Up close and personal with GP100

Subject: General Tech | April 28, 2016 - 01:47 PM |
Tagged: nvidia, GP100, pascal

The Tech Report takes you on a walk through NVIDIA's HPC products to show you just what is interesting about the Tesla P100 HPC which Jen-Hsun Huang introduced us to.  The background gives you an idea of how much has changed from their first forays into HPC to this new 16nm process, 610mm² chip with 56 SMs.  If you missed out on the presentation or wanted some more information about how they pulled off FP16 on natively FP32 hardware or how the cache of this chip was set up then click on over and read it for yourself.

gp100sm.png

"Nvidia's GP100 "Pascal" GPU launched on the Tesla P100 HPC accelerator a couple weeks ago. Join us as we take an in-depth look at what we know about this next-generation graphics processor so far, and what it might mean for the consumer GeForces of the future."

Here is some more Tech News from around the web:

Tech Talk

 

Report: NVIDIA GP104 Die Pictured; GTX 1080 Does Not Use HBM

Subject: Graphics Cards | April 22, 2016 - 10:16 AM |
Tagged: rumor, report, pascal, nvidia, leak, graphics card, gpu, gddr5x, GDDR5

According to a report from VideoCardz (via Overclock.net/Chip Hell) high quality images have leaked of the upcoming GP104 die, which is expected to power the GeForce GTX 1070 graphics card.

NVIDIA-GP104-GPU.jpg

Image credit: VideoCardz.com

"This GP104-200 variant is supposedly planned for GeForce GTX 1070. Although it is a cut-down version of GP104-400, both GPUs will look exactly the same. The only difference being modified GPU configuration. The high quality picture is perfect material for comparison."

A couple of interesting things have emerged with this die shot, with the relatively small size of the GPU (die size estimated at 333 mm2), and the assumption that this will be using conventional GDDR5 memory - based on a previously leaked photo of the die on PCB.

NVIDIA-Pascal-GP104-200-on-PCB.jpg

Alleged photo of GP104 using GDDR5 memory (Image credit: VideoCardz via ChipHell)

"Leaker also says that GTX 1080 will feature GDDR5X memory, while GTX 1070 will stick to GDDR5 standard, both using 256-bit memory bus. Cards based on GP104 GPU are to be equipped with three DisplayPorts, HDMI and DVI."

While this is no doubt disappointing to those anticipating HBM with the upcoming Pascal consumer GPUs, the move isn't all that surprising considering the consistent rumors that GTX 1080 would use GDDR5X.

Is the lack of HBM (or HBM2) enough to make you skip this generation of GeForce GPU? This author points out that AMD's Fury X - the first GPU to use HBM - was still unable to beat a GTX 980 Ti in many tests, even though the 980 Ti uses conventional GDDR5. Memory is obviously important, but the core defines the performance of the GPU.

If NVIDIA has made improvements to performance and efficiency we should see impressive numbers, but this might be a more iterative update than originally expected - which only gives AMD more of a chance to win marketshare with their upcoming Radeon 400-series GPUs. It should be an interesting summer.

Source: VideoCardz

Podcast #394 - Measuring VR Performance, NVIDIA's Pascal GP100, Bristol Ridge APUs and more!

Subject: General Tech | April 7, 2016 - 02:47 PM |
Tagged: VR, vive, video, tesla p100, steamvr, Spectre 13.3, rift, podcast, perfmon, pascal, Oculus, nvidia, htc, hp, GP100, Bristol Ridge, APU, amd

PC Perspective Podcast #394 - 04/07/2016

Join us this week as we discuss measuring VR Performance, NVIDIA's Pascal GP100, Bristol Ridge APUs and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

This episode of the PC Perspective Podcast is sponsored by Lenovo!

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malventano

Subscribe to the PC Perspective YouTube Channel for more videos, reviews and podcasts!!

Manufacturer: NVIDIA

93% of a GP100 at least...

NVIDIA has announced the Tesla P100, the company's newest (and most powerful) accelerator for HPC. Based on the Pascal GP100 GPU, the Tesla P100 is built on 16nm FinFET and uses HBM2.

nvidia-2016-gtc-pascal-banner.png

NVIDIA provided a comparison table, which we added what we know about a full GP100 to:

  Tesla K40 Tesla M40 Tesla P100 Full GP100
GPU GK110 (Kepler) GM200 (Maxwell) GP100 (Pascal) GP100 (Pascal)
SMs 15 24 56 60
TPCs 15 24 28 (30?)
FP32 CUDA Cores / SM 192 128 64 64
FP32 CUDA Cores / GPU 2880 3072 3584 3840
FP64 CUDA Cores / SM 64 4 32 32
FP64 CUDA Cores / GPU 960 96 1792 1920
Base Clock 745 MHz 948 MHz 1328 MHz TBD
GPU Boost Clock 810/875 MHz 1114 MHz 1480 MHz TBD
FP64 GFLOPS 1680 213 5304 TBD
Texture Units 240 192 224 240
Memory Interface 384-bit GDDR5 384-bit GDDR5 4096-bit HBM2 4096-bit HBM2
Memory Size Up to 12 GB Up to 24 GB 16 GB TBD
L2 Cache Size 1536 KB 3072 KB 4096 KB TBD
Register File Size / SM 256 KB 256 KB 256 KB 256 KB
Register File Size / GPU 3840 KB 6144 KB 14336 KB 15360 KB
TDP 235 W 250 W 300 W TBD
Transistors 7.1 billion 8 billion 15.3 billion 15.3 billion
GPU Die Size 551 mm2 601 mm2 610 mm2 610mm2
Manufacturing Process 28 nm 28 nm 16 nm 16nm

This table is designed for developers that are interested in GPU compute, so a few variables (like ROPs) are still unknown, but it still gives us a huge insight into the “big Pascal” architecture. The jump to 16nm allows for about twice the number of transistors, 15.3 billion, up from 8 billion with GM200, with roughly the same die area, 610 mm2, up from 601 mm2.

nvidia-2016-gp100_block_diagram-1-624x368.png

A full GP100 processor will have 60 shader modules, compared to GM200's 24, although Pascal stores half of the shaders per SM. The GP100 part that is listed in the table above is actually partially disabled, cutting off four of the sixty total. This leads to 3584 single-precision (32-bit) CUDA cores, which is up from 3072 in GM200. (The full GP100 architecture will have 3840 of these FP32 CUDA cores -- but we don't know when or where we'll see that.) The base clock is also significantly higher than Maxwell, 1328 MHz versus ~1000 MHz for the Titan X and 980 Ti, although Ryan has overclocked those GPUs to ~1390 MHz with relative ease. This is interesting, because even though 10.6 TeraFLOPs is amazing, it's only about 20% more than what GM200 could pull off with an overclock.

Continue reading our preview of the NVIDIA Pascal architecture!!

Rumor: NVIDIA's Next GPU Called GTX 1080, Uses GDDR5X

Subject: Graphics Cards | March 11, 2016 - 05:03 PM |
Tagged: rumor, report, pascal, nvidia, HBM2, gtx1080, GTX 1080, gtx, GP104, geforce, gddr5x

We are expecting news of the next NVIDIA graphics card this spring, and as usual whenever an announcement is imminent we have started seeing some rumors about the next GeForce card.

GeForce-GTX.jpg

(Image credit: NVIDIA)

Pascal is the name we've all being hearing about, and along with this next-gen core we've been expecting HBM2 (second-gen High Bandwidth Memory). This makes today's rumor all the more interesting, as VideoCardz is reporting (via BenchLife) that a card called either the GTX 1080 or GTX 1800 will be announced, using the GP104 GPU core with 8GB of GDDR5X - and not HBM2.

The report also claims that NVIDIA CEO Jen-Hsun Huang will have an announcement for Pascal in April, which leads us to believe a shipping product based on Pascal is finally in the works. Taking in all of the information from the BenchLife report, VideoCardz has created this list to summarize the rumors (taken directly from the source link):

  • Pascal launch in April
  • GTX 1080/1800 launch in May 27th
  • GTX 1080/1800 has GP104 Pascal GPU
  • GTX 1080/1800 has 8GB GDDR5X memory
  • GTX 1080/1800 has one 8pin power connector
  • GTX 1080/1800 has 1x DVI, 1x HDMI, 2x DisplayPort
  • First Pascal board with HBM would be GP100 (Big Pascal)

VideoCardz_Chart.png

Rumored GTX 1080 Specs (Credit: VideoCardz)

The alleged single 8-pin power connector with this GTX 1080 would place the power limit at 225W, though it could very well require less power. The GTX 980 is only a 165W part, with the GTX 980 Ti rated at 250W.

As always, only time will tell how accurate these rumors are; though VideoCardz points out "BenchLife stories are usually correct", though they are skeptical of the report based on the name GTX 1080 (though this would follow the current naming scheme of GeForce cards).

Source: VideoCardz

GDDR5X Memory Standard Gets Official with JEDEC

Subject: Graphics Cards, Memory | January 22, 2016 - 11:08 AM |
Tagged: Polaris, pascal, nvidia, jedec, gddr5x, GDDR5, amd

Though information about the technology has been making rounds over the last several weeks, GDDR5X technology finally gets official with an announcement from JEDEC this morning. The JEDEC Solid State Foundation is, as Wikipedia tells us, an "independent semiconductor engineering trade organization and standardization body" that is responsible for creating memory standards. Getting the official nod from the org means we are likely to see implementations of GDDR5X in the near future.

The press release is short and sweet. Take a look.

ARLINGTON, Va., USA – JANUARY 21, 2016 –JEDEC Solid State Technology Association, the global leader in the development of standards for the microelectronics industry, today announced the publication of JESD232 Graphics Double Data Rate (GDDR5X) SGRAM.  Available for free download from the JEDEC website, the new memory standard is designed to satisfy the increasing need for more memory bandwidth in graphics, gaming, compute, and networking applications.

Derived from the widely adopted GDDR5 SGRAM JEDEC standard, GDDR5X specifies key elements related to the design and operability of memory chips for applications requiring very high memory bandwidth.  With the intent to address the needs of high-performance applications demanding ever higher data rates, GDDR5X  is targeting data rates of 10 to 14 Gb/s, a 2X increase over GDDR5.  In order to allow a smooth transition from GDDR5, GDDR5X utilizes the same, proven pseudo open drain (POD) signaling as GDDR5.

“GDDR5X represents a significant leap forward for high end GPU design,” said Mian Quddus, JEDEC Board of Directors Chairman.  “Its performance improvements over the prior standard will help enable the next generation of graphics and other high-performance applications.”

JEDEC claims that by using the same signaling type as GDDR5 but it is able to double the per-pin data rate to 10-14 Gb/s. In fact, based on leaked slides about GDDR5X from October, JEDEC actually calls GDDR5X an extension to GDDR5, not a new standard. How does GDDR5X reach these new speeds? By doubling the prefech from 32 bytes to 64 bytes. This will require a redesign of the memory controller for any processor that wants to integrate it. 

gddr5x.jpg

Image source: VR-Zone.com

As for usable bandwidth, though information isn't quoted directly, it would likely see a much lower increase than we are seeing in the per-pin statements from the press release. Because the memory bus width would remain unchanged, and GDDR5X just grabs twice the chunk sizes in prefetch, we should expect an incremental change. No mention of power efficiency is mentioned either and that was one of the driving factors in the development of HBM.

07-bwperwatt.jpg

Performance efficiency graph from AMD's HBM presentation

I am excited about any improvement in memory technology that will increase GPU performance, but I can tell you that from my conversations with both AMD and NVIDIA, no one appears to be jumping at the chance to integrate GDDR5X into upcoming graphics cards. That doesn't mean it won't happen with some version of Polaris or Pascal, but it seems that there may be concerns other than bandwidth that keep it from taking hold. 

Source: JEDEC

Report: NVIDIA Pascal GP104 Discovered, May Not Use HBM

Subject: Graphics Cards | January 11, 2016 - 06:05 PM |
Tagged: rumor, report, pascal, nvidia, HBM2, hbm, GP104

A delivery of GPUs and related test equipment from Taiwan to Banglore has led to speculation about NVIDIA's upcoming GP104 Pascal GPU.

GP104_delivery.png

Image via Zauba.com

How much information can be gleaned from an import shipping manifest (linked here)? The data indicates a chip with a 37.5 x 37.5 mm package and 2152 pins, which is being attributed to the GP104 based on knowledge of “earlier, similar deliveries” (or possible inside information). This has prompted members of the 3dcenter.org forums (German language) to speculate on the use of GDDR5 or GDDR5X memory based on the likelihood of HBM being implemented on a die of this size. 

Of course, NVIDIA has stated that Pascal will implement 3D memory, and the upcoming GP100 will reportedly be on a 55 x 55 mm package using HBM2. Could this be a new, lower-cost part using the existing GDDR5 standard or the faster GDDR5X instead? VideoCardz and WCCFtech have posted stories based on the 3DCenter report, and to quote directly from the VideoCardz post on the subject:

"3DCenter has a theory that GP104 could actually not use HBM, but GDDR5(X) instead. This would rather be a very strange decision, but could NVIDIA possibly make smaller GPU (than GM204) and still accommodate 4 HBM modules? This theory is not taken from the thin air. The GP100 aka the Big Pascal, would supposedly come in 55x55mm BGA package. That’s 10mm more than GM200, which were probably required for additional HBM modules. Of course those numbers are for the whole package (with interposer), not just the GPU."

All of this is a lot to take from a shipping record that might not even be related to an NVIDIA product, but the report has made the rounds at this point so now we’ll just have to wait for new information.

Source: 3DCenter.org

CES 2016 Podcast Day 1 - Lenovo, NVIDIA Press Conference, new AMD GPUs and more!

Subject: General Tech | January 5, 2016 - 04:40 AM |
Tagged: podcast, video, CES, CES 2016, Lenovo, Thinkpad, x1 carbon, x1 yoga, nvidia, pascal, amd, Polaris, FinFET, 14nm

CES 2016 Podcast Day 1 - 01/05/16

CES is just beginning. Join us for announcements from Lenovo, NVIDIA Press Conference, new AMD GPUs and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Josh Walrath, Allyn Malventano, Ken Addison and Sebastian Peak

Program length: 1:11:05

Be sure to subscribe to the PC Perspective YouTube channel!!

CES 2016: NVIDIA Launches DRIVE PX 2 With Dual Pascal GPUs Driving A Deep Neural Network

Subject: General Tech | January 5, 2016 - 01:17 AM |
Tagged: tegra, pascal, nvidia, driveworks, drive px 2, deep neural network, deep learning, autonomous car

NVIDIA is using the Consumer Electronics Show to launch the Drive PX 2 which is the latest bit of hardware aimed at autonomous vehicles. Several NVIDIA products combine to create the company's self-driving "end to end solution" including DIGITS, DriveWorks, and the Drive PX 2 hardware to train, optimize, and run the neural network software that will allegedly be the brains of future self-driving cars (or so NVIDIA hopes).

NVIDIA DRIVE PX 2 Self Driving Car Supercomputer.jpg

The Drive PX 2 hardware is the successor to the Tegra-powered Drive PX released last year. The Drive PX 2 represents a major computational power jump with 12 CPU cores and two discrete "Pascal"-based GPUs! NVIDIA has not revealed the full specifications yet, but they have made certain details available. There are two Tegra SoCs along with two GPUs that are liquid cooled. The liquid cooling consists of a large metal block with copper tubing winding through it and then passing into what looks to be external connectors that attach to a completed cooling loop (an exterior radiator, pump, and reservoir).

There are a total of 12 CPU cores including eight ARM Cortex A57 cores and four "Denver" cores. The discrete graphics are based on the 16nm FinFET process and will use the company's upcoming Pascal architecture. The total package will draw a maximum of 250 watts and will offer up to 8 TFLOPS of computational horsepower and 24 trillion "deep learning operations per second." That last number relates to the number of special deep learning instructions the hardware can process per second which, if anything, sounds like an impressive amount of power when it comes to making connections and analyzing data to try to classify it. Drive PX 2 is, according to NVIDIA, 10 times faster than it's predecessor at running these specialized instructions and has nearly 4 times the computational horsepower when it comes to TLOPS.

Similar to the original Drive PX, the driving AI platform can accept and process the inputs of up to 12 video cameras. It can also handle LiDAR, RADAR, and ultrasonic sensors. NVIDIA compared the Drive PX 2 to the TITAN X in its ability to process 2,800 images per second versus the consumer graphics card's 450 AlexNet images which while possibly not the best comparison does make it look promising.

NVIDIA DRIVE PX 2 DRIVEWORKS.jpg

Neural networks and machine learning are at the core of what makes autonomous vehicles possible along with hardware powerful enough to take in a multitude of sensor data and process it fast enough. The software side of things includes the DriveWorks development kit which includes specialized instructions and a neural network that can detect objects based on sensor input(s), identify and classify them, determine the positions of objects relative to the vehicle, and calculate the most efficient path to the destination.

Specifically, in the press release NVIDIA stated:

"This complex work is facilitated by NVIDIA DriveWorks™, a suite of software tools, libraries and modules that accelerates development and testing of autonomous vehicles. DriveWorks enables sensor calibration, acquisition of surround data, synchronization, recording and then processing streams of sensor data through a complex pipeline of algorithms running on all of the DRIVE PX 2's specialized and general-purpose processors. Software modules are included for every aspect of the autonomous driving pipeline, from object detection, classification and segmentation to map localization and path planning."

DIGITS is the platform used to train the neural network that is then used by the Drive PX 2 hardware. The software is purportedly improving in both accuracy and training time with NVIDIA achieving a 96% accuracy rating at identifying traffic signs based on the traffic sign database from Ruhr University Bochum after a training session lasting only 4 hours as opposed to training times of days or even weeks.

NVIDIA claims that the initial Drive PX has been picked up by over 50 development teams (automakers, universities, software developers, et al) interested in autonomous vehicles. Early access to development hardware is expected to be towards the middle of the year with general availability of final hardware in Q4 2016.

The new Drive PX 2 is getting a serious hardware boost with the inclusion of two dedicated graphics processors (the Drive PX was based around two Tegra X1 SoCs), and that should allow automakers to really push what's possible in real time and push the self-driving car a bit closer to reality and final (self) drive-able products. I'm excited to see that vision come to fruition and am looking forward to seeing what this improved hardware will enable in the auto industry!

Coverage of CES 2016 is brought to you by Logitech!

PC Perspective's CES 2016 coverage is sponsored by Logitech.

Follow all of our coverage of the show at http://pcper.com/ces!

Source: NVIDIA

Meet the OberonStation, kid friendly and powered with the son of Pascal

Subject: General Tech | December 3, 2015 - 12:41 PM |
Tagged: OberonStation, pascal, oberon

To paraphrase Barbie, "Linux is hard".  Present a child with a Linux powered Pi of whichever flavour you like and you will spend a lot more time trying to explain why they have to do things a certain way instead of letting them create on their own.  The OberonStation was released at the same time as the Pi Zero we have heard about but it has a significant difference.  It uses a descendent of the Pascal programming language, which some readers may remember for both the OS and the programs which will run on the OberonStation.  This simplifies things greatly and while it will limit what the device can do compared to a Pi it also means it is a better teaching tool for young programmers who won't have to learn the odd and twisted world of Linux ... or at least not yet.

The Register compares it to learning on a ZX Spectrum or Amiga 600, simple enough to grasp but yet useful enough to give you a solid foundation in programming practices and functions.  This will make it more interesting and accessible for youth you want to corrupt with thoughts of a future in programming and electronics.  It is unfortunately sold out, if you are still interested in turning your kids or young relatives to the dark side consider one of the littleBits kits available at MAKE such as the Deluxe Kit, it is a great way to introduce them to electronics and to get some nifty devices out of the deal as well!

ObStAnato.png

"Two tiny, inexpensive, single-board educational computers just shipped. One has had lots of coverage already, but the odds are you've never heard of the other machine. However, the idea behind the obscure one is more important."

Here is some more Tech News from around the web:

Tech Talk

 

Source: The Register