news.buyenne.com

(credit: CSPAN)

With a tiny change to the rules, the Food and Drug Administration made it a bit harder for Martin Shkreli and his ilk to make a killing by jacking up the prices of off-patent drugs.

The regulatory tweak now allows a “priority” or expedited review process for any generic drug that would compete with an off-patent drug that is only made by one company—the kinds of drugs that have seen skyrocketing price tags of late. The faster review process could cut the window for a pharmaceutical company to have a monopoly over the drug from years to months, sharply cutting profits from potential price gouging.

In an e-mail to Bloomberg, FDA spokesperson Sandy Walsh wrote that the agency expects as many as 125 generic drug applications will now be fast-tracked due to the change. The agency previously expedited reviews of generics that would compete with newly off-patent brand name drugs.

After first being teased at E3 2015, AMD has finally made its dual Fury GPU official. Dubbed the Radeon Pro Duo, the card combines two of AMD's top tier Fiji GPUs (as used in the Fury X and Fury Nano) onto a single card, resulting in a claimed 16 teraflops of compute performance. The price for such power? A mere $1499 (UK pricing TBC, but probably around £1200). The Radeon Pro Duo goes on sale in "early" Q2 2016.

While that price might seem steep, it is substantially less than Nvidia's most recent dual dual-GPU offering, the Titan Z, which launched at $3000 (£2399) before dropping to $2000 (£1499). AMD's previous dual-GPU card, the R9 295X2, launched at $1500 before dropping to less than $1000 months after launch.

You do get a lot for your cash, though. Both GPUs on the Radeon Pro Duo sport the full array of 4096 stream processors, 256 texture units, and 256 ROPs. There's 8GB of high bandwidth memory on board, split between the two GPUs, running at 1GHz on a substantial 4096-bit bus for 512GB/s of bandwidth. Like the Fury X, the Radeon Pro Duo is liquid cooled via an all-in-one unit with a 120mm radiator.

For the first time in a long time, AMD has an honest-to-goodness GPU product roadmap, and it names the company's next two GPU architectures: Vega and Navi.

Revealed at this year's Game Developers Conference during the AMD "Capsaicin" event, the roadmap is light on details, but it does hint at what the future might hold for AMD's GPUs. For starters, Vega is due to arrive early in 2017, not long after the release of Polaris. Interestingly, the roadmap explicity calls out Vega's use of HBM2 memory, a feature that was originally supposed to be a part of the upcoming Polaris architecture and used alongside traditional GDDR5 memory.

In an interview with PC Perspective, AMD's Raja Koduri hinted that Polaris would instead use HBM1, rather than its more accomplished counterpart. Of particular concern is that current HBM1 implementations are limited to 4GB stacks—HBM2 can go as high as 16GB—which could carry over to Polaris. Given that GPU memory requirements have skyrocketed over the past year, that could put Polaris at a significant disadvantage, particularly when Nvidia has confirmed that at least some Pascal parts will use HBM2.