AMD FirePro S-Series Introduces Hardware-Based GPU Virtualization

Subject: Graphics Cards | February 3, 2016 - 02:37 AM |
Tagged: virtual machines, virtual graphics, mxgpu, gpu virtualization, firepro, amd

AMD made an interesting enterprise announcement today with the introduction of new FirePro S-Series graphics cards that integrate hardware-based virtualization technology. The new FirePro S1750 and S1750 x2 are aimed at virtualized workstations, render farms, and cloud gaming platforms where each virtual machine has direct access to the graphics hardware.

The new graphics cards use a GCN-based Tonga GPU with 2,048 stream processors paired with 8GB of ECC GDDR5 memory on the single slot FirePro S1750. The dual slot FirePro S1750 x2, as the name suggests, is a dual GPU card that features a total of 4,096 shaders (2,048 per GPU) and 16 GB of ECC GDDR5 (8 GB per GPU). The S1750 has a TDP of 150W while the dual-GPU S1750 x2 variant is rated at 265W and either can be passively cooled.

AMD FirePro S1750 x2 Hardare-based virtualized GPU MxGPU.png

Where the graphics cards get niche is the inclusion of what AMD calls MxGPU (Multi-User GPU) technology which is derived from the SR-IOV (Single Root Input/Output Virtualization) PCI-Express standard. According to AMD, the new FirePro S-Series allows virtual machines direct access to the full range of GPU hardware (shaders, memory, ect.) and OpenCL 2.0 support on the software side. The S1750 supports up to 16 simultaneous users and the S1750 x2 tops out at 32 users. Each virtual machine is allocated an equal slice of the GPU, and as you add virtual machines the equal slices get smaller. AMD’s solution to that predicament is to add more GPUs to spread out the users and allocate each VM more hardware horsepower. It is worth noting that AMD has elected not to charge companies any per-user licensing fees for all these VMs the hardware supports which should make these cards more competitive.

The graphics cards use ECC memory to correct errors when dealing with very large numbers and calculations and every VM is reportedly protected and isolated such that one VM can not access any data of a different VM stored in graphics memory.

I am interested to see how these stack up compared to NVIDIA’s GRID and VGX GPU virtualization specialized graphics cards. The difference between the software versus hardware-based virtualization may not make much difference, but AMD’s approach may be every so slightly more efficient with the removal of layer between the virtual machine and hardware. We’ll have to wait and see, however.

Enterprise users will be able to pick up the new cards installed in systems from server manufacturers sometime in the first half of 2016. Pricing for the cards themselves appears to be $2,399 for the single GPU S1750 and $3,999 for the dual GPU S1750 x2.

Needless to say, this is all a bit more advanced (and expensive!) than the somewhat finicky 3D acceleration option desktop users can turn on in VMWare and VirtualBox! Are you experimenting with remote workstations and virtual machines for thin clients that can utilize GPU muscle? Does AMD’s MxGPU approach seem promising?

Source: AMD

EVGA Winter 2016 Prize Pack and Giveaway!!

Subject: General Tech, Graphics Cards, Motherboards, Cases and Cooling | February 2, 2016 - 02:07 PM |
Tagged: Z170, PSU, power supply, motherboard, GTX 970, giveaway, ftw, evga, contest

For many of you reading this, the temperature outside has fallen to its deepest levels, making it hard to even bare the thought of going outdoors. What would help out a PC enthusiast and gamer in this situation? Some new hardware, delivered straight to your door, to install and assist in warming up your room, that's what!

PC Perspective has partnered up with EVGA to offer up three amazing prizes for our fans. They include a 750 G2 power supply (obviously with a 750 watt rating), a Z170 FTW motherboard and a GTX 970 SSC Gaming ACX 2.0+ graphics card. The total prize value is over $650 based on MSRPs!

All you have to do to enter is follow the easy steps in the form below. 

We want to thank EVGA for its support of PC Perspective in this contest and over the years. Here's to a great 2016 for everyone!

EVGA Winter 2016 Giveaway!!

 

The ~$220 showdown, XFX R9 380 DD Black Edition OC 4GB versus the GTX 960

Subject: Graphics Cards | January 25, 2016 - 03:19 PM |
Tagged: XFX R9 380 Double Dissipation Black Edition OC 4GB, xfx, gtx 960

In one corner is the XFX R9 380 DD Black Edition OC 4GB, at factory settings and with an overclock of 1170MHz core and 6.4GHz memory and in the other corner is a GTX 960 with a 1178MHz Boost clock and 7GHz memory.  These two contenders will compete in a six round 1080p match featuring Fallout 4, Project Cars, Witcher 3, GTAV, Dying Light and BF4 to see which is worthy of your hard earned buckaroos.  Your referee for today will be [H]ard|OCP, tune in to see the final results.

1452968502DlKPGLEWlN_1_7_l.jpg

"Today we evaluate a custom R9 380 from XFX, the XFX R9 380 DD BLACK EDITION OC 4GB. Sporting a hefty factory overclock and the Ghost Thermal 3.0 custom cooling with Double Dissipation, we compare it to an equally priced reference GeForce GTX 960. Find out which video card provides the better bargain."

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

Graphics Cards

 

Source: [H]ard|OCP

AMD Shows Dual-Fiji Graphics Card in a Falcon Northwest PC at VRLA

Subject: Graphics Cards | January 25, 2016 - 11:51 AM |
Tagged: fury x2, Fiji, dual fiji, amd

Lo and behold! The dual-Fiji card that we have previous dubbed the AMD Radeon Fury X2 still lives! Based on a tweet from AMD PR dude Antal Tungler, a PC from Falcon Northwest at the VRLA convention was utilizing a dual-GPU Fiji graphics card to power some demos.

This prototype Falcon Northwest Tiki system was housing the GPU beast but no images were shown of the interior of the system. Still, it's good to see AMD at least recognize that this piece of hardware still exists at all, since it was initially promised to the enthusiast market by "fall of 2015."  Even in October we had hints that the card might be coming soon after seeing some shipping manifests leak out to the web. 

dualfuryken_0.jpg

Better late than never, right? One theory floating around inside the offices here is that AMD is going to release the Fury X2 along with the VR headsets coming out this spring, with hopes of making it THE VR graphics card of choice. The value of using multi-GPU for VR is interesting, with one GPU dedicated to each eye, though the pitfalls that could haunt both AMD and NVIDIA in this regard (latency, frame time consistency) make the technological capability a debate. 

Source: Twitter

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

Phoronix Tests Almost a Decade of GPUs

Subject: Graphics Cards | January 20, 2016 - 03:26 PM |
Tagged: nvidia, linux, tesla, fermi, kepler, maxwell

It's nice to see long-term roundups every once in a while. They do not really provide useful information for someone looking to make a purchase, but they show how our industry is changing (or not). In this case, Phoronix tested twenty-seven NVIDIA GeForce cards across four architectures: Tesla, Fermi, Kepler, and Maxwell. In other words, from the GeForce 8 series all the way up to the GTX 980 Ti.

phoronix-2016-many-nvidia-roundup.jpg

Image Credit: Phoronix

Nine years of advancements in ASIC design, with a doubling time-step of 18 months, should yield a 64-fold improvement. The number of transistors falls short, showing about a 12-fold improvement between the Titan X and the largest first-wave Tesla, although that means nothing for a fabless semiconductor designer. The main reason why I include this figure is to show the actual Moore's Law trend over this time span, but it also highlights the slowdown in process technology.

Performance per watt does depend on NVIDIA though, and the ratio between the GTX 980 Ti and the 8500 GT is about 72:1. While this is slightly better than the target 64:1 ratio, these parts are from very different locations in their respective product stacks. Swapping the 8500 GT for the following year's 9800 GTX, which leads to a comparison between top-of-the-line GPUs of their respective times, and you see a 6.2x improvement in performance per watt versus the GTX 980 Ti. On the other hand, that part was outstanding for its era.

I should note that each of these tests take place on Linux. It might not perfectly reflect the landscape on Windows, but again, it's interesting in its own right.

Source: Phoronix

TSMC Allegedly Wants 5nm by 2020

Subject: Graphics Cards, Processors | January 19, 2016 - 11:38 PM |
Tagged: TSMC

Digitimes is reporting on statements that were allegedly made by TSMC co-CEO, Mark Liu. We are currently seeing 16nm parts come out of the foundry, which is expected to be used in the next generation of GPUs, replacing the long-running 28nm node that launched with the GeForce GTX 680. (It's still unannounced whether AMD and NVIDIA will use 14nm FinFET from Samsung or GlobalFoundries, or 16nm FinFET from TSMC.)

Update (Jan 20th, @4pm EST): Couple minor corrections. Radeon HD 7970 launched at 28nm first by a couple of months. I just remember NVIDIA getting swamped in delays because it was a new node, so that's probably why I thought of the GTX 680. Also, AMD announced during CES that they will use GlobalFoundries to fab their upcoming GPUs, which I apparently missed. We suspect that NVIDIA will use TSMC, and have assumed that for a while, but it hasn't been officially announced yet (if ever).

tsmc.jpg

According to their projections, which (again) are filtered through Digitimes, the foundry expects to have 7nm in the first half of 2018. They also expect to introduce extreme ultraviolet (EUV) lithography methods with 5nm in 2020. Given that Silicon in a solid has a lattice spacing of ~0.54nm at room temperature, 7nm transistors will consist of about 13 atoms, and 5nm transistors will have features containing about 9 atoms.

We continue the march toward the end of silicon lithography.

Even if the statement is correct, much can happen between then and now. It wouldn't be the first time that I've seen a major foundry believe that a node would be available, but end up having it delayed. I wouldn't hold my breath, but I might cross my fingers if my hands were free.

At the very least, we can assume that TSMC's roadmap is 16nm, 10nm, 7nm, and then 5nm.

Source: Digitimes

Samsung Mass Produces HBM2 Memory

Subject: Graphics Cards, Memory | January 19, 2016 - 11:01 PM |
Tagged: Samsung, HBM2, hbm

Samsung has just announced that they have begun mass production of 4GB HBM2 memory modules. When used on GPUs, four packages can provide 16GB of Video RAM with very high performance. They do this with a very wide data bus, which trade off frequency for transferring huge chunks. Samsung's offering is rated at 256 GB/s per package, which is twice what the Fury X could do with HBM1.

samsung-2016-4GB-HBM2-DRAM-structure_main.jpg

They also expect to mass produce 8GB HBM2 packages within this calendar year. I'm guessing that this means we'll see 32GB GPUs in the late-2016 or early-2017 time frame unless "within this year" means very, very soon (versus Q3/Q4). They will likely be for workstation or professional cards, but, in NVIDIA's case, those are usually based on architectures that are marketed to high-end gaming enthusiasts through some Titan offering. There's a lot of ways this could go, but a 32GB Titan seems like a bit much; I wouldn't expect that this affects the enthusiast gamer segment. It might mean that professionals looking to upgrade from the Kepler-based Tesla K-series might be waiting a little longer, maybe even GTC 2017. Alternatively, they might get new cards, just with a 16GB maximum until a refresh next year. There's not enough information to know one way or the other, but it's something to think about when more of it starts rolling in.

Samsung's HBM2 are compatible with ECC, although I believe that was also true for at least some HBM1 modules from SK Hynix.

Source: Samsung

Report: NVIDIA Preparing GeForce GTX 980MX and 970MX Mobile GPUs

Subject: Graphics Cards | January 19, 2016 - 10:31 AM |
Tagged: rumor, report, nvidia, GTX 980MX, GTX 980M, GTX 970MX, GTX 970M, geforce

NVIDIA is reportedly preparing faster mobile GPUs based on Maxwell, with a GTX 980MX and 970MX on the way.

img-01.jpg

The new GTX 980MX would sit between the GTX 980M and the laptop version of the full GTX 980, with 1664 CUDA cores (compared to 1536 with the 980M), 104 Texture Units (up from the 980M's 96), a 1048 MHz core clock, and up to 8 GB of GDDR5. Memory speed and bandwidth will reportedly be identical to the GTX 980M at 5000 MHz and 160 GB/s respectively, with both GPUs using a 256-bit memory bus.

The GTX 970MX represents a similar upgrade over the existing GTX 970M, with CUDA Core count increased from 1280 to 1408, Texture Units up from 80 to 88, and 8 additional raster devices available (56 vs. 48). Both the 970M and 970MX use 192-bit GDDR5 clocked at 5000 MHz, and available with the same 3 GB or 6 GB of frame buffer.

WCCFtech prepared a chart to demonstrate the differences between NVIDIA's mobile offerings:

Model GeForce GTX 980 Laptop Version GeForce GTX 980MX

GeForce GTX 980M

GeForce GTX 970MX GeForce GTX 970M GeForce GTX 965M

GeForce GTX 960M

Architecture

Maxwell Maxwell Maxwell Maxwell Maxwell Maxwell Maxwell
GPU GM204 GM204 GM204 GM204 GM204 GM204 GM107
CUDA Cores 2048 1664 1536 1408 1280 1024 640
Texture Units 128 104 96 88 80 64 40
Raster Devices 64 64 64 56 48 32 16
Clock Speed 1218 MHz 1048 MHz 1038 MHz 941 MHz 924 MHz 950 MHz 1097 MHz
Memory Bus 256-bit 256-bit 256-bit 192-bit 192-bit 128-bit 128-bit
Frame Buffer 8 GB GDDR5 8/4 GB GDDR5 8/4 GB GDDR5 6/3 GB GDDR5 6/3 GB GDDR5 4 GB GDDR5 4 GB GDDR5
Memory Frequency 7008 MHz 5000 MHz 5000 MHz 5000 MHz 5000 MHz 5000 MHz 5000 MHz
Memory Bandwidth 224 GB/s 160 GB/s 160 GB/s 120 GB/s 120 GB/s 80 GB/s 80 GB/s
TDP ~150W 125W 125W 100W 100W 90W 75W

These new GPUs will reportedly be based on the same Maxwell GM204 core, and TDPs are apparently unchanged at 125W for the GTX 980MX, and 100W for the 970MX.

We will await any official announcement.

Source: WCCFtech

AMD High-End Polaris Expected for 2016

Subject: Graphics Cards | January 18, 2016 - 09:44 PM |
Tagged: Polaris, amd

When AMD announced their Polaris architecture at CES, it was focused on mid-range applications. Their example was an add-in board that could compete against an NVIDIA GeForce GTX 950, 1080p60 medium settings in Battlefront, but do so at 39% less wattage than this 28nm, Maxwell chip. These Polaris chips are planned for a “mid 2016” launch.

amd-2016-polaris-blocks.jpg

Raja Koduri, Chief Architect for the Radeon Technologies Group, spoke with VentureBeat at the show. In his conversation, he mentioned two architectures, Polaris 10 and Polaris 11, in the context of a question about their 2016 product generation. In the “high level” space, they are seeing “the most revolutionary jump in performance so far.” This doesn't explicitly state that the high-end Polaris video card will launch in 2016. That said, when combined with the November announcement, covered by us as “AMD Plans Two GPUs in 2016,” it further supports this interpretation.

We still don't know much about what the actual performance of this high-end GPU will be, though. AMD was able to push 8 TeraFLOPs of compute throughput by creating a giant 28nm die and converting the memory subsystem to HBM, which supposedly requires less die complexity than a GDDR5 memory controller (according to a conference call last year that preceded Fury X). The two-generation jump will give them more complexity to work with, but that could be partially offset by a smaller die because of the potential differences in yields (and so forth).

Also, while the performance of the 8 TeraFLOP Fury X was roughly equivalent to NVIDIA's 5.6 TeraFLOP GeForce GTX 980 Ti, we still don't know why. AMD has redesigned a lot of their IP blocks with Polaris; you would expect that, if something unexpected was bottlenecking Fury X, the graphics manufacturer wouldn't overlook it the next chance that they are able to tweak it. This could have been graphics processing or something much more mundane. Either way, upcoming benchmarks will be interesting.

And it seems like that may be this year.

Source: VentureBeat