Subject: Graphics Cards | May 23, 2018 - 09:01 PM | Ken Addison
Tagged: vega frontier edition, titan xp, specviewperf 13, specgpc
SPECgpc, makers of industry standard benchmarks such as SPECint, released an updated version of SPECviewperf today. The new SPECviewperf 13, is an update to the industry staple benchmark for measuring the graphics performance in workstation and professional applications.
Ranging from a wide array of applications such as Solidworks, Maya, Creo, 3ds Max, and more, SPECviewperf provides an insight into the performance of mission-critical, but often difficult to benchmark scenarios.
Changes for this new version of SPECviewperf include:
- Support for 4K resolution displays.
- New reporting methods, including JSON output that enables more robust and flexible result parsing.
- A new user interface that will be standardized across all SPEC/GWPG benchmarks.
- New workloads and scoring that reflect the range of activities found in real-world applications.
- Various bug fixes and performance improvements.
Given that the changes include new datasets for the energy, medical, Creo, and Maya viewsets, as well as tweaks to the others, we decided to grab some quick results from two high-end prosumer level GPUs, the NVIDIA Titan Xp and the AMD RX Vega Frontier Edition.
The full testbed configuration is listed below:
|Test System Setup|
Intel Core i9-7960XE
|Motherboard||ASUS PRIME X299 Deluxe|
32GB Corsair Vengeance DDR4-3200
Operating at: 2400MHz
|Storage||Intel Optane SSD DC P4800X 750GB|
NVIDIA GeForce TITAN Xp 12GB
AMD Radeon Vega Frontier Edition (Liquid) 16GB
AMD Radeon Pro 18.Q2.1
|Power Supply||Corsair RM1000x|
|Operating System||Windows 10 Pro x64 RS4|
While we see the Titan Xp handily winning most of the tests in SPECviewperf 13, there are some notable exceptions, including the newly updated energy workload where the Vega Frontier Edition manages to pull off a 13% lead. Additionally, Solidworks—a very widely used application for CAD work—sees a 23% performance advantage for AMD.
SPECviewperf is a benchmark that we rely on to evaluate profession application performance, and we are glad to see it's getting some improvements.
For anyone curious about the performance of their system, SPECviewperf 13 is free to download and use for non-profit entities that do not sell computer hardware, software, or related services.
How deep is your learning?
Recently, we've had some hands-on time with NVIDIA's new TITAN V graphics card. Equipped with the GV100 GPU, the TITAN V has shown us some impressive results in both gaming and GPGPU compute workloads.
However, one of the most interesting areas that NVIDIA has been touting for GV100 has been deep learning. With a 1.33x increase in single-precision FP32 compute over the Titan Xp, and the addition of specialized Tensor Cores for deep learning, the TITAN V is well positioned for deep learning workflows.
In mathematics, a tensor is a multi-dimensional array of numerical values with respect to a given basis. While we won't go deep into the math behind it, Tensors are a crucial data structure for deep learning applications.
NVIDIA's Tensor Cores aim to accelerate Tensor-based math by utilizing half-precision FP16 math in order to process both dimensions of a Tensor at the same time. The GV100 GPU contains 640 of these Tensor Cores to accelerate FP16 neural network training.
It's worth noting that these are not the first Tensor operation-specific hardware, with others such as Google developing hardware for these specific functions.
|PC Perspective Deep Learning Testbed|
|Processor||AMD Ryzen Threadripper 1920X|
|Motherboard||GIGABYTE X399 AORUS Gaming 7|
|Memory||64GB Corsair Vengeance RGB DDR4-3000|
|Storage||Samsung SSD 960 Pro 2TB|
|Power Supply||Corsair AX1500i 1500 watt|
|OS||Ubuntu 16.04.3 LTS|
|Drivers||AMD: AMD GPU Pro 17.50
For our NVIDIA testing, we used the NVIDIA GPU Cloud 17.12 Docker containers for both TensorFlow and Caffe2 inside of our Ubuntu 16.04.3 host operating system.
For all tests, we are using the ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) data set.
Looking Towards the Professionals
This is a multi-part story for the NVIDIA Titan V:
Earlier this week we dove into the new NVIDIA Titan V graphics card and looked at its performacne from a gaming perspective. Our conclusions were more or less what we expected - the card was on average ~20% faster than the Titan Xp and about ~80% faster than the GeForce GTX 1080. But with that $3000 price tag, the Titan V isn't going to win any enthusiasts over.
What the Titan V is meant for in reality is the compute space. Developers, coders, engineers, and professionals that use GPU hardware for research, for profit, or for both. In that case, $2999 for the Titan V is simply an investment that needs to show value in select workloads. And though $3000 is still a lot of money, keep in mind that the NVIDIA Quadro GP100, the most recent part with full-performance double precision compute from the Pascal chip, is still selling for well over $6000 today.
The Volta GV100 GPU offers 1:2 double precision performance, equating to 2560 FP64 cores. That is a HUGE leap over the GP102 GPU used on the Titan Xp that uses a 1:32 ratio, giving us just 120 FP64 cores equivalent.
|Titan V||Titan Xp||GTX 1080 Ti||GTX 1080||GTX 1070 Ti||GTX 1070||RX Vega 64 Liquid||Vega Frontier Edition|
|Base Clock||1200 MHz||1480 MHz||1480 MHz||1607 MHz||1607 MHz||1506 MHz||1406 MHz||1382 MHz|
|Boost Clock||1455 MHz||1582 MHz||1582 MHz||1733 MHz||1683 MHz||1683 MHz||1677 MHz||1600 MHz|
|Memory Clock||1700 MHz MHz||11400 MHz||11000 MHz||10000 MHz||8000 MHz||8000 MHz||1890 MHz||1890 MHz|
|384-bit G5X||352-bit G5X||256-bit G5X||256-bit||256-bit||2048-bit HBM2||2048-bit HBM2|
|Memory Bandwidth||653 GB/s||547 GB/s||484 GB/s||320 GB/s||256 GB/s||256 GB/s||484 GB/s||484 GB/s|
|TDP||250 watts||250 watts||250 watts||180 watts||180 watts||150 watts||345 watts||300 watts|
|Peak Compute||12.2 (base) TFLOPS
14.9 (boost) TFLOPS
|12.1 TFLOPS||11.3 TFLOPS||8.2 TFLOPS||7.8 TFLOPS||5.7 TFLOPS||13.7 TFLOPS||13.1 TFLOPS|
|Peak DP Compute||6.1 (base) TFLOPS
7.45 (boost) TFLOPS
|0.37 TFLOPS||0.35 TFLOPS||0.25 TFLOPS||0.24 TFLOPS||0.17 TFLOPS||0.85 TFLOPS||0.81 TFLOPS|
The current AMD Radeon RX Vega 64, and the Vega Frontier Edition, all ship with a 1:16 FP64 ratio, giving us the equivalent of 256 DP cores per card.
Test Setup and Benchmarks
Our testing setup remains the same from our gaming tests, but obviously the software stack is quite different.
|PC Perspective GPU Testbed|
|Processor||Intel Core i7-5960X Haswell-E|
|Motherboard||ASUS Rampage V Extreme X99|
|Memory||G.Skill Ripjaws 16GB DDR4-3200|
|Storage||OCZ Agility 4 256GB (OS)
Adata SP610 500GB (games)
|Power Supply||Corsair AX1500i 1500 watt|
|OS||Windows 10 x64|
Applications in use include:
- Cinebench R15
- Sisoft Sandra GPU Compute
- SPECviewperf 12.1
Let's not drag this along - I know you are hungry for results! (Thanks to Ken for running most of these tests for us!!)
Subject: Graphics Cards | November 17, 2017 - 02:08 PM | Ryan Shrout
Tagged: titan xp, Star Wars, nvidia, jedi order, jedi, geforce, galactic empire, empire
NVIDIA has a coup on its hands this holiday. With the release of Battlefront II today and The Last Jedi next month, a new series of Titan Xp cards is available that will make Star Wars fans giggle with excitement! This is the same Titan Xp performance we expect but with a completely new external design and style, available in both a red-themed Galactic Empire version and a green-themed Jedi Order option.
Check out the video above for the unboxing and my thoughts as I swoon over them...
If you want some more pictures of the goods, I have them here as well.
Do note - though it's hard to recommend a $1200 graphics card to many people, these cards almost seem like a steal considering they are priced at the same cost as the standard Titan Xp models. I know that the price for these custom shrouds in short runs was not cheap, so its almost like NVIDIA is giving Star Wars that double as PC enthusiasts a little gift for the holidays.
Okay, that might be a stretch... But come on, look how awesome these graphics cards look!!
We are working up a full system build (time for my personal upgrade!) with these two GPUs and will have a build log of that up before Christmas. Don't worry, we plan on properly presenting this hardware through an all-glass chassis!
Subject: General Tech | November 9, 2017 - 02:38 PM | Alex Lustenberg
Tagged: video, titan xp, teleport, starcraft 2, raja koduri, radeon, qualcomm, podcast, nvidia, Intel, centriq, amplifi, amd
PC Perspective Podcast #475 - 11/09/17
Join us for discussion on Intel with AMD graphics, Raja's move to Intel, and more!
The URL for the podcast is: http://pcper.com/podcast - Share with your friends!
- iTunes - Subscribe to the podcast directly through the iTunes Store (audio only)
- Google Play - Subscribe to our audio podcast directly through Google Play!
- RSS - Subscribe through your regular RSS reader (audio only)
- MP3 - Direct download link to the MP3 file
Hosts: Josh Walrath, Jeremy Hellstrom, Allyn Malventano, Ken Addison
Peanut Gallery: Alex Lustenberg, Jim Tanous
Program length: 1:29:42
Week in Review:
News items of interest:
Hardware/Software Picks of the Week
1:13:40 Allyn: Relatively cheap Samsung 82” (!!!) 4K TV
1:17:45 Jeremy: What exactly is a "technology certificate license" Logitech?
1:23:45 Josh: 1800X for $399!!!!!
1:24:50 Ken: The Void Wallet
Subject: Graphics Cards | November 7, 2017 - 02:04 PM | Jeremy Hellstrom
Tagged: Star Wars, nvidia, titan xp, disney
Priced at $1200, you can choose to power your gaming rig with either the light side of the Force or the dark side. NVIDIA have announced two new Titan Xp GPUs, one battle scarred and lightsaber green representing the Rebel Alliance and a pristine black card which glows a familiar red. It would seem that they are a bit behind the times as neither of those organizations exist in the current Star Wars timeline but that doesn't make them any less attractive to fans.
The specifications are familiar, a Pascal-based GP102 GPU, with 3840 CUDA cores @ 1.6GHz, and 12GB of GDDR5X memory running at 11.4Gbps. The look is very unique however, so if you are a big fan of Star Wars then this might just be something you want to consider. The full PR and launch movie are just below.
Tatooine, Outer Rim Territory—NVIDIA has announced two new collector’s edition NVIDIA TITAN Xp GPUs created for the ultimate Star Wars fan. The new Jedi Order™ and Galactic Empire™ editions of the NVIDIA TITAN Xp have been crafted to reflect the look and feel of the Star Wars galaxy.
These new Star Wars collector’s edition GPUs pay homage to the light side/dark side dichotomy, and contain hints of the Star Wars galaxy, such as the hilt of Luke Skywalker's lightsaber and light panels reminiscent of the Death Star.
The Jedi Order GPU simulates the wear and tear and battle-worn finish of many items used by the Rebel Alliance, resulting from its diecast aluminum cover being subjected to an extensive, corrosive salt spray.
Conversely, the Galactic Empire GPU’s finish features simple, clean lines, emulating the high-end, orderly nature of the resource-rich Empire.
Both versions have multiple windowed areas to showcase internals and lighting, evoking each faction’s lightsabers, green and red, respectively. The finishes of both versions took over a year to perfect.
The retail box packaging also pays homage to the light and dark sides of the Force, with the Jedi Order edition bathed in white, and the Galactic Empire edition bathed in black.
Exclusive Pre-Order Access for GeForce Experience Users
GeForce Experience users get exclusive pre-order access to purchase(1) the Jedi Order and Galactic Empire TITAN Xp editions before the cards are broadly available in mid-November. Starting tomorrow, GeForce Experience users can purchase one card of each design by using their log-in credentials in the NVIDIA store.
Power! Unlimited Power!
The Jedi Order and Galactic Empire TITAN Xp GPUs use the NVIDIA Pascal-based GP102 GPU, each with 3,840 CUDA cores running at 1.6GHz and 12GB of GDDR5X memory running at 11.4Gbps.
Their staggering 12TFLOPs of processing power under the hood allows Star Wars fans to play any of today’s most cutting-edge titles at the highest resolution with the highest detail quality turned on.
Priced at $1,200, each edition also includes a collectible electroformed metal badge containing the insignia of their preferred alliance.
Subject: Graphics Cards | April 6, 2017 - 01:13 PM | Scott Michaud
Tagged: titan xp, pascal, nvidia
While I realize that it’s the other way around if anything, part of me wants to believe that NVIDIA released this new graphics card, the TITAN Xp, solely to prevent people from calling last year’s Titan X “Titan XP”. Alternatively, they could be trolling everyone, but doing so with a legit product launch.
The NVIDIA TITAN Xp is, finally, a fully-unlocked GP102 for the consumer market, which was previously exclusive to the Tesla P40 and Quadro P6000 graphics cards. The extra 256 CUDA cores and slight bump in boost clocks equate to an expected 10.7% increase in boost shader capacity (12.15 TFLOPs vs 10.97 TFLOPs). Memory bandwidth, for its 12GB of GDDR5X, has also increase from 480 GB/s to 547.7 GB/s, which is a 14.1% increase.
NVIDIA's blog post also mentions that macOS drivers are coming this month.
The NVIDIA TITAN Xp is available now from NVIDIA’s website for $1200 USD. 2016’s NVIDIA Titan X is also listed at $1200, but is out of stock for some weird reason… hmm. It’s almost like they released an all-around better product at the same price point.
A Beautiful Graphics Card
As a surprise to nearly everyone, on July 21st NVIDIA announced the existence of the new Titan X graphics cards, which are based on the brand new GP102 Pascal GPU. Though it shares a name, for some unexplained reason, with the Maxwell-based Titan X graphics card launched in March of 2015, this is card is a significant performance upgrade. Using the largest consumer-facing Pascal GPU to date (with only the GP100 used in the Tesla P100 exceeding it), the new Titan X is going to be a very expensive, and very fast gaming card.
As has been the case since the introduction of the Titan brand, NVIDIA claims that this card is for gamers that want the very best in graphics hardware as well as for developers and need an ultra-powerful GPGPU device. GP102 does not integrate improved FP64 / double precision compute cores, so we are basically looking at an upgraded and improved GP104 Pascal chip. That’s nothing to sneeze at, of course, and you can see in the specifications below that we expect (and can now show you) Titan X (Pascal) is a gaming monster.
|Titan X (Pascal)||GTX 1080||GTX 980 Ti||TITAN X||GTX 980||R9 Fury X||R9 Fury||R9 Nano||R9 390X|
|GPU||GP102||GP104||GM200||GM200||GM204||Fiji XT||Fiji Pro||Fiji XT||Hawaii XT|
|Rated Clock||1417 MHz||1607 MHz||1000 MHz||1000 MHz||1126 MHz||1050 MHz||1000 MHz||up to 1000 MHz||1050 MHz|
|Memory Clock||10000 MHz||10000 MHz||7000 MHz||7000 MHz||7000 MHz||500 MHz||500 MHz||500 MHz||6000 MHz|
|Memory Interface||384-bit G5X||256-bit G5X||384-bit||384-bit||256-bit||4096-bit (HBM)||4096-bit (HBM)||4096-bit (HBM)||512-bit|
|Memory Bandwidth||480 GB/s||320 GB/s||336 GB/s||336 GB/s||224 GB/s||512 GB/s||512 GB/s||512 GB/s||320 GB/s|
|TDP||250 watts||180 watts||250 watts||250 watts||165 watts||275 watts||275 watts||175 watts||275 watts|
|Peak Compute||11.0 TFLOPS||8.2 TFLOPS||5.63 TFLOPS||6.14 TFLOPS||4.61 TFLOPS||8.60 TFLOPS||7.20 TFLOPS||8.19 TFLOPS||5.63 TFLOPS|
GP102 features 40% more CUDA cores than the GP104 at slightly lower clock speeds. The rated 11 TFLOPS of single precision compute of the new Titan X is 34% higher than that of the GeForce GTX 1080 and I would expect gaming performance to scale in line with that difference.
Titan X (Pascal) does not utilize the full GP102 GPU; the recently announced Pascal P6000 does, however, which gives it a CUDA core count of 3,840 (256 more than Titan X).
A full GP102 GPU
The complete GPU effectively loses 7% of its compute capability with the new Titan X, although that is likely to help increase available clock headroom and yield.
The new Titan X will feature 12GB of GDDR5X memory, not HBM as the GP100 chip has, so this is clearly a unique chip with a new memory interface. NVIDIA claims it has 480 GB/s of bandwidth on a 384-bit memory controller interface running at the same 10 Gbps as the GTX 1080.