# Inside Pascal: NVIDIA's Newest Computing Platform **URL:** \ **Category:** Technical Blog\ **Created:** [April 5, 2016, 5:23pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541 "2016-04-05T17:23:55Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![jwitsoe](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/jwitsoe/32/16591_2.png) [@jwitsoe](https://forums.developer.nvidia.com/u/jwitsoe)\ **Post date:** [April 5, 2016, 5:23pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/1 "2016-04-05T17:23:55Z")
Originally published at: [https://developer.nvidia.com/blog/inside-pascal/](https://developer.nvidia.com/blog/inside-pascal/) At the 2016 GPU Technology Conference in San Jose, NVIDIA CEO Jen-Hsun Huang announced the new NVIDIA Tesla P100, the most advanced accelerator ever built. Based on the new NVIDIA Pascal GP100 GPU and powered by ground-breaking technologies, Tesla P100 delivers the highest absolute performance for HPC, technical computing, deep learning, and many computationally intensive… ---
**Author:** ![anon64215536](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon64215536](https://forums.developer.nvidia.com/u/anon64215536)\ **Post date:** [April 5, 2016, 7:23pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/2 "2016-04-05T19:23:33Z")
to be a chip 16nm FinFET not you think that is too large, besides achieving consume the outrageous amount of 300 watts? ---
**Author:** ![anon87907916](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon87907916](https://forums.developer.nvidia.com/u/anon87907916)\ **Post date:** [April 5, 2016, 7:59pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/3 "2016-04-05T19:59:46Z")
Disappointing no actual GPUs named or seen. ---
**Author:** ![anon79358340](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon79358340](https://forums.developer.nvidia.com/u/anon79358340)\ **Post date:** [April 5, 2016, 8:10pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/4 "2016-04-05T20:10:44Z")
Does Nvidia still develop gaming GPU's? ---
**Author:** ![anon33080794](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon33080794](https://forums.developer.nvidia.com/u/anon33080794)\ **Post date:** [April 5, 2016, 8:20pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/5 "2016-04-05T20:20:03Z")
They can Just do optimisations synchronously, That's why pascal will be HPC only and volta gaming only ---
**Author:** ![anon15124065](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon15124065](https://forums.developer.nvidia.com/u/anon15124065)\ **Post date:** [April 5, 2016, 8:20pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/6 "2016-04-05T20:20:14Z")
Interesting post my man. One part stands out to me: "Tesla P100 is the first GPU accelerator to use High Bandwidth Memory 2 (HBM2)." Is it confirmed the P100 line, which I assume is THE next line to hit the shelves, will indeed have HBM2? Confirmed? Where are the actual cards? ---
**Author:** ![anon52956801](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon52956801](https://forums.developer.nvidia.com/u/anon52956801)\ **Post date:** [April 5, 2016, 8:29pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/7 "2016-04-05T20:29:28Z")
Really disappointed that Nvidia failed to release any info on the gaming Pascal GPU'S today. ---
**Author:** ![anon79970564](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon79970564](https://forums.developer.nvidia.com/u/anon79970564)\ **Post date:** [April 5, 2016, 10:33pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/8 "2016-04-05T22:33:08Z")
The real question is, how many frames per second will I get on Solitaire? ---
**Author:** ![anon1555642](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon1555642](https://forums.developer.nvidia.com/u/anon1555642)\ **Post date:** [April 5, 2016, 11:48pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/9 "2016-04-05T23:48:55Z")
go back to wcftcftctcth. grown ass men with a full time job as an AMD fanboi give me creeps ---
**Author:** ![anon45887450](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon45887450](https://forums.developer.nvidia.com/u/anon45887450)\ **Post date:** [April 6, 2016, 1:44am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/10 "2016-04-06T01:44:40Z")
Thats all great but what does it mean? Does it mean that graphics cards are going to be able to run Crysis at ultra in 4K on laptops? If so when, if not why not? ---
**Author:** ![anon26332651](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon26332651](https://forums.developer.nvidia.com/u/anon26332651)\ **Post date:** [April 6, 2016, 3:31am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/11 "2016-04-06T03:31:46Z")
The only time I will ever buy a NVIDIA card again is when they release a single card that is able to play 4K resolution max ULTRA settings at a constant 60FPS. ---
**Author:** ![anon51531848](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon51531848](https://forums.developer.nvidia.com/u/anon51531848)\ **Post date:** [April 6, 2016, 3:33am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/12 "2016-04-06T03:33:15Z")
When is going to come pascal? ---
**Author:** ![anon33870937](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon33870937](https://forums.developer.nvidia.com/u/anon33870937)\ **Post date:** [April 6, 2016, 3:39am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/13 "2016-04-06T03:39:11Z")
Tesla P100... ---
**Author:** ![anon94792593](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon94792593](https://forums.developer.nvidia.com/u/anon94792593)\ **Post date:** [April 6, 2016, 4:29am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/14 "2016-04-06T04:29:48Z")
That's the max wattage. The card itself will apparently be much more efficient though. So you'd actually be getting much more performance for how much power you are using. The extra TDP will probably really help in GPU Boost. ---
**Author:** ![anon64215536](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon64215536](https://forums.developer.nvidia.com/u/anon64215536)\ **Post date:** [April 6, 2016, 5:46am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/15 "2016-04-06T05:46:56Z")
all in good time ---
**Author:** ![anon64215536](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon64215536](https://forums.developer.nvidia.com/u/anon64215536)\ **Post date:** [April 6, 2016, 5:47am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/16 "2016-04-06T05:47:51Z")
all in good time please! ---
**Author:** ![anon40970205](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon40970205](https://forums.developer.nvidia.com/u/anon40970205)\ **Post date:** [April 6, 2016, 10:08am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/17 "2016-04-06T10:08:45Z")
NVIDIA is doing rather well in the gaming GPU market: [http://www.digitaltrends.co...](http://www.digitaltrends.com/computing/nvidia-add-in-graphics-market "http://www.digitaltrends.com/computing/nvidia-add-in-graphics-market") It is my impression that the Tesla P100 will be quite expensive as NVIDIA (and the fabs working with them) work to ramp up their ability to mass produce the technologies that this card features. (Technologies such as 16nm FinFET, HBM2, NVLink, etc.) ---
**Author:** ![anon59554936](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon59554936](https://forums.developer.nvidia.com/u/anon59554936)\ **Post date:** [April 6, 2016, 10:17am UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/18 "2016-04-06T10:17:13Z")
I was expecting that NVIDIA will announce for the first time a product faster at double precision computation than the AMD FirePro Hawaii that I am currently using. Nevertheless, a very pleasant surprise was the good support for ECC memory. This is a very important feature for myself and for others for whom accuracy & reliability is even more important than speed. The presence of ECC memory will certainly be very important for my future purchasing decisions, because when ECC is missing or it slows too much the computation, many annoying software workarounds are required for result verification. ---
**Author:** ![anon90977389](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon90977389](https://forums.developer.nvidia.com/u/anon90977389)\ **Post date:** [April 6, 2016, 5:27pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/19 "2016-04-06T17:27:04Z")
neither AMD or Nvidia has that capability right now ---
**Author:** ![anon52956801](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@anon52956801](https://forums.developer.nvidia.com/u/anon52956801)\ **Post date:** [April 6, 2016, 7:32pm UTC](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541/20 "2016-04-06T19:32:33Z")
I'm no fanboy. I was really looking forward to see Nvidia release some information about Pascal gaming GPU'S [Next page](https://forums.developer.nvidia.com/t/inside-pascal-nvidias-newest-computing-platform/148541.md?page=2)