• 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Turing Discussion Thread
#11
(03-15-2017, 02:01 AM)SteelCrysis Wrote: Wouldn't it be interesting if Tesla the car company integrated Nvidia Tesla GPUs into their cars? :smirk:

Apparently Tesla stopped working with the driverless car company that Intel just bought because someone was killed while using the Tesla auto pilot. I would be surprised if Tesla did not consider nVidia to replace them.

I did not realize this, but nVidia already works with Tesla on their driverless car technology:

http://www.nvidia.ca/object/tesla-and-nvidia.html

Quote:Tesla Motors and NVIDIA have partnered since the early development of the revolutionary Model S. Today, all Tesla vehicles—Model S, Model X, and the upcoming Model 3—will be equipped with an NVIDIA-powered on-board “supercomputer” that can provide full self-driving capability. - See more at: http://www.nvidia.ca/object/tesla-and-nv...HfShA.dpuf
  Reply
#12
Here's the source for the OP

http://www.digitimes.com/news/a20170313PB201.html
Quote:Taiwan Semiconductor Manufacturing Company (TSMC) has landed orders for high performance computing (HPC) chips for AI applications from Nvidia and Qualcomm, respectively, according to a Chinese-language Commercial Times report.

TSMC will fabricate Nvidia's next generation Volta GPU using a 12nm process, said the paper, which added that the Volta GPU will be paired with Nvidia's Xavier supercomputer chips for self-driving car applications.

TSMC also produces the 256-core Nvidia Pascal GPU and dual-core Denver 2 CPU for Nvidia's recently released JetsonTX2 supercomputer platform, using a 16nm process, the paper indicated.
  Reply
#13
According to this website, Volta is coming in Q3.
http://news.mydrivers.com/1/528/528313.htm
Quote:After the release of the top Titan Xp , in addition to the legendary entry card GTX 1030 , NVIDIA Pascal (Pascal) this generation of family has been completely successful, the next step is naturally waiting for the next generation of "GeForce 20 series" code-named "Volta" (volt).
In accordance with the traditional update habits, NVIDIA's next-generation graphics card should be to the end of this year or even early next year will be released ...

According to the latest news, NVIDIA plans to release GeForce 20 series in advance, is expected to be released in the third quarter of this year, at the same time GeForce 20 series of product prices, market positioning will be re-planning, in particular, will increase the price of single card to enhance profits Do the market.
Of course, this can also better fight back AMD, continue to suppress each other in the high-end market.
Volta architecture is not yet clear the specific characteristics of NVIDIA official almost nothing mentioned , but from all indications , it should be TSMC 16nm FinFET process, continue to deepen the structure, improve energy efficiency, and hope to popularize HBM2 memory.
[Image: s_d999cd5c96e144f385e3637017e08b0b.jpg]
  Reply
#14
As I said in the other thread, you are the new rumor king, apoppin. :muscle:
  Reply
#15
(04-17-2017, 02:52 PM)SickBeast Wrote: As I said in the other thread, you are the new rumor king, apoppin.  :muscle:

What? Isn't this the Volta discussion thread? And I replied appropriately in the other thread when GStanford said Volta isn't far off.

I think we will see Volta before the holiday season. But I was thinking it would be the Tesla version. That is why I so wanted to go to the GTC - but Nvidia will not invite me this year and I can't pay $660 for a one day pass. That roadmap image is from a recent GTC, and it sure looks like early 2018 (or earlier)
:emo:
  Reply
#16
We will see. I think your initial assumption about it being a Tesla part is correct. I don't think nVidia will break with their current pattern which is to release their new cards from the top down.
  Reply
#17
(04-17-2017, 03:12 PM)SickBeast Wrote: We will see.  I think your initial assumption about it being a Tesla part is correct.  I don't think nVidia will break with their current pattern which is to release their new cards from the top down.

Well, we have seen Nvidia's release schedule shorten between each product cycle. They have made a lot of money and they can afford to have several teams of engineers working on multiple unreleased products. I would not be surprised if they were well along on the Einstein architecture which is after Volta.

They may be able to release GeForce right after Tesla - it's going to depend on yields. Volta is evidently new architecture - but on the same or a similar process to Pascal. This year is doable IMO. Unlikely perhaps, but we'll see.

If I can come up with an extra $660, I'll go up to the GTC. Most likely, I'll just watch the keynotes online.
:crying:
  Reply
#18
I think Volta will release for the holidays at the end of the year. Oct/Nov.
It could be a 750ti type card, to test the new architecture.
If yields are good ,it could be the GV104.
  Reply
#19
(04-18-2017, 04:44 AM)happy medium Wrote: I think Volta will release for the holidays at the end of the year. Oct/Nov.
It could be a 750ti type card, to test the new architecture.
If yields are good ,it could be the GV104.

It's certainly possible that Nvidia could release GV102 first since it is on the same process as Pascal.

New architecture on a new process is usually much more difficult and I would then expect a smaller GPU first.
  Reply
#20
https://www.techpowerup.com/233187/nvidi...tesla-v100
Quote:This chip is a beast of a processor: it packs 21 billion transistors (up from 15,3 billion found on the P100); it's built on TSMC's 12 nm FF process (evolving from Pascal's 16 nm FF); and measures a staggering 815 mm² (from the P100's 610 mm².) This is such a considerable leap in die-area that we can only speculate on how yields will be for this monstrous chip, especially considering the novelty of the 12 nm process that it's going to leverage. But now, the most interesting details from a gaming perspective are the 5,120 CUDA cores powering the V100 out of a total possible 5,376 in the whole chip design, which NVIDIA will likely leave for their Titan Xv. These are divided in 84 Volta Streaming Multiprocessor Units with each carrying 64 CUDA cores (84 x 64 = 5,376, from which NVIDIA is cutting 4 Volta Streaming Multiprocessor Units for yields, most likely, which accounts for the announced 5,120.) Even in this cut-down configuration, we're looking at a staggering 42% higher pure CUDA core-count than the P100's. The new V100 will offer up to 15 FP 32 TFLOPS, and will still leverage a 16 GB HBM2 implementation delivering up to 900 GB/s bandwidth (up from the P100's 721 GB/s). No details on clock speed or TDP as of yet, but we already have enough details to enable a lengthy discussion... Wouldn't you agree?
  Reply


Forum Jump:


Users browsing this thread: 9 Guest(s)