During the Computer Vision and Pattern Recognition conference in Salt Lake City on Wednesday, NVIDIA CEO Jensen Huang pulled a PR stunt eased by NVIDIA's currently entrenched position in the AI-acceleration market. The new TITAN V graphics card being given away under the "CEO Edition" tag feature more than double the amount of HBM memory - up to 32 GB of HBM 2 memory compared to the original Titan V's 12 GB.

This is, essentially, a Titan-branded Quadro GV100 accelerator, made all the more exotic for the limited-edition branding. It features the GV100 graphics processor - a large chip with a die area of 815 mm² and 21,100 million transistors. It features 5120 shading units, 320 texture mapping units and 128 ROPs. Also included are 640 tensor cores which help improve the speed of machine learning applications.

Videocardz is running a story where some of their sources have seemingly confirmed the Radeon RX Vega model's codenames according to the particular GPU that's being run, with some juicy extra tidbits for your consumption pleasure. Naturally, as Videocardz themselves put it, codenames be codenames, and are always subject to change.

However, what is arguably more interesting is the supposed segregation between models. Apparently, the RX Vega XTX is the same GPU that ticks inside AMD's Vega Frontier Edition, only with a reference water cooling solution attached to it. They report that the board should pull in 375 W of power, with the GPU pulling in 300 W of those. The Vega XT will reportedly be a more mundane air-cooled version of the graphics card, as are the until-now launched Frontier Edition versions of it (with a reduced 285 W board power, with the ASIC now pulling 220 of those watts.) The most interesting point, though, is the Vega XL. Videocardz is reporting that this will be a cut-down version of the Vega XTX and Vega XT's 4096 Stream Processors, down to 3584 Stream Processors, and that it will be sold exclusively in custom variants designed by AMD's AIB partners. Board power and ASIC power are the same as the Vega XT version, though, which seems strange, considering the not insignificant cut down in graphics processing resources. It is unclear as of yet the amount of HBM 2 memory the AIB-exclusive Vega XL will carry, but the Vega XTX and Vega XT should both deliver 8 GB of it.

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.

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.