Developer Watch: CUVI 0.5 released

Subject: Editorial, General Tech, Graphics Cards | July 26, 2011 - 08:39 PM |
Tagged: gpgpu, Developer Watch, CUVI

Code that can be easily parallelized into many threads have been streaming over to the GPU with many applications and helper libraries taking advantage of CUDA and OpenCL primarily. Thus for developers who wish to utilize the GPU more but are unsure where to start there are more and more options for libraries of functions to call and at least partially embrace their video cards. OpenCV is a library of functions for image manipulation and, while GPU support is ongoing through CUDA, primarily runs on the CPU. CUVIlib, which has just launched their 0.5 release, is a competitor to OpenCV with a strong focus on GPU utilization, performance, and ease of implementation. While OpenCV is licensed as BSD which is about as permissive a license as can be offered, CUVI is not and is based on a proprietary EULA.

Benchmark KLT - CUVILib from TunaCode on Vimeo

Benchmark KLT - OpenCV from TunaCode on Vimeo.

The little plus signs are the computer tracking motion. CUVI (top; 33fps), OpenCV (bottom; 2.5fps)

(Video from CUVIlib)

Despite the proprietary and non-free for commercial use nature of CUVI they advertise large speedups for certain algorithms. For their Kanade-Lucas-Tomasi Feature Tracker algorithm when compared with OpenCV’s implementation they report a three-fold increase in performance with just a GeForce 9800GT installed and 8-13x faster when using a high end computing card such as the Tesla C2050. Their feature page includes footage of two 720p high definition videos undergoing the KLT algorithm with the OpenCV CPU method chugging at 2.5 fps contrasted with CUVI’s GPU-accelerated 33fps. Whether you would prefer to side with OpenCV’s GPU advancements or pay CUVIlib to augment what OpenCV is not good enough for your needs at is up to you, but either future will likely involve the GPU.

Source: CUVIlib

Podcast #162 - Adventures in Bitcoin Mining, the Eyefinity experience, Ultrabooks and more!

Subject: General Tech | July 14, 2011 - 04:38 PM |
Tagged: podcast, bitcoin, mining, gpu, gpgpu, amd, nvidia, eyefinity, APU

PC Perspective Podcast #162 - 7/14/2011

This week we talk about our adventures in Bitcoin Mining, the Eyefinity experience, Ultrabooks and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malventano

This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!

Program length: 1:16:40

Program Schedule:

  1. 0:00:40 Introduction
  2. 1-888-38-PCPER or
  4. and
  5. 0:02:10 Bitcoin Currency and GPU Mining Performance Comparison
  6. 0:22:48 Bitcoin Mining Update: Power Usage Costs Across the United States
  7. 0:34:15 This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!
  8. 0:34:50 Eyefinity and Me
  9. 0:45:00 Video Perspective: AMD A-series APU Dual Graphics Technology Performance
  10. 0:47:02 As expected NVIDIA's next generation GPU release schedule was a bit optimistic
  11. 0:49:40 A PC Macbook Air: Can Intel has?
  12. 0:53:00 PC: for all your Xbox gaming needs
  13. 0:56:06 Email from Howard
  14. 1:00:28 Email from Ian
  15. 1:03:00 Email from Jan
    1. In case you're interested, here are almost 150mpix of HDR:
  16. 1:08:55 Quakecon Reminder -
  17. 1:09:45 Hardware / Software Pick of the Week
    1. Ryan: Dropped the ball
    3. Josh: Finally getting cheap enough for me to buy
    4. Allyn:
  18. 1-888-38-PCPER or
  20. and
  21. 1:15:15 Closing

Wish you CUDA had a GPGPU C++ template? Now you can!

Subject: General Tech, Graphics Cards | June 29, 2011 - 08:58 PM |
Tagged: gpgpu, CUDA

If you have seen our various news articles regarding how a GPU can be useful in many ways, and you are a developer yourself, you may be wondering how to get in on that action. Recently Microsoft showed off their competitor to OpenCL known as C++ AMP and AMD showed off some new tools designed to help developers of OpenCL. Everything was dead silent on the CUDA front at the AMD Fusion Developer Summit, as expected, but that does not mean that no-one is helping people who do not mind being tied in to NVIDIA. An open-sourced project has been created to generate template file for programmers wishing to do some of their computation in CUDA and wish a helping hand setting up the framework.


You may think the videocard is backwards, but clearly its DVI heads are in front.

The project was started by Pavel Kartashev and is a Java application that accepts form input and generates CUDA code to be imported into your project. The application will help you generate the tedious skeleton code for defining variables and efficiently using the GPU architecture leaving you to program the actual process to be accomplished itself. The author apparently plans to create a Web-based version which should be quite easy with the Java-based nature of his application. Personally I would find myself more interested in the local application or a widget to leaving my web browser windows to reference material. That said, I am sure that someone would like this tool in their web browser, possibly more people than are like-minded with me.

If you are interested in contributing either financially or through labor he asks that you contact him through the email tied with his Paypal account (likely for spam reasons, so I can assume posting it here would be the opposite of helpful). The rest of us can sit back, enjoy our GPU-enabled applications, and bet on how long it will take NVIDIA to reach out to him. I got all next week.

KGPU lets the Linux kernel harness your GPU's power

Subject: General Tech, Graphics Cards | May 6, 2011 - 05:25 PM |
Tagged: linux, kgpu, gpgpu

PC Per has discussed using the GPU as a massively-parallel augment to the CPU for a very long time to allow the latter to focus on the branching logic (“if/then/else”) and other processes it is good at that GPUs are not. AMD and Intel both have their attempts to bundle the benefits of a GPU on to their CPU parts with their respective technologies. Currently most of the applications outside of the scientific community are gaming and multimedia; however, as the presence of stronger GPUs saturates, we are seeing more and more functions relegate to the GPU.


So happy together!

KGPU is an attempt to bring the horsepower of the GPU to the fingertips of the Linux kernel. While the kernel itself will remain a CPU function, the attempt allows the kernel to offload the parallel stuff to the GPU for large speed-ups and keep the CPU free for more. Their current version shows whole multiple speedups of eCryptfs, an encrypted filesystem, in terms of maximum read and write bandwidth by allowing the GPU to deal with the AES cipher.

We should continue to see speedups as tasks that would be perfect for the GPU are finally allowed to be with their true love. Furthermore, as the number of tasks relegated to the GPU increases we should continue to see more and stronger GPUs embedded in PCs which should decrease the fears for PC game developers worried about the number of PCs capable of running their applications. I am sure that is great news to many of our frequent readers.

Source: KGPU Project