DigiTimes is reporting, through "sources from the upstream supply chain", that AMD's current shortage of RX Vega cards to distribute to the retail market will continue at least until October. The tech reporting site says that sources are pointing towards the package integration of HBM2 memory (from SK Hynix or Samsung Electronics) and the Vega GPU (manufactured on Global Foundries' 14 nm FinFet) as being at fault here, due to low yield rates for this packaging effort. However, some other sources point towards the issue being with the packaging process itself, done by Advanced Semiconductor Engineering (ASE) through use of SiP technology. Whichever one of these cases may be, it seems the problem lies with AMD's choice to use HBM2 on their Vega graphics architecture.

As a footnote to its story, DigiTimes is also reporting that according to industry sources, NVIDIA has, in light of RX Vega's performance, decided to postpone the launch of Volta-based GPUs towards the first quarter of 2018.

It looks like AMD will combine its two latest intellectual properties, the "Zen" CPU micro-architecture, and the "Vega" graphics architecture into a single silicon after all, as reports citing leaked OpenCL tables confirm that the company's upcoming Ryzen "Raven Ridge" APU will feature graphics compute units (CUs) based on the "Vega" architecture. It's becoming increasingly clear, that "Raven Ridge" features a "Zen" CCX unit, and a "Vega" based graphics core with up to 12 NGCUs, making up 768 stream processors. The "Zen" CCX talks to the "Vega" graphics core using Infinity Fabric, the same interconnect used between two CCX units on the "Summit Ridge" silicon, and between two "Summit Ridge" dies on the Ryzen Threadripper MCM.

The "Raven Ridge" silicon will hence feature up to 4 CPU cores, with SMT enabling up to 8 threads, up to 8 MB of L3 cache, a "Vega" based graphics core with up to 12 NGCUs making 768 stream processors, a dual-channel DDR4 integrated memory controller, and the same integrated southbridge as "Summit Ridge," featuring two SATA 6 Gb/s ports, and USB 3.0 ports directly from the SoC. In addition, you get a PCI-Express 3.0 x16 interface for graphics, which can be split into two x8 for 2-way multi-GPU. The OpenCL listings speak about two distinct variants, one with 11 NGCUs, and another with 8. AMD plans to roll out the first "Raven Ridge" based products as Ryzen 5 series and Ryzen 7 series mobile APUs, with a desktop debut a little later.

ATI RX Vega cooler, Alphacool has the perfect cooling solutions for the start of the new AMD Vega graphics card generation. The NexXxoS GPX Vega Version now offers an improved backplate with a side shield to cover the PCB. This also improves its cooling performance, since heat is distributed more evenly over the front connection. If you use a graphics card with a NexXxoS GPX cooler and want to switch over to an AMD Vega, you'll be happy to hear about the corresponding upgrade kits for your cooler.

The Eiswolf GPX-Pro will still be an AIO solution, and will still come pre-filled with an integrated pump built around new "reverse flow" technology for whisper-quiet operation. The pure copper radiator from the well-known NexXxoS series with 120mm and a thickness of 45mm provides outstanding cooling performance.

Paraphrasing our own VSG, "So, this happened". AMD has gone out and done it: they've released a Beta driver specifically geared towards blockchain-based workloads, which should improve the company's GPU performance in generating money for miners. The driver is compatible with close to the entirety of AMD's GCN lineup - all the way from hot-from-the-foundry Vega to AMD's HD 7900 series. As AMD puts it, this is a driver solely purposed towards blockchain workloads - no gaming or graphics workloads (read, what graphics cards were originally meant to do) are officially supported in this release.

Apparently, AMD took it upon themselves to release this driver due to AMD's well documented DAG performance decrease for Ethereum mining hashrates. Specifically, according to Legit Reviews, the Radeon RX 480 went from an expected 14.8 MH/s at DAG #199 (down from 24.6 MH/s at DAG #130) to a prospective 24.8 MH/s DAG #199 performance according to Claymore's benchmark script. Performance improvements from the non-blockchain-geared driver release seem to stand at around 10-15%, which isn't too shabby from a single, Beta driver release.

AMD today has made available for early adopters the Crimson ReLive Edition 17.8.1 drivers. Users of other AMD graphics cards other than the newly released RX Vega 64 beware: these drivers are for exclusive use on those graphics cards.

For those early adopters who have a Vega 64 on their hands already, these drivers are for you. If you're currently on the fence on whether or not to make the plunge to a new red-powered graphics card, make sure to read our own resident W1zzard's reviews of AMD's latest foray into the high performance graphics processing market for both the RX Vega 56 and RX Vega 64 graphics cards. You might be surprised. Download the drivers from the link below.DOWNLOAD: AMD Radeon Software Crimson Relive Edition Radeon RX Vega Series Driver​

In a slightly anemic post on their website, Gigabyte has been the first of AMD's AIB partners to showcase a reference design RX Vega 56 graphics card. This was a silent addition to their website; no press releases have been sent out as of yet. There is only so much a company can say about their reference design graphics cards, though, absent of coming up with interesting phrases to sell the card's capabilities. Specifically, Gigabyte praised:

Next Gen Compute Units
These revamped nCUs (1 nCU = 64 stream processors) are designed to operate at incredible clock speeds and deliver extreme gaming experiences with the newest high resolution and high refresh rate monitors.

Trying to keep our community entertained and distracted from the growing pains and expectations of waiting for the death of AMD's imposed NDAs on Vega reviews is one of our missions. As such, while we know what you want are actual performance numbers, price/performance charts, and an in-depth, independent review, you'll not find such answers in this post. You will find, however, some interesting tidbits on AMD RX Vega designs. In this case, a triple-fan cooling solution for AMD's RX Vega 56 (the smaller Vega).

SAPPHIRE Technology has announced the launch of the much-anticipated SAPPHIRE Radeon Vega 64 enthusiast graphics cards. The Vega architecture boasts significant improvements focused on maximizing the performance. Vega cards are designed for enthusiasts seeking top-of-the-chart framerates in games of today and tomorrow - in Ultra details and VR.

SAPPHIRE Technology is introducing three Vega-powered models:

• SAPPHIRE Radeon RX Vega 64 8GB HBM2 Liquid Cooled
• SAPPHIRE Radeon RX Vega 64 8GB HBM2
• SAPPHIRE Radeon RX Vega 64 8GB HBM2 Limited Edition

It seems that AMD's RX Vega lineup won't be too far away from the norm, it seems. Street knowledge almost always says that it's the runner-up to the highest performing graphics card that is the more interesting in a price-performance ratio, and it seems that AMD knows this as well. Steve Burke from Gamer's Nexus has reported on AMD's NDA dates and the company's indications to reviewers on changing up the game leading up to reviews: they're asking that publications focus on the Vega 56 ahead of the halo Vega 64.

This might be somewhat bad news for those who wanted to see the Vega 64 compete in favorable terms with the GTX 1080; this decision by AMD is obviously geared towards making the best impact on the company's product line and image. The fact that AMD can offer a more compelling argument over the Vega 64 means that Vega 56 will probably have an easier battle in the $400 camp (if you can find it at those prices on launch, that is.)

Disclaimer: take this post with a bucket of salt. However, the information here, if true, could heavily impact AMD's RX Vega cards' stock at launch and in the subsequent days, so, we're sharing this so our readers can decide on whether they want to pull the trigger for a Vega card at launch, as soon as possible, or risk what would seem like the equivalent of a mining Black Friday crowd gobbling up AMD's RX Vega models' stock. Remember that AMD has already justified delays for increased stock so as to limit the impact of miners on the available supply.

The information has been put out by two different sources already. The first source we encountered (and which has been covered by some media outlets solo) has been one post from one of OC UK's staff, Gibbo, who in a forum post, said "Seems the hash rate on VEGA is 70-100 per card, which is insanely good. Trying to devise some kind of plan so gamers can get them at MSRP without the miners wiping all the stock out within 5 minutes of product going live."

EK Water Blocks, the Slovenia-based premium computer liquid cooling gear manufacturer has proven its market leadership once again by presenting Full Cover water blocks for the long awaited AMD Radeon Vega architecture based high-end graphics cards. Customers will be able to transform their GPU into a stunningly beautiful single slot graphics card and the water cooling block will allow it to reach higher frequencies, thus providing more performance during gaming or other GPU intense tasks.

EK-FC Radeon Vega
This water block directly cools the GPU, HBM2 memory, and VRM (voltage regulation module) as water flows directly over these critical areas thus allowing the graphics card and it's VRM to remain stable under high overclocks. EK-FC Radeon Vega water block features a central inlet split-flow cooling engine design for best possible cooling performance, which also works flawlessly with reversed water flow without adversely affecting the cooling performance. This kind of efficient cooling will allow your high-end graphics card to reach higher boost clocks, thus providing more performance during gaming or other GPU intense tasks. Moreover, such design offers great hydraulic performance allowing this product to be used in liquid cooling systems using weaker water pumps.

TweakTown has put forth an article wherein they claim to have received info from industry insiders regarding the upcoming Vega 56's performance. Remember that Vega 56 is the slightly cut-down version of the flagship Vega 64, counting with 56 next-generation compute units (NGCUs) instead of Vega 64's, well, 64. This means that while the Vega 64 has the full complement of 4,096 Stream processors, 256 TMUs, 64 ROPs, and a 2048-bit wide 8 GB HBM2 memory pool offering 484 GB/s of bandwidth, Vega 56 makes do with 3,548 Stream processors,192 TMUs, 64 ROPs, the same 8 GB of HBM2 memory and a slightly lower memory bandwidth at 410 GB/s.

The Vega 56 has been announced to retail for about $399, or $499 with one of AMD's new (famous or infamous, depends on your mileage) Radeon Packs. The RX Vega 56 card was running on a system configured with an Intel Core i7-7700K @ 4.2GHz, 16 GB of DDR4-3000 MHz RAM, and Windows 10 at 2560 x 1440 resolution.

In an interview, AMD's Chris Hook justified Vega's delayed release due to a wish to increase available stock for gamers who want to purchase the new high-performance architecture by AMD. In an interview with HardOCP, Chris Hook had this to say:

"Part of the reason it's taken us a little longer to launch Vega - and I'll be honest about that - is that we wanted to make sure we were launching with good volume. (...) Obviously we've got to compensate for things like coin-miners, they're going to want to get their hands on these. We believe we're launching with a volume that will ensure that gamers can get their hands on them, and that's what's important to us."

It appears that AMD tried their best to increase production and stock volumes so as to mitigate price fluctuations upon Vega's entry to the market due to above normal demand from cryptocurrency miners. The jury is still out on whether Vega will be an option for mining due to its exquisite architecture, however. Still, this sounds as good a reason as any to delay Vega for as long as it has been already. Just a few more days until we see what AMD managed with this one, folks. Check the video after the break.

In a bid to preempt sales of the Radeon Pro Vega Frontier Edition, and the Pro WX 9100, NVIDIA expanded the feature-set of its consumer-segment TITAN Xp graphics card, with certain features reserved for its Quadro family of graphics cards, through a driver update. NVIDIA is rolling out its latest GeForce software update, which adds professional features for applications such as Maya, unlocking "3X more performance" for the software.

Priced at USD $1,199, the TITAN Xp packs a full-featured "GP102" graphics processor, with 3,840 CUDA cores, 240 TMUs, 96 ROPs, and 12 GB of GDDR5X memory across the chip's 384-bit wide memory interface. At its given memory clock of 11.4 GHz (GDDR5X-effective), the card has a memory bandwidth of 547.6 GB/s, which is higher than the 484 GB/s of the Radeon Pro Vega Frontier Edition.DOWNLOAD: NVIDIA GeForce 385.12 for TITAN Xp

Ethereum is a strange little thing. When you open up your Blockfolio to look at how much you're valued right now, it can be as a fine bit of coffee in the morning, perking you up for the entire day, or a wrecking ball to your capitalist, speculative heart. However, even if you don't believe in the technology, there are many people who do believe: at least, in the future value of it. They believe it so much, really, that they're willing to rent entire airplanes to transport mining equipment (read graphics cards). And we're talking Boeing 747 here, not your average private jet (handy infographic on the pictures below, by the way.)

Ethereum's price fluctuations notwithstanding, which saw the currency soar from $10 at the beginning of the year to a historical high of $400 in mid-June, seems to have somehow settled around a $200 support level. At that value, it's still profitable to mine - even with the increased difficulty of the myriad of miners, dedicated or not, who have flooded towards the GPU-based workloads that support the cryptocurrency's POW (Proof of Work) design. And faith - or expectation of future value is so high, that mining conglomerates (the ones with the greatest running costs, but also pretty scalable profits - aren't willing to waste more idle time than they possibly can. Marco Streng, chief executive of Genesis Mining, told Quartz that "Time is critical, very critical. For example, we are renting entire airplanes, Boeing 747s, to ship on time. Anything else, like shipping by sea, loses so much opportunity."

AMD is reportedly scaling down efforts on its end to support and promote multi-GPU technologies such as CrossFire, and not in favor of open-standards such as DirectX 12 native multi-GPU, either. Speaking to GamersNexus, an AMD representative confirmed that while the new Radeon RX Vega family of graphics cards support CrossFire, the company may not allocate as many resources as it used to with older GPU launches, in promoting or supporting it.

This is keeping up with trends in the industry moving away from multi-GPU configurations, and aligns with NVIDIA's decision to dial-down investment in SLI. This also more or less confirms that AMD won't build a Radeon RX series consumer graphics product based on two "Vega 10" ASICs. At best, one can expect dual-GPU cards for the professional or GPU-compute markets, such as the Radeon Pro or Radeon Instinct brands.

AMD today is announcing the latest update to their Radeon Pro Hardware and Software, which brings with it enhanced features designed to fully take advantage of the company's new high-performance Vega graphics micro-architecture. Namely, AMD has announced the Radeon Pro WX 9100, the Radeon Pro SSG, and Radeon Vega Frontier Edition (already launched) along with new Radeon Pro Software for the same.

As per AMD, the Radeon Pro WX 9100 workstation graphics card is designed to excel in the most demanding media and entertainment, and design and manufacturing workloads. Delivering up to 12.3 TFLOPS of peak single precision compute performance, the Radeon Pro WX 9100 graphics card represents a new era of professional graphics capabilities fueled by powerful Next-Gen Compute Units3 with Rapid Packed Math and an Enhanced Geometry Pipeline which improves processing efficiencies. Compared to the AMD FirePro W9100, the Radeon Pro WX 9100 runs models more than twice as fast, delivering over 2.6X the peak throughput-per-clock.

Remember that awesome Vega Holocube that made its way around the web some time ago? How it looked like a über-cool tachometer of sorts for GPU utilization. Well, as you might have noticed, AMD's RX Vega pricing is extremely competitive in regards to the technology they offer on-board; this, coupled with AMD's play for a higher price-performance ratio than the competition, means that AMD is left with less wiggle room for bundling this kind of extras with their RX Vega graphics cards.

However, AMD has released a statement, which while confirming the sad news of no Holocube bundling or availability to accompany RX Vega's launch come August, leaves the door open for a later-in-time launch. The statement reads "AMD appreciates the excitement and curiosity surrounding the Radeon Holocube. The Radeon Holocube was developed as a prototype and at this time, it is one of very few that exist in the world. The Holocube will not be shipping with Radeon RX Vega in August." You can check some videos of the Holocube in action after the break.

It has been a huge weekend of product announcements and launches from AMD, which expanded not just its client computing CPU lineup on both ends, but also expanded its Radeon graphics cards family with both client- and professional-segment graphics cards. This article provides a brief summary of everything AMD launched or announced today, with their possible market-availability dates.

The first custom AIB partner graphics card that we have a chance to look at is none other than ASUS' ROG Strix. AS usual, everything about this particular offering from ASUS screams customization - from the purpose-built PCB and power delivery, to the oversized, triple-slot cooling design with three fans, and premium backplate design for better heat dissipation; all of these should greatly improve temps over Vega's reference design with better acoustics, at the same time. As with almost all AIB partner offerings, there will be two offerings based on this model, differing only in regards to out-of-box clock speeds.

ASUS' latest DirectCU III cooling system makes an appearance, combining Super Alloy Power II components and their Auto Extreme manufacturing technology. Max contact GPU technology makes its way here, as does FanConnect II, which provides hybrid-controlled fan headers and a comprehensive set of tuning options with GPU Tweak II to optimize system cooling and performance even further. As with most ASUS ROG products nowadays, the ROG Strix Vega 64 graphics card will feature support for ASUS AURA RGB LED. Display outputs include 2x HDMI (for VR systems), 2x DisplayPort and 1x DVI. No pricing was announced at time of writing, though you should count on this offering being near the top pricing bracket between AIB cards.

AMD had two press days over the weekend to cover a whole bunch of announcements- Ryzen Threadripper, RX Vega, Vega Pro and more. They provided details galore on the Vega microarchitecture, and the two RX Vega versions. Well, make that three now. AMD at Capcaicin SIGGRAPH 2017 also announced and showed off the RX Vega Nano.

Raja Koduri, Senior Vice-president of AMD's Radeon Technology Group, came up on stage minutes ago and handed over one of the very few working samples of this new card to Tim Sweeney, founder of Epic Games and Unreal Engine. The RX Vega Nano is an update to the R9 Nano from 2015 which was based off AMD's "Fiji" microarchitecture and was the then king of efficiency and small form factor support. We were only just talking about how RX Vega missed an opportunity with HBM2 to provide another mITX GPU and looks like AMD agreed.

AMD has been on a roll recently releasing new hardware and software products alike, but nothing has been as eagerly anticipated as RX Vega- their upcoming Radeon GPU flagship for gamers and PC enthusiasts alike. Today we are happy to be able to share some photographs we took of the retail RX Vega card ourselves, which in turn also provides some useful information to digest while we all await more.After the break, we have more pictures and information from other sources so be sure to read further.

AMD's Vega Frontier Edition was a release that seemingly left most users either scratching their heads in bewilderment or - more specifically - disappointed. Some of this disappointment seemed to stem from a desire to see the long-awaited RX Vega consumer graphics card performance in the wild - or at least snagging a preview of it. Alas, the Frontier Edition's gaming performance was a disappointment when one considers the expected performance of AMD's underlying hardware - 4096 Stream processors and 16 GB of HBM2 memory - as well as the fact that this is AMD's first high-performance architecture since the Fury line of graphics cards. But to be fair to AMD, they did warn us - the Frontier Edition isn't the right graphics card for gamers.

One of the points of contention for this new release was that AMD delivered a graphics card that straddled the prosumer equation - offering both Pro drivers for professional workloads, and a Gaming Mode which should allow developers to seamlessly jump from development mode to testing mode through a driver toggle. However, when used at launch of the Frontier Edition - and even now - this toggle is little more than a dud. Mostly, what it does is remove the Wattman control panel.

Nordic Hardware is running a piece where they affirm their sources in the Swedish market have confirmed some retailers have already received first pricing information for AMD's upcoming RX Vega graphics cards. This preliminary pricing information places the Radeon RX Vega's price-tag at around 7,000 SEK (~$850) excluding VAT. Things take a turn towards the ugly when we take into account that this isn't even final retail price for consumers: add in VAT and the retailer's own margins, and prospective pricing is expected at about 9,000 SEK (~$1093). Pricing isn't fixed, however, as it varies between manufacturers and models (which we all know too well), and current pricing is solely a reference ballpark.

There is a possibility that the final retail prices will be different from these quoted ones, and if latest performance benchmarks are vindicated, they really should be. However, Nordic Hardware quotes their sources as saying these prices are setting a boundary for "real and final", and that the sentiment among Swedish retailers is that the pricing "Feels wrong". For reference, NVIDIA's GTX 1080 Ti is currently retailing at around 8,000 SEK (~971) including VAT, while the GTX 1080, which RX Vega has commonly been trading blows with, retails for around 5600 SEK (~$680) at the minimum. This should go without saying, but repare your body for the injection of a NaCl solution.

Ahead of its July 27 unveiling at AMD's grand media event on the sidelines of SIGGRAPH, performance benchmarks of the elusive Radeon RX Vega consumer graphics card surfaced once again. Someone with access to an RX Vega sample, with its GPU clocked at 1630 MHz and memory at 945 MHz, put it through 3DMark. One can tell that it's RX Vega and not Pro Vega Frontier Edition, looking at its 8 GB video memory amount.

In three test runs, the RX Vega powered machine yielded a graphics score of 22,330 points, 22,291 points, and 20.949 points. This puts its performance either on-par or below that of the GeForce GTX 1080, but comfortably above the GTX 1070. The test-bench consisted of a Core i7-5960X processor, and graphics driver version 22.19.640.2.