Prices of the two top crypto-currencies with DIY and small-scale miners, Ethereum and Bitcoin, dropped to yearly lows Monday, with Ethereum falling just a touch below USD $140, and Bitcoin at $4,700. This is in stark contrast to January, when Bitcoin scraped $20,000, making it among the most valuable "currencies" in human history. The direct impact of the crypto-currency slide falls on graphics card prices, at least for currencies which are viable to mine with graphics cards.

Across the board, new graphics card prices are at record lows for the year, with AMD's flagship Radeon RX Vega 64 going for as low as $399 brand-new. These cards were priced upwards of $1,500 and barely available this January. The RX 580, which was priced upwards of $700 in January, can be had for under $200. Prices of NVIDIA "Pascal" graphics cards are similarly low, with the GTX 1070 Ti going for under $400. For whatever strange reason, the GTX 1080 Ti is still marked up, selling for prices on par with RTX 20-series SKUs such as the RTX 2080. You can also expect a torrent of used graphics cards on E-bay and tech forums.

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.

AMD today announced the AMD Radeon Instinct MI60 and MI50 accelerators, the world's first 7nm datacenter GPUs, designed to deliver the compute performance required for next-generation deep learning, HPC, cloud computing and rendering applications. Researchers, scientists and developers will use AMD Radeon Instinct accelerators to solve tough and interesting challenges, including large-scale simulations, climate change, computational biology, disease prevention and more.

"Legacy GPU architectures limit IT managers from effectively addressing the constantly evolving demands of processing and analyzing huge datasets for modern cloud datacenter workloads," said David Wang, senior vice president of engineering, Radeon Technologies Group at AMD. "Combining world-class performance and a flexible architecture with a robust software platform and the industry's leading-edge ROCm open software ecosystem, the new AMD Radeon Instinct accelerators provide the critical components needed to solve the most difficult cloud computing challenges today and into the future."

AMD today held its "New Horizon" event for investors, offering guidance and "color" on what the company's near-future could look like. At the event, the company formally launched its Radeon Instinct MI60 GPU-based compute accelerator; and disclosed a few interesting tidbits on its next-generation "Zen 2" mircroarchitecture. The Instinct MI60 is the world's first GPU built on the 7 nanometer silicon fabrication process, and among the first commercially available products built on 7 nm. "Rome" is on track to becoming the first 7 nm processor, and is based on the Zen 2 architecture.

The Radeon Instinct MI60 is based on a 7 nm rendition of the "Vega" architecture. It is not an optical shrink of "Vega 10," and could have more number-crunching machinery, and an HBM2 memory interface that's twice as wide that can hold double the memory. It also features on-die logic that gives it hardware virtualization, which could be a boon for cloud-computing providers.

Last August Chinese pC maker Zhongshan Subor announced a mysterious new console/PC hybrid called Subor Z+ with an interesting spec sheet. The most intriguing part of that machine was none other than a new AMD SoC custom with the code name 'Fenghuang/FireFlight'. Based on the Zen architecture instead of the Jaguar used in consoles such as the Xbox One X or PS4 Pro, this SoC has a CPU with 4 cores and 8 threads at 3.0 GHz a Vega-based GPU with 24 CUs at 1300 MHz, 8 GB GDDR5, 128 GB SSD and 1 TB HDD.

The preliminary tests that we could see thanks to DigitalFoundry have now been completed with a new series of benchmarks from a Chinese YouTube user in which we can see the Subor Z+ running different Windows games at more than 60 fps in some of them. The graphics power sits between a RX 570 and a GTX 1060 according to the content producer, and among the results we have different scores showing how far this can go. For example, Fire Strike Extreme (486 points), Time Spy (3288), Tomb Raider (74.81 fps without clarifying graphic config), Cinebench (110/581) or PUBG, which was running at around 50-55 fps at 1080p and with low level of detail.

AMD Investor Relations will host a "Next Horizon" event on November 6th, and although there is no confirmation on what products will be announced there, the title alone makes us think about AMD's Zen 2 architecture. The company has just explained that on that day their executives will "discuss the innovation of AMD products and technology, specifically designed with the datacenter on industry-leading 7 nm process technology". AMD announced Ryzen and quite a lot of details about the Zen's processors on their last "Horizon" event, so it seems plausible that the incoming event will be perfect to talk about its next-gen architecture. That focus on the 7 nm process technology will probably make AMD talk about their new Vega graphics, but it seems end users will have to wait, as datacenters come first.

Blackmagic Design today announced the Blackmagic eGPU Pro, an external graphics processor featuring the blazingly fast AMD Radeon RX Vega 56 graphics processor. Designed to accelerate pro creative software such as DaVinci Resolve, 3D games and VR, the Blackmagic eGPU Pro delivers nearly twice the performance of the original Blackmagic eGPU model and up to 22x faster performance than the built-in graphics on a 13-inch MacBook Pro.

The Blackmagic eGPU Pro features a built-in AMD Radeon RX Vega 56, two Thunderbolt 3 ports, a new DisplayPort for connecting 5K displays, HDMI 2.0, 85W of charging power and four USB 3.1 connections. Designed in collaboration with Apple, the integrated design brings cutting-edge workstation-class graphics processing and computational acceleration to customers working in professional video, playing 3D games or using the latest virtual reality software.

Today Apple has introduced its new iPad Pro and has resurrected both the MacBook Air, now with Retina display, and the Mac mini. In addition to all these new announcements, there's another one the company didn't talk about at the event: an update for the MacBook Pro that will now feature AMD Radeon Pro Vega graphics chips. According to Apple, this will allow a 60% improvement in performance over the Radeon Pro 560X, the most powerful GPUs available to date for the MacBook Pro.

These professional-oriented chips are manufactured on a 14 nm process, this is not the 7 nanometer Vega 20 that's expected to be released later this year for the enterprise space. The GPU is codenamed "Vega 12" and comes with HBM2 memory, which helps reduce space requirements in a notebook, compared to traditional GDDR5 memory. Vega Pro 20 in the MacBook Pro has 20 CUs (1,280 shaders), Vega Pro 16 has 16 CUs (1,024 shaders). Both MacBook Pro configurations will be available on November 14th at a price yet to be determined.

AMD "Vega 20" is a new GPU based on existing "Vega" graphics architecture, which will be fabbed on the 7 nanometer silicon fabrication process, and bolstered with up to 32 GB of HBM2 memory across a 4096-bit memory interface that's double the bus-width of "Vega 10". AMD CEO Lisa Su already exhibited a mock-up of this chip at Computex 2018, with an word that alongside its "Zen 2" based EPYC enterprise processors, "Vega 20" will be the first 7 nm GPU. AMD could still make good on that word, only don't expect to find one under your tree this Holiday.

According to GamersNexus, the first "Vega 20" products won't launch before the turn of the year, and even in 2019, one can expect product launches till the end of Q1 (before April). GamersNexus cites reliable sources hinting at the later-than-expected arrival of "Vega 20" as part of refuting alleged "Final Fantasy XV" benchmarks of purported "Vega 20" engineering samples doing rounds on the web. Lisa Su stressed the importance of data-center GPUs in AMD's Q3-2018 earnings call, which could hint at the possibility of AMD allocating its first "Vega 20" yields to high-margin enterprise brands such as Radeon Pro and Radeon Instinct.

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

Following the release of theQ3 financial results by AMD, the stock market was quick to respond to less-than-expected operating income and market share numbers with a ~9.2% drop in share price before the markets closed. This was then followed by fervent after-hours trading resulting an even bigger drop to a share price of $17.88 at the time of this post, compared to the starting value of $25.04 earlier today. The small hike and drop after-hours also indicates some enterprising parties made use of the lower share values to their profit.

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

Arcturus is the fourth brightest star in the night sky, and could be the a new GPU architecture by AMD succeeding "Navi," according to a Phoronix report. The codename of Navi-successor has long eluded AMD's roadmap slides. The name "Arcturis" surfaced on Phoronix community forums, from a post by an AMD Linux liaison who is a member there. The codename is also supported by the fact that AMD is naming its GPU architectures after the brightest stars in the sky (albeit in a descending order of their brightness). Polaris is the brightest, followed by Vega, Navi, and Arcturus.

AMD last referenced the Navi-successor on a roadmap slide during its 2017 Financial Analyst Day presentation by Mark Papermaster. That slide mentioned "Vega" to be built on two silicon fabrication processes, 14 nm and "14 nm+." We know now that AMD intends to build a better-endowed "Vega" chip on 7 nm, which could be the world's first 7 nm GPU. "Navi" is slated to be built on 7 nm as the process becomes more prevalent in the industry. The same slide mentions Navi-successor as being built on "7 nm+," which going by convention, could refer to an even more advanced process than 7 nm. Unfortunately, even in 2017, when the industry was a touch more optimistic about 7 nm, AMD expected the Navi-successor to only come out by 2020. We're not holding our breath.

Remember the SMACH Z? Me neither. It was a long attempt in the making, with multiple Kickstarter campaigns that finally resulted in an actual product coming to market later this year. The SMACH Z is a handheld gaming PC with an x86 processor, that was originally supposed to use a 5" 720p screen powered off an AMD G-series SoC (System on a Chip). It was then updated to use an AMD Merlin Falcon (Excavator) R-Series RX-421BD clocked at 2.1 GHz SoC with an integrated Radeon R7 series GPU at 800 MHz to run a 6" 1080p display, that was in turn embedded in a handheld gaming console, effectively making it a portable gaming PC. Perhaps it was a good thing that the product took its time, since they have now decided to use updated internals for the final product- once more from AMD- in the form of the Ryzen Embedded V1605B SoC with AMD Radeon Vega 8 graphics.

eBOM reports that AMD has announced it will be showcasing the SMACH Z in their booth presence at the Tokyo Game Show which commences later this week. This marks yet another gaming platform that AMD will be powering, although it is less powerful than the other ones. The SMACH Z isavailable for pre-order in three different variants (Z, Z Pro, and Z Ultra) which have different starting configurations, but can be customized as with most pre-built PCs. All variants can run off the Linux-based SMACH OS or Windows 10, retain the 6" 1080p touch screen, support up to 16 GB of dual channel DDR4 memory and 256 GB of solid state storage, and have an optional camera as well. Prices begin at $699 and go up to $1199, with a 10% discount for pre-order for the console expected to be available December, 2018. For those interested, there are some preliminary benchmarks released by SMACH from earlier this year.

TechPowerUp today released the latest version of TechPowerUp GPU-Z, the popular graphics subsystem information and diagnostics utility. Version 2.11.0 introduces support for NVIDIA GeForce RTX 20-series "Turing" graphics cards, including the RTX 2080 Ti, RTX 2080, and RTX 2070. Support is also added for a few exotic OEM variants we discovered over the months, including GTX 750 Ti (GM107-A), GTX 1050 Ti Mobile 4 GB, Quadro P1000, Tesla P100 DGXS, GeForce 9200. From the AMD stable, we add support for "Vega 20," "Fenghuang" semi-custom SoC for Zhongshan Subor, Ryzen 5 Pro 2500U, 5 Pro 2400G, 3 Pro 2200G, 3 Pro 2300U, 3 2200GE, Athlon 200GE, and Embedded V1807B. Intel UHD 610, UHD P630 (Xeon), Coffee Lake GT3e (i5-8259U), are now supported.

Among the new features are system RAM usage sensors, temperature monitoring offsets for AMD Ryzen Threadripper 2000 series processors, and the ability to identify USB-C display output, GDDR6 memory standard, and 16 Gbit density memory chips. Several under-the-hood improvements were made, including WDDM-based memory monitoring for AMD GPUs, replacing ADL sensors that tend to be buggy. GPU-Z also cleans up QueryExternal files from your Temp folder. Grab GPU-Z from the link below.DOWNLOAD: TechPowerUp GPU-Z v2.11.0

The change-log follows.

xGMI (inter-chip global memory interconnect) is a cable-capable version of AMD's Infinity Fabric interconnect. A line of code in the latest version of AMDGPU Linux drivers reveals that "Vega 20" will support xGMI. This line tells the driver to check the state of xGMI link. A practical implementation of this could be inter-card high-bandwidth bridge connectivity that would otherwise saturate the PCI-Express host bus; similar to NVIDIA's usage of the new NVLink bridge for Quadro and Tesla products based on its "Volta" and "Turing" GPU architectures.

By no means should xGMI and NVLink implementations be interpreted as a coming back of multi-GPU to the gaming space. There are still no takers for DirectX 12 multi-GPU, and fewer AAA games support SLI or CrossFire. Even at higher resolutions/refresh-rates, existing SLI/CrossFire physical-layer standards have sufficient bandwidth for multi-GPU. The upcoming GeForce RTX 2000 graphics cards feature a new multi-GPU connector that's physically NVLink, but this is probably an attempt by NVIDIA to discard the legacy SLI bus and minimize redundant interfaces on its silicon. The TU102 and TU104 chips are implemented in the enterprise segment with the Quadro RTX family. The main application of xGMI/NVLink is to make multi-GPU hardware setups abstract to deep-learning software, so hardware can scale in the background with memory access spanning multiple GPUs. "Vega 20" will be launched in Radeon Pro and Radeon Instinct avatars late-2018.

AMD is giving finishing touches to its Athlon Pro 200GE socket AM4 SoC, which it could position against Intel's $50-ish Celeron LGA1151 SKUs. Leaked slides by PCEva reveals that it's a heavily cut-down 14 nm "Raven Ridge" die. For starters, unlike previous-generation Athlon-branded products on platforms such as FM2, the Athlon 200GE won't lack integrated graphics. Only 3 out of 11 Vega NGCUs will be enabled, translating to 192 stream processors, which should be enough for desktop, 2D, and video acceleration, but not serious gaming, even at low resolutions.

The CPU config is 2-core/4-thread, with 512 KB L2 cache per core, and 4 MB shared L3 cache. The CPU is clocked at 3.20 GHz, with no Precision Boost features. You still get GuardMI commercial-grade hardware security features. There is a big catch with one of its uncore components. The PCIe root-complex only supports PCI-Express 3.0 x4 out of your motherboard's topmost x16 slot, not even x8. Ryzen "Raven Ridge" APUs already offer a crippled x8 connectivity through this slot. AMD claims that the Athlon 200GE will be "up to 19 percent faster" than Intel Pentium G4560 at productivity work. When it launches on 6th September with market availability from 18th September, the Athlon Pro 200GE will be priced at USD $55.

AMD today at VMworld in Las Vegas announced their new, high-density computing, dual-GPU Radeon Pro V340 accelerator. This graphics card (or maybe accelerator) is based on the same Vega that makes AMD's consumer graphics card lineup, and crams its dual GPUs into a single card with a dual-slot design. 32 GB of second-generation Error Correcting Code (ECC) high-bandwidth memory (HBM) greases the wheels for the gargantuan amounts of data these accelerators are meant to crunch and power through, even as media processing requirements go through the roof.

AMD is giving final touches to the new Radeon Pro WX 8200 professional graphics card. Launched over a year following the Radeon Pro WX 9100, the WX 8200 has a leaner feature-set, while continuing to be based on AMD's current IP. The card still uses the 14 nm "Vega 10" MCM, but with a core-config akin to that of the RX Vega 56. You get 56 NGCUs working out to 3,584 stream processors, 224 TMUs, 64 ROPs, and a 4096-bit wide HBM2 memory interface, handling 16 GB of memory on this card. The air-cooled card also has a leaner connectivity load-out, with just four mini-DisplayPort 1.4 connectors (the WX 9100 comes with six). Its 8-pin + 6-pin connectors are positioned at the rear-end to be SSI workstation-friendly. The card surfaced on CompuBench database, in which its performance numbers are only slightly behind those of the WX 9100, but significantly better than the "Polaris 20" based WX 7100. AMD is expected to launch this card at SIGGRAPH 2018.

One of the first Intel NUC (next unit of computing) mini PCs to feature completely discrete GPUs (and not MCMs of CPUs and GPUs), the "Crimson Canyon" NUC8i3CYSM and NUC8i3CYSN, are up for pre-order. The former is priced at USD $529, while the latter goes for $574. The two combine Intel's 10 nm Core i3-8121U "Cannon Lake" SoC with AMD Radeon 540 discrete GPU. Unlike the "Hades Canyon" NUC, which features an MCM with a powerful AMD Radeon Vega M GPU die and a quad-core "Kaby Lake" CPU die; the "Crimson Canyon" features its processor and GPU on separate packages. The Radeon 540 packs 512 stream processors, 32 TMUs, and 16 ROPs; with 2 GB of GDDR5 memory.

All that's differentiating the NUC8i3CYSM from the NUC8i3CYSN is memory. You get 4 GB of LPDDR4 memory with the former, and 8 GB of it with the latter. Both units come with a 2.5-inch 1 TB HDD pre-installed. You also get an M.2-2280 slot with PCIe 3.0 x4 wiring, and support for Optane caching. Intel Wireless-AC 9560 WLAN card handles wireless networking, while an i219-V handles wired. Connectivity includes four USB 3.0 type-A ports, one of which has high current; an SDXC card reader, CIR, two HDMI 2.0 outputs, and 7.1-channel HD audio. The NUC has certainly grown in size over the years. This one measures 117 mm x 112 mm x 52 mm (WxDxH). An external 90W power-brick adds to the bulk.

Chinese PC maker Zhongshan Subor believes that there is space for a class of devices between game consoles and gaming desktops, targeted at Chinese gamers that game a lot online, and won't mind a little productivity on the side. The same class of people are repulsed by the idea of gaming desktops from traditional OEMs, which tend to be overpriced; and don't want to burn their hands building their own PC. For them, there's a new console-desktop; which runs common PC OS, plays PC versions of games, and runs PC apps, while exhibiting some characteristics of a console (perhaps a dashboard, and a highly customized user-interface stack), called simply SUBOR.

A part of what makes SUBOR affordable compared to OEM gaming desktops is because every component is purpose-built, including the SoC at the heart of it. This semi-custom SoC is codenamed "Fenghuang." The chip is a cut above the one that powers the PS4 Pro or Xbox One X. It combines a 4-core/8-thread CPU based on AMD's latest "Zen" architecture, compared to the low-power "Jaguar" derivatives that power the fastest consoles. The CPU runs at up to 3.00 GHz of clocks, and has 4 MB of L3 cache. The GPU is equally impressive: based on "Vega," it packs 24 NGCUs, translating to 1,536 stream processors, and the latest feature-set, including DirectX 12 and Vulkan. The GPU engine ticks at up to 1.30 GHz. 8 GB of GDDR5 memory across a 256-bit wide interface, is hardwired to the SoC (no memory expansion). The SUBOR will be unveiled at China Joy 2018.

AMD in its Q2-2018 investors conference call dropped more hints at when it plans to launch its 3rd generation Ryzen processors, based on its "Zen2" architecture. CEO Lisa Su stated in the Q&A session that rollout of 7 nm Ryzen processors will only follow that of 7 nm EPYC (unlike 1st generation Ryzen preceding 1st generation EPYC). What this effectively means is that the fabled 16-core die with 8 cores per CCX won't make it to the desktop platform any time soon (at least not in the next three quarters, certainly not within 2018).

AMD CEO touched upon the development of the company's 7 nm "Rome" silicon, which will be at the heart of the company's 2nd generation EPYC processor family. 2nd generation EPYC, as you'd recall from our older article, is based on 7 nm "Zen2" architecture, and not 12 nm "Zen+." 3rd generation Ryzen is expected to be based on "Zen2." As of now, the company is said to have completed tape-out of "Rome," and is sending samples out to its industry partners for further testing and validation. The first EPYC products based on this will begin rolling out in 2019. The 7 nm process is also being used for a new "Vega" based GPU, which has taped out, and will see its first enterprise-segment product launch within 2018.

As AMD is moving closer towards completing its staggered Ryzen 2000 series' launch, first benchmarks and silicon photos have surfaced. AMD's Ryzen 3 2300X is a quad-core solution that leverages the Zen+ architecture on the 12 nm process, improving performance and power consumption over the original Ryzen 3 1300X. Alongside the new CPU line, AMD is also expected to refresh its chipset offerings, with a revised B450 superseding the B350 chipset - though users can drop in their Ryzen 2000 series processors on 300-series chipsets, provided they have the adequate BIOS already installed.

The Ryzen 3 2300X, paired with a BIOSTAR X370 motherboard, was put through its paces under CPU-Z (where it scored 509 and 2020 points in the single and multi-thread benchmarks respectively), as well as in Cinebench (where it scored 690 points). The 2300X can seemingly boost up to 4.2 GHz without any manual overclocking from its 3.5 GHz base clock - an improvement of around 500 MHz in the XFR-enabled boost over its predecessor, which only hit 3.7 GHz.

Samsung has reportedly doubled its manufacturing output of HBM2 (high-bandwidth memory 2) stacks. Despite this, the company may still fall short of the demand for HBM2, according to HPC expert Glenn K Lockwood, Tweeting from the ISC 2018, the annual HPC industry event held between 24th to 28th June in Frankfurt, where Samsung was talking about its 2nd generation "Aquabolt" HBM2 memory, which is up to 8 times faster than GDDR5, with up to 307 GB/s bandwidth from a single stack.

While HBM2 is uncommon on consumer graphics cards (barring AMD's flagship Radeon RX Vega series, and NVIDIA's TITAN V), the memory type is in high demand with HPC accelerators that are mostly GPU-based, such as AMD Radeon Instinct series, and NVIDIA Tesla. The HPC industry itself is riding the gold-rush of AI research based on deep-learning and neural-nets. FPGAs, chips that you can purpose-build for your applications, are the other class of devices soaking up HBM2 inventories. The result of high demand, coupled with high DRAM prices could mean HBM2 could still be too expensive for mainstream client applications.

ASRock, which is the latest company to extend its product portfolio to graphics cards, has announced that they will be offering their AMD Phantom series of graphics cards in the EMEA region (Europe, Middle-East and Africa) starting July 1st. The roll-out should see the Polaris-based graphics cards being introduced first, since product codes for the Vega variants haven't been made known yet. With demand from miners relatively cooled with lower (and lowering still) cryptocurrency values, perhaps ASRock has decided that stock of their Phantom series is enough now to fulfill orders from these additional regions.

Back at Computex, AMD showed a demo of their Vega 20 graphics processor, which is produced using a refined 7 nanometer process. We also reported that the chip has a twice-as-wide memory interface, effectively doubling memory bandwidth, and alsomaximum memory capacity. The smaller process promises improvements to power efficiency, which could let AMD run the chip at higher frequencies for more performance compared to the 14 nanometer process of existing Vega.

As indicated by AMD during Computex, the 7 nanometer Vega is a product targeted at High Performance Compute (HPC) applications, with no plans to release it for gaming. As they clarified later, the promise of "7 nanometer for gamers" is for Navi, which follows the Vega architecture. It's even more surprising to see AOTS results for a non-gaming card - my guess is that someone was curious how well it would do in gaming.