As global market changes spur demand for augmented reality (AR) technology, there is an increasing need for innovations that combine the best technologies in CPU, GPU and machine learning into a single SOC (system on chip) to allow for the creation of the most demanding AR experiences while maintaining power efficiency.

Magic Leap today announced it is partnering with AMD on an AR technology solution that includes a semi-custom SOC to enable enterprise users to re-imagine and transform how virtual content and information is visualized and merged with real-world environments.

AMD at its Computex event shed some light on its IP partnership with Samsung. We already knew this was going to be a closer collaboration than most IP licensing deals, as AMD themselves announced this would be a semi-custom solution designed between both companies. AMD CEO Lisa Su described the technology to be embedded in the upcoming Samsung Exynos SoC as being based on RDNA2 - but this likely is just a marketing and clarity perspective on AMD's technology being implemented, since between the design of RDNA2 and the announcement of the Samsung partnership a lot of water has necessarily run under AMD's graphics IP bridge.

Lisa Su did however confirm that two key RDNA2 technologies will find their way into Samsung's Exynos: Variable Rate Shading (VRS) and Raytracing. This isn't he first time VRS has made an appearance on a mobile SoC - it's already been implemented by Qualcomm in the Adreno 660 GPU (part of the Snapdragon 888 SoC design). However, Raytracing does seem to be a first for the SoC market, and Samsung might just edge out competition in its time to market with this technology. more details will certainly be shared as we get closer to the fabled AMD-partnered Exynos release.

AMD finally made a big announcement on its ambitious FidelityFX Super Resolution (FSR) technology, the company's rival to NVIDIA's popular DLSS. Much like it, FSR aims to significantly improve gaming performance with minimal loss in image quality, through a sophisticated supersampling algorithm. At this point, AMD did not detail the nuts and bolts of the feature, but mentioned how the feature could look to gamers.

There are four FSR presets typically available to a supported game—Ultra Quality, Quality, Balanced, and Performance, which AMD claims offer performance gains of 59% for "Ultra Quality," 102% for "Quality," 153% for "Balanced," and 206% for "Performance." These should come particularly handy when playing games with raytracing on; and were measured on "Godfall" with RX 6800 XT, with 4K "epic" preset, and raytracing enabled. As of now, the company is working with over 10 game studios and game engine developers to integrate FSR, and the technology is expected to support "over 100 CPUs and GPUs."Update Jun 22nd: We have now posted our in-depth review of AMD Radeon FidelityFX Super Resolution (FSR).

The FSR slide-deck follows.

AMD today released the Radeon RX 6000M series mobile graphics lineup, based on the RDNA2 graphics architecture. These GPUs offer full DirectX 12 Ultimate readiness, including real-time raytracing capability. The lineup is led by the Radeon RX 6800M, followed by the RX 6700M, and the RX 6600M. The RX 6800M and RX 6700M are based on the 7 nm "Navi 22" silicon, while the RX 6600M debuts the "Navi 23" silicon. The RX 6800M appears to be maxing out the "Navi 22" silicon, much like the desktop RX 6700 XT. It features 40 RDNA2 compute units, amounting to 2,560 stream processors; game clocks of up to 2.30 GHz, 12 GB of GDDR6 memory across a 192-bit wide memory interface, and 96 MB of Infinity Cache. The RX 6700M is slightly cut down, with 36 compute units (2,304 stream processors), the same 2.30 GHz game clocks, 10 GB of video memory possibly across a 160-bit wide memory bus, and 80 MB of Infinity Cache.

The new RX 6600M debuts the 7 nm "Navi 23" silicon, with 28 RDNA2 compute units, game clocks of 2177 MHz, 8 GB of GDDR6 memory across a 128-bit wide memory bus, and 32 MB of Infinity Cache. All three chips feature Smart Access Memory (resizable BAR), and support for AMD SmartShift, a feature that load-balances the discrete GPU with an AMD iGPU. AMD claims that the RX 6800M and RX 6700M are fit for 1440p gaming, with the RX 6800M beating the RTX 2070 Notebook by anywhere between 40-70%, and 120 FPS in a large selection of e-sports titles. The company also claims that the RX 6800M beats the GeForce RTX 3080 8 GB by 14-39%. The RX 6600M, meanwhile is shown matching the RTX 3060 6 GB, in AMD's tests. Notebooks powered by AMD Radeon RX 6000M discrete graphics are shipping now.The graphics press-deck follows.

AMD today announced the launch of its first Ryzen 5000 series desktop processors with integrated graphics, under the Ryzen 5000G and Ryzen Pro 5000G lines. These processors are based on the 7 nm "Cezanne" silicon, featuring up to 8 CPU cores based on the "Zen 3" microarchitecture, an iGPU based on the "Vega" graphics architecture with up to 8 compute units, but updated display- and media-acceleration engines; 512 KB of L2 cache per core, and 16 MB of L3 cache that's shared between all eight cores. Built in the Socket AM4 package, the processors are compatible with AMD 500-series chipset motherboards. The chips feature PCI-Express Gen 3 downstream I/O.

The consumer Ryzen 5000G series include the Ryzen 7 5700G, and the Ryzen 5 5600G. The 5700G features an 8-core/16-thread CPU, clock speeds of 3.80 GHz, with up to 4.60 GHz boost, and all 8 iGPU compute units being unlocked with up to 2.00 GHz engine clocks. The 5600G, on the other hand, has a 6-core/12-thread CPU clocked at 3.90 GHz, with up to 4.40 GHz boost, and 7 iGPU compute units with up to 1.90 GHz engine clocks. Both chips have their TDP rated at 65 W. AMD claims that the 5700G beats the Core i7-11700 in a variety of content creation and iGPU gaming tasks, as shown in the graphs below; and the iGPU is capable of 1080p e-sports gaming. The 5700G is priced at USD $359, and the 5600G goes for $259. Both chips are available from August 5, 2021.

AMD CEO Dr Lisa Su takes centerstage to demonstrate the latest from AMD. These include announcements from nearly all of the company's business lines, including Ryzen processors, EPYC enterprise processors, Radeon graphics, and more.02:14 UTC: AMD is all about high-performance - Dr Su02:15 UTC: Nearly 100 EPYC based server solutions, and over 400 EPYC-powered cloud instances, by 2022

ASUS teased what is possibly its final round of Socket AM4 motherboards based on the AMD X570 chipset. The boards are based on the X570 chipset with the latest AGESA update that runs the chipset cooler, so thay can made do with fanless heatsink cooling. The teaser pic reveals at least four models—one based in the coveted ProArt line of creator motherboards; one from the TUF Gaming line of value-ended gaming motherboards; one form the ROG Strix series of premium gaming motherboards; and the last from the ROG Crosshair series of enthusiast/overclocking motherboards.

The motherboard in the bottom-right quadrant isn't the Crosshair VIII Dark Hero, but very likely a next-gen Crosshair Formula product. The bottom-left board could be a successor to the ROG Strix X570-E Gaming. The top-right board could be a TUF Gaming X570 Pro successor; while the top-left could be an all new product based in the ProArt series.

Update May 31st: ASUS clarified in a Facebook post that these motherboards use the same X570 chipset, but take advantage of the latest AGESA firmware that lowers TDP of the chipset just enough for motherboard designers to use fanless heatsinks.

Leading global motherboard manufacturer, ASRock, is proud to announce its latest X570S & B550 PG Riptide motherboards for AMD Ryzen AM4 desktop processors. "Riptide is named after a specific kind of water current with strong wave that occurs in the ocean. Riptide is unapparent, yet strong, fast and carries a powerful punch; this is the design philosophy of ASRock PG Riptide series motherboards" Said Chris Lee, General Manager of ASRock motherboard & gaming peripherals business unit.

The Riptide is a new crew of Phantom Gaming series, these stylishly PG Riptide series motherboards are armed to the teeth with gear designed to fulfill gamers everyday needs, without biting into the bank account unlike other similarly spec'd, high-end motherboards.

AMD is preparing to switch things up a bit with its upcoming AM5 platform. The new platform is said to bring significant changes to the design of the socket and the CPU package, where we will see some new design choices and decisions. For starters, all of the processors made for the AM5 platform will come in a land grid array (LGA) configuration, very similar to that of Intel. Thanks to the rendering of ExecutableFix, we got to see exactly how will the new LGA design look like. And today, we get to see more details of the AMD's upcoming Raphael processor's integrated heat spreader (IHS) design.

The IHS serves the purpose of spreading the heat away from the die and dissipating it efficiently. However, IHS designs can sometimes be very interesting. According to this rendering from ExecutableFix, AMD's upcoming Raphael design, based on Zen 4 core, will feature a unique IHS design, which can be seen below.

Marvell today announced its new Bravera SC5 controller family, bringing unprecedented performance, best-in-class efficiency, and leading security features to address ever-expanding workloads in the cloud. The massive amount of data to be processed in cloud data centers is driving demand for faster and higher bandwidth storage in these environments. Marvell's Bravera SC5 SSD controllers address the critical requirements for scalable, containerized cloud storage infrastructure. By enabling the highest performing flash storage solutions, Marvell's controllers are poised to be the foundation for data centers that offer ultra-low latency, real-time applications while also providing cost-optimized, cloud-scale capacity.

As the industry's first SSD controllers to support PCIe 5.0 and NVMe 1.4b, Marvell's Bravera SC5 doubles the performance compared to PCIe 4.0 SSDs. This contributes to accelerated workloads and reduced latency, dramatically improving the user experience. In order to meet cloud service providers' stringent security requirements to ensure users' data is safe and protected, the controllers offer FIPS-compliant root of trust (RoT), AES 256-bit encryption and multi-key revocation. The new controllers are the first with a hardware-based Elastic SLA Enforcer to assure quality of service (QoS) and provide metering capabilities per customer to increase overall storage efficiency and utilization while lowering total cost of ownership (TCO).

Today, we have talked about AMD's upcoming Raphael lineup of processors in the article you can find here. However, it seems like the number of leaks on AMD's plans just keeps getting greater. Thanks to the "itacg" on Weibo, we have learned that AMD's Ryzen 8000 desktop series of processors are reportedly codenamed as Granite Ridge. This new codename denotes the Zen 5 based processors, manufactured on TSMC's 3 nm (N3) node. Another piece of information is that AMD's Ryzen 8000 series APUs are allegedly called Strix Point, and they also use the 3 nm technology, along with a combination of Zen 5 and Zen 4 core design IPs. We are not sure how this exactly works out, so we have to wait to find out more.

AMD's second processor microarchitecture on the Socket AM5 platform, the Ryzen 7000 "Raphael," could introduce a 20% IPC gain over its predecessor, according to a report by Moore's Law is Dead. The processor debuts the company's "Zen 4" microarchitecture, which clocks IPC gains over the rumored "Zen 3+" microarchitecture that the Ryzen 6000 "Rembrandt" processor debuts with, on Socket AM5. The upper limit of AMD's core-counts appear to remain at 16-core for the flagship part. With "Zen 4" CCDs (8-core chiplets) being built on 5 nm, the source predicts a 50% performance/Watt gain. The chips could also introduce AVX-512 support. The Ryzen "Raphael" processor is due for 2022.

AMD's next-generation HPC accelerator card, the Instinct MI200, is expected to launch later this year. CEO Dr Lisa Su, speaking at a financial event hosted by JPMorgan stated that the company would launch the next-generation of CDNA architecture this year. The card debuts the company's new CDNA2 compute architecture, and is on its way to supercomputers already announced. The Instinct MI200 HPC accelerator card is based on the new "Aldebaran" compute accelerator package, which is a multi-chip module of not just the compute silicon and memory dies; but one that has multiple compute dies.

We've known since last week that AMD's upcoming desktop processor socket, AM5, will be a land-grid array (LGA), much like Intel's desktop sockets; and today we have a first-look at what the land-grid will look like, courtesy of ExecutableFix, who first broke news of AM5 being an LGA of 1,718 pins. Below is a render of the AM5 contact pad (the underside of the processor). The 1,718 contacts span across the fiberglass substrate, with no socket island in the middle for ancillaries. All electrical ancillaries are located on the obverse side of the substrate, surrounding the die(s). The substrate area will remain 40 mm x 40 mm, so the processor package will be roughly of the same size as AM4. In comparison, Intel's upcoming LGA1700 package is expected to measure 37.5 mm x 45 mm (a rectangular substrate).

ExecutableFix put out a handful more details about the I/O of this socket. Apparently, AM5 is a pure-DDR5 platform, with no backwards compatibility with DDR4. The socket features a dual-channel DDR5 memory interface. The PCI-Express interface is PCI-Express 4.0, with the socket putting out 28 lanes in total. 16 of these go to the PEG slot(s), four to an M.2 NVMe slot, and possibly the remaining eight as chipset bus. Considering these are Gen 4, the next-generation X670 (X570 successor) chipset could have double the chipset-bus bandwidth compared to Intel Z590. A typical Socket AM5 chip, such as "Rembrandt," could feature a TDP of 120 W, going up to 170 W, according to the source.

AMD is in a constant process of processor development, and there are always new technologies on the horizon. Back in March of 2020, the company has revealed that it is working on new X3D packaging technology, that integrated both 2.5D and 3D approaches to packing semiconductor dies together as tightly as possible. Today, we are finally getting some more information about the X3D technology, as we have the first codename of the processor that is featuring this advanced packaging technology. According to David Schor, we have learned that AMD is working on a CPU that uses X3D tech with stacked dies, and it is called Milan-X.

The Milan-X CPU is AMD's upcoming product designed for data center usage. The rumors suggest that the CPU is designed for heavy bandwidth and presumably a lot of computing power. According to ExecutableFix, the CPU uses a Genesis-IO die to power the connectivity, which is an IO die from EPYC Zen 3 processors. While this solution is in the works, we don't know the exact launch date of the processor. However, we could hear more about it in AMD's virtual keynote at Computex 2021. For now, take this rumor with a grain of salt.

GIGABYTE Technology, one of the top global manufacturers of motherboards, graphics cards, and hardware solutions, announces today the latest AORUS Gen4 7000s Prem. SSD with up to 7 GB/s read speed while optimizing passive thermal dissipation, which promises no throttling under long-lasting operation. Through the SSD Tool Box application, users can have an instant control on overall operation of SSD.

AORUS Gen4 7000s Prem. SSD adopts the PCIe 4.0 NVMe M.2 interface and it equips the latest Phison E18 selected 8-channel controller, which provides users with ultimate random access rate, as well as the high speed 3D-TLC NAND Flash and SLC cache design that brings the PCIe 4.0 into full play. With the read speed up to 7 GB/s and write speed up to 6.85 GB/s, AORUS Gen4 7000s Prem. SSD can power up content creators, gamers, and users eager for extreme performance.

A reliable source with AMD and NVIDIA leaks, ExecutableFix has shared some interesting bits of early information on AMD's next-generation Socket AM5. Apparently this will be AMD's first mainstream-desktop socket that does away with pins on the processor package, shifting them to the motherboard, in a Land Grid Array (LGA) format. This won't be AMD's first client LGA, though, as it was the Quad FX platform from 2006, which used a pair of Socket F LGAs. Socket AM5 will have a pin-count of 1,718 pins, 18 more than Intel's upcoming Socket LGA1700, on which its 12th Gen Core "Alder Lake-S" is expected to be based.

AMD will give the I/O of its client desktop platform a major update, with the introduction of DDR5 memory. Socket AM5 processors are expected to feature a dual-channel DDR5 memory interface. With Intel "Alder Lake-S" implementing DDR5, too, you now know why every major memory manufacturer is unveiling their first DDR5 U-DIMM product development. Interestingly, the PCI-Express interface on Socket AM5 will remain PCI-Express 4.0, even though PCI-Express 5.0 is being rumored for "Alder Lake-S." The switch to PCI-Express 5.0 may not be significant from a graphics cards perspective immediately, but paves the way for next-gen M.2 NVMe SSDs with double the transfer-rates of current drives that use PCI-Express 4.0. AMD is developing the new 600-series chipset to do with its next-generation Socket AM5 processors.

A highly plausible looking AMD Radeon RX 6600 series graphics card is doing rounds on the web. The card is purportedly an AMD reference-design OEM-trim "Navi 23" board. We know from recent rumors that the 7 nm "Navi 23" silicon powers the upcoming Radeon RX 6600 XT and RX 6600. The picture only shows a portion of the card, the back-plate as viewed toward the rear I/O, but the bar-code sticker is unmistakable. The sticker reveals the OEM to be PC Partner, which is known to make all OEM and retail reference-design AMD Radeon graphics cards, which are marked "MBA" (made by AMD). You'll find a similar-looking bar-code sticker on all AMD reference-design cards, regardless of the AIB partner marketing it.

The bar-code sticker references "Navi 23 XT," which is very likely the Radeon RX 6600 XT. The card has 8 GB of GDDR6 memory, and its display outputs include one HDMI, and three DisplayPorts. Elsewhere in the picture, we get valuable insights into the design of the cooler, revealing that the card features an aluminium fin-stack heatsink with one or more axial fans (top-flow), rather than a channel-type lateral blower-type cooling solution. The "Navi 23" silicon is rumored to feature up to 32 RDNA2 compute units that amount to 2.048 stream processors, a PCI-Express 4.0 x8 host interface, much like the RX 5500 XT, and a 128-bit wide GDDR6 memory interface.

AMD today announced that AMD President and CEO Dr. Lisa Su will keynote COMPUTEX 2021, one of the leading global technology tradeshows focused on the theme of "Building Global Technology Ecosystems" in 2021. Dr. Su will present the AMD vision for the future of computing, including the growing adoption of AMD high-performance computing and graphics solutions in the keynote titled "AMD Accelerating - The High-Performance Computing Ecosystem." The digital keynote will be livestreamed at 10:00 AM (GMT+8) on Tuesday, June 1 and can be accessed on the COMPUTEX 2021 Hybrid platform as well as AMD.com.

AMD's roadmap for notebook processors from 2020 - 2022 has recently been leaked and it reveals some interesting information for the launch of Zen 3+ and Navi 2. AMD will release the Rembrandt "H" series for mobile workstations in 2022 manufactured on the 6nm node with Navi 2 graphics and a Zen 3+ core design. These chips will include PCIe 4.0, LPDDR5/DDR5, and USB 4 support and will come with a power target of 45 W while a 15 W lineup of U series processors will also be released with identical specifications. The roadmap also shows the launch of Dragon Crest processors for tablets and handheld devices in 2022 with Navi 2 graphics and Zen 2 core designs. AMD is also set to launch the Barcelo "U" series for ultrathin laptops with very similar specifications to Cezanne "U".

HP introduced its latest gaming hardware and software designed for today's gamers with the powerful OMEN 16 and OMEN 17, bright and customizable OMEN 25i Gaming Monitor, and community gaming with OMEN OASIS Beta feature in OMEN Gaming Hub. The company also debuted Victus by HP, its next-generation mainstream-level gaming PC portfolio, with a 16-inch laptop.

Gaming continues to be an outlet for entertainment and connecting with friends. Two out of three people are spending more time watching videos and gaming than they did prior to the pandemic, with one in four gaming three to four hours more and almost one in five gaming six to ten hours more a week6. HP's next-generation gaming portfolio is designed for both veteran gamers and enthusiast explorers to be entertained, connected, and empowered to progress in their favorite games.

As AMD's upcoming feature that rivals NVIDIA DLSS nears release, reportedly this June, a USPTO patent application sheds some light on its inner workings. In its November 2019 application, AMD describes the feature as "Gaming Super Resolution." The abstract points to what the feature essentially does—downscaling or upscaling images using various methods, with the goal of improving performance, without much loss in fidelity. "The present application provides devices and methods for efficiently super-resolving an image, which preserves the original information of the image while upscaling the image and improving fidelity. The devices and methods utilize linear and non-linear up-sampling in a wholly learned environment," the application reads.

The application emphasizes on using a combination of linear and non-linear upscaling methods to improve the fidelity of the lower-resolution render output to the user's display resolution, including leveraging a "wholly learned" AI deep-learning network. This would be a DNN that relies on ground-truth information to reconstruct some fidelity to the upscaled image. "The devices and methods include a gaming super resolution (GSR) network architecture which efficiently super resolves images in a convolutional and generalizable manner."

AMD has recently confirmed that the upcoming B2 stepping for Ryzen 5000 processors will only improve production and availability with no impact on performance. The new stepping will be deployed within the next 6 months and will be fully compatible with existing motherboards without the need for a BIOS update. We initially believed that the new revisions may bring small performance improvements similar to existing Ryzen XT products however with this recent confirmation from AMD we now know that this is not the case. AMD has not confirmed if they are preparing a potential Ryzen 5000XT series which would likely be the final release on the AM4 platform.

AMDAs part of our continued effort to expand our manufacturing and logistics capabilities, AMD will gradually move AMD Ryzen 5000 Series Desktop Processors to B2 Revision over the next 6 months. The revision does not bring improvements in terms of functionality or performance, furthermore, no BIOS update will be required.

Intel will detail its 12th Gen Core "Alder Lake" client and "Sapphire Rapids" server CPU microarchitectures at the Hot Chips 33 conclave, this August. In fact, Intel's presentation leads the CPU sessions on the opening day of August 23. "Alder Lake" will be the session opener, followed by AMD's presentation of the already-launched "Zen 3," and IBM's 5 GHz Z processor powering its next-gen mainframes. A talk on Xeon "Sapphire Rapids" follows this. Hot Chips is predominantly an engineering conclave, where highly technical sessions are presented by engineers from major semiconductor firms; and so the sessions on "Alder Lake" and "Sapphire Rapids" are expected to be very juicy.

"Alder Lake" is Intel's attempt at changing the PC ecosystem by introducing hybrid CPU cores, a concept introduced to the x86 machine architecture with "Lakefield." The processor will also support next-generation I/O, such as DDR5 memory. The "Sapphire Rapids" server CPU microarchitecture will see an increase in CPU core counts, next-gen I/O such as PCI-Express 5.0, CXL 1.1, DDR5 memory, and more.

AMD (NASDAQ: AMD) today announced that its Board of Directors approved a new share repurchase program. Under this program, the company intends to repurchase up to $4 billion of outstanding AMD common stock. AMD expects to fund repurchases through cash generated from operations which have been strengthened by the company's strong operational results.

"Today's announcement reflects our confidence in AMD's business and the successful execution of our multi-year growth strategy," said Dr. Lisa Su, AMD president and CEO. "Our strong financial results and growing cash generation enable us to invest in the business and begin returning capital to our shareholders." Under this program, which is designed to return value to AMD stockholders, offset dilution from stock issuances, and reduce share count over time, the company will repurchase stock in the open market. This repurchase program has no termination date and may be suspended or discontinued at any time.