JPR Notes Huge Increase in Enthusiast AIBs for 2015

Subject: Graphics Cards | February 29, 2016 - 07:06 PM |
Tagged: nvidia, amd, AIB, pc gaming

Jon Peddie Research, which is market analysis firm that specializes in PC hardware, has compiled another report about add-in board (AIB) sales. There's a few interesting aspects to this report. First, shipments of enthusiast AIBs (ie: discrete GPUs) are up, not a handful of percent, but a whole two-fold. Second, AMD's GPU market share climbed once again, from 18.8% up to 21.1%.

jpr-aib-february-2016.png

This image seems contradict their report, which claims the orange line rose from 44 million in 2014 to 50 million in 2015. I'm not sure where the error is, so I didn't mention it in the news post.
Image Credit: JPR

The report claims that neither AMD nor NVIDIA released a “killer new AIB in 2015.” That... depends on how you look at it. They're clearly referring to upper mainstream, which sit just below the flagship and contribute to a large chunk of enthusiast sales. If they were including the flagship, then they ignored the Titan X, 980 Ti, and Fury line of GPUs, which would just be silly. Since they were counting shipped units, though, it makes sense to neglect those SKUs because they are priced way above the inflection point in actual adoption.

jpr-aib-february-2016-table.png

Image Credit: JPR

But that's not the only “well... sort-of” with JPR's statement. Unlike most generations, the GTX 970 and 980 launched late in 2014, rather than their usual Spring-ish cadence. Apart from the GeForce GTX 580, this trend has been around since the GeForce 9000-series. As such, these 2014 launches could have similar influence as another year's early-2015 product line. Add a bit of VR hype, and actual common knowledge that consoles are lower powered than PCs this generation, and you can see these numbers make a little more sense.

Even still, a 100% increase in enthusiast AIB shipments is quite interesting. This doesn't only mean that game developers can target higher-end hardware. The same hardware to consume content can be used to create it, which boosts both sides of the artist / viewer conversation in art. Beyond its benefits to society, this could snowball into more GPU adoption going forward.

Source: JPR

MWC 16: Imagination Technologies Ray Tracing Accelerator

Subject: Graphics Cards, Mobile, Shows and Expos | February 24, 2016 - 01:46 AM |
Tagged: raytracing, ray tracing, PowerVR, mwc 16, MWC, Imagination Technologies

For the last couple of years, Imagination Technologies has been pushing hardware-accelerated ray tracing. One of the major problems in computer graphics is knowing what geometry and material corresponds to a specific pixel on the screen. Several methods exists, although typical GPUs crush a 3D scene into the virtual camera's 2D space and do a point-in-triangle test on it. Once they know where in the triangle the pixel is, if it is in the triangle, it can be colored by a pixel shader.

imagtech-2016-PowerVR-GR6500-GPU-PowerVR-Wizard-GPUs.png

Another method is casting light rays into the scene, and assigning a color based on the material that it lands on. This is ray tracing, and it has a few advantages. First, it is much easier to handle reflections, transparency, shadows, and other effects where information is required beyond what the affected geometry and its material provides. There are usually ways around this, without resorting to ray tracing, but they each have their own trade-offs. Second, it can be more efficient for certain data sets. Rasterization, since it's based around a “where in a triangle is this point” algorithm, needs geometry to be made up of polygons.

It also has the appeal of being what the real world sort-of does (assuming we don't need to model Gaussian beams). That doesn't necessarily mean anything, though.

At Mobile World Congress, Imagination Technologies once again showed off their ray tracing hardware, embodied in the PowerVR GR6500 GPU. This graphics processor has dedicated circuitry to calculate rays, and they use it in a couple of different ways. They presented several demos that modified Unity 5 to take advantage of their ray tracing hardware. One particularly interesting one was their quick, seven second video that added ray traced reflections atop an otherwise rasterized scene. It was a little too smooth, creating reflections that were too glossy, but that could probably be downplayed in the material ((Update: Feb 24th @ 5pm Car paint is actually that glossy. It's a different issue). Back when I was working on a GPU-accelerated software renderer, before Mantle, Vulkan, and DirectX 12, I was hoping to use OpenCL-based ray traced highlights on idle GPUs, if I didn't have any other purposes for it. Now though, those can be exposed to graphics APIs directly, so they might not be so idle.

The downside of dedicated ray tracing hardware is that, well, the die area could have been used for something else. Extra shaders, for compute, vertex, and material effects, might be more useful in the real world... or maybe not. Add in the fact that fixed-function circuitry already exists for rasterization, and it makes you balance gain for cost.

It could be cool, but it has its trade-offs, like anything else.

Valve Releases SteamVR Performance Test - Is Your Rig Ready?

Subject: Graphics Cards | February 22, 2016 - 11:03 PM |
Tagged: vive, valve, steamvr, steam, rift, performance test, Oculus, htc

Though I am away from my stacks of hardware at the office attending Mobile World Congress in Barcelona, Valve dropped a bomb on us today in the form of a new hardware performance test that gamers can use to determine if they are ready for the SteamVR revolution. The aptly named "SteamVR Performance Test" is a free title available through Steam that any user can download and run to get a report card on their installed hardware. No VR headset required!

And unlike the Oculus Compatibility Checker, the application from Valve runs actual game content to measure your system. Oculus' app only looks at the hardware on your system for certification, not taking into account the performance of your system in any way. (Overclockers and users with Ivy Bridge Core i7 processors have been reporting failed results on the Oculus test for some time.)

screen1.jpg

The SteamVR Performance Test runs a set of scenes from the Aperture Science Robot Repair demo, an experience developed directly for the HTC Vive and one that I was able to run through during CES last month. Valve is using a very interesting new feature called "dynamic fidelity" that adjusts image quality of the game in a way to avoid dropped frames and frame rates under 90 FPS in order to maintain a smooth and comfortable experience for the VR user. Though it is the first time I have seen it used, it sounds similar to what John Carmack did with the id Tech 5 engine, attempting to balance performance on hardware while maintaining a targeted frame rate.

The technology could be a perfect match for VR content where frame rates above or at the 90 FPS target are more important than visual fidelity (in nearly all cases). I am curious to see how Valve may or may not pursue and push this technology in its own games and for the Vive / Rift in general. I have some questions pending with them, so we'll see what they come back with.

fury.png

A result for a Radeon R9 Fury provided by AMD

Valve's test offers a very simple three tiered breakdown for your system: Not Ready, Capable and Ready. For a more detailed explanation you can expand on the data to see metrics like the number of frames you are CPU bound on, frames below the very important 90 FPS mark and how many frames were tested in the run. The Average Fidelity metric is the number that we are reporting below and essentially tells us "how much quality" the test estimates you can run at while maintaining that 90 FPS mark. What else that fidelity result means is still unknown - but again we are trying to find out. The short answer is that the higher that number goes, the better off you are, and the more demanding game content you'll be able to run at acceptable performance levels. At least, according to Valve.

screen2.jpg

Because I am not at the office to run my own tests, I decided to write up this story using results from a third part. That third party is AMD - let the complaining begin. Obviously this does NOT count as independent testing but, in truth, it would be hard to cheat on these results unless you go WAY out of your way to change control panel settings, etc. The demo is self run and AMD detailed the hardware and drivers used in the results.

  • Intel i7-6700K
  • 2x4GB DDR4-2666 RAM
  • Z170 motherboard
  • Radeon Software 16.1.1
  • NVIDIA driver 361.91
  • Win10 64-bit

GPU Score
2x Radeon R9 Nano 11.0
GeForce GTX 980 Ti 11.0
Radeon R9 Fury X 9.6
Radeon R9 Fury 9.2
GeForce GTX 980 8.1
Radeon R9 Nano 8.0
Radeon R9 390X 7.8
Radeon R9 390 7.0
GeForce GTX 970 6.5

These results were provided by AMD in an email to the media. Take that for what you will until we can run our own tests.

First, the GeForce GTX 980 Ti is the highest performing single GPU tested, with a score of 11 - because of course it goes to 11. The same score is reported on the multi-GPU configuration with two Radeon R9 Nanos so clearly we are seeing a ceiling of this version of the SteamVR Performance Test. With a single GPU score of 9.2, that is only a 19% scaling rate, but I think we are limited by the test in this case. Either way, it's great news to see that AMD has affinity multi-GPU up and running, utilizing one GPU for each eye's rendering. (AMD pointed out that users that want to test the multi-GPU implementation will need to add the -multigpu launch option.) I still need to confirm if GeForce cards scale accordingly. UPDATE: Ken at the office ran a quick check with a pair of GeForce GTX 970 cards with the same -multigpu option and saw no scaling improvements. It appears NVIDIA has work to do here.

Moving down the stack, its clear why AMD was so excited to send out these early results. The R9 Fury X and R9 Fury both come out ahead of the GeForce GTX 980 while the R9 Nano, R9 390X and R9 390 result in better scores than NVIDIA's GeForce GTX 970. This comes as no surprise - AMD's Radeon parts tend to offer better performance per dollar when it comes to benchmarks and many games.

badresult2.jpg

There is obviously a lot more to consider than the results this SteamVR Performance Test provides when picking hardware for a VR system, but we are glad to see Valve out in front of the many, many questions that are flooding forums across the web. Is your system ready??

Source: Valve

LinuxGameCast Benchmarks Vulkan on Linux

Subject: Graphics Cards | February 20, 2016 - 12:11 AM |
Tagged: vulkan, linux

Update: Venn continued to benchmark and came across a few extra discoveries. For example, he disabled VDPAU and jumped to 89.6 FPS in OpenGL and 80.6 FPS in Vulkan. Basically, be sure to read the whole thread. It might be updated further even. Original post below (unless otherwise stated).

On Windows, the Vulkan patch of The Talos Principle leads to a net loss in performance, relative to DirectX 11. This is to be expected when a developer like Croteam optimizes their game for existing APIs, and tries to port all that work to a new, very different standard, with a single developer and three months of work. They explicitly state, multiple times, not to expect good performance.

croteam-2016-talos-benchmark-vulkan.png

Image Credit: Venn Stone of LinuxGameCast

On Linux, Venn Stone of LinuxGameCast found different results. With everything maxed out at 1080p, his OpenGL benchmark reports 38.2 FPS, while his Vulkan raises this to an average of 66.5 FPS. Granted, this was with an eight-core AMD FX-8150, which launched with the Bulldozer architecture back in 2011. It did not have the fastest single-threaded performance, falling behind even AMD's own Phenom II parts before it in that regard.

Still, this is a scenario that allowed the game to scale to Bulldozer's multiple cores and circumvent a lot of the driver overhead in OpenGL. It resulted in a 75% increase in performance, at least for people who pair a GeForce 980 Ti ((Update: The Ti was a typo. Venn uses a standard GeForce GTX 980.)) with an eight-core, Bulldozer CPU from 2011.

Report: NVIDIA Working on Another GeForce GTX 950 GPU

Subject: Graphics Cards | February 16, 2016 - 05:01 PM |
Tagged: rumor, report, nvidia, Maxwell 2.0, GTX 950 SE, GTX 950 LP, gtx 950, gtx 750, graphics card, gpu

A report from VideoCardz.com claims that NVIDIA is working on another GTX 950 graphics card, but not the 950 Ti you might have expected.

gtx950.jpg

Reference GTX 950 (Image credit: NVIDIA)

While the GTX 750 Ti was succeeded by the GTX 950 in August of last year, the higher specs for this new GPU came at the cost of a higher TDP (90W vs. 60W). This new rumored GTX 950, which might be called either 950 SE or 950 LP according to the report, would be a lower power version of the GTX 950, and would actually have a lot more in common with the outgoing GTX 750 Ti than the plain GTX 750 as we can see from this chart:

chart.png

(Image credit: VideoCardz)

As you can see the GTX 750 Ti is based on GM107 (Maxwell 1.0) and has 640 CUDA cores, 40 TUs, 16 ROPs, and it operates at 1020 MHz Base/1085 MHz Boost clocks. The reported specs of this new GTX 950 SE/LP would be nearly identical, though based on GM206 (Maxwell 2.0) and offering greater memory bandwidth (and slightly higher power consumption).

The VideoCardz report was sourced from Expreview, which claimed that this GTX 950 SE/LP product would arrive next month at some point. This report is a little more vague than some of the rumors we see, but it could very well be that NVIDIA has a planned replacement for the remaining Maxwell 1.0 products on the market. I would have personally expected to see a"Ti” product before any “LE/LP” version of the GTX 950, and this reported name seems more like an OEM product than a retail part. We will have to wait and see if this report is accurate.

Source: VideoCardz

EVGA Releases GeForce GTX 980 Ti VR Edition

Subject: Graphics Cards | February 10, 2016 - 10:59 PM |
Tagged: VR, vive vr, Oculus, evga, 980 Ti

You might wonder what makes a graphics card “designed for VR,” but this is actually quite interesting. Rather than plugging your headset into the back of your desktop, EVGA includes a 5.25” bay that provides 2x USB 3.0 ports and 1x HDMI 2.0 connection. The use case is that some users will want to easily connect and disconnect their VR devices, which, knowing a few indie VR developers, seems to be a part of their workflow. The same may be true of gamers, but I'm not sure.

evga-2016-980Ti-VR-Header_BG.jpg

While the bay allows for everything, including the HDMI plug via an on-card port, to be connected internally, you will need a spare USB 3.0 header on your motherboard to hook it up. It would have been interesting to see whether EVGA could have attached a USB 3.0 controller on the add-in board, but that might have been impossible (or unpractical) given that the PCIe connector would need to be shared with the GPU (not to mention the complexity of also adding a USB 3.0 controller to the board). Also, I expect motherboards should have at least one. If not, you can find USB 3.0 add-in cards with internal headers.

evga-2016-980ti.jpg

The card comes in two sub-versions, one with the NVIDIA-style blower cooler, and the other with EVGA's ACX 2.0+ cooler. I tend to prefer exposed fan GPUs because they're easier to blow air into after a few years, but you might have other methods to control dust.

Both are currently available for $699.99 on Newegg.com, while Amazon only lists the ACX2.0+ cooler version, and that's out of stock. It is also $699.99, though, so that should be what to expect.

Source: EVGA

Mods like memory; the Gainward GTX 960 Phantom 4GB

Subject: Graphics Cards | February 4, 2016 - 10:51 PM |
Tagged: gainward, GTX 960 Phantom 4GB. gtx 960, NVIDA, 4GB

If you don't have a lot of cash on hand for games or hardware, a 4k adaptive sync monitor with two $600 GPUs and a collection of $80 AAA titles simply isn't on your radar.  That doesn't mean you have to toss in your love of gaming for occasional free to play gaming sessions; you just have to adapt.  A prime example are those die hard Skyrim fans who have modded the game to oblivion over the past few years, with many other games and communities that may not be new but are still thriving.  Chances are that you are playing at 1080p so a high powered GPU is not needed, however mods that upscale textures and many others do love huge tracts of RAM. 

So for those outside of North America looking for a card they can afford after a bit of penny pinching, check out Legion Hardware's review of the 4GB version of the Gainward GTX 960 Phantom.  It won't break any benchmarking records but it will let you play the games you love and even new games as their prices inevitably decrease over time.

Image_03S.jpg

Today we are checking out Gainward’s premier GeForce GTX 960 graphics card, the Phantom 4GB. Equipped with twice the memory buffer of standard cards, it is designed for extreme 1080p gaming. Therefore it will be interesting to see how the Phantom 4GB compares to a 2GB GTX 960..."

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

Graphics Cards

 

AMD FirePro S-Series Introduces Hardware-Based GPU Virtualization

Subject: Graphics Cards | February 3, 2016 - 07:37 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 - 07:07 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 - 08:19 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 - 04:51 PM |
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 - 04:08 PM |
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 - 08:26 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 20, 2016 - 04:38 AM |
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 20, 2016 - 04:01 AM |
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 - 03:31 PM |
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 19, 2016 - 02:44 AM |
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

Catalyst Crimson Edition 16.1 Hotfix Drivers Released

Subject: Graphics Cards | January 14, 2016 - 12:42 AM |
Tagged: graphics drivers, amd

AMD's recent “Hotfix” drivers don't seem to mean what NVIDIA's does. In the Green Team's case, they usually fix one or two issues that slipped past QA. While they likely won't break anything, they are probably a bad idea to install if you're not experiencing the listed problems. The changelog on AMD's drivers are significantly longer with a list of known issues that is roughly the same size.

amd-2015-crimson-logo.png

So should you install it? That depends. It's a little less cut-and-dry than NVIDIA's hotfixes, which are only useful for a handful of people. It sounds like the worst known issue is “Game stuttering may be experienced when running two Radeon R9 295X2 graphics cards in CrossFire mode” and “Display corruption may occur on multiple display systems when it has been running idle for some time.” The latter would affect me greatly, because I run four displays and basically never sleep or shutdown (except for updates). On the other hand, it fixes a variety of crash, hang, and flicker issues.

Check it out. If it sounds good, then pick it up. Otherwise, wait for the next Beta or WHQL driver.

Source: AMD

GeForce Hotfix Driver 361.60 Released

Subject: Graphics Cards | January 13, 2016 - 01:11 AM |
Tagged: graphics drivers, graphics driver, nvidia

NVIDIA has been pushing for WHQL certification for their drivers, but sometimes issues slip through QA, both at Microsoft and their own, internal team(s). Sometimes these issues will be fixed in a future release, but sometimes they push out a “HotFix” driver immediately. This is often great for people who experience the problems, but they should not be installed otherwise.

nvidia-2015-bandaid.png

In this case, GeForce Hotfix driver 361.60 fixes two issues. One is listed as “install & clocking related issues,” which refers to the GPU memory clock. According to Manuel Guzman of NVIDIA, some games and software was not causing the driver to fully wake the memory clock to a high-performance state. The other issue is “Crashes in Photoshop & Illustrator,” which fixes blue screen issues in both software, and possibly other programs that use the GPU in similar ways. I've never seen GeForce Driver 361.43 cause a BSOD in Photoshop, but I am a few versions behind with CS5.5.

Download links are available at NVIDIA Support, but unaffected users should just wait for an official driver in case the patch causes other issues, due to its minimal QA.

Source: NVIDIA

Report: NVIDIA Pascal GP104 Discovered, May Not Use HBM

Subject: Graphics Cards | January 11, 2016 - 11:05 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