News Posts matching "GPU"

Return to Keyword Browsing

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."

AMD Patents Variable Rate Shading Technique for Console, VR Performance Domination

While developers have become more and more focused on actually taking advantage of the PC platform's performance - and particularly graphical technologies - advantages over consoles, the truth remains that games are being optimized for the lowest common denominator first. Consoles also share a much more user-friendly approach to gaming - there's no need for hardware updates or software configuration, mostly - it's just a sit on the couch and leave it affair, which can't really be said for gaming PCs. And the console market, due to its needs for cheap hardware that still offers performance levels that can currently fill a 4K resolution screen, are the most important playground for companies to thrive. Enter AMD, with its almost 100% stake in the console market, and Variable Rate Shading.

As we've seen with NVIDIA's Turing implementation for Variable Rate Shading, this performance-enhancing technique works in two ways: motion adaptive shading and content adaptive shading. Motion adaptive shading basically takes input from previous frames in order to calculate which pixels are moving fast across the screen, such as with a racing perspective - fast-flying detail doesn't stay focused in our vision so much that we can discern a relative loss in shading detail, whilst stationary objects, such as the focused hypercar you're driving, are rendered in all their glory. Valuable compute time can be gained by rendering a coarse approximation of the pixels that should be in that place, and upscaling them as needed according to the relative speed they are moving across the frame. Content adaptive shading, on the other hand, analyzes detail across a scene, and by reducing shading work to be done across colors and detail that hasn't had much movement in the previous frame and frames - saves frame time.

NVIDIA Partners with OBS for GeForce Optimization and RTX Encoder

We saw a glimpse of this at the NVIDIA suite during CES 2019, with a beta version coming out shortly after. NVIDIA and OBS (Open Broadcaster Software) have since brought out the full release of a new OBS Studio, version 23.0.1, that adds improved support for NVIDIA GeForce cards. In particular, their latest and greatest RTX lineup, including the new desktop RTX 2060 as well as the mobile and Max-Q variants, will see an FPS impact drop by as much as 66% according to NVIDIA's internal testing. Some example results are seen below, with games such as Fortnite, PUBG, Call of Duty: Black Ops 4 - Blackout, and Apex Legends seeing a frame rate boost by up to 48% compared to x264 Fast, and 27% compared to x264 Very Fast.

Given this is a result of NVENC, NVIDIA's hardware encoder, in place, older GeForce GPUs (GTX 600-series and newer that support NVENC) will also see some benefits. GeForce RTX GPUs just get to enjoy a bit more- up to 15% more, in fact, in efficiency as far as bitrate consumption for the same graphical fidelity. NVIDIA effectively says that "GeForce RTX GPUs can stream with superior image quality compared to x264 Fast, and on par with x264 Medium", thus putting in a strong case for single-PC gaming and streaming, as opposed to having a dedicated streaming PC. They have even put out a video to go over the enhancements, which will no doubt interest game streamers on the PC platform.

Manli Announces GeForce GTX 1660 Ti Series Graphics Cards

Manli Technology Group Limited, the major Graphics Cards, and other components manufacturer, today announced the brand new 16 series graphics solution, Manli GeForce GTX 1660 Ti with two options: Single Fan and Blower Fan.

The Manli GeForce GTX 1660 Ti is equipped with the world's fastest memory, 6 GB of GDDR6, and a 192 bit memory controller. The base clock is 1500 MHz which can dynamically boost up to 1770 MHz to deliver a smooth and fast gaming experience. Meanwhile, it is packed with the award-winning NVIDIA Turing architecture, adaptive shading technology, and NVIDIA Ansel which delivers super resolution of images.

NVIDIA TU116 GPU Pictured Up Close: Noticeably Smaller than TU106

Here is the first picture of NVIDIA's 12 nm "TU116" silicon, which powers the upcoming GeForce GTX 1660 Ti graphics card. While the size of the package itself is identical to that of the "TU106" on which the RTX 2060 and RTX 2070 are based; the die of the TU116 is visibly smaller. This is because the chip physically lacks RT cores, and only has two-thirds the number of CUDA cores as the TU106, with 1,536 against the latter's 2,304. The die area, too, is about 2/3rds that of the TU106. The ASIC version of TU116 powering the GTX 1660 Ti is "TU116-400-A1."

VideoCardz scored not just pictures of the ASIC, but also the PCB of an MSI GTX 1660 Ti Ventus graphics card, which reveals something very interesting. The PCB has traces for eight memory chips, across a 256-bit wide memory bus, although only six of them are populated with memory chips, making up 6 GB over a 192-bit bus. The GPU's package substrate, too, is of the same size. It's likely that NVIDIA is using a common substrate, with an identical pin-map between the TU106 and TU116, so AIC partners could reduce PCB development costs.

ASUS NVIDIA GeForce GTX 1660 Ti Models With 3 GB VRAM Registered With the EEC

It seems that NVIDIA may be pulling another GTX 1060 when it comes to memory configurations of its upcoming midrange, non-RTX GPU. If ASUS' filling with the EEC (Eurasian Economic Commission) are anything to go by - and they usually are - then the green team is looking to tier their GTX 1660 Ti graphics cards via memory culling, offering it in both 6 GB and 3 GB versions. The GTX 1660 Ti and GTX 1660 will supersede NVIDIA's highest-volume GTX

In all, there are 9 SKUs for the GTX 1660 Ti 3 GB graphics card being filed with the EEC, which usually preempts graphics card launches in those domains. These slot in nicely with ASUS' plans for 6 GB versions of the GTX 1660 Ti, almost to a card - though ASUS' STRIXX-branded graphics cards seem, for now, to only be available in 6 GB versions. Of course, the 3 GB of VRAM on the GTX 1060 allow the card to achieve a desirable performance/dollar ratio, but at the cost of some performance, with the penalty increasing alongside resolution - but these are cards that likely won't ever be used for 4K gaming. While 3 GB graphics cards still fare relatively well, as we've seen, the latest games are pushing over 3 GB of video RAM more often than not, which leaves the 3 GB version of the graphics card somewhat of a less than choice when it comes to AAA gaming. But when it comes to competitive multiplayer game,s it likely will be more than enough.

Mobile NVIDIA GeForce RTX GPUs Will Vary Wildly in Performance, Clocks Lowered Substantially

NVIDIA is in the process of rolling out the first implementations of its RTX 2000 series GPUs in mobile form, and if the going is as is being reported, it's going to be a little rough for users to actually extrapolate their performance from product to product. This is because manufacturers are apparently getting a whole lot of leeway in how to clock their products, according to their solution's thermal characteristics and design philosophy.

What this means is that NVIDIA's RTX 2080 Max-Q, for example, can be clocked as low as 735 MHz, which is a more than 50% downclock from its desktop counterpart (1,515 MHz). The non-Max-Q implementation of NVIDIA's RTX 2080, for now, seems to be clocked at around 1,380 MHz, which is still a close to 200 Mhz downclock. Of course, these lowered clocks are absolutely normal - and necessary - for these products, particularly on a huge chip such as the one powering the RTX 2080. The problem arises when manufacturers don't disclose clockspeeds of the GPU in their particular implementation - a user might buy, say, an MSI laptop and an ASUS one with the exact same apparent configuration, but GPUs operating at very different clockspeeds, with very different levels of performance. Users should do their due research when it comes to the point of choosing what mobile solution sporting one of these NVIDIA GPUs they should choose.

AMD Re-structures Leadership Team; James Prior Leaves AMD

Let me be the first to say that the two may not be directly related, but it is an awfully strong coincidence that both pieces of news come out on the same day. Indeed, earlier in the day AMD put out a press release (full release past the break) announcing "multiple organizational changes focused on strengthening the company's senior leadership team and accelerating growth." Several familiar names have been promoted within the company to be in charge of more products and visions across their CPU and GPU business units. Mark Papermaster, for example, is now an executive VP as well as CTO of AMD, and the company has also hired in new talent, including industry veteran Sandeep Chennakeshu, as executive VP of "Computing and Graphics responsible for the company's high-performance PC, gaming and semi-custom businesses".

Perhaps all this re-structuring and new hiring comes in handy, at a time when we have seen several people leave AMD for Intel or otherwise. Indeed, shortly after that press release went out, word got to us that James Prior, Senior Product Manager for AMD, and an ardent employee for nearly 6 years, is no longer working for the company. We have no word yet on what is next for James, but it was more than a small surprise to know that the person you just spoke with at CES, and had a long conversation of AMD's desktop processors, is gone just like that. We have known James for many years now, and can attest to his work ethics as well as being a great guy all-round. We wish him the best in his future ventures, and look forward to also seeing how AMD's re-structuring turns out.

Phanteks Announces the Release of New Glacier Series Products and Accessories

Phanteks today announced the launch of two new Glacier series GPU blocks, corresponding backplates, a vertical GPU bracket and flat riser cables to add to their product portfolio. This includes the Glacier G2080Ti XTREME and the Glacier G2080Ti STRIX for the Gigabyte AORUS Extreme RTX 2080/2080 Ti and the ASUS Strix RTX 2080/2080 Ti respectively. Both of these blocks use a minimalist design that extends the length of the PCB, allowing for a full cover fit to cool the GPU, VRAM and VRMs alike. Integrated digital RGB lighting coupled with an anodized or chrome-plate cover plate, a polished acrylic top, and a nickel-plated copper cold plate round off the aesthetics.

Phanteks made sure to give some love to the NVIDIA Founders Edition RTX 2080(Ti) cards as well with Glacier G2080Ti backplate that is designed to work with their own Glacier G2080TiFE water block, since the AIC cards come with their own backplate that can be re-used with the GPU blocks mentioned above. We get two color options here, and the backplate extends the entire length of the PCB again. The GPU blocks will be available for $149.99 each and the backplate costs $29.99/39.99 for the black/chrome versions towards the end of this month. Read past the break for more on their new accessories.

HTC Vive Pro Eye: Hands On with Hardware and Software

The Vive Cosmos was not the only major announcement coming out of HTC's Vive business unit at CES this year. While that has massive mainstream appeal, the company was quick to let us know that it was still to early to comment further than what has already been covered in the aforelinked news post. Instead, they invited us to their suite to take a closer look at the Vive Pro Eye- one of the few things that really stood out for us at the trade show.

The Vive Pro Eye is, as the name would suggest, a new SKU with integrated eye tracking in the Vive Pro HMD. Working together with Tobii, the Vive Pro Eye allows for a more natural control mechanism within VR via eye controls, which in turn means a revamped menu navigation system is possible. This allows for increased accessibility to end users with disability, more optimization on VR performance, and detailed analysis of VR experiences for both the client and the businesses alike. Read past the break for a breakdown of our experience with the Vive Pro Eye, and the various demos on hand to showcase the feature.

Bitspower at CES 2019- New Blocks, Sensor Displays, Fans, and LN2 Cooling!

CES may have officially ended but our coverage from the trade show continues. Bitspower had invited TechPowerUp to come visit their suite, mentioning there would be something new and unexpected, and that indeed was the case. Our tour began with the customary showcase of the new GPU water blocks compatible with reference, and board partner designs, for the new NVIDIA GeForce RTX 2060 and relatively new AIC RTX 2070/80(Ti) cards as well. These feature integrated RGB lighting compatible with all major motherboard lighting solutions for control, and adopt the split central-inlet flow design as well.

PowerColor Shows Off New Thunderbolt 3 eGPU Enclosures at CES 2019

While at CES 2019 we had the opportunity to visit with PowerColor who were showing off their latest external GPU enclosures including the TBX-180/240FU, and the TBX-750FA. Starting with the TBX-750FA this external GPU enclosure uses a Thunderbolt 3 (40Gbps) connection and has a 750-watt internal power supply. Due to the size of not only the enclosure but the power supply as well, graphics cards measuring up to 335 x 170 x 58 mm (13.18 x 6.69 x 2.28 inches). When you factor in maximum GPU power is rated at 500-watts pretty much any GPU on the market should work with this enclosure like a cat with a box if it fits it sits. Connectivity options consist of the 1x Thunderbolt 3 port for connection to the host system, 1x Gigabit Ethernet, 5x USB 3.0 (3 up front, 2 in back), 1x SD 4.0, and finally 1x SATA. Overall the enclosure measures in at 359 x 179 x 198 mm and supports Windows 10 and MacOS 10.13.4 or later.

ASUS Announces Ryzen-powered TUF Gaming FX505DY and FX705DY Gaming Notebooks

ASUS today announced TUF Gaming FX505DY and TUF Gaming FX705DY, a pair of gaming laptops powered by the latest AMD Ryzen 5 3550H processor, with up to 32GB of RAM, and a range of storage options. This new platform is paired with discrete Radeon graphics tightly coupled to vivid FreeSync displays. Slim bezels frame the NanoEdge displays to further enhance immersion and shrink the overall footprint, while the reinforced chassis help the machines survive everyday life. Intelligently designed and carefully built, FX505DY and FX705DY balance performance, battery life, and affordability to provide a better gaming experience.

AMD's Ryzen processors have taken desktops by storm, and TUF Gaming laptops lead the deployment of the newest version. Otherwise known as Picasso, this 2nd Gen Ryzen Mobile APU is built with industry-leading 12 nm technology. The Ryzen 5 3550H chip powering FX505DY and FX705DY boasts four cores and eight threads that deliver capable performance for popular games and everyday work. Multithreaded performance is particularly strong, yet the processor fits into a 35W power envelope that doesn't compromise battery life.

NVIDIA to Implement 7nm EUV Node for its 2020 GPUs

NVIDIA will implement the 7 nanometer EUV (extreme ultraviolet) lithography to build its future generation of GPUs slated for 2020, according to Japanese publication MyNavi.jp. The GPU giant could be among the first customers besides IBM, to contract Samsung for 7 nm EUV mass-production of GPUs. IBM will use the Korean semiconductor giant for manufacturing Z-series processors and FPGAs. Samsung announced in October 2018 that it will begin risk-production on its 7 nm EUV node in early-2019.

An earlier report from 2018 also forecast NVIDIA implementing 7 nm DUV (deep ultraviolet) node of TSMC for its 2019 GPU lineup. With news of the company now working with Samsung on 7 nm EUV for 2020, this seems less likely. It's possible that NVIDIA could somehow split its next generation GPU lineup between TSMC 7 nm DUV and Samsung 7 nm EUV, with the latter being used for chips with higher transistor-counts, taking advantage of the node's higher deliverable transistor densities.

Lenovo Confirms Mobile GeForce GTX 1160 GPU, Or Does It?

It was about 6 months ago that we posted a news story about how a Lenovo representative mentioned that the successor to NVIDIA's GeForce 10-series of GPUs would be named the 11-series. Fast forward in time, we know how that turned out with the recently announced RTX 20-series instead. The rumor mill has not taken a break over the holidays, however, with consistent postings and speculation online about how NVIDIA will announce not only the RTX 2060 at CES 2019, but also a whole new GTX 11-series accompanying it that is aimed to meet gaming needs without real-time ray tracing support and at a lower price point respective to the equivalent RTX SKU.

Perhaps it is fitting that Lenovo provides more fuel to this fire once again, with a listing of a mobile GeForce GTX 1160 (N18E) graphic solution on their upcoming Legion Y530 and Y7000P laptops. VideoCardz.com was quick to capture a screenshot of the specs listing, seen below, that describes it as a "next generation GPU", albeit with an asterisk hinting that the specification may not be final. Indeed, Lenovo has since changed the description on that product page to remove all signs of said 11-series mobile GPUs, and the LaptopMedia specs database for the Legion Y530 also now mentions a "GTX 2060" with 6 GB of VRAM instead. The only thing we know for sure is that we are not sure of anything, and it may well be that a GeForce 11-series, if it even exists, is a mobile-only platform. Hopefully CES will shed more light on this matter, and stay tuned for our coverage of the event accordingly.

AMD Radeon Technology Group, Senior VP and General Manager, Mike Rayfield to Resign

AMD's Radeon Technology Group (RTG) continues to be in a state of flux, with another executive leaving the company. This time, RTG General Manager and Senior Vice President, Mike Rayfield (pictured on the left below) will be resigning by year's end, marking the second time in a calendar year the group has been devoid of a formal leader. Rayfield previously worked for NVIDIA as the General Manager of their Tegra business unit, and was Vice President and General Manager of Micron's mobile storage business unit prior to that. Having served in all these roles for quite some time, it is somewhat of a surprise to see him leaving AMD so quickly, having only just joined the company back in February 2018. With that said, AMD has said the reason for this departure is so that he can "spend more time with his family and pursue his personal passions".

David Wang (picture on the right below), the current Senior Vice President of Engineering at RTG, will be his interim successor. He already has a storied history at AMD, having worked on ATI/AMD graphics cards as a GPU engineer from the R300 to GCN 1.0 in a time period ranging from the years 2000 to 2012. Under AMD's dual leadership model which was implemented after Raja Koduri's resignation, both Wang and Rayfield have worked together leading the RTG group. Thanks to this, the transition of duties should be relatively smooth even though Wang's role is only temporary, and it will be interesting to see whom AMD picks as Rayfield's long-term successor.

3DFX's Canceled Rampage GPU Pictured, Put Through the Paces in 3D Mark 2001

3DFX is a well-known name for most in our community, I'd wager (I don't have the data to back me up on that, but bare with me). The company is one of the highest-profile defunct companies that vied for a place in the desktop, high-performance GPU space back in the day, and brought its guns bearing on NVIDIA and then ATI. The Rampage was the last GPU ever developed by the company, and looked to compete with NVIDIA's GeForce3. That never saw the light of day, though, with the company shutting its doors before development became viable for market release.

DSOGaming has some images of some of the Rampage GPUs that survived 3DFX's closure, though, and the graphics card is shown running Max Payne, Unreal Tournament & 3DMark 2001. For those of you that ever had a 3DFX graphics card, these should bring you right down memory lane. Enjoy.

Intel 10nm "Ice Lake" to Combine "Sunny Cove" CPU Cores with Gen11 iGPU

Intel's upcoming "Ice Lake" die could be the company's biggest processor innovation in a decade, combining new clean-slate design "Sunny Cove" CPU cores, and a new integrated graphics solution based on the company's Gen11 architecture. "Sunny Cove" introduces significant IPC (single-thread performance) gains over "Coffee Lake," introduces new ISA instruction sets, including AVX-512; and a brand new uncore component; while the Gen11 graphics core is Intel's first iGPU to reach the 1 TFLOP/s mark. Intel demonstrated the ultra-low power "Ice Lake-U" SoC platform in its 2018 Architecture Day briefing.

This "Ice Lake-U" chip, with its TDP in the ballpark of 15 W, was shown ripping through 7-zip and "Tekken 7." With 7-zip, Intel was trying to demonstrate vector-AES and SHA-NI improving archive encryption performance by 75 percent over "Skylake." The Gen11 iGPU was shown providing a smoother gameplay than Skylake with Gen9, although the company neither mentioned resolution, nor frame-rates. Anandtech wagers it's above 30 fps.

Ex-Hardware.fr GPU Editor Damien Triolet Jumps Ship from AMD RTG to Intel

Oh hey remember this news post from July last year? Damien Triolet's work history off-late has been one of many such recent stories. These tend to begin with AMD, and RTG in particular, getting a cash infusion and growing in 2016 and 2017 to where they hired some of the best engineers and marketing personnel from the industry- media or otherwise. This follows a more stagnant GPU division in 2017-2018, Intel deciding to dip their toes back into the discrete GPU market, and in turn.. persuading many to cross over to the blue side.

According to Damien's LinkedIn and FaceBook profiles, he has started working for Intel from November 26, 2018 in a technical marketing position in their Gaming and Graphics division, a role analogous to his from his days at AMD. Presumably, he joins Raja Koduri and the many others who have followed this exact path of late, and everyone remains curious as to what the finished retail product will be. In the meantime, we here at TechPowerUp wish him the best again for his new venture. We had the pleasure of interacting with Damien on multiple occasions in the past, some as colleagues in the media giving hardware manufacturers a hard time, and others when he was hosting us as an AMD employee. His tenure at Hardware.fr has been inspiring to us, with excellent reviews that no doubt were what caught the eyes of AMD in the first place, and Intel will definitely gain from his presence.

NVIDIA GeForce RTX 2070 and 2080 Mobile Could Make an Appearance at CES 2019

With NVIDIA's GeForce RTX 20-series having already released for desktops, it was only a matter of time until laptops got the RTX treatment as well. Current rumors are suggesting that Nvidia will officially launch their GeForce RTX 20-series mobility GPUs on January 6th at CES with the RTX 2070 and RTX 2070 Max-Q taking center stage. An embargo date of January 26th has also been set, with NVIDIA delaying their final release drivers until then. Meaning final performance results for the new mobile GPUs won't be available until after the embargo date, which should coincide with the general availability of RTX 20-series equipped laptops.

Along with the RTX 2070 and 2070 Max-Q mobility parts, the flagship RTX 2080 Max-Q which isn't expected at the show, is still in the works, with its TU104M 1eab device ID having been leaked earlier. The rest of the GeForce 20-series mobility GPUs are likely to use the GTX moniker if NVIDIA's desktop lineup is anything to go by; however, that is merely speculation at this point.

AMD Radeon RX 570 and China-specific RX 580 2048SP Based on Exact Same Chip

It's no news that AMD's Radeon RX 570 graphics card is carved out of the same "Polaris 20" silicon as the RX 580, by disabling 4 out of 36 GCN compute units. AMD kicked a controversy recently, when it launched a China-specific Radeon RX 580-branded SKU with the core-configuration of the cheaper RX 570, confusing Chinese consumers. It turns out that this RX 580 2,048 SP SKU is based on the same exact ASIC variant of the "Polaris 20" silicon as the RX 570, with the only difference being device ID.

We watch a lot of GamersNexus content. Our GPU Database curator noticed something interesting in their recent teardown of a Dataland Radeon RX 580 (2,048 SP) graphics card directly imported from China. The unique ASIC sub-variant code etched on the GPU's aluminium reinforcement brace matches that of the RX 570. AMD internally refers to the RX 570 as "Polaris 20 XL," and its ASIC code etched is supposed to be "215-0910052." For the RX 580, the real one, aka "Polaris 20 XTX," the code etched is "215-0910038." Thanks to GamersNexus' high-resolution filming, our curator was able to spot the ASIC code for "Polaris 20 XL" on the Dataland card's GPU. This confirms that AMD merely took an RX 570 and gave it a different device ID to create the RX 580 2,048 SP, leaving consumers to wade through the confusion.
Return to Keyword Browsing