This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.
Topics - JeGX
« on: January 12, 2015, 05:17:42 PM »
This note gives a set of guidelines and recommendations for coding in C++ for the ATLAS experiment.
There are several reasons for maintaining and following a set of programming guidelines. First, by following some rules, one can avoid some common errors and pitfalls in C++ programming, and thus have more reliable code. But even more important: a computer program should not only tell the machine what to do, but it should also tell other people what you want the machine to do. (For much more elaboration on this idea, look up references on "literate programming," such as .) This is obviously important any time when you have many people working on a given piece of software, and such considerations would naturally lead to code that is easy to read and understand. Think of writing ATLAS code as another form of publication, and take the same care as you would writing up an analysis for colleagues.
- ATLAS C++ coding guidelines
- ATLAS Experiment
« on: January 12, 2015, 02:02:28 PM »
Tungsten is a physically based renderer originally written for the yearly renderer competition at ETH. It simulates full light transport through arbitrary geometry based on unbiased integration of the rendering equation using path tracing.
Tungsten is written in C++11 and makes use of Intel's high-performance geometry intersection library embree. Tungsten takes full advantage of multicore systems and tries to offer good performance through frequent benchmarking and optimization. At least SSE3 support is required to run the renderer.
- Github: https://github.com/tunabrain/tungsten
- Article: http://noobody.org/tungsten.html
GL-Z is a simple OpenGL information tool. More information and download:
« on: November 21, 2014, 06:50:48 AM »
EIZO Corporation (TSE: 6737) today announced the new FlexScan EV2730Q, a 26.5-inch square monitor with a 1920 × 1920 resolution (1:1 aspect ratio). The monitor is the newest addition to EIZO’s FlexScan EcoView Series which combines both ergonomic and environmental features for an economical result.
FlexScan EV2730QThe FlexScan EV2730Q is wide all around – the unique 1920 × 1920 resolution provides users with 78% more pixels compared with a standard widescreen 1920 × 1080 monitor. The extended vertical space is convenient for displaying large amounts of information in long windows, reducing the need for excess scrolling and providing a more efficient view of data. This makes the monitor ideal for displaying information such as CAD or program development data with a more complete overall view on screen.
The non-glare IPS panel has wide viewing angles, making the monitor comfortable to view in any workstation and from any angle. The ergonomically designed stand with height adjustment, tilt, and swivel provides positioning flexibility and user comfort.
To lower eyestrain, the monitor utilizes an EIZO-developed solution that regulates brightness to make flicker unperceivable. In addition, the wide dimming range allows the monitor to be adjusted to just 1% of maximum brightness for higher comfort in dimly-lit work environments.
Five preset modes are included – sRGB, Movie, Paper, and two modes with user-adjustable settings. Paper mode reduces the amount of blue light to help prevent eye fatigue.
The monitor includes EIZO’s own EcoView technologies such as EcoView Optimizer 2, which saves power by reducing the backlight brightness and increasing the gain when displaying mostly dark content. In addition, Auto EcoView automatically adjusts the screen’s brightness in accordance with changes in ambient lighting to trim power usage while reducing eye fatigue.
A presence sensor called EcoView Sense 2 detects when the user leaves the desk and automatically switches to power save mode. When the user returns, EcoView Sense 2 powers the monitor on again. It detects both the user’s movements and body heat for increased accuracy.
- Press release: http://www.eizoglobal.com/press/releases/htmls/ev2730q.html
- Home page: http://www.eizoglobal.com/products/flexscan/ev2730q/index.html
« on: November 20, 2014, 01:54:01 PM »
Visual Studio 2015 Preview is now available, so here's an updated feature table for the Core Language:
« on: November 19, 2014, 10:37:35 AM »
So, you just got access to the latest supercomputer with thousands of GPUs. Obviously this is going to help you a lot with accelerating your scientific calculations, but how are you going to analyze, reduce and visualize this data? Historically, you would be forced to write everything out to disk, just to later read it back into another data analysis cluster.
Wouldn’t it be nice if you could analyze and visualize your data as it is being generated, without having to go through a file system? And wouldn’t it be cool to interact with the simulation, maybe even modifying parameters while the simulation is running?
And wouldn’t it be nice to use your GPU for that as well? As it turns out, you can actually do this. It’s called in-situ visualization, meaning visualization of datasets in-place where they are computed. High-quality, high performance rendering and visualization is just one of the capabilities of the Tesla Accelerated Computing Platform.
Cosmological simulations like those undertaken by a group led by Professor Simon Portegies-Zwart at the Leiden Observatory in the Netherlands provide a good example of present-day in-situ visualization. To understand how the Milky Way galaxy formed, and how dark matter influenced the process, they run very large-scale GPU-accelerated gravitational simulations with the Bonsai2 code. Their simulations are so powerful and efficient, that their code is one of the nominees for this year’s Gordon Bell awards.
First up is a new antialiasing method called MFAA, or Multi-Frame Sampled AA. This new method alternates the AA sample pattern, which is now programmable via software, in both temporal and spatial directions.
The goal is to change the AA sample pattern in a way to produce near 4xMSAA quality at the effective cost of 2x MSAA (in terms of performance).
NVIDIA's new Multi-Frame Sampled Anti-Aliasing is finally coming out, two full months behind the release and reveal of the GTX 980 and the MFAA technology in general. Despite that delay, the current shipping driver only supports MFAA on twenty PC games and uses a silent white list method that requires a lot of research on the part of the gamer to determine compatibility. Clearly this isn't what NVIDIA expected or desired, but that is where we are on the launch of the AA method with the baddest name around.
Still, even though we could fairly call this MFAA release small by expectations placed on the tech by NVIDIA, it does appear to work as desired in those games that are supported. In my time with it, the image quality it provided was better than 2x MSAA and nearly to that of 4x MSAA with performance closer to 2x MSAA than 4x MSAA. That alone would give MFAA a spot in our list of favorite features for Maxwell if it just supported more games!
Time will tell if MFAA is a feature that NVIDIA continues to work on and improve or if it will be one of the many graphics technologies from the last 15 years to find its way to the list of also-rans. Even looking at the list of ATI/AMD/NVIDIA specific AA methods alone will leave you dizzy with acronym-confusion. Not having SLI support for MFAA also seems like a really glaring omission considering these are the same types of users that are willing to enable off-shoot options in the control panel like this.
For now though, a very limited subset of NVIDIA's gamers (GTX 980/970) will be able to enjoy the benefits of MFAA on a very limited subset of modern PC games. It has potential, but needs a lot of work and attention from the driver team to keep the plates spinning.
« on: November 19, 2014, 10:31:04 AM »
After the long hard working in HPC field, ASUS now presents the GPU server ESC8000 G3 supporting up to eight double deck GPU cards as well as optimized thermal design for both CPUs and GPUs. ESC8000 G3 is the latest supercomputer based on Intel® Xeon® processor E5-2600 v3 product family, featuring front parallel redundant fan placement and dedicated air-tunnel for individual GPUs, six hot-swappable 2.5” SATA HDD/SSD bays, 2+1 80 PLUS Platinum 1600W CRPS , 8 PCI-E Gen3 x16 and 2 PCI-E Gen3 x8 expansion slots. ESC8000 G3 is targeted to hit 20Tera floating points with the latest generation GPU cards and achieve an outstanding performance result in Top500 and Green500.
« on: November 18, 2014, 10:40:28 AM »
This test makes C++ code draw into an HTML canvas element.
The C++ code renders to an uint8 buffer directly (without OpenGL or anything like that). That C++ code is converted to asm.js, then executed from JS making it modify the contents of an HTML canvas element.
Performance is quite low compared to GPU rendering, but still quite usable if target resolution is not very big. For "retro"-style, pixel-art stuff it should work quite well.
A WebGL realtime simulation of fluids using SPH particles animations and marching cubes to create the geometry.
« on: November 18, 2014, 09:45:17 AM »
In this series we’ll be looking at the benefits of AMD’s Mantle API over Microsoft’s DirectX 11.
This is a five part series; in part 1 we’ll be looking at the performance of AMD’s flagship single GPU the Radeon R9 290X.
Clearly Mantle offers current Radeon R9 290X owners an easy way to boost the performance of their hardware for free. That’s good news for those users that purchased their hardware with the belief that Mantle enabled games would eventually come this far into the mainstream. It’s also good news for AMD and its partners in the video game industry who have stacked up quite a bit of support for this API.
« on: November 18, 2014, 09:39:04 AM »
Highlights of AMD Catalyst 14.11.2 Windows Beta Driver Performance Improvements:
- Dragon Age: Inquisition performance optimizations
- Up to 5% performance increase over Catalyst™ 14.11.1 beta in single GPU scenarios with Anti-Aliasing enabled.
- Optimized AMD CrossFire™ profile
- Far Cry 4 performance optimizations
- Up to 50% performance increase over Catalyst™ 14.11.1 beta in single GPU scenarios with Anti-Aliasing enabled.
- Cat 14.11.2 Win7/Win8 64-bit
- Cat 14.11.2 Win7/Win8 32-bit
- Release notes
« on: November 11, 2014, 05:55:37 PM »
It was the peak of the Cold War, and President John F Kennedy responded to years of Russian dominance in space by committing that we would take a man to the moon and back again. With the Apollo 11 mission, that oath was fullfilled.
Or was it?
There are conspiracy theorists who believe that the photos are forgeries because of inconsistencies in the lighting. Why can Buzz Aldrin be seen when he is in a shadow? Why aren’t there any stars? Did we just see a studio light?
Powered by NVIDIA Maxwell™ GPU architecture and Epic’s UE4 and using NVIDIA’s Voxel Global Illumination (or VXGI) we explore the Apollo 11 landing site and put the landmark photo of Buzz Aldrin descending to the moon’s surface to the test.
« on: November 11, 2014, 08:51:04 AM »
The new GeForce Game Ready driver, release 344.65 WHQL, includes improvements which allows GeForce owners to continue to have the ultimate gaming platform. In addition, this Game Ready WHQL driver ensures you'll have the best possible gaming experience for Assassin’s Creed: Unity
- Assassin's Creed Unity GeForce Game Ready Driver Available Now
- R344.65 Win7/Win8 64-bit
- R344.65 Win7/Win8 32-bit
- R344.65 Win7/Win8 64-bit
- R344.65 Win7/Win8 32-bit
« on: November 10, 2014, 03:06:06 PM »
Better late than never, I received this nice card: the MSI's Radeon R9 290X Gaming 4G. This Radeon is powered by the Hawaii GPU (XT version) and comes with 4GB of GDDR5 and the Twin Frozr IV VGA cooler (I must say that the Twin Frozr IV is absolutely quiet at idle).
AMD Catalyst 14.9 WHQL:
GPU Caps Viewer:
AMD Catalyst 14.9 WHQL:
GPU Caps Viewer:
Sadly, it's pretty clear that if you run these games on Linux your experience isn't going to be as good, and you'll be getting less "gaming value" vs. Windows. We're not talking about a bunch of little indy titles, these are big releases: Borderlands: The Pre-Sequel, Borderlands 2, Tropico 5, XCOM: Enemy Unknown, Sid Meier's Civilization V. My take is the devs doing these ports just aren't doing their best to optimize these releases for Linux and/or OpenGL.
A nice little tidbit from this report: "Unfortunately, Aspyr are currently still unable to provide support for non-Nvidia graphics cards, as with Borderlands 2. This doesn't mean the game won't work if you have an AMD or Intel GPU, but just that you're not guaranteed to receive help from the developer - the current driver situation for non-Nvidia cards may lead to degraded performance." Huh? This is not a good situation.
« on: November 07, 2014, 01:25:54 PM »
Like many other visual effects, games attempt to mimic transparent (or translucent as it’s often synonymously referred to in the games industry) objects as closely as possible. Real world transparent objects are often modelled in games using a simple set of equations and rules; simplifications are made, and laws of physics are bent, in an attempt to reduce the cost of simulating such a complex phenomenon. For the most part we can get plausible results when rendering semi-transparent objects by ignoring any refraction or light scattering in participating media. In this article we’re going to focus on a few key methods for transparency rendering, discuss the basics and propose some alternatives/optimizations which should be of use to anyone who hasn’t heard them before.
Full article: https://developer.nvidia.com/content/transparency-or-translucency-rendering