This site may earn affiliate commissions from the links on this page. Terms of use.

GTX980-Ti

When Nvidia demoed Pascal at GDC 2016 last month, many readers were a fleck unhappy that the company didn't give more details on what its upcoming consumer cards would wait like. The latest rumors are that Nvidia may have stopped production on its GM204 products like the GTX 980 Ti, 980, and 970 in order to quickly supplant those products with a GP104 derivative.

GP104 is the name for Nvidia's next-generation consumer-level Pascal card, and it'll debut long before the HPC-oriented GP100 does. The full scientific version of Pascal isn't scheduled to launch before the tail terminate of this year, whereas nosotros expect to see these new consumer cards launching as early as June. This would put AMD and Nvidia on similar time frames (AMD has yet to reveal its launch dates, but we expect cards in June or July).

What can gamers await?

Nvidia released the total whitepaper on Pascal GP100 last calendar week, and while we can't draw many conclusions at this juncture, there are a few things we can safely assume will exist common to the two architectures. First, Pascal supports improved compute preemption compared with Maxwell. From Nvidia's whitepaper:

Compute Preemption is some other important new hardware and software characteristic added to GP100 that allows compute tasks to be preempted at instruction-level granularity, rather than thread cake granularity every bit in prior Maxwell and Kepler GPU architectures. Compute Preemption prevents long-running applications from either monopolizing the system (preventing other applications from running) or timing out.

This suggests that Pascal however won't support asynchronous compute workloads in the aforementioned fashion AMD'south GCN hardware does, though the verdict is however out on whether this capability will play a significant role in shaping performance in a bulk of DirectX 12 titles. It also suggests Pascal will see a smaller operation punishment with async compute enabled than Maxwell did, since it can interleave compute workloads more finer than its predecessor.

Pascal-SM

The image above shows the structure of a Pascal GP100 SM unit. Pascal is heavily focused on double-precision compute, which ways the GP104 variant of the bit will probably remove these units altogether, then use the infinite savings to pack in more single-precision FP32 cores. Expect limited double precision support, simply as we saw with GM204 and GM200.

One significant departure would be the mode Nvidia hits its targets. Kepler and Maxwell both relied on two dissimilar dies — the highest end cards were anchored by GK110 / GM200, while the high-end segment was anchored by GK104 / GM204. These rumors suggest that Nvidia will replace the GTX 980 Ti with the total iteration of GP104, while the time to come GTX *80 and *70 cards will exist farther cut down from this base model.

As for the bigger picture, I'd await AMD and Nvidia to both launch GPUs with 8GB of RAM and possibly some 4GB cards depending on price brackets and targets from the ii companies. Polaris and Pascal are likely to drop within weeks of each other, then I wouldn't run out and purchase a card from 1 company before we've had a chance to put them head to head.