Report: NVIDIA GeForce GTX 1050 Ti Based on Pascal GP107

Subject: Graphics Cards | October 2, 2016 - 12:12 PM |
Tagged: rumor, report, pascal, nvidia, GTX 1050 Ti, graphics card, gpu, GP107, geforce

A report published by VideoCardz.com (via Baidu) contains pictures of an alleged NVIDIA GeForce GTX 1050 Ti graphics card, which is apparently based on a new Pascal GP107 GPU.

NVIDIA-GTX-1050-Ti-PCB-1.jpg

Image credit: VideoCardz

The card shown is also equipped with 4GB of GDDR5 memory, and contains a 6-pin power connector - though such a power requirement might be specific to this particular version of the upcoming GPU.

NVIDIA-GTX-1050-Ti-PCB-2.jpg

Image credit: VideoCardz

Specifications for the GTX 1050 Ti were previously reported by VideoCardz, with a reported GPU-Z screenshot. The card will apparently feature 768 CUDA cores and a 128-bit memory bus, with clock speeds (for this particular sample) of 1291 MHz base, 1392 MHz boost (with some room to overclock, from this screenshot).

NVIDIA-GeForce-GTX-1050-Ti-GPUZ-Specs.jpg

Image credit: VideoCardz

An official announcement for the new GPU has not been made by NVIDIA, though if these PCB photos are real it probably won't be far off.

Source: VideoCardz

NVIDIA Teases Low Power, High Performance Xavier SoC That Will Power Future Autonomous Vehicles

Subject: Processors | October 1, 2016 - 06:11 PM |
Tagged: xavier, Volta, tegra, SoC, nvidia, machine learning, gpu, drive px 2, deep neural network, deep learning

Earlier this week at its first GTC Europe event in Amsterdam, NVIDIA CEO Jen-Hsun Huang teased a new SoC code-named Xavier that will be used in self-driving cars and feature the company's newest custom ARM CPU cores and Volta GPU. The new chip will begin sampling at the end of 2017 with product releases using the future Tegra (if they keep that name) processor as soon as 2018.

NVIDIA_Xavier_SOC.jpg

NVIDIA's Xavier is promised to be the successor to the company's Drive PX 2 system which uses two Tegra X2 SoCs and two discrete Pascal MXM GPUs on a single water cooled platform. These claims are even more impressive when considering that NVIDIA is not only promising to replace the four processors but it will reportedly do that at 20W – less than a tenth of the TDP!

The company has not revealed all the nitty-gritty details, but they did tease out a few bits of information. The new processor will feature 7 billion transistors and will be based on a refined 16nm FinFET process while consuming a mere 20W. It can process two 8k HDR video streams and can hit 20 TOPS (NVIDIA's own rating for deep learning int(8) operations).

Specifically, NVIDIA claims that the Xavier SoC will use eight custom ARMv8 (64-bit) CPU cores (it is unclear whether these cores will be a refined Denver architecture or something else) and a GPU based on its upcoming Volta architecture with 512 CUDA cores. Also, in an interesting twist, NVIDIA is including a "Computer Vision Accelerator" on the SoC as well though the company did not go into many details. This bit of silicon may explain how the ~300mm2 die with 7 billion transistors is able to match the 7.2 billion transistor Pascal-based Telsa P4 (2560 CUDA cores) graphics card at deep learning (tera-operations per second) tasks. Of course in addition to the incremental improvements by moving to Volta and a new ARMv8 CPU architectures on a refined 16nm FF+ process.

  Drive PX Drive PX 2 NVIDIA Xavier Tesla P4
CPU 2 x Tegra X1 (8 x A57 total) 2 x Tegra X2 (8 x A57 + 4 x Denver total) 1 x Xavier SoC (8 x Custom ARM + 1 x CVA) N/A
GPU 2 x Tegra X1 (Maxwell) (512 CUDA cores total 2 x Tegra X2 GPUs + 2 x Pascal GPUs 1 x Xavier SoC GPU (Volta) (512 CUDA Cores) 2560 CUDA Cores (Pascal)
TFLOPS 2.3 TFLOPS 8 TFLOPS ? 5.5 TFLOPS
DL TOPS ? 24 TOPS 20 TOPS 22 TOPS
TDP ~30W (2 x 15W) 250W 20W up to 75W
Process Tech 20nm 16nm FinFET 16nm FinFET+ 16nm FinFET
Transistors ? ? 7 billion 7.2 billion

For comparison, the currently available Tesla P4 based on its Pascal architecture has a TDP of up to 75W and is rated at 22 TOPs. This would suggest that Volta is a much more efficient architecture (at least for deep learning and half precision)! I am not sure how NVIDIA is able to match its GP104 with only 512 Volta CUDA cores though their definition of a "core" could have changed and/or the CVA processor may be responsible for closing that gap. Unfortunately, NVIDIA did not disclose what it rates the Xavier at in TFLOPS so it is difficult to compare and it may not match GP104 at higher precision workloads. It could be wholly optimized for int(8) operations rather than floating point performance. Beyond that I will let Scott dive into those particulars once we have more information!

Xavier is more of a teaser than anything and the chip could very well change dramatically and/or not hit the claimed performance targets. Still, it sounds promising and it is always nice to speculate over road maps. It is an intriguing chip and I am ready for more details, especially on the Volta GPU and just what exactly that Computer Vision Accelerator is (and will it be easy to program for?). I am a big fan of the "self-driving car" and I hope that it succeeds. It certainly looks to continue as Tesla, VW, BMW, and other automakers continue to push the envelope of what is possible and plan future cars that will include smart driving assists and even cars that can drive themselves. The more local computing power we can throw at automobiles the better and while massive datacenters can be used to train the neural networks, local hardware to run and make decisions are necessary (you don't want internet latency contributing to the decision of whether to brake or not!).

I hope that NVIDIA's self-proclaimed "AI Supercomputer" turns out to be at least close to the performance they claim! Stay tuned for more information as it gets closer to launch (hopefully more details will emerge at GTC 2017 in the US).

What are your thoughts on Xavier and the whole self-driving car future?

Also read:

Source: NVIDIA

The Founders Edition is not the foundation of NVIDIA's retail career

Subject: General Tech | September 29, 2016 - 03:14 PM |
Tagged: nvidia, competition, jen-hsun huang, Founder's Edition

When Microsoft launched the Surface there were negative reactions from vendors who saw this as new competition from what was previously their partner.  Today DigiTimes reports that certain unnamed GPU vendors have similar feelings about NVIDIA's Founder's Edition cards.  Jen-Hsun responded to these comments today, stating that the Founders Editions were "purely to solve problems in graphics card design". 

While he did not say that NVIDIA would not consider continuing practice in future cards he does correctly point out that they did share everything about the design and results with the vendors.  Those vendors are still somewhat upset about the month in which only Founder's Editions were available for sale as they feel they lost some possible profits by not being able to sell their custom designed GPUs.  Then again, considering the limited supply on the market, the amount of sales they could have made that extra month would certainly have been limited.  It will be interesting to see if we hear more about this directly from the vendors in the coming weeks.

product_9_20160511110531_5732a17b96b90.png

"Since Nvidia has restricted its graphics card brand partners from releasing in-house designed graphics cards within a month after the releases of its Founders Edition card, the graphics card vendors are displeased with the decision as it had given Nvidia time to earn early profits without competition."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes

More VR testing, Trickster VR on the Vive

Subject: Graphics Cards | September 27, 2016 - 01:57 PM |
Tagged: VR, trickster vr, amd, nvidia, htc vive

[H]ard|OCP continues their look into the performance of VR games on NVIDIA's Titan X, GTX 1080, 1070, 1060 and 970 as well as AMD's Fury X and RX 480.  This particular title allowed AMD to shine, they saw the RX 480 come within a hair of matching the GTX 1060 which is a first for them and shows that AMD can be a contender in the VR market.  Pop by to see their review in full.

1474559750rGnsjoIAJs_6_1.jpg

"Arm yourself with a bow and arrows, a magic sword that flies, or if you prefer, a handful of throwing darts. Then get ready to take on the procedurally generated fantasy world full of cartoonish Orcs, and more Orcs, and some other Orcs. Headshots count as well as chaining your shots so aim is critical. Did I mention the Orcs?"

Here are some more Graphics Card articles from around the web:

Graphics Cards

Source: [H]ard|OCP

Podcast #418 - Air cooler roundup, Samsung 960 EVO and Pro announced and more!

Subject: General Tech | September 22, 2016 - 11:25 AM |
Tagged: video, Samsung, rivet, podcast, nvidia, msi, killer network, fatal1ty, evga, cooler, amd, 960 PRO, 960 EVO

PC Perspective Podcast #418 - 09/22/16

Join us this week as we discuss an air cooler roundup, Samsung 960 EVO and Pro announcement 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!

Hosts:  Josh Walrath, Jeremy Hellstrom, Sebastian Peak and Ken Addison

NVIDIA Releases GeForce 372.90 Drivers

Subject: Graphics Cards | September 21, 2016 - 05:54 PM |
Tagged: nvidia, graphics drivers

With Forza Horizon 3 coming out for Ultimate Edition SKU users in a little over a day, NVIDIA has released their new Game Ready drivers. GeForce 372.90 drivers roll in all of NVIDIA's fixes for the game that have been discovered during its development.

nvidia-geforce.png

Thankfully, unlike the slippage that I've witnessed from them recently in this regard, the release notes for 372.90 are quite verbose (PDF). For instance, and this probably affects a few of our readers, NVIDIA has finally fixed the issue with HTC Vive over DisplayPort. Their description sounds like it wasn't failing to connect, as users believed, but rather it was just failing to light up the display. Of course, from a user's standpoint, a black screen is a black screen, but it's interesting to see what honest admissions of what exactly any given error was.

So, TL;DR: HTC Vive users should be able to use it over DisplayPort with Pascal again.

Also, they announced that the driver contains security updates. They don't elaborate on what specifically was fixed, especially since it will take a while for users to update, but it sounds like NVIDIA was in bug-fixing mode with this driver, which I appreciate.

You can get GeForce 372.90 from GeForce Experience and their website.

Source: NVIDIA

NVIDIA Bundles Gears of War 4 with GTX 1080 & GTX 1070

Subject: Graphics Cards | September 20, 2016 - 03:58 PM |
Tagged: microsoft, xbox, xbox one, pc gaming, nvidia, GTX 1080, gtx 1070

NVIDIA has just announced that specially marked, 10-series GPUs will be eligible for a Gears of War 4 download code. This bundle applies to GeForce GTX 1080 and GeForce GTX 1070 desktop GPUs, as well as laptops which integrate either of those two GPUs. As always, if you plan on purchasing a GPU due to this bundle, make sure that the product page for your retailer mentions the bundle.

nvidia-2016-gears-of-war-4-nvidia-geforce-gtx-bundle-key.jpg

Also, through the Xbox Play Anywhere initiative, NVIDIA claims that this code can be used to play the game on Xbox One as well. Xbox Play Anywhere allows users to purchase a game on either of Microsoft's software stores, Xbox Store or Windows Store, and it will automatically count as a purchase for the cross-platform equivalent. It also has implications for cloud saves, but that's a story for another day.

The bundle begins today, September 20th. Gears of War 4 launches on October 11th.

Source: NVIDIA

Podcast #417 - Maximus VIII Forumla, MoCA adapters, GFE logins and more!!

Subject: General Tech | September 15, 2016 - 01:58 PM |
Tagged: VR, video, tesla, Silverstone, podcast, nvidia, msi, MoCA, Maximus VIII Formula, MasterLiquid, holodeck, GFE, geforce experience, euclideon, cooler master, asus, actiontec

PC Perspective Podcast #417 - 09/15/16

Join us this week as we discuss the Maximus VIII Forumla, MoCA adapters, GFE logins 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!

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

Program length: 1:36:39
  1. Week in Review:
  2. This episode is brought to you by Casper! (Use code “pcper”)
  3. News items of interest:
  4. Hardware/Software Picks of the Week
  5. Closing/outro

Eight is enough, looking at how the new Telsa HPC cards from NVIDIA will work

Subject: General Tech | September 14, 2016 - 01:06 PM |
Tagged: pascal, tesla, p40, p4, nvidia, neural net, m40, M4, HPC

The Register have package a nice explanation of the basics of how neural nets work in their quick look at NVIDIA's new Pascal based HPC cards, the P4 and P40.  The tired joke about Zilog or Dick Van Patten stems from the research which has shown that 8-bit precision is most effective when feeding data into a neural net.  Using 16 or 32-bit values slows the processing down significantly while adding little precision to the results produced.  NVIDIA is also perfecting a hybrid mode, where you can opt for a less precise answer produced by your local, presumably limited, hardware or you can upload the data to the cloud for the full treatment.  This is great for those with security concerns or when a quicker answer is more valuable than a more accurate one.

As for the hardware, NVIDIA claims the optimizations on the P40 will make it "40 times more efficient" than an Intel Xeon E5 CPU and it will also provide slightly more throughput than the currently available Titan X.  You can expect to see these arrive in the market sometime over then next two months.

newtesla.PNG

"Nvidia has designed a couple of new Tesla processors for AI applications – the P4 and the P40 – and is talking up their 8-bit math performance. The 16nm FinFET GPUs use Nv's Pascal architecture and follow on from the P100 launched in June. The P4 fits on a half-height, half-length PCIe card for scale-out servers, while the beefier P40 has its eyes set on scale-up boxes."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register

The GTX 1050 is scheduled to launch at the end of September but ...

Subject: General Tech | September 9, 2016 - 12:44 PM |
Tagged: rumour, nvidia, gtx 1050

DigiTimes have heard that NVIDIA hope to release the GTX 1050 at the end of the month or early in October but there are hints it may be somewhat of a paper launch.  NVIDIA will have some silicon for sale but only a few who are quick enough on the draw will be able to purchase them; similar to the launch of the GTX 1080 and 1070 or even AMD's new cards for that matter.  Both vendors had great difficulty providing retailers with cards to sell at launch, the supply has increased and prices are much closer to the MSRP than they were a month ago but there are still plenty of out of stock models when you start looking for deals. 

Hopefully this situation will resolve soon, but for now patience is recommended for upgraders on a tight budget.

index.png

"Nvidia's Pascal-based GeForce GTX 1080, 1070 and 1060 graphics cards are seeing strong demand from the market and therefore are currently in tight supply. To further expand into the market, Nvidia is planning to release its mid-range GTX 1050 graphics card at the end of September at the earliest."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes