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

GPU-Hero-Feature

Nvidia'due south Pascal GPU architecture has been one of Nvidia's longest-lived product lines in the by xx years. It further refined and improved the technologies Nvidia introduced with Maxwell, along with making some architectural improvements of its ain, and it competes extremely well against AMD's Polaris and Vega product lines. But Pascal is also sometime for a high-finish GPU architecture, specially 1 that hasn't undergone a major SKU shakeout since launch. While Kepler beats it in historic period (GTX 680 debuted in March 2012, with the GTX 980 arriving in September 2014), Nvidia eventually replaced its top-finish GTX 680 SKU with the GTX 780, which offered significantly additional functioning, as well as various improvements throughout the 7xx stack. Beyond launching the GTX 1080 Ti almost a yr agone and the 1070 Ti late last twelvemonth, Nvidia hasn't made any changes to the Pascal family.

For the past few weeks nosotros've seen rumors popping up that Nvidia would presently introduce a new GPU family, maybe at the GTC or GDC conferences this yr. Nosotros haven't discussed the topic considering all our attempts to confirm those rumors pointed in the opposite direction. At present, THG has chimed in, indicating that their rumor mill suggests nosotros won't run into new consumer GPUs based on the upcoming Turing architectures in the next few months.

NVIDIA-Telsa-V100 Volta

Nvidia'southward Volta uses HBM2, but there'south no sign NV will adopt information technology for its consumer cards. GDDR6 is the expected memory standard for next-gen high-end cards.

Nvidia is supposedly prepping new cards based on Volta for non-gaming workloads with a new compute compages, supposedly nicknamed Ampere, coming in the nigh-future as well. The consumer follow-upward to Pascal is reportedly nicknamed "Turing," though nosotros've seen some publications arguing that Ampere is the consumer part and Tesla the compute-oriented GPU. Ampere as the compute GPU seems to align more than closely with "Volta" as a brand name, only we've got no inside information on that one way or the other.

It feels a bit odd to say this, merely the biggest questions surrounding Nvidia's adjacent-generation GPU, whatever codename information technology uses, have relatively petty to practice with gaming performance. There'southward pregnant concern future GPUs could exist impossible to detect in marketplace if they outperform electric current Pascal fries at cryptocurrency mining. We already saw this happen with 14nm fries from AMD and Nvidia at the 14/16nm node and nobody wants a sequel with ongoing shortages that could have a yr or more than to improve.

The question of which node these GPUs will use is too up for some contend. TSMC'southward 10nm nodes accept, as far as nosotros're aware, been deployed near entirely for mobile products. TSMC has likewise guided that it believes its 10nm products are a short-lived node. This is a similar strategy to what nosotros saw at 20nm, where neither AMD nor Nvidia tapped the node for GPUs and information technology was replaced by FinFETs fairly chop-chop. It's possible, therefore, that Nvidia will target TSMC'southward interim 12nm node (call up "optimized 16nm") rather than moving to a make-new node in 2018.

The other reason Nvidia can afford to accept its time in many of these efforts is considering AMD'due south Vega isn't really nipping at its proverbial heels. Vega 56'south pb over the GTX 1070 was largely eliminated past the GTX 1070 Ti, and the increased cryptocurrency demand for AMD GPUs has fabricated them less relevant to Nvidia in any example. We covered this in some detail earlier this week, but with AMD GPUs currently seeing more cost inflation than their Nvidia counterparts, Nvidia has fifty-fifty less reason to push for new part introductions. Hopefully this also ways they've had the time to discover ways to prevent cryptocurrency miners from yanking all the desktop GPUs out of the market when new products practice inevitably launch, and to ensure a robust supply of product so we don't see the same supply shortages as happened in 2016.