The top technology companies in China have been ordering a lot of NVIDIA enterprise-grade GPUs, even though U.S. sanctions have prevented the shipment of A100 and H100 models (plus AMD's MI250 Instinct accelerator) to the nation in recent times. ByteDance - best known for developing TikTok - managed to grab plenty of Ampere enterprise units prior to last Autumn's cutoff period, and has continued to purchase Team Green's H800 GPU, which is a cut-down version of the H100 flagship. Smaller outfits are relying on less direct sources to acquire HBC GPUs—according to a Reuters investigative article, international trade restrictions have created a thriving black market for "top-end NVIDIA AI chips."

Their reporters carried out some on-site sleuthing: "Visiting the famed Huaqiangbei electronics area in the southern Chinese city of Shenzhen is a good bet - in particular, the SEG Plaza skyscraper whose first 10 floors are crammed with shops selling everything from camera parts to drones. The chips are not advertised but asking discreetly works...They don't come cheap. Two vendors there, who spoke with Reuters in person on condition of anonymity, said they could provide small numbers of A100 artificial intelligence chips made by the U.S. chip designer, pricing them at $20,000 a piece - double the usual price."

New benchmarks of an RX Vega engineering sample video card have surfaced. There have been quite a few benchmarks for this card already, which manifests with the 687F:C1 identifier. The new, GTX 1080 beating benchmark (Gaming X version, so a factory overclocked one) comes courtesy of 3D Mark 11, with the 687F:C1 RX Vega delivering 31,873 points in its latest appearance (versus 27,890 in its first). Since the clock speed of the 687F:C1 RX Vega has remained the same throughout this benchmark history, I think it's fair to say these improvements have come out purely at the behest of driver and/or firmware level performance improvements.

It's here. The Radeon Vega that's not for gamers, that is. After what seems like a year of waiting forward to AMD's next generation GPU architecture, so it has finally appeared. As we all knew was going to be the case, Vega's first foray in the market is geared at the more profitable professional sector of the market. The good news for professionals: the pricing is lower than previously reported. Instead of the expected $1,199 and $1,799 for an air cooled or water-cooled version of the card respectively, AMD is commanding a much less demanding price tag of $999 for the air cooled version (available now) and $1,499 for the water-cooled one (to be available in Q3.)

One thing that deserves to be placed before the break is a software feature of the new Vega Frontier Edition graphics cards: AMD has changed their driver scheme into a single-package installer (available in the source), with both the professional-geared drivers, and the gaming ones as well. This means that after all that Raja Koduri told us to wait for AMD's consumer, gaming-oriented RX Vega graphics cards, these will probably work just as well for gaming as for professional workloads.

Where is Vega? When is it launching? On AMD's Financial Analyst Day 2017, Raja Koduri spoke about the speculation in the past few weeks, and brought us an answer: Radeon Vega Frontier Edition is the first iteration of Vega, aimed at data scientists, immersion engineers and product designers. It will be released in the second half of June for AMD's "pioneers". The wording, that Vega Frontier Edition will be released in the second half of June, makes it so that AMD still technically releases Vega in the 2H 2017... It's just not the consumer, gaming Vega version of the chip. This could unfortunately signify an after-June release time-frame for consumer GPUs based on the Vega micro-architecture.

This news comes as a disappointment to all gamers who have been hoping for Vega for gaming, because it reminds of what happened with dual Fiji. A promising design which ended up unsuitable for gaming and was thus marketed for content creators as Radeon Pro Duo, with little success. But there is still hope: it just looks like we really will have to wait for Computex 2017 to see some measure of details on Vega's gaming prowess.

It looks like AMD is confident enough on its HBC (High-Bandwidth Cache) and HBCC (High-Bandwidth Cache Controller) technology, and other assorted improvements to overall Vega memory management, to consider 4 GB as enough memory for high-performance gaming and applications. On a Beijing tech summit, AMD announced that its RX Vega cards (the highest performers in their next generation product stack, which features rebrands of their RX 400 line series of cards to th new RX 500) will come in at 4 GB and 8 GB HBM 2 (512 GB/s) memory amounts. The HBCC looks to ensure that we don't see a repeat of AMD's Fury X video card, which featured first generation HBM (High-Bandwidth memory), at the time limited to 4 GB stacks. But lacking extensive memory management improvements meant that the Fury X sometimes struggled on memory-heavy workloads.

If the company's Vega architecture deep dive is anything to go by, they may be right: remember that AMD put out a graph showing how the memory allocation is almost twice as big as the actual amount of memory used - and its here, with smarter, improved memory management and allocation, that AMD is looking to make do with only 4 GB of video memory (which is still more than enough for most games, mind you). This could be a turn of the screw moment for all that "more is always better" philosophy.