Podcast #397 - AMD Radeon Pro Duo, NZXT Manta, AMD's new deal with China, and more!

Subject: General Tech | April 28, 2016 - 01:50 PM |
Tagged: video, radeon pro duo, podcast, nzxt, nvidia, Manta, GTX 1080, GT 710, GP104, amd, Alpha 12

PC Perspective Podcast #397 - 04/28/2016

Join us this week as we discuss the AMD Radeon Pro Duo, NZXT Manta, AMD's new deal with China, 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!!

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 #396 - MSI Gaming Notebooks, Intel Layoffs, the PlayStation Neo and more!

Subject: General Tech | April 21, 2016 - 01:37 PM |
Tagged: podcast, video, msi, Intel, Playstation, ps4, neo, ps4k, phanteks, idf, Optane, XPoint, western digital, nvidia, GTX 1080

PC Perspective Podcast #396 - 04/21/2016

Join us this week as we discuss MSI Gaming Notebooks, Intel Layoffs, the PlayStation Neo 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!!

Report: NVIDIA GTX 1080 GPU Cooler Pictured

Subject: Graphics Cards | April 19, 2016 - 11:08 AM |
Tagged: rumor, report, nvidia, leak, GTX 1080, graphics card, gpu, geforce

Another reported photo of an upcoming GTX 1080 graphics card has appeared online, this time via a post on Baidu.

GTX1080.jpg

(Image credit: VR-Zone, via Baidu)

The image is typically low-resolution and features the slightly soft focus we've come to expect from alleged leaks. This doesn't mean it's not legitimate, and this isn't the first time we have seen this design. This image also appears to only be the cooler, without an actual graphics card board underneath.

We have reported on the upcoming GPU rumored to be named "GTX 1080" in the recent past, and while no official announcement has been made it seems safe to assume that a successor to the current 900-series GPUs is forthcoming.

Source: VR-Zone

NVIDIA Releases 364.96 Hotfix Driver

Subject: Graphics Cards | April 14, 2016 - 06:44 PM |
Tagged: nvidia, graphics drivers

The GeForce 364.xx line of graphics drivers hasn't been smooth for NVIDIA. Granted, they tried to merge Vulkan support into their main branch at the same time as several new games, including DirectX 12 ones, launched. It was probably a very difficult period for NVIDIA, but WHQL-certified drivers should be better than this.

nvidia-2015-bandaid.png

Regardless, they're trying, and today they released GeForce Hot Fix Driver 364.96. Some of the early reactions mock NVIDIA for adding “Support for DOOM Open Beta” as the only listed feature of a “hotfix” driver, but I don't see it. It's entirely possible that the current drivers have a known issue with DOOM Open Beta and, thus, they require a hotfix. It's not necessarily “just a profile,” and “profiles” isn't exactly what a hardware vendor does to support a new title.

But anyway, Manuel Guzman, one of the faces for NVIDIA Customer Care, also says that this driver includes fixes for FPS drops in Dark Souls 3. According to some forum-goers, despite its numbering, it also does not contain the Vulkan updates from 364.91. This is probably a good thing, because it would be a bit silly to merge developer-branch features into a customer driver that only intends to solve problems before an official driver can be certified. I mean, that's like patching a flat tire, then drilling a hole in one of the good ones to mess around with it, too.

The GeForce 364.96 Hotfix Drivers are available at NVIDIA's website. If you're having problems, then it might be your solution. Otherwise? Wait until NVIDIA has an official release (or you start getting said problems).

NVIDIA Releases 364.91 Beta Drivers for Developers

Subject: Graphics Cards | April 10, 2016 - 09:04 PM |
Tagged: nvidia, vulkan, graphics drivers

This is not a main-line, WHQL driver. This is not even a mainstream beta driver. The beta GeForce 364.91 drivers (364.16 on Linux) are only available on the NVIDIA developer website, which, yes, is publicly accessible, but should probably not be installed unless you are intending to write software and every day counts. Also, some who have installed it claim that certain Vulkan demos stop working. I'm not sure whether that means the demo is out-of-date due to a rare conformance ambiguity, the driver has bugs, or the reports themselves are simply unreliable.

khronos-2016-vulkanlogo2.png

That said, if you are a software developer, and you don't mind rolling back if things go awry, you can check out the new version at NVIDIA's website. It updates Vulkan to 1.0.8, which is just documentation bugs and conformance tweaks. These things happen over time. In fact, the initial Vulkan release was actually Vulkan 1.0.3, if I remember correctly.

The driver also addresses issues with Vulkan and NVIDIA Optimus technologies, which is interesting. Optimus controls which GPU acts as primary in a laptop, switching between the discrete NVIDIA one and the Intel integrated one, depending on load and power. Vulkan and DirectX 12, however, expose all GPUs to the system. I'm curious how NVIDIA knows whether to sleep one or the other, and what that would look like to software that enumerates all compatible devices. Would it omit listing one of the GPUs? Or would it allow the software to wake the system out of Optimus should it want more performance?

Anywho, the driver is available now, but you probably should wait for official releases. The interesting thing is this seems to mean that NVIDIA will continue to release non-public Vulkan drivers. Hmm.

Source: NVIDIA

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!!

EVGA Releases NVIDIA GeForce GTX 950 Low Power Cards

Subject: Graphics Cards | April 5, 2016 - 11:57 AM |
Tagged: PCIe power, nvidia, low-power, GTX950, GTX 950 Low Power, graphics card, gpu, GeForce GTX 950, evga

EVGA has announced new low-power versions of the NVIDIA GeForce GTX 950, some of which do not require any PCIe power connection to work.

02G-P4-0958-KR_no_6_pin.jpg

"The EVGA GeForce GTX 950 is now available in special low power models, but still retains all the performance intact. In fact, several of these models do not even have a 6-Pin power connector!"

With or without power, all of these cards are full-on GTX 950's, with 768 CUDA cores and 2GB of GDDR5 memory. The primary difference will be with clock speeds, and EVGA provides a chart to illustrate which models still require PCIe power, as well as how they compare in performance.

evga_chart.png

It looks like the links to the 75W (no PCIe power required) models aren't working just yet on EVGA's site. Doubtless we will soon have active listings for pricing and availability info.

Source: EVGA