Tuesday, May 31, 2011
NVIDIA's quad-core Kal-El used to demo next-gen mobile graphics, blow minds (video)
Built to run on the company's quad-core Kal-El processor, NVIDIA demoed the new goodness on a Honeycomb slate with 1280 x 800 resolution and the frame rates remained smooth throughout. NVIDIA promises the production chip will be 25 to 30 percent faster than the one on display today. Full video demo follows after the break. See more in
Saturday, May 28, 2011
Install Cuda 4.0 on Ubuntu 11.04
NVIDIA Cuda 4.0 was released in this month. It includes Performance Primitives (NPP) library for image/video processing using multi-GPU programming. It is supported on many PCs and laptops with NVIDIA GPUs, including Thinkpad T410 with NVIDIA NVS 3100M.
Ubuntu 11.04 was released in the last month. Here is my instruction to install Cuda 4.0 on Ubuntu 11.04 on my Thinkpad T410 (thanks to instructions from http://forums.nvidia.com/index.php?showtopic=198030)
1. Install dependencies
sudo apt-get install build-essential gcc-4.4 g++-4.4 libxi-dev libxmu-dev freeglut3-dev
2. And download and install
- CUDA Toolkit for Ubuntu Linux 10.10 (sudo sh ...)
- CUDA Tools SDK (sudo sh ...)
- GPU Computing SDK code samples (no sudo)
from the following links:
| LINUX | DOWNLOADS |
|---|---|
| Developer Drivers for Linux (270.41.19) | 32-bit 64-bit |
CUDA Toolkit
| documentation |
| CUDA Toolkit for Fedora 13 | 32-bit 64-bit |
| CUDA Toolkit for RedHat Enterprise Linux 6.0 | 64-bit |
| CUDA Toolkit for RedHat Enterprise Linux 5.5 | 32-bit 64-bit |
| CUDA Toolkit for RedHat Enterprise Linux 4.8 | 64-bit |
| CUDA Toolkit for Ubuntu Linux 10.10 | 32-bit 64-bit |
| CUDA Toolkit for OpenSUSE 11.2 | 32-bit 64-bit |
| CUDA Toolkit for SUSE Linux Enterprise Server 11 SP1 | 32-bit 64-bit |
| CUDA Tools SDK | 32-bit 64-bit |
| GPU Computing SDK code samples | download |
3. Download the Developer Drivers for Linux (270.41.19) from the above link. For driver installation, you need to
(1) remove the current nvidia packages you might have installed
sudo apt-get remove nvidia-common nvidia-current
(2) go to the text window via ctrl+alt+F2.
(3) stop X
sudo service gdm stop(4) remove the nouveau module
sudo apt-get --purge remove xserver-xorg-video-nouveau(5) stop gdm and restart X
sudo service gdm startRestart the system
(6) stop X
sudo service gdm stop(7) install driver
sudo sh devdriver_4.0_linux_32_270.41.19.run(7) restart X
sudo service gdm start4. Assuming you have accepted the default install location /usr/local/cuda, you should add the following in the .bashrc file of your home folder.
export CUDA_HOME="/usr/local/cuda"
export LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:${CUDA_HOME}/lib64"
export PATH=${CUDA_HOME}/bin:${PATH}
run ldconfig as root for it to take effect:
source ~/.bashrcand
sudo ldconfig5. make nvcc use gcc/g++ version 4.4, for example, in home directory
mkdir gcc44
cd gcc4
ln -s /usr/bin/cpp-4.4 cpp
ln -s /usr/bin/gcc-4.4 gcc
ln -s /usr/bin/g++-4.4 g++
edit /usr/local/cuda/bin/nvcc.profile to look in the gcc44 directory (give it the full path)
compiler-bindir =/home/xxx/gcc44 6. run make in NVIDIA_GPU_Computing_SDK/C
cd ~/NVIDIA_GPU_Computing_SDK/C
make
7. verify CUDA 4.0 installation by running the deviceQuery sample in the NVIDIA_GPU_Computing_SDK/C
bin/linux/release/deviceQuerymy Thinkpad T410 shows
[deviceQuery] starting...
linux/release/deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Found 1 CUDA Capable device(s)
Device 0: "NVS 3100M"
CUDA Driver Version / Runtime Version 4.0 / 4.0
CUDA Capability Major/Minor version number: 1.2
Total amount of global memory: 256 MBytes (268107776 bytes)
( 2) Multiprocessors x ( 8) CUDA Cores/MP: 16 CUDA Cores
GPU Clock Speed: 1.47 GHz
Memory Clock rate: 810.00 Mhz
Memory Bus Width: 64-bit
Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)
Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 16384
Warp size: 32
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 2147483647 bytes
Texture alignment: 256 bytes
Concurrent copy and execution: Yes with 1 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Concurrent kernel execution: No
Alignment requirement for Surfaces: Yes
Device has ECC support enabled: No
Device is using TCC driver mode: No
Device supports Unified Addressing (UVA): No
Device PCI Bus ID / PCI location ID: 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 1, Device = NVS 3100M
[deviceQuery] test results...
PASSED
Press ENTER to exit...
linux/release/deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Found 1 CUDA Capable device(s)
Device 0: "NVS 3100M"
CUDA Driver Version / Runtime Version 4.0 / 4.0
CUDA Capability Major/Minor version number: 1.2
Total amount of global memory: 256 MBytes (268107776 bytes)
( 2) Multiprocessors x ( 8) CUDA Cores/MP: 16 CUDA Cores
GPU Clock Speed:
Memory Clock rate:
Memory Bus Width:
Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)
Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 16384
Warp size:
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch:
Texture alignment:
Concurrent copy and execution: Yes with 1 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Concurrent kernel execution: No
Alignment requirement for Surfaces: Yes
Device has ECC support enabled: No
Device is using TCC driver mode: No
Device supports Unified Addressing (UVA): No
Device PCI Bus ID / PCI location ID: 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 1, Device = NVS 3100M
[deviceQuery] test results...
PASSED
Press ENTER to exit...
Thursday, May 26, 2011
Skype instructions to get around crashes on Windows
Skype issued the following instructions for workarounds for Skype on Windows:
Windows Vista and Windows 7
1. Close Skype.
a. Right-click the Skype icon in the system tray (at the bottom right of the screen)
b. Choose Quit.
2. Ensure that "Show hidden files and folders" is switched on.
a. Click Start, type run and press Enter.
b. Type control folders and click OK.
c. Select the View tab and ensure relevant entry is enabled.
3. Locate the shared.xml file.
a. Click Start, type run and press Enter.
b. Type %appdata%skype and click OK.
c. Delete the shared.xml file.
4. Restart Skype. The shared.xml file will be recreated.
Note: At 3. I just backed up the data in C:\Users\win7\AppData\Roaming\Skype and deleted C:\Users\win7\AppData\Roaming\Skype, and restarted and Skype works again.
Skype Suffers Mysterious Global Crash
This morning I could not use Skype on Windows 7 since it kept crashing even after reinstalling and rebooting Windows system. The Skype iPhone app and Skype on Windows Vista seem OK.
According to
"Skype appears to have suffered an inexplicable worldwide crash on Thursday, users have been reporting on Twitter.
Floods of angry users have said they have been booted of the system and are now unable to login or even start up the Skype program itself.
The Wall Street Journal had commented that buying Skype would give Microsoft a recognized brand name on the Internet at a time when it is struggling to get more traction in the consumer market.
However, since the major deal, Skype has become victim to unspecified problems, with some reports of the program shutting down with a Windows error message."
Monday, May 23, 2011
46-megapixel DSLR Creates New Market for Medium-format Photographers
Sigma Corporation of America announced to ship SD1 camera in early June. 
It contains a 46 megapixel 23.5×15.7mm APS-C X3 Full-color image sensor. The 46 effective megapixel (4,800×3,200×3 layers) and 44 recording megapixel (4,704×3,136×3 layers) 23.5×15.7mm APS-C X3 direct image sensor featured in the Sigma SD1 captures all primary RGB colors at each and every pixel location, ensuring the capture of full and complete color. Using three silicon-embedded layers of photo detectors, stacked vertically to take advantage of silicon’s ability to absorb red, green and blue light at different respective depths, it efficiently reproduces color more accurately, and offers sharper resolution, pixel for pixel, than any conventional image sensor. Since color moiré is not generated, the use of a low-pass filter is not required, meaning light and color, generated by the 46 megapixel APS-C X3 direct image sensor is captured with a three-dimensional feel.
With this sensor, ISO sensitivity can be selected from 100 to 6400. The SD1 captures light effectively and ensures noiseless image processing. The image sensor provides high definition with rich, graduated tones.
The Sigma SD1 will be available for the MSRP of $9,700 through select authorized Sigma dealers.
See more in
Friday, May 20, 2011
Cloud Computing Tops Fastest-Growing Tech Skills
According to "The Rising Demand for Tech Talent" report from Dice, Cloud computing is still in relative infancy but it tops the list in growth with openings up nearly two-fold over the last year. The importance of reducing hardware and operating costs is driving the need for those with virtualization experience, specifically VMware, helping this skill come in at #2 on the list.
Thanks to the boom in cloud-based applications, Java/J2EE, Oracle and C languages have topped the list of most common tech skills found in Dice job postings for quite some time. The demand for JavaScript has been up 86% year/year.
See more in
Thursday, May 19, 2011
Machine vision and vision-guided robotics markets expected to record 9.3% growth from 2010-2015
Industry analyst firm Marketsandmarkets, published that list the total global machine-vision system and component market at US$15.3 billion by the year 2015, with cameras and smart cameras accounting for approximately 27.3% of total revenue. It expects the global market to record a compound annual growth rate (CAGR) of 9.3% over the five-year period forecasted. The worldwide machine-vision system and components market is estimated to reach $9830.4 million in 2010, according to Marketsandmarkets. The cameras market is exhibiting the fastest growht, growing at 10.2% CAGR from 2010-2015 as a result of the lower costs and ease-of-use of leading-edge smart cameras. The processor, software, and hardware segment is expected to reach $3641.6 million in 2015 with CAGR estimated at 8.8% over the five-year period.
The market study shows that Asia-Pacific has the largest market share and is the regional leader in growth, at 11.1% from 2010-2015, and forecasted to continue this trend. North America is the second largest market for machine vision, occupying 32.2% of 2010 market share. The rest of the world (ROW) was the smallest market for components and systems in 2010.
See more in
Subscribe to:
Posts (Atom)
