Connecting Pascal's triangle with the Maxwell Equations

Subject: General Tech | March 27, 2014 - 01:10 PM |
Tagged: pascal, nvlink, nvidia, maxwell, jen-hsun huang, GTC

Before we get to see Volta in action NVIDIA is taking a half step and releasing the Pascal architecture which will use Maxwell-like Streaming Multiprocessors and will introduce stacked or 3D memory which will reside on the same substrate as the GPU.  Jen-Hsun claimed this new type of memory will vastly increase the bandwidth available, provide two and a half times the capacity and be four times as energy efficient at the same time.  Along with the 3D memory announcement was the revealing of NVLink, an alternative interconnect which he claims will offer 5-12 times the bandwidth of PCIe and will be utilized by HPC systems.  From his announcement that NVLink will feature eight 20Gbps lanes per block or as NVIDIA is calling them, bricks, which The Tech Report used to make a quick calculation and came up with an aggregate bandwidth of a brick of around 20GB/s.  Read on to see what else was revealed.

View Full Size

"Today during his opening keynote at the Nvidia GPU Technology Conference, CEO Jen-Hsun Huang offered an update to Nvidia's GPU roadmap. The big reveal was about a GPU code-named Pascal, which will be a generation beyond the still-being-introduced Maxwell architecture in the firm's plans."

Here is some more Tech News from around the web:

Tech Talk

March 27, 2014 | 04:12 PM - Posted by Anonymous (not verified)

Before we get to see Volta in action NVIDIA is taking a half step and releasing the Pascal architecture which will use Maxwell-like Streaming Multiprocessors and will introduce stacked or 3D memory which will reside on the same substrate as the GPU.

Pretty sure based on everything we knew about Volta from a year ago, Pascal is just a replacement codename. The details look practically the same (Unified Memory, Stacked memory) with the only new addition in details being NVLink.

Still speculation that Einstein (previous codename to come out after Maxwell) also got scrapped some years ago, or it may be a complete merging of Nvidia's Exascale computing due in 2018 on 10nm.

March 27, 2014 | 04:57 PM - Posted by Jeremy Hellstrom

Pascal is still on the roadmap with no release date so it is possible it will fall by the wayside.  At this point though NVIDIA still seems to be planning to release Pascal sometime in the future.

March 27, 2014 | 05:10 PM - Posted by Anonymous (not verified)

NvLink is just CAPI - Coherent Accelerator Processor Interface, renamed!

See the IBM founded OpenPOWER Foundation (Formally called "OpenPOWER Consortium") Nivida is in with IBM and Others, so Like AMD's marketing hijacking the generic term HSA as a buzzword, Nvidia just Renames CAPI to NVLink, pure marketing BS at work here! The same goes for LightPeak to Thunderbolt, as well as other technology renamining to give credit where credit is not dew! look for others to implement this technology, with equally ridiculous marketing terms!

HSA was around long before AMD abused the term, so do not equate AMD's HSA implementation and use of the term with Anyone else's HSA implementation of HSA, and everyone will have a version of HSA, just like everyone will have a version of CAPI! Oh those open standards renamed by the marketing monkeys just to make their companies look innovative!

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

By submitting this form, you accept the Mollom privacy policy.