Subject: Graphics Cards | March 8, 2013 - 09:17 AM | Tim Verry
Tagged: quadro, nvidia, kepler, k6000, gk110
Earlier this week, NVIDIA updated its Quadro line of workstation cards with new GPUs with GK104 “Kepler” cores. The updated line introduced four new Kepler cards, but the Quadro 6000 successor was notably absent from the NVIDIA announcement. If rumors hold true, professionals may get access to a K6000 Quadro card after all, and one that is powered by GK110 as well.
According to rumors around the Internet, NVIDIA has reserved its top-end Quadro slot for a GK110-based graphics card. Dubbed the K6000 (and in line with the existing Kepler Quadro cards), the high-end workstation card will feature 13 SMX units, 2,496 CUDA cores, 192 Texture Manipulation Units, 40 Raster Operations Pipeline units, and a 320-bit memory bus. The K6000 card will likely have 5GB of GDDR5 memory, like its Tesla K20 counterpart. Interestingly, this Quadro K6000 graphics card has one less SMX unit than NVIDIA’s Tesla K20X and even NVIDIA’s consumer-grade GTX Titan GPU. A comparison between the rumored K6000 card, the Quadro K5000 (GK104), and other existing GK110 cards is available in the table below. Also, note that the (rumored) K6000 specs put it more in like with the Tesla K20 than the K20X, but as it is the flagship Quadro card I felt it was still fair to compare it to the flagship Telsa and GeForce cards.
|Quadro K6000||Tesla K20X||GTX Titan||GK110 Full (Not available yet)||Quadro K5000|
|DP TFLOPS||~1.17 TFLOPS||1.31 TFLOPS||1.31 TFLOPS||~1.4 TFLOPS||.09 TFLOPS|
The Quadro cards are in an odd situation when it comes to double precision floating point performance. The Quadro K5000 which uses GK104 brings an abysmal 90 GFLOPS of double precision. The rumored GK110-powered Quadro K6000 brings double precision performance up to approximately 1 TFLOPS, which is quite the jump and shows that GK104 really was cut down to focus on gaming performance! Further, the card that the K6000 is replacing in name, the Quadro 6000 (no prefixed K), is based on NVIDIA’s previous-generation Fermi architecture and offers .5152 TFLOPS (515.2 GFLOPS) of double precision performance. On the plus side, users can expect around 3.5 TFLOPS of single precision horsepower, which is a substantial upgrade over Quadro 6000's 1.03 TFLOPS of single precision floating point. For comparison, the GK104-based Quadro K5000 offers 2.1 TFLOPS of single precision. Although it's no full GK110, it looks to be the Quadro card to beat for the intended usage.
Of course, Quadro is more about stable drivers, beefy memory, and single precision than double precision, but it would be nice to see the expensive Quadro workstation cards have the ability to pull double duty, as it were. NVIDIA’s Tesla line is where DP floating point is key. It is just a rather wide gap between the two lineups that the K6000 somewhat closes, fortunately. I would have really liked to see the K6000 have at least 14 SMX units, to match consumer Titan and the Tesla K20X, but rumors are not looking positive in that regard. Professionals should expect to see quite the premium with the K6000 versus the Titan, despite the hardware differences. It will likely be sold for around $3,000.
No word on availability, but the card will likely be released soon in order to complete the Kepler Quadro lineup update.
Subject: General Tech, Graphics Cards | March 6, 2013 - 08:02 PM | Scott Michaud
Tagged: quadro, nvidia
Be polite, be efficient, have a plan to Kepler every card that you meet.
The professional graphics market is not designed for gamers although that should have been fairly clear. These GPUs are designed to effectively handle complex video, 3D, and high resolution display environments found in certain specialized workspaces.
This is the class of cards which allow a 3D animator to edit their creations with stereoscopic 3D glasses, for instance.
NVIDIA's branding will remain consistent with the scheme developed for the prior generation. Previously, if you were in the market for a Fermi-based Quadro solution, you would have the choice between: the Quadro 600, the 2000, the 4000, the 5000, and the 6000. Now that the world revolves around Kepler... heh heh heh... each entry has been prefixed with a K with the exception of the highest-end 6000 card. These entries are therefore:
- Quadro K600, 192 CUDA Cores, 1GB, $199 MSRP
- Quadro K2000, 384 CUDA Cores, 2GB, $599 MSRP
- Quadro K4000, 768 CUDA Cores, 3GB, $1,269 MSRP
- Quadro K5000, 1536 CUDA Cores, 4GB + ECC, $2,249 MSRP
This product line is demonstrated graphically by the NVIDIA slide below.
Clicking the image while viewing the article will enlargen it.
It should be noted that each of the above products have been developed on the series of GK10X architectures and not the more computationally-intensive GK110 products. As the above slide alludes: while these Quadro cards are designed to handle the graphically-intensive applications, they are designed to be paired with GK110-based Tesla K20 cards to offload the GPGPU muscle.
Should you need the extra GPGPU performance, particularly when it comes to double precision mathematics, those cards can be found online for somewhere in the ballpark of $3,300 and $3,500.
The new Quadro products were available starting yesterday, March 5th, from “leading OEM and Channel Partners.”
Subject: Graphics Cards | March 5, 2013 - 02:28 PM | Jeremy Hellstrom
Tagged: nvidia, geforce, graphics drivers
After evaluating the evolution of AMD's drivers over 2012, [H]ard|OCP has now finalized their look at NVIDIA's offerings over the past year. They chose a half dozen drivers spanning March to December, tested on both the GTX680 and GTX 670. As you can see throughout the review, NVIDIA's performance was mostly stable apart from the final driver of 2012 which provided noticeably improved performance in several games. [H] compared the frame rates from both companies on the same chart and it makes the steady improvement of AMD's drivers over the year even more obvious. That does imply that AMD's initial drivers for this year needed improvement and that perhaps the driver team at AMD has a lot of work cut out for them in 2013 if they want to reach a high level of performance across the board, with game specific improvements offering the only deviation in performance.
"We have evaluated AMD and NVIDIA's 2012 video card driver performances separately. Today we will be combining these two evaluations to show each companies full body of work in 2012. We will also be looking at some unique graphs that show how each video cards driver improved or worsened performance in each game throughout the year."
Here are some more Graphics Card articles from around the web:
- AMD EyeFinity - Issues with Triple-Screen setups and 120Hz Refresh Rates @ Tweaktown
- Low-End NVIDIA/AMD GPU Comparison On Open-Source Drivers @ Phoronix
- AMD Radeon HD 7950 Boost vs. Nvidia GeForce GTX 660 Ti: frametimes @ Hardware.info
- Radeon Gallium3D Can Beat AMD's Catalyst In Select Workloads @ Phoronix
- Sapphire Radeon HD 7870 OC GHz Edition @ Funkykit
- AMD Radeon HD 7970 GHz Edition vs. Nvidia GeForce GTX 680: frametimes review @ Hardware.info
- NVIDIA Chips Comparison Table @ Hardware Secrets
- NVIDIA GeForce GTX Titan Video Card Review @ Legit Reviews
- GTX TITAN: The beast to unseat the best! @ Bjorn3D
- NVIDIA GeForce GTX TITAN: The Most Advanced Single-GPU Video Card Ever Made @Hi Tech Legion
- GTX TITAN Single Card @ Bjorn3D
- sus GeForce GTX 660 DirectCU II OC 2 GB @ X-bit Labs
- Gigabyte GeForce GTX Titan 6GB @ eTeknix
- Nvidia GeForce GTX Titan 3-way/4-way SLI review incl 5760x1080 and frametimes @ Hardware.info
- Sparkle GeForce GTX 650 Ti Dragon Series @ Kitguru
Subject: Graphics Cards | March 4, 2013 - 04:31 PM | Ryan Shrout
Tagged: video, tomb raider, tahiti, radeon, never settle reloaded, live, crysis, amd
UPDATE: Missed the live stream? Relive the incredible experience right here!
On March 5th on the PC Perspective Live! page we will be streaming some game action of the new Tomb Raider. In what might be one of the most impressive game series reboots in history, this iteration of the action-adventure gameplay is definitely the most impressive looking to date. And don't forget all the hair animation we are likely to see...
We will be teaming up with AMD once again to provide a fun and exciting PCPer Game Stream that includes game demonstrations and of course, prizes and game keys for those that watch the event LIVE!
UPDATE: We are excited to announce that Crystal Dynamics' Brian Horton, Senior Art Director for Tomb Raider, will be joining us on the PC Perpsective Game Stream to answer questions and to give us more detail on the visual effects at work in the PC version of the game!
Tomb Raider Game Stream
5pm PT / 8pm ET - March 5th
Warning: this one will DEFINITELY have mature language and content!!
The stream will be sponsored by AMD and its Never Settle Reloaded game bundles which we previously told you about. Depending on the AMD Radeon HD 7000 series GPU that you buy, you could get some amazing free games including:
Radeon HD 7900 Series
- FREE Crysis 3
- FREE Bioshock Infinite
Radeon HD 7800 Series
- FREE Bioshock Infinite
- FREE Tomb Raider
Radeon HD 7900 CrossFire Set
- FREE Crysis 3
- FREE Bioshock Infinite
- FREE Tomb Raider
- FREE Far Cry 3
- FREE Hitman: Absolution
- FREE Sleeping Dogs
AMD's Antal Tungler (@ColoredRocks on twitter) will be joining us via Skype to talk about the game's technology, performance considerations as well as helping me with some co-op gaming!
Of course, just to sweeten the deal a bit we have some prizes lined up for those of you that participate in our Tomb Raider Game Stream:
- 2 x Gigabyte Radeon HD 7870 OC 2GB graphics cards (plus Tomb Raider & Bioshock Infinite)
- 1 x HIS 7850 iPower IceQ Turbo 4GB graphics card (plus Tomb Raider & Bioshock Infinite)
- 3 x Combo codes for both Tomb Raider AND Bioshock Infinite
Pretty nice, huh? All you have to do to win is be present on the PC Perspective Live! Page during the event as we will announce both the content/sweepstakes method AND the winners!
Stop in on March 5h for some PC gaming fun!!
Subject: Graphics Cards | February 27, 2013 - 09:42 PM | Josh Walrath
Tagged: workstations, virtualization, Teradici, remote management, R5000, pitcairn, PCoIP, firepro, amd
A few days back AMD released one of their latest FIREPRO workstation graphics cards. For most users out there this will be received with a bit of a shrug. This release is a bit different though, and it reflects a change in direction in the PC market. The original PC freed users from mainframes and made computing affordable for most people. Today we are seemingly heading back to the mainframe/thin client setup of yore, but with hardware and connectivity that obviously was not present in the late 70s. The FIREPRO R5000 is hoping to redefine remote graphics.
Today’s corporate environment is chaotic when it comes to IT systems. The amount of malware, poor user decisions, and variability in software and hardware configurations is a constant headache to IT workers. A big push it to make computing more centralized in the company with easy oversight from IT workers. Servers with multiple remote users can be more easily updated and upgraded than going to individual PCs around the offices to do the same work. This is good for a lot of basic users, but it does not address the performance needs of power users who typically run traditional workstations.
AMD hopes to change that thinking with the R5000. This is a Pitcairn based product (7800 series on the desktop) that is built to workstation standards. It also features a secret weapon; the Teradici TERA2240 host processor. Teradici is a leader in PCoIP technology. PCoIP is simply “PC over IP”. Instead of a traditional remote host which limits performance and desktop space, Teradici developed PCoIP to more adequately send large amounts of pixel data over a network. The user essentially is able to leverage the power of a modern GPU rather than rely on the more software based rendering of remote sessions. The user has a thin client provided by a variety of OEMs to choose from and they connect directly over IP.
The advantages here is that the GPU is again used to its full potential, which is key for those doing heavy video editing work, 3D visualization, and CADD type workloads. The latest R5000 can support resolutions up to 2560x1600 up to two displays. The same card can support 1920x1200 on four displays. It supports upwards of 60 fps in applications. The TERA2240 essentially encodes the output and streams it over IP. The thin client re-encodes the stream and displays the results. This promises very low latency over smaller networks, and very manageable latency over large or wide area networks.
The downside here is that one client at a time can connect to the card. The card cannot be virtualized as such so that multiple users can access the resources of the GPU. The card CAN run in a virtualized environment, but it is again limited to one client per card. Multiple cards can be placed in each server and the hardware is then placed in its own VM. While this makes management of hardware a bit easier, it still is an expensive solution when it comes to a per user basis. Where efficiency may be regained is when it is placed in an environment where shift work takes place. Or another setting is a University where these cards are housed in high powered servers away from classrooms so cooling and sound are not issues impeding learning.
Subject: Graphics Cards | February 26, 2013 - 10:04 AM | Ryan Shrout
Tagged: amd, tressfx, lara croft, tomb raider, crystal dynamics
Last week we got an email from AMD teasing an upcoming technology called TressFX that had something to do with hair and something to do with graphics. It should come as no surprise today that AMD has announced that TressFX is a hair modeling technology that utilized DirectCompute for simulation. The proper rendering of hair has been a thorn in the side of game developers for decades now and it seems that with every generation of GPU released by either NVIDIA or AMD/ATI we would see a tech demo about how hair modeling "has been changed forever."
This time though, we are seeing the technology in a AAA gaming title.
TressFX Hair revolutionizes Lara Croft’s locks by using the DirectCompute programming language to unlock the massively-parallel processing capabilities of the Graphics Core Next architecture, enabling image quality previously restricted to pre-rendered images. Building on AMD’s previous work on Order Independent Transparency (OIT), this method makes use of Per-Pixel Linked-List (PPLL) data structures to manage rendering complexity and memory usage.
DirectCompute is additionally utilized to perform the real-time physics simulations for TressFX Hair. This physics system treats each strand of hair as a chain with dozens of links, permitting for forces like gravity, wind and movement of the head to move and curl Lara’s hair in a realistic fashion. Further, collision detection is performed to ensure that strands do not pass through one another, or other solid surfaces such as Lara’s head, clothing and body. Finally, hair styles are simulated by gradually pulling the strands back towards their original shape after they have moved in response to an external force.
It's a lot of technology for a little bit of rendering - but realistic hair presents a very unique problem and I am very interested to see this in action when Tomb Raider releases on March 5th.
I asked AMD a couple of questions including if this was going to be a technology that NVIDIA users would be missing out on. Their response? "We don't create features that lock out other vendors." That doesn't mean GTX 600-series card users will have access to this accelerated hair technology or that it will perform similarly if they do, but I'll take a look when I get my hands on the game.
We are hoping to get some video to go along with our screenshots as I think that will have a stronger impact. You can find more details on AMD's TressFX landing page.
Subject: Graphics Cards | February 25, 2013 - 08:01 PM | Josh Walrath
Tagged: nvidia, tegra, tegra 4, Tegra 4i, pixel, vertex, PowerVR, mali, adreno, geforce
When Tegra 4 was introduced at CES there was precious little information about the setup of the integrated GPU. We all knew that it would be a much more powerful GPU, but we were not entirely sure how it was set up. Now NVIDIA has finally released a slew of whitepapers that deal with not only the GPU portion of Tegra 4, but also some of the low level features of the Cortex A15 processor. For this little number I am just going over the graphics portion.
This robust looking fellow is the Tegra 4. Note the four pixel "pipelines" that can output 4 pixels per clock.
The graphics units on the Tegra 4 and Tegra 4i are identical in overall architecture, just that the 4i has fewer units and they are arranged slightly differently. Tegra 4 is comprised of 72 units, 48 of which are pixel shaders. These pixel shaders are VLIW based VEC4 units. The other 24 units are vertex shaders. The Tegra 4i is comprised of 60 units, 48 of which are pixel shaders and 12 are vertex shaders. We knew at CES that it was not a unified shader design, but we were still unsure of the overall makeup of the part. There are some very good reasons why NVIDIA went this route, as we will soon explore.
If NVIDIA were to transition to unified shaders, it would increase the overall complexity and power consumption of the part. Each shader unit would have to be able to handle both vertex and pixel workloads, which means more transistors are needed to handle it. Simpler shaders focused on either pixel or vertex operations are more efficient at what they do, both in terms of transistors used and power consumption. This is the same train of thought when using fixed function units vs. fully programmable. Yes, the programmability will give more flexibility, but the fixed function unit is again smaller, faster, and more efficient at its workload.
On the other hand here we have the Tegra 4i, which gives up half the pixel pipelines and vertex shaders, but keeps all 48 pixel shaders.
If there was one surprise here, it would be that the part is not completely OpenGL ES 3.0 compliant. It is lacking in one major function that is required for certification. This particular part cannot render at FP32 levels. It has been quite a few years since we have heard of anything not being able to do FP32 in the PC market, but it is quite common to not support it in the power and transistor conscious mobile market. NVIDIA decided to go with a FP 20 partial precision setup. They claim that for all intents and purposes, it will not be noticeable to the human eye. Colors will still be rendered properly and artifacts will be few and far between. Remember back in the day when NVIDIA supported FP16 and FP32 while they chastised ATI for choosing FP24 with the Radeon 9700 Pro? Times have changed a bit. Going with FP20 is again a power and transistor saving decision. It still supports DX9.3 and OpenGL ES 2.0, but it is not fully OpenGL ES 3.0 compliant. This is not to say that it does not support any 3.0 features. It in fact does support quite a bit of the functionality required by 3.0, but it is still not fully compliant.
This will be an interesting decision to watch over the next few years. The latest Mali 600 series, PowerVR 6 series, and Adreno 300 series solutions all support OpenGL ES 3.0. Tegra 4 is the odd man out. While most developers have no plans to go to 3.0 anytime in the near future, it will eventually be implemented in software. When that point comes, then the Tegra 4 based devices will be left a bit behind. By then NVIDIA will have a fully compliant solution, but that is little comfort for those buying phones and tablets in the near future that will be saddled with non-compliance once applications hit.
The list of OpenGL ES 3.0 features that are actually present in Tegra 4, but the lack of FP32 relegates it to 2.0 compliant status.
The core speed is increased to 672 MHz, well up from the 520 MHz in Tegra 3 (8 pixel and 4 vertex shaders). The GPU can output four pixels per clock, double that of Tegra 3. Once we consider the extra clock speed and pixel pipelines, the Tegra 4 increases pixel fillrate by 2.6x. Pixel and vertex shading will get a huge boost in performance due to the dramatic increase of units and clockspeed. Overall this is a very significant improvement over the previous generation of parts.
The Tegra 4 can output to a 4K display natively, and that is not the only new feature for this part. Here is a quick list:
2x/4x Multisample Antialiasing (MSAA)
24-bit Z (versus 20-bit Z in the Tegra 3 processor) and 8-bit Stencil
4K x 4K texture size incl. Non-Power of Two textures (versus 2K x 2K in the Tegra 3 processor) – for higher quality textures, and easier to port full resolution textures from console and PC games to Tegra 4 processor. Good for high resolution displays.
16:1 Depth (Z) Compression and 4:1 Color Compression (versus none in Tegra 3 processor) – this is lossless compression and is useful for reducing bandwidth to/from the frame buffer, and especially effective in antialiasing processing when processing multiple samples per pixel
Percentage Closer Filtering for Shadow Texture Mapping and Soft Shadows
Texture border color eliminate coarse MIP-level bleeding
sRGB for Texture Filtering, Render Surfaces and MSAA down-filter
1 - CSAA is no longer supported in Tegra 4 processors
This is a big generational jump, and now we only have to see how it performs against the other top end parts from Qualcomm, Samsung, and others utilizing IP from Imagination and ARM.
Subject: General Tech, Graphics Cards | February 25, 2013 - 01:32 PM | Jeremy Hellstrom
Tagged: jon peddie, graphics, market share
If last weeks report from Jon Peddie Research on sales for all add in and integrated graphics had you worried, the news this week is not gong to help boost your confidence. This week the report focuses solely on add in boards and the drop is dramatic; Q4 2012 sales plummeted just short of 20% compared to Q3 2012. When you look at the entire year, sales dropped 10% overall as AMD's APUs are making serious inroads into the mobile market, as are Intel's, with many notebooks being sold without a discrete GPU. The losses are coming from the mainstream market, enthusiast level GPUs actually saw a slight increase in sales but the small volume is utterly drowned by the mainstream market. You can check out the full press release here.
"JPR found that AIB shipments during Q4 2012 behaved according to past years with regard to seasonality, but the drop was considerably more dramatic. AIB shipments decreased 17.3% from the last quarter (the 10 year average is just -0.68%). On a year-to-year comparison, shipments were down 10%."
Here is some more Tech News from around the web:
- 3DMark Review @ OCC
- Trendnet N300 Easy-N-Range Extender @ Rbmods
- NETGEAR ProSafe GS110T Gigabit SmartSwitch @ Benchmark Reviews
- Quantum computer one step closer after ‘true’ quantum calculation @ The Register
- Microsoft brings Azure back online @ The Register
- Understanding Camera Optics & Smartphone Camera Trends, A Presentation by Brian Klug @ AnandTech
- MWC Sunday roundup: HP Slate, Ascend P2 and Firefox phones @ The Inquirer
- AMD releases Firepro R5000 with remote display technology @ The Inquirer
- The TR Podcast 129: PlayStation 4, Titan, and more
Subject: Graphics Cards | February 22, 2013 - 05:29 PM | Ryan Shrout
Tagged: tressfx, amd
I got an odd email just now that I thought I would share with you. From AMD's Gaming Evolved account I got this:
You're at the top of your game. Why isn't your hair? TressFX is specially formulated with dynamic compounds like PPLL to re-energize your tired locks with vitality and luster.
An odd campaign for sure, but it appears that on Tuesday AMD is going to discuss a technology that will bring realistic hair to gaming. Finally some use for all that GPGPU horsepower on the Southern Islands graphics cards?
In case you missed it...
In one of the last pages of our recent NVIDIA GeForce GTX TITAN graphics card review we included an update to our Frame Rating graphics performance metric that details the testing method in more detail and showed results for the first time. Because it was buried so far into the article, I thought it was worth posting this information here as a separate article to solict feedback from readers and help guide the discussion forward without getting lost in the TITAN shuffle. If you already read that page of our TITAN review, nothing new is included below.
I am still planning a full article based on these results sooner rather than later; for now, please leave me your thoughts, comments, ideas and criticisms in the comments below!
Why are you not testing CrossFire??
If you haven't been following our sequence of stories that investigates a completely new testing methodology we are calling "frame rating", then you are really missing out. (Part 1 is here, part 2 is here.) The basic premise of Frame Rating is that the performance metrics that the industry is gathering using FRAPS are inaccurate in many cases and do not properly reflect the real-world gaming experience the user has.
Because of that, we are working on another method that uses high-end dual-link DVI capture equipment to directly record the raw output from the graphics card with an overlay technology that allows us to measure frame rates as they are presented on the screen, not as they are presented to the FRAPS software sub-system. With these tools we can measure average frame rates, frame times and stutter, all in a way that reflects exactly what the viewer sees from the game.
We aren't ready to show our full sets of results yet (soon!) but the problems lie in that AMD's CrossFire technology shows severe performance degradations when viewed under the Frame Rating microscope that do not show up nearly as dramatically under FRAPS. As such, I decided that it was simply irresponsible of me to present data to readers that I would then immediately refute on the final pages of this review (Editor: referencing the GTX TITAN article linked above.) - it would be a waste of time for the reader and people that skip only to the performance graphs wouldn't know our theory on why the results displayed were invalid.
Many other sites will use FRAPS, will use CrossFire, and there is nothing wrong with that at all. They are simply presenting data that they believe to be true based on the tools at their disposal. More data is always better.
Here are these results and our discussion. I decided to use the most popular game out today, Battlefield 3 and please keep in mind this is NOT the worst case scenario for AMD CrossFire in any way. I tested the Radeon HD 7970 GHz Edition in single and CrossFire configurations as well as the GeForce GTX 680 and SLI. To gather results I used two processes:
- Run FRAPS while running through a repeatable section and record frame rates and frame times for 60 seconds
- Run our Frame Rating capture system with a special overlay that allows us to measure frame rates and frame times with post processing.
Here is an example of what the overlay looks like in Battlefield 3.
Frame Rating capture on GeForce GTX 680s in SLI - Click to Enlarge
The column on the left is actually the visuals of an overlay that is applied to each and every frame of the game early in the rendering process. A solid color is added to the PRESENT call (more details to come later) for each individual frame. As you know, when you are playing a game, multiple frames will make it on any single 60 Hz cycle of your monitor and because of that you get a succession of colors on the left hand side.
By measuring the pixel height of those colored columns, and knowing the order in which they should appear beforehand, we can gather the same data that FRAPS does but our results are seen AFTER any driver optimizations and DX changes the game might make.
Frame Rating capture on Radeon HD 7970 CrossFire - Click to Enlarge
Here you see a very similar screenshot running on CrossFire. Notice the thin silver band between the maroon and purple? That is a complete frame according to FRAPS and most reviews. Not to us - we think that frame rendered is almost useless.