Personal Profile

CUDA

GPU Caps Viewer 1.34.0 Released

A new version of GPU Caps Viewer (OpenGL, Vulkan, OpenCL and CUDA utility) is available.

GPU Caps Viewer 1.34.0 Released

GPU Caps Viewer 1.34.0 Released

1 – Overview

GPU Caps Viewer 1.34.0 adds the support of the latest GeForce GTX 1080 Ti, Radeon RX 580, RX 570 and RX 560 (based on Polaris 10/11 GPUs) as well as Radeon Pro WX 7100, WX 5100 and WX 4100.

New Vulkan and OpenGL demos (based on GeeXLab engine) have been added in the 3D demos panel:


GPU Caps Viewer 1.34 + new GeeXLab demos
All GeeXLab demos can now be launched using the command line:

GpuCapsViewer.exe /demo_win_width=1920 /demo_win_height=1080
/demo_fullscreen /run_gxl_demo=vk_shadertoy_geomechanical
/benchmark_log_results /benchmark_duration=10000 /demo_msaa=0
/vk_gpu_index=0

Command line parameters can be found in the _run_geexlab_benchmark.bat file available in GPU Caps Viewer folder. The benchmark results are saved in a CSV file (_gxl_benchmark_results.csv).


GPU Caps Viewer 1.34 + new GeeXLab demos

Another change brought to GPU Caps concerns the UAC (User Account Control) execution level that has been reset to the default value (as invoker). The previous UAC level (administrator) didn’t work well with launching demos via the command line.

GPU Caps Viewer 1.33 + GeForce GTX 1060

GPU Caps Viewer 1.33 + GeForce GTX 1060

All Vulkan code has been recompiled with latest Vulkan headers (v1.0.45).


>> Update: 2017.04.29 <<

GPU Caps Viewer 1.34.3.1 is a maintenance release and comes with a new VK-Z version. VS2015 generates some strange patterns in the 32-bit version of VK-Z and no matter the way I compile VK-Z, the 32-bit version of VK-Z is still flagged as infected by some antivirus. The 64-bit version of VK-Z is clean so I just replaced the 32-bit version by the 64-bit one. GPU Caps Viewer has been updated to execute VK-Z x64 on Windows 64-bit only…

>> Update: 2017.04.26 <<

GPU Caps Viewer 1.34.3.0 is a maintenance release and improves the detection of recent AMD Radeon GPUs (RX 580, RX 570, RX 480 and RX 470). GPU Shark has been updated to version 0.9.11.4. VK-Z has been updated to version 0.6.0.5 32-bit (it has been recompiled with other compilation options in order to avoid false positive detection with antivirus. I really don’t understand this pesky problem!).

>> Update: 2017.04.16 <<

GPU Caps Viewer 1.34.2.1 is available with VK-Z 0.6.0.3. The previous 32-bit version of VK-Z was detected as infected by some antivirus scanners. Now VK-Z 32-bit is clean for Nod32, Avira, Avast, Kaspersky, AVG, Norton, and MacAfee.

>> Update: 2017.04.14 <<

GPU Caps Viewer 1.34.2.0 adds the support of NVIDIA TITAN Xp. GPU Shark and VK-Z have been updated to their latest versions.

>> Update: 2017.04.01 <<

GPU Caps Viewer 1.34.1.0 improves the detection of AMD Radeon GPUs in some systems that include Intel iGPU + AMD Radeon GPU. A new GeeXLab/OpenGL demo has been added (Alien Corridor).

GPU Caps Viewer 1.34.1

GPU Caps Viewer 1.34.1


2 – Dowloads

2.1 – Portable version (zip archive – no installation required):

2.2 – Win32 installer:

For any feedback or bug report, a thread on Geeks3D forums is available HERE.

 

3 – What is GPU Caps Viewer?

GPU Caps Viewer is a graphics card information utility focused on the OpenGL, Vulkan, OpenCL and CUDA API level support of the main (primary) graphics card. For Vulkan, OpenCL and CUDA, GPU Caps Viewer details the API support of each capable device available in the system. GPU Caps Viewer offers also a simple GPU monitoring facility (clock speed, temperature, GPU usage, fan speed) for NVIDIA GeForce and AMD Radeon based graphics cards. GPU data can be submitted to an online GPU database.


GPU Caps Viewer panels

4 – Changelog

Version 1.34.3.1 – 2017.04.29
! replaced VK-Z 0.6.0.5 32-bit by VK-Z 0.6.0.3 64-bit.
VK-Z 64-bit does not produce false positive with some
antivirus. VK-Z 64-bit is only executed on Windows 64-bit.

Version 1.34.3.0 – 2017.04.20
! improved detection of Radeon RX 580, RX 570,
RX 480 and RX 470.
! updated: GPU Shark 0.9.11.4
! updated: VK-Z 0.6.0.5
! updated: ZoomGPU 1.20.4 (GPU monitoring library).

Version 1.34.2.1 – 2017.04.16
! updated: VK-Z 0.6.0.3

Version 1.34.2.0 – 2017.04.14
+ added support of NVIDIA TITAN Xp.
! updated Radeon RX 560 shader cores.
! updated: VK-Z 0.6.0
! updated with GeeXLab SDK libs.
! updated: GPU Shark 0.9.11.3
! updated: ZoomGPU 1.20.3 (GPU monitoring library).

Version 1.34.1.0 – 2017.04.01
! improves the detection of AMD Radeon GPUs in some systems
that include Intel iGPU + AMD Radeon GPU.
+ added new OpenGL demo (GeeXLab): Alien Corridor (based on this demo).
Command line demo codename: gl21_shadertoy_mp_alien_corridor
! updated: GPU Shark 0.9.11.2
! updated: ZoomGPU 1.20.2 (GPU monitoring library).

Version 1.34.0.0 – 2017.03.25
+ added support of the GeForce GTX 1080 Ti.
+ added support of AMD Radeon RX 580, RX 570 and RX 560.
+ added support of AMD Radeon Pro WX 7100, WX 5100, WX4100,
WX 4150 and WX 4130.
+ added initial support of AMD Polaris 12 and Vega 10 based videocards.
+ added new parameters for launching GeeXLab demos via the command line.
+ added new Vulkan and OpenGL demos (GeeXLab): Vulkan geomechanical (based on this demo), OpenGL rainforest (based on this demo), OpenGL radialblur (based on this demo), OpenGL rhodium (based on this demo), OpenGL cell shading, OpenGL geometry instancing, OpenGL gs mesh exploder.
! set UAC (User Account Control) execution level to as invoker.
! recompiled with latest Vulkan API headers (v1.0.45).
! updated with latest GeeXLab SDK libs.
! updated: GPU Shark 0.9.11.1
! updated: ZoomGPU 1.20.1 (GPU monitoring library).

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp

NVIDIA TITAN Xp

NVIDIA has more or less silently launched a new high end graphics card around 10 days ago. Here are some pictures of the TITAN Xp versus the TITAN X (launched last year), both gaming cards being based on a Pascal GP102 GPU…

The TITAN Xp is based on a full GP102 GPU with 3840 CUDA cores while the TITAN X has only 3584 CUDA cores. The TITAN Xp has 240 texture units while the TITAN X has 224 texture units. Both cards have the same number of ROPs (96) and the same amount of memory: 12GB of GDDR5X.

On the physical side, there are few differences between the TITAN Xp and the TITAN X. NVIDIA has not changed the name on the VGA shroud: TITAN X for both cards…

NVIDIA TITAN Xp

NVIDIA TITAN Xp


The only things that distinguish both cards are the box, the PCB color (brown for the Xp) and the DVI connector (the Xp has no DVI connector):

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X

NVIDIA TITAN Xp vs TITAN X


The TITAN Xp alone:

NVIDIA TITAN Xp

NVIDIA TITAN Xp

NVIDIA TITAN Xp

NVIDIA TITAN Xp

Latest NVIDIA JetPack Developer Tools Will Double Your Deep Learning Performance

Latest NVIDIA JetPack Developer Tools Will Double Your Deep Learning Performance

Latest NVIDIA JetPack Developer Tools Will Double Your Deep Learning Performance

Today NVIDIA released a major update of the JetPack SDK with new developer tools and libraries that doubles the performance of deep learning applications on the Jetson TX1 Developer Kit, the world’s highest performance platform for deep learning on embedded systems.

JetPack 2.3 is available as a free download and is focused on making it easier for developers to add complex AI and deep learning capabilities to intelligent machines. This update includes the new TensorRT deep learning inference engine, the latest versions of CUDA 8 and cuDNN 5.1, and tighter camera and multimedia integration to easily add complex AI and deep learning abilities to intelligent machines.

JetPack 2.3 chart
See footnotes below.

In addition, NVIDIA announced a new partnership with Leopard Imaging Inc., a Jetson Preferred Partner that specializes in the creation of camera solutions. The new camera API included in the JetPack 2.3 release delivers enhanced functionality to ease developer integration.

Download JetPack 2.3 today.

Chart footnotes:

  • The efficiency was measured using the methodology outlined in the whitepaper.
  • Jetson TX1 efficiency is measured at GPU frequency of 691 MHz.
  • Intel Core i7-6700k efficiency was measured for 4 GHz CPU clock.
  • GoogLeNet batch size was limited to 64 as that is the maximum that could run with Jetpack 2.0. With Jetpack 2.3 and TensorRT, GoogLeNet batch size 128 is also supported for higher performance.
  • FP16 results for Jetson TX1 are comparable to FP32 results for Intel Core i7-6700k as FP16 incurs no classification accuracy loss over FP32.
  • Latest publicly available software versions of IntelCaffe and MKL2017 beta were used.
  • For Jetpack 2.0 and Intel Core i7, non-zero data was used for both weights and input images. For Jetpack 2.3 (TensorRT) real images and weights were used.

GPUs Help Find a Massive New Reef Hiding Behind Great Barrier Reef

GPUs Help Find a Massive New Reef Hiding Behind Great Barrier Reef

GPUs Help Find a Massive New Reef Hiding Behind Great Barrier Reef

Australian scientists made a significant discovery hiding behind the world-famous Great Barrier Reef. The discovery was made using cutting-edge surveying technology, which revealed vast fields of doughnut-shaped mounds measuring up to 300 meters across and up to 10 meters deep.

“We’ve known about these geological structures in the northern Great Barrier Reef since the 1970s and 80s, but never before has the true nature of their shape, size and vast scale been revealed,” said Dr Robin Beauman of James Cook University, who helped lead the research.

The scientists from James Cook University, Queensland University of Technology, and University of Sydney used LiDAR data collected from the Australian Navy to help reveal this deeper, subtler reef. They then used CUDA and GeForce GTX 1080 GPUs to compile and visualize the huge 3D bathymetry datasets.

“Having a high-performance GPU has been critical to this ocean mapping research,” says Beauman.

North-westerly view of the Bligh Reef area off Cape York. Depths are colored red (shallow) to blue (deep), over a depth range of about 50 meters. Bathymetry data from Australian Hydrographic Service.

North-westerly view of the Bligh Reef area off Cape York. Depths are colored red (shallow) to blue (deep), over a depth range of about 50 meters. Bathymetry data from Australian Hydrographic Service.

The discovery has opened up many other new avenues of research.

“For instance, what do the 10-20 meter thick sediments of the bioherms tell us about past climate and environmental change on the Great Barrier Reef over this 10,000 year time-scale? And, what is the finer-scale pattern of modern marine life found within and around the bioherms now that we understand their true shape?”

Next up, the researchers plan to employ autonomous underwater vehicle technologies to unravel the physical, chemical and biological processes of the structures.

Advanced Real-Time Visualization for Robotic Heart Surgery

Advanced Real-Time Visualization for Robotic Heart Surgery

Advanced Real-Time Visualization for Robotic Heart Surgery

Researchers at the Harvard Biorobotics Laboratory are harnessing the power of GPUs to generate real-time volumetric renderings of patients’ hearts. The team has built a robotic system to autonomously steer commercially available cardiac catheters that can acquire ultrasound images from within the heart. They tested their system in the clinic and reported their results at the 2016 IEEE International Conference on Robotics and Automation (ICRA) in Stockholm, Sweden.

The team used an Intracardiac Echocardiography (ICE) catheter, which is equipped with an ultrasound transducer at the tip, to acquire 2D images from within a beating heart. Using NVIDIA GPUs, the team was able to reconstruct a 4D (3D + time) model of the heart from these ultrasound images.

Generating a 4D volume begins with co-registering ultrasound images that are acquired at different imaging angles but at the same phase of the cardiac cycle. The position and rotation of each image with respect to the world coordinate frame is measured using electromagnetic (EM) trackers that are attached to the catheter body. This point cloud is then discretized to lie on a 3D grid. Next, infilling is performed to fill the gaps between the slices, generating a dense volumetric representation of the heart. Finally, the volumes are displayed to the surgeon using volume rendering via raycasting, leveraging the CUDA – OpenGL interoperability. The team accelerated the volume reconstruction and rendering algorithms using two NVIDIA TITAN GPUs.

“ICE catheters are currently seldom used due to the difficulty in manual steering,” said principal investigator Prof. Robert D. Howe, Abbott and James Lawrence Professor of Engineering at Harvard University. “Our robotic system frees the clinicians of this burden, and presents them with a new method of real-time visualization that is safer and higher quality than the X-ray imaging that is used in the clinic. This is an enabling technology that can lead to new procedures that were not possible before, as well as improving the efficacy of the current ones.”

Providing real-time procedure guidance requires the use of efficient algorithms combined with a high-performance computing platform. Images are acquired at up to 60 frames per second from the ultrasound machine. Generating volumetric renderings from these images in real-time is only possible using GPUs.

NVIDIA TITAN X

NVIDIA TITAN X

The Ultimate.

The NVIDIA TITAN X, featuring the NVIDIA Pascal architecture, is the ultimate graphics card. Whatever you’re doing, this groundbreaking TITAN X gives you the power to accomplish things you never thought possible.
Limit 2 per customer
Watch VideoWATCH FULL VIDEO

NVIDIA PASCAL

THE WORLD’S MOST ADVANCED GPU ARCHITECTURE

GeForce GTX 10-series graphics cards are powered by Pascal to deliver up to 3x the performance of previous-generation graphics cards, plus innovative new gaming technologies and breakthrough VR experiences.

UP TO 3XFASTER PERFORMANCE
LATEST GAMING TECHNOLOGIES
NEXT-GEN VR EXPERIENCES
*Up to 3X faster performance for GeForce GTX 10 Series when compared to the GTX 900 Series

Irresponsible Amount of Performance

We packed the most raw horsepower we possibly could into this GPU. Driven by 3584 NVIDIA CUDA® cores running at 1.5GHz, TITAN X packs 11 TFLOPs of brute force. Plus it’s armed with 12 GB of GDDR5X memory – one of the fastest memory technologies in the world.

NVIDIA TITAN X
GPU Architecture Pascal
Frame Buffer 12 GB G5X
Memory Speed 10 Gbps
Boost Clock 1531 MHz

View Full Specs

Design Excellence

TITAN X is crafted to offer superior heat dissipation using vapor chamber cooling technology in a die cast aluminum body. It’s a powerful combination of brilliant efficiency, stunning design, and industry-leading performance.

NVIDIA SLI® TECHNOLOGY

SLI ULTRA BRIDGESLI

GEFORCE GTX SLI HB BRIDGE

NVIDIA’s new SLI bridge doubles the available transfer bandwidth compared to the NVIDIA Maxwell architecture. Delivering silky-smooth gameplay, it’s the best way to experience surround gaming—and it’s only compatible with the NVIDIA TITAN X, GeForce GTX 1080 and GeForce GTX 1070 graphics cards.

$XXX.XX
SELECT BRIDGE SIZE
2-Slot
3-Slot
4-Slot

Help me choose which size >

BUY NOW
Limit 1 per customer

SIgn up for the GeForce GTX Newsletter

JOIN NOW

Shop Now

NVIDIA TITAN X

NVIDIA TITAN X
Limit 2 per customer

Assisting Farmers with Artificial Intelligence

Assisting Farmers with Artificial Intelligence

Assisting Farmers with Artificial Intelligence

With our planet getting warmer and warmer, and carbon dioxide levels steadily creeping up, companies are using deep learning to help cope with the effects that climate change is having on their crops.   

An article on MIT Technology Review highlights PEAT, a German company using CUDA, TITAN X GPUs and the cuDNN-accelerated Caffe deep learning framework to provide farmers with a plant disease and diagnostics management tool. Farmers are able to take a picture of their affected plants, upload it to PEAT’s “Plantix” mobile app and get treatment recommendations within seconds. The database currently contains information on 52 crops worldwide and the ability to detect 160 plant diseases, pests and nutrient deficiencies with 95% accuracy.

EAT’s Plantix app provides detailed symptom descriptions to empower farmers to take autonomous decisions on their disease management.

EAT’s Plantix app provides detailed symptom descriptions to empower farmers to take autonomous decisions on their disease management.

As mobile phones are now ubiquitous throughout the developing world, this solution provides the last-mile connectivity that farmers need to deal with the impact of a changing climate.

Facebook and CUDA Accelerate Deep Learning Research

Facebook and CUDA Accelerate Deep Learning Research

Facebook and CUDA Accelerate Deep Learning Research

Last Thursday at the International Conference on Machine Learning (ICML) in New York, Facebook announced a new piece of open source software aimed at streamlining and accelerating deep learning research. The software, named Torchnet, provides developers with a consistent set of widely used  deep learning functions and utilities. Torchnet allows developers to write code in a consistent manner speeding development and promoting code re-use both between experiments and across multiple projects.

Torchnet sits atop the popular Torch deep learning framework benefits from GPU acceleration using CUDA and cuDNN.

Torchnet sits atop the popular Torch deep learning framework benefits from GPU acceleration using CUDA and cuDNN.

Torchnet sits atop the popular Torch deep learning framework benefits from GPU acceleration using CUDA and cuDNN. Further, Torchnet has built-in support for asynchronous, parallel data loading and can make full use of multiple GPUs for vastly improved iteration times. This automatic support or multi-GPU training helps Torchnet take full advantage of powerful systems like the NVIDIA DGX-1 with its eight Tesla P100 GPUs.

Facebook and CUDA Accelerate Deep Learning Research

Facebook and CUDA Accelerate Deep Learning Research

According to the Torchnet research paper, its modular design makes it easy to re-use code in a series of experiments. For instance, running the same experiments on a number of different datasets is accomplished simply by plugging in different dataloaders. And the evaluation criterion can be changed easily by plugging in a different performance meter.

Torchnet adds another powerful tool to data scientists’ toolkit and will help speed the design and training of neural networks, so they can focus on their next great advancement.

Creating Virtual Reality Experiences for the NFL with GPUs

 Bucs VR Creating Virtual Reality Experiences for the NFL with GPUs

Bucs VR Creating Virtual Reality Experiences for the NFL with GPUs

The Tampa Bay Buccaneers unveiled a state-of-the-art experience to provide fans with the ability to virtually sample the new gameday enhancements that will debut beginning with the team’s 2016 season.

While the new Raymond James Stadium is under construction, current and prospective ticket holders can use a virtual reality headset to experience the new stadium before it opens in September. The realistic preview is also valuable in attracting potential sponsors by helping executives visualize their company’s logo inside the stadium.

Brian Killingsworth, chief marketing officer of the Buccaneers, said the Bucs are the first professional sports team to integrate video and a “three-dimensional environment with full freedom of motion touring capabilities.”

An aerial view of what the overhauled Raymond James Stadium will look like for the 2016 season. (Tampa Bay Buccaneers)

An aerial view of what the overhauled Raymond James Stadium will look like for the 2016 season. (Tampa Bay Buccaneers)

MVP Interactive, a four-year old Philadelphia creative agency, used CUDA and the new GeForce GTX 1080 to develop the experience with Unreal Engine.

“We’re seeing a massive opportunity to leverage the technology to give a view from the seats from a season-ticket perspective, and of course corporate sponsors are really important to the finances of a particular team. When folks have their first opportunity to experience virtual reality, that alone helps qualify a sales pitch,” MVP Interactive CEO James Giglio said.

World’s First Real-Time 3D Oil Painting Simulator

World’s First Real-Time 3D Oil Painting Simulator

World’s First Real-Time 3D Oil Painting Simulator

The painting and drawing tools most people use are 2D, but now a new project gives artists the ability to choose any brush they like, a limitless array of paint colors, and use the same natural twists and turns of the brush to create the rich textures of oil painting, all on a digital canvas.

Delivering such a realistic, physically-based painting tool requires some heavy-duty computational power, so Adobe Research collaborated with NVIDIA to create the world’s first real-time simulation-based 3D painting system with bristle-level interactions entirely with CUDA. Adobe Researchers Zhili Chen and Byungmoon Kim originally developed Project Wetbrush in 2015, but and have collaborated with NVIDIA software experts to optimize their application performance, allowing them to add even more GPU-accelerated features to the system.

This is just the beginning for the project. Using deep learning, some of the most computationally challenging physical simulations could potentially be added to create more responsive and realistic brush dynamics, or the system could even learn from itself.

World’s First Real-Time 3D Oil Painting Simulator

World’s First Real-Time 3D Oil Painting Simulator



Popular Pages
Popular posts
Interested
About me

My name is Sayed Ahmadreza Razian and I am a graduate of the master degree in Artificial intelligence .
Click here to CV Resume page

Related topics such as image processing, machine vision, virtual reality, machine learning, data mining, and monitoring systems are my research interests, and I intend to pursue a PhD in one of these fields.

جهت نمایش صفحه معرفی و رزومه کلیک کنید

My Scientific expertise
  • Image processing
  • Machine vision
  • Machine learning
  • Pattern recognition
  • Data mining - Big Data
  • CUDA Programming
  • Game and Virtual reality

Download Nokte as Free


Coming Soon....

Greatest hits

Anyone who has never made a mistake has never tried anything new.

Albert Einstein

The fear of death is the most unjustified of all fears, for there’s no risk of accident for someone who’s dead.

Albert Einstein

Imagination is more important than knowledge.

Albert Einstein

It’s the possibility of having a dream come true that makes life interesting.

Paulo Coelho

Gravitation is not responsible for people falling in love.

Albert Einstein

Waiting hurts. Forgetting hurts. But not knowing which decision to take can sometimes be the most painful.

Paulo Coelho

One day you will wake up and there won’t be any more time to do the things you’ve always wanted. Do it now.

Paulo Coelho

You are what you believe yourself to be.

Paulo Coelho


Site by images
Statistics
  • 2,319
  • 10,075
  • 92,535
  • 25,499
Recent News Posts