing on notebooks with MSHybrid; incorrect OpenGL rendering context on GeForce GTX 1050 and GTX 1070; missing textures in "Doom" (2016) with the Vulkan renderer; random BSODs on Oculus VR software; stability issues with "LA Noire VR," and stuttering in some exotic configurations on "Call of Duty: Black Ops 4." A key bug with G-Sync stuttering on machines upgrading to Windows 10 1803 has also been fixed. Grab the driver from the link below.DOWNLOAD: NVIDIA GeForce 399.07 WHQL Software

Basemark launched today Basemark GPU, a new graphics performance evaluation tool for systems with Vulkan 1.0, OpenGL 4.5 or OpenGL ES 3.1 graphics APIs. This tool enables the industry to objectively and reliably quantify and compare graphics performance of next generation mobile, automotive and desktop processors.

"We have poured all of our soul and expertise in making this product. The work started two and half years ago and this massive project has culminated in today's launch of a true state-of-the-art product," said Arto Ruotsalainen, CEO of Basemark. "We believe Basemark GPU will become an essential tool for anyone tasked to evaluate graphics performance in systems ranging from smart phones, smart TVs and cars to PCs."

Apple, at WWDC 2018, announced that with the latest update to MacOS, its operating system for iMac desktops and MacBooks, the company is deprecating two of the industry's leading APIs, OpenGL and OpenCL, in a bid to boost adoption of its own Metal API. OpenGL and OpenCL applications will continue to function on MacOS 10.14, but the APIs themselves will be deprecated going forward. The removal of OpenGL from future MacOS releases breaks most AAA cross-platform games playable on the Mac, particularly distributed over Steam. The deprecation of OpenCL comes as a surprise to the scientific community, as several computational applications running on Mac Pros will be affected. Adobe Creativity Suite applications take advantage of both APIs. Apple is pushing for Metal's compute-shader features to replace the API.

The latest update for the Steam software brought with it an important new addition for the quality of life of gamers under the Linux or Windows suns everywhere: persistent shader caches for games. In the latest change-log, users are treated to the following message: "New feature: Shader Pre-Caching. Whenever possible, depending on hardware and driver support, Steam can download pre-compiled shaders for your specific video card. This reduces load times and in-game stuttering during the first few launches of OpenGL- and Vulkan-based games on supported hardware. This feature may use a small amount of additional bandwidth as Steam uploads and analyzes a shader usage report after each run of the game. The feature can be disabled via a new entry in the Settings dialog.

Under Steam Settings, you'll find a new Shader Pre-Caching item. The description reads as follows: "Shader Pre-Caching allows Steam to download pre-compiled GPU shaders matching your system configuration. This allows Vulkan and OpenGL games to load faster and improve framerate stability during gameplay. If enabled, Steam will collect shaders from your system when needed. Enabling this feature may slightly increase disk and bandwidth usage."

NVIDIA today released the GeForce 387.92 Game Ready Graphics Drivers, which presents a more comprehensive package than most Game Ready drivers. This time, the changes aren't mostly limited to new, upcoming games support, though that's still part of the package. On that front, you can count on these drivers being optimized for the upcoming Middle-earth: Shadow of War and The Evil Within 2, as well as Forza Motorsport 7, on which NVIDIA expects anywhere between 15% and 25% performance improvement (which should help improve NVIDIA's situation). On the VR space, this driver package brings the optimal experience for 4A Games' Artika.1 (if you recognize the studios' name, it's probably because they're the ones behind the Metro game series.

Also interesting, however, are the feature updates that come with this driver package. Fast Sync is now supported for SLI configurations, though Maxwell architecture users should steer clear of 4K resolution, which isn't supported for this feature. There's also NVIDIA GameStream support for HDR under Windows 10. On the renderer side, we see added support for OpenGL 4.6, as well as for DirectX Intermediate Language (DXIL). This includes full support for DirectX 12 Shader Model 6.0 ( for features such as Wavemath), and the DirectX Shader Compiler, though it's only supported on NVIDIA Kepler and later GPUs. There are also some improvements to full-screen Vulkan applications, though this particular change may cause more errors while leaving and entering full-screen mode (Alt-Tab). Grab the drivers from the link below right here on TPU, and find the change-log after the break.DOWNLOAD: NVIDIA GeForce 387.92 Game Ready Drivers

The Khronos Group, an open consortium of leading hardware and software companies, announces from the SIGGRAPH 2017 Conference the immediate public availability of the OpenGL 4.6 specification. OpenGL 4.6 integrates the functionality of numerous ARB and EXT extensions created by Khronos members AMD, Intel, and NVIDIA into core, including the capability to ingest SPIR-V shaders.

SPIR-V is a Khronos-defined standard intermediate language for parallel compute and graphics, which enables content creators to simplify their shader authoring and management pipelines while providing significant source shading language flexibility. OpenGL 4.6 adds support for ingesting SPIR-V shaders to the core specification, guaranteeing that SPIR-V shaders will be widely supported by OpenGL implementations.

NVIDIA has released an update to its GeForce Experience application that is sure to be loved by streamers and gamers alike who previously found ShadowPlay support on Vulkan and OpenGL games to be lacking. Version 3.6 of the program adds official support to games that make use of these renderers. Screenshot, video, and broadcast functions that Shadowplay enables are enhanced by the addition of support for these APIs, which means you can now use ShadowPlay with a press of a hotkey to record and stream your Doom and Minecraft gameplay at 4K 60fps.

Other improvements include a unified Broadcast screen and a newly revamped Video and Screenshot upload interface: YouTube and Twitch streamers can now control broadcast options from a unified screen, and log in to all services from there as well. NVIDIA has also worked some improvements to its GeForce Experience Gallery, by adding an upload history screen that displays all prior uploads and locations. You now also have the option of instantly jumping to the file location of a screenshot or video in Windows Explorer through a new button.

With the success of Blizzard's "Overwatch," it's only natural for game studio Bethesda to develop the oldest, most successful hero-based FPS brand from the early 2000s, "Quake III Arena," into a brand-new title that keeps up with the times, and perhaps even sets new standards. That title is "Quake Champions," and Bethesda is tapping into big id Software talent in its development.

"Quake Champions" will by driven by a proprietary engine that's not id Tech 6. This game will take advantage of the Vulkan API, besides an OpenGL fallback, and as part of an agreement between Bethesda and AMD, it could feature optimization for AMD Ryzen processors. "Quake Champions" will build on the things that made Quake III Arena a cult-classic, besides featuring a cutting-edge production design. Besides PC, the game will launch on the Xbox One and PlayStation 4 platforms.

NVIDIA today unveiled the NVIDIA Jetson TX2, a credit card-sized platform that delivers AI computing at the edge -- opening the door to powerfully intelligent factory robots, commercial drones and smart cameras for AI cities. Jetson TX2 offers twice the performance of its predecessor, or it can run at more than twice the power efficiency, while drawing less than 7.5 watts of power. This allows Jetson TX2 to run larger, deeper neural networks on edge devices. The result: smarter devices with higher accuracy and faster response times for tasks like image classification, navigation and speech recognition.

"Jetson TX2 brings powerful AI capabilities at the edge, making possible a new class of intelligent machines," said Deepu Talla, vice president and general manager of the Tegra business at NVIDIA. "These devices will enable intelligent video analytics that keep our cities smarter and safer, new kinds of robots that optimize manufacturing, and new collaboration that makes long-distance work more efficient."

After putting in work in the OpenGL, WebGL, and most recently, Vulkan APIs, the technology industry consortium Khronos Group is setting its sights on the VR industry and ecosystems. Their aim: to create a "cross-vendor, royalty-free, open standard" for the VR development community. This move is an effort to prevent the VR system from fragmenting itself towards an eventual collapse, considering the multiple engines to create content, platforms to sell that content through, and a few different hardware options with casuistically different requirements and tool-sets. As a result, for a developer to support SteamVR (OpenVR), Oculus (OVR), and OSVR, it has a lot of work to do, since each platform (with its unique runtime) interfaces with the game engine in a different way. Developers must account for the intricacies of each platform during the development process.

The folks over at 3dcenter.org have compiled comprehensive historical GPU AIB market share data for our digestion. While we recently reported on Q3'16 and its comparison to the quarter before and the same period last year, this information spans a near 14 year quarter-on-quarter time frame. The compilers have quite helpfully included points of reference along the timeline which highlight the two major GPU manufacturers milestone desktop product line debuts.

It is worth noting that their exact numbers differ slightly to the ones Jon Peddie Research provided as 3dcenter have also cited the work of Mercury Research, which appears more conservative. The figures provided in their own graph split the difference between the two sources to give us a more impartial look at the market.

At SC16, AMD announced that Radeon GPU technology will be available to Google Cloud Platform users worldwide. Starting in 2017, Google will use AMD's fastest available single-precision dual GPU compute accelerators, Radeon-based AMD FirePro S9300 x2 Server GPUs, to help accelerate Google Compute Engine and Google Cloud Machine Learning services. AMD FirePro S9300 x2 GPUs can handle highly parallel calculations, including complex medical and financial simulations, seismic and subsurface exploration, machine learning, video rendering and transcoding, and scientific analysis. Google Cloud Platform will make the AMD GPU resources available for all their users around the world.

"Graphics processors represent the best combination of performance and programmability for existing and emerging big data applications," said Raja Koduri, senior vice president and chief architect, Radeon Technologies Group, AMD. "The adoption of AMD GPU technology in Google Cloud Platform is a validation of the progress AMD has made in GPU hardware and our Radeon Open Compute Platform, which is the only fully open source hyperscale GPU compute platform in the world today. We expect that our momentum in GPU computing will continue to accelerate with future hardware and software releases and advances in the ecosystem of middleware and libraries."

In what promises to be AMD's most ambitious (and lucrative) semi-custom hardware deal to date, the company partnered with CoreAVI, a leading manufacturer of commercial jet avionics, to develop high-performance cockpit display modules that perform on-the-fly terrain mapping. The company is designing special variants of its Radeon embedded GPUs and APUs (as in accelerated processing units, not auxiliary power); which drive high-resolution cockpit displays with reliable levels of performance.

The company is tapping into its most proven GPU IP and the ubiquitous x86 CPU architecture to drive PFD (primary flight display) modules. AMD hardware's surplus-to-requirement processing power comes in handy in accelerating terrain mapping software on-the-fly. On the software side of things, AMD is tapping into open industry standards such as OpenGL, custom-built for mission-critical (safety-critical) applications. AMD isn't new to the CoreAVI product stack. The company has been supplying extended temperature-range variants of its Radeon embedded GPUs to the company for some time now.A video presentation follows.

Vulkan, the new-generation cross-platform 3D graphics API governed by the people behind OpenGL, the Khronos Group, is gaining in relevance, with Google making it the primary 3D graphics API for Android. AMD said that it's actively promoting the API. Responding to a question by TechPowerUp in its recent Radeon Technology Group (RTG) first anniversary presser, its chief Raja Koduri agreed that the company is actively working with developers to add Vulkan to their productions, and optimize them for Radeon GPUs. This, we believe, could be due to one of many strategic reasons.

First, Vulkan works inherently better on AMD Graphics CoreNext GPU architecture because it's been largely derived from Mantle, a now defunct 3D graphics API by AMD that brings a lot of "close-to-metal" API features that make game consoles more performance-efficient, over to the PC ecosystem. The proof of this pudding is the AAA title and 2016 reboot of the iconic first-person shooter "Doom," in which Radeon GPUs get significant performance boosts switching from the default OpenGL renderer to Vulkan. These boosts aren't as pronounced on NVIDIA GPUs.

NVIDIA released the GeForce 369.00 Beta drivers featuring three new OpenGL extensions released by its architecture review board (ARB), and NVIDIA in 2016. These include the "ARB_gl_spirv," which works on NVIDIA "Kepler" architecture and above; the "EXT_window_rectangles," extension, which requires NVIDIA "Fermi" architecture and above; and the homebrew "NVX_blend_equation_advanced_multi_draw_buffers," which requires NVIDIA "Pascal" architecture. These updates to OpenGL are also shipped for the Linux platform via the 367.36.02 drivers. Grab the drivers from the links below.DOWNLOAD: NVIDIA GeForce 369.00 BetaImage Credit: DigitalTrends

Over the weekend, Bethesda shipped the much awaited update to "DOOM" which can now take advantage of the Vulkan API. A performance investigation by ComputerBase.de comparing the game's Vulkan renderer to its default OpenGL renderer reveals that Vulkan benefits AMD GPUs far more than it does to NVIDIA ones. At 2560 x 1440, an AMD Radeon R9 Fury X with Vulkan is 25 percent faster than a GeForce GTX 1070 with Vulkan. The R9 Fury X is 15 percent slower than the GTX 1070 with OpenGL renderer on both GPUs. Vulkan increases the R9 Fury X frame-rates over OpenGL by a staggering 52 percent! Similar performance trends were noted with 1080p. Find the review in the link below.

AMD today announced AMD Multiuser GPU (MxGPU) for blade servers, AMD FirePro S7100X GPU. AMD MxGPU is the industry's first and only hardware-virtualized GPU compliant with the SR-IOV (Single Root I/O Virtualization) PCIe virtualization standard. The AMD FirePro S7100X GPU is a simple, secure solution for graphics virtualization providing workstation-class experience for up to 16 users that is practically indistinguishable from a native desktop experience.

Using AMD Multiuser GPU (MxGPU) technology, the AMD FirePro S7100X GPU harnesses silicon expressly designed for graphics virtualization and conforming with the virtualization industry standard, SR-IOV to allow easy integration into existing hypervisor ecosystems. The AMD FirePro S7100X GPU is the newest addition to the AMD line of graphics virtualization products, designed in an ultra-compact form factor with a TGP of just 100W that makes it ideal for blade server deployments. Hewlett Packard Enterprise (HPE) is the first to offer the AMD FirePro S7100X GPU in HPE ProLiant WS460c Gen9 Graphics Server Blades available now.

Microsoft added two new features to its Universal Windows Platform (UWP), the company's non-Win32 application environment built around the Windows Store and modern UI. With the latest update to Windows 10, Microsoft updated UWP to support adaptive-sync technologies such as NVIDIA G-SYNC and AMD FreeSync; and removed frame-rate limits. Games built on UWP (such as "Quantum Break") suffered from frame-rate caps.

UWP continues to be criticized for taking a "walled-garden" approach to third-party apps, restricting them to Microsoft APIs such as DirectX. The platform continues to suffer from several limitations for games, such as support for APIs such as OpenGL and Vulkan; and proprietary multi-GPU technologies such as SLI and CrossFire; or support for game-mods.

NVIDIA released today its latest "Hotfix" GeForce drivers that add optimization for an unannounced game and a minor GeForce Experience-related bug. To begin with, GeForce 364.96 Hotfix driver comes with optimization (read: "support") for DOOM: Open Beta. Don't expect SLI support on this game's OpenGL-based engine, though. The drivers also address a bug with GeForce Experience that caused it to not open correctly without an active Internet connection.DOWNLOAD: NVIDIA GeForce 364.96 Hotfix for Windows 10 64-bit | Windows 10 32-bit | Windows 8/7/Vista 64-bit | Windows 8/7/Vista 32-bit

NVIDIA announced the Quadro M6000, its new high-end workstation single-GPU graphics card. Based on the GM200 silicon, and leveraging the "Maxwell" GPU architecture, the M6000 maxes out all the hardware features of the chip, featuring 3,072 CUDA cores, 192 TMUs, 96 ROPs, and a 384-bit wide GDDR5 memory interface, holding 24 GB of memory, double that of the GeForce GTX TITAN X. Its peak single-precision floating point performance is rated at 7 TFLOP/s.

Where the M6000 differs from its the GTX TITAN X is its workstation-grade features. It drops the HDMI 2.0 connector for a total of four DisplayPort 1.2 connectors, supporting a total of four 4K Ultra HD displays. The dual-link DVI connector stays on. There's also an optional stereoscopic 3D connector. The nView MultiDisplay tech provides more flexible display-head configurations than the ones you find on NVIDIA's consumer graphics GPUs; you also get NVIDIA GPUDirect support, which gives better memory sharing access for multi-GPU systems. The M6000 supports most modern 3D APIs, such as DirectX 12, OpenGL 4.5, and Vulkan; with compute capabilities over CUDA, OpenCL, and DirectCompute. NVIDIA didn't reveal pricing.

At Embedded World today, AMD announced its 3rd Generation AMD Embedded G-Series SoCs and the Embedded G-Series LX SoC, providing customers a broadened portfolio of performance options. The latest offerings expand developers' ability to scale x86 platforms, starting with the entry-level AMD Embedded G-Series LX SoC, which is pin compatible to the previous generation G-Series SoC devices. Also announced today are two new, higher performing 3rd Generation AMD Embedded G-Series SoCs, codenamed "Prairie Falcon" and "Brown Falcon," which introduce for the first time pin compatibility for G-Series processors with the higher performance AMD Embedded R-Series SoC.

The new products expand upon the low power capabilities of the award-winning AMD Embedded G-Series SoC platform, bringing scalable performance, power, and price across the CPU, GPU, multimedia, and I/O controller hardware, helping to lower development costs for AMD customers. Together, the new G-Series processors deliver immersive, graphically rich experiences across a broad range of platforms, from entry-level to mainstream gaming, digital signage, imaging, and industrial control.