Guru3D.com
  • HOME
  • NEWS
    • Channels
    • Archive
  • DOWNLOADS
    • New Downloads
    • Categories
    • Archive
  • GAME REVIEWS
  • ARTICLES
    • Rig of the Month
    • Join ROTM
    • PC Buyers Guide
    • Guru3D VGA Charts
    • Editorials
    • Dated content
  • HARDWARE REVIEWS
    • Videocards
    • Processors
    • Audio
    • Motherboards
    • Memory and Flash
    • SSD Storage
    • Chassis
    • Media Players
    • Power Supply
    • Laptop and Mobile
    • Smartphone
    • Networking
    • Keyboard Mouse
    • Cooling
    • Search articles
    • Knowledgebase
    • More Categories
  • FORUMS
  • NEWSLETTER
  • CONTACT

New Reviews
PowerColor RX 6650 XT Hellhound White review
FSP Hydro PTM Pro (1200W PSU) review
ASUS ROG Radeon RX 6750 XT STRIX review
AMD FidelityFX Super Resolution 2.0 - preview
Sapphire Radeon RX 6650 XT Nitro+ review
Sapphire Radeon RX 6950 XT Sapphire Nitro+ Pure review
Sapphire Radeon RX 6750 XT Nitro+ review
MSI Radeon RX 6950 XT Gaming X TRIO review
MSI Radeon RX 6750 XT Gaming X TRIO review
MSI Radeon RX 6650 XT Gaming X review

New Downloads
AIDA64 Download Version 6.70
FurMark Download v1.30
Display Driver Uninstaller Download version 18.0.5.1
Download Samsung Magician v7.1.1.820
Intel ARC graphics Driver Download Version: 30.0.101.1732
HWiNFO Download v7.24
GeForce 512.77 WHQL driver download
Intel HD graphics Driver Download Version: 30.0.101.1960
AMD Radeon Software Adrenalin 22.5.1 WHQL driver download
3DMark Download v2.22.7359 + Time Spy


New Forum Topics
[3rd-Party Driver] Amernime Zone Radeon Insight 22.5.1 WHQL Driver Pack (Released) Fine Utilise Power of RadeonPRO Software & SweetFX Part 2 AMD Software Preview Driver May 2022 driver download and discussion Gigabyte AORUS Z690i ULTRA motherboards being recalled - Problems with PCIe 4 are the cause Alleged images of the new NVIDIA RTX 40 GPU heatsink have surface online Intel raptor Lake Caches Confirmed through leaked CPU-Z screenshot Rumor: NVIDIA could unveil a GeForce GTX 1630 this month Acer Predator Helios 300 with 3D Display, New Predator Triton Laptops and Gaming Displays Intel Arc desktop graphics cards from Intel are further delayed (could be September at the earliest) ASUS releases two Radeon RX 6400 variants with Axial-tech fan coolers.




Guru3D.com » News » NVIDIA Refreshes GPU Roadmap and Announces Pascal

NVIDIA Refreshes GPU Roadmap and Announces Pascal

by Hilbert Hagedoorn on: 03/25/2014 07:26 PM | source: | 7 comment(s)
NVIDIA Refreshes GPU Roadmap and Announces Pascal

During a keynote speech at our annual GPU Technology Conference in San Jose, Calif., NVIDIA CEO Jen-Hsun Huang updated our public GPU roadmap with the announcement of Pascal, the GPU family that will follow this year’s Maxwell GPUs. 

Named for 17th century French mathematician Blaise Pascal, our next-generation family of GPUs will include three key new features: stacked DRAM, unified memory and NVLink.

  • 3D Memory: Stacks DRAM chips into dense modules with wide interfaces, and brings them inside the same package as the GPU. This lets GPUs get data from memory more quickly – boosting throughput and efficiency – allowing us to build more compact GPUs that put more power into smaller devices. The result: several times greater bandwidth, more than twice the memory capacity and quadrupled energy efficiency.
  • Unified Memory: This will make building applications that take advantage of what both GPUs and CPUs can do quicker and easier by allowing the CPU to access the GPU’s memory, and the GPU to access the CPU’s memory, so developers don’t have to allocate resources between the two.
  • NVLink: Today’s computers are constrained by the speed at which data can move between the CPU and GPU. NVLink puts a fatter pipe between the CPU and GPU, allowing data to flow at more than 80GB per second, compared to the 16GB per second available now.
  • Pascal Module: NVIDIA has designed a module to house Pascal GPUs with NVLink. At one-third the size of the standard boards used today, they’ll put the power of GPUs into more compact form factors than ever before.

Pascal is due in 2016.

---

NVIDIA GPU accelerators have emerged in High-Performance Computing as an energy-efficient way to provide significant compute capability. The Green500 supercomputer list makes this clear: the top 10 supercomputers on the list feature NVIDIA GPUs. Today at the 2014 GPU Technology Conference, NVIDIA announced a new interconnect called NVLink which enables the next step in harnessing the full potential of the accelerator, and the Pascal GPU architecture with stacked memory, slated for 2016.

Stacked Memory

Pascal will support stacked memory, a technology which enables multiple layers of DRAM components to be integrated vertically on the package along with the GPU. Stacked memory provides several times greater bandwidth, more than twice the capacity, and quadrupled energy efficiency, compared to current off-package GDDR5. Stacked memory lets us combine large, high-bandwidth memory in the same package with the GPU, allowing us to place the place the voltage regulators close to the chip for efficient power delivery. Stacked Memory, combined with a new Pascal module that is one-third the size of current PCIe boards, will enable us to build denser solutions than ever before.

Outpacing PCI Express

Today a typical system has one or more GPUs connected to a CPU using PCI Express. Even at the fastest PCIe 3.0 speeds (8 Giga-transfers per second per lane) and with the widest supported links (16 lanes) the bandwidth provided over this link pales in comparison to the bandwidth available between the CPU and its system memory. In a multi-GPU system, the problem is compounded if a PCIe switch is used. With a switch, the limited PCIe bandwidth to the CPU memory is shared between the GPUs. The resource contention gets even worse when peer-to-peer GPU traffic is factored in.

pci-e_single_dual

NVLink addresses this problem by providing a more energy-efficient, high-bandwidth path between the GPU and the CPU at data rates 5 to 12 times that of the current PCIe Gen3. NVLink will provide between 80 and 200 GB/s of bandwidth, allowing the GPU full-bandwidth access to the CPU’s memory system.

A Flexible and Energy-Efficient Interconnect

The basic building block for NVLink is a high-speed, 8-lane, differential, dual simplex bidirectional link. Our Pascal GPUs will support a number of these links, providing configuration flexibility. The links can be ganged together to form a single GPU↔CPU connection or used individually to create a network of GPU↔CPU and GPU↔GPU connections allowing for fast, efficient data sharing between the compute elements.

nvlink_single_dual

When connected to a CPU that does not support NVLink, the interconnect can be wholly devoted to peer GPU-to-GPU connections enabling previously unavailable opportunities for GPU clustering.

nvlink_quad

Moving data takes energy, which is why we are focusing on making NVLink a very energy efficient interconnect. NVLink is more than twice as efficient as a PCIe 3.0 connection, balancing connectivity and energy efficiency.

Understanding the value of the current ecosystem, in an NVLink-enabled system, CPU-initiated transactions such as control and configuration are still directed over a PCIe connection, while any GPU-initiated transactions use NVLink. This allows us to preserve the PCIe programming model while presenting a huge upside in connection bandwidth.

What NVLink and Stacked Memory Mean for Developers

Today, developers devote a lot of effort to optimizing and avoiding PCIe transfer bottlenecks. Current applications that have devoted time to maximizing concurrency of computation and communication will enjoy a boost from the enhanced connection.

NVLink and stacked memory enable acceleration of a whole new class of applications. The large increase in GPU memory size and bandwidth provided by stacked memory will enable GPU applications to access a much larger working set of data at higher bandwidth, improving efficiency and computational throughput, and reducing the frequency of off-GPU transfers. Crafting and optimizing applications that can exploit the massive GPU memory bandwidth as well as the CPU↔GPU and GPU↔GPU bandwidth provided by NVLink will allow you to take the next steps towards exascale computing.

Starting with CUDA 6, Unified Memory simplifies memory management by giving you a single pointer to your data, and automatically migrating pages on access to the processor that needs them. On Pascal GPUs, Unified Memory and NVLink will provide the ultimate combination of simplicity and performance. The full-bandwidth access to the CPU’s memory system enabled by NVLink means that NVIDIA’s GPU can access data in the CPU’s memory at the same rate as the CPU can. With the GPU’s superior streaming ability, the GPU will sometimes be able to stream data out of the CPU’s memory system even faster than the CPU.



NVIDIA Refreshes GPU Roadmap and Announces Pascal




« GeForce Titan Z has 12GB Graphics memory and has Dual GPUs · NVIDIA Refreshes GPU Roadmap and Announces Pascal · NVIDIA Launches NVLINK - High-Speed GPU Interconnect »

Related Stories

Nvidia responds to AMD FreeSync - 01/08/2014 01:33 PM
Well it was bound to happen sooner rather then later, but Nvidia spoke about AMD FreeSync. The interview is with Tom Petersen who spoke with the guys from techReport. So the credits and everything re...

NVIDIA Reveals Tegra Note - 09/18/2013 02:56 PM
Rumors have been floating around for a while now, but today its finally announced as NVIDIA Reveals the Tegra Note. The Tegra Note platform delivers features such as Tegra 4, a stylus, good audio, H...

NVIDIA reponds to Linus Torvals Remarks - 06/20/2012 11:03 AM
The statement follows on this reaction from the man: Supporting Linux is important to NVIDIA, and we understand that there are people who are as passionate about Linux as an open source platform as we...

NVIDIA rebrands GeForce GT 620 and GeForce 605 for OEMs - 04/05/2012 10:12 AM
NVIDIA has rebadged its GeForce GT 520 and GeForce 510 GPUs for OEM clients. The GeForce GT 520 is rebranded to GeForce GT 620 and the GeForce 510 lives on as the GeForce 605. OpenGL driver support ha...

Nvidia Reportedly Delays the Kal-El SoC Launch - 08/03/2011 10:33 AM
As you guys know, Kal-El will be the successor of the current Tegra 2 SOC and it features no less than four processing cores based on the ARM Cortex A9 architecture, which are clocked at 1.5GHz, as we...


2 pages 1 2


WhiteLightning
Moderator



Posts: 29361
Joined: 2007-09-19

#4788709 Posted on: 03/25/2014 07:30 PM
looking forward to this one

nexus_711
Senior Member



Posts: 221
Joined: 2010-09-23

#4788716 Posted on: 03/25/2014 07:35 PM
Looking forward to it too! But first lets see how high-end Maxwell will perform.

moab600
Senior Member



Posts: 6414
Joined: 2004-09-30

#4788723 Posted on: 03/25/2014 07:43 PM
Impressive. we meet in 2016

Fox2232
Senior Member



Posts: 11809
Joined: 2012-07-20

#4788744 Posted on: 03/25/2014 07:58 PM
nVlink looks good on paper, but thanks for: "Yet another proprietary technology."

And BTW, image with 4 GPUs is one of most hilarious images nVidia posted and they do post such on regular basis.
I wonder who can spot stupidity there.

MadGizmo
Senior Member



Posts: 1396
Joined: 2008-06-09

#4788751 Posted on: 03/25/2014 08:03 PM
NVLink support for IBM's Power CPUs means we see don't it soon for gaming when Intel doesn't support it.

Edit: Fixed a negative at the wrong place. ;)

2 pages 1 2


Post New Comment
Click here to post a comment for this news story on the message forum.


Guru3D.com © 2022