Get More Insight
Hybrid DSP provide hardware and software tools for research and development groups and organizations. We allow you to:
- Gather and generate more data through use of the highest speed digitizers and waveform generators (ADC/DAC)
- Store more data faster through tried and tested SSD and HDDs in various RAID configurations
- Process more data on FPGA, CPU and GPU
Write GPU Code in .NET - CUDAfy .NET – General Purpose GPU on .NET
Hybrid DSP’s CUDAfy .NET tools and libraries allow easy development of high performance GPGPU applications completely from the Microsoft .NET framework. Modern graphics cards provide the potential of massive speed increase over CPUs for non-graphics related intensive numeric operations. Many large data set operations such as matrices can see a 100x or more speed up. CUDAfy allows .NET developers to easily create complex applications that split processing cleanly between host and GPU. New OpenCL support allows CUDAfy to run on AMD GPUs and Intel CPUs and most applications will need no modification to take advantage of this new feature. CUDAfy is the easiest way by far to use the CUDA programming model on any platform.
25 Mar 2014: GTC2014 kicks off in San Jose today. At 16:00 on Thursday in room 210C John Hauck will present C# with CUDAfy: Image Stitching Concepts.
24 Mar 2014: Once CUDA 6.0 is official CUDAfy will be updated to support it. Until that time please do not update.
29 Nov 2013: CUDAfy 1.26 is released today and brings SIMD functions, warp shuffle and support for classes.
11 Sep 2013: We really encourage CUDAfy users to consider taking a commercial license if you are making source code changes or want to embed the sources or library in your own application. Please remember that CUDAfy is LGPL. If you are complying with LGPL and CUDAfy is useful to you please donate to Harmony Through Education. This small charity is doing wonderful work at its school for handicapped children in India.
31 Aug 2013: CUDAfy 1.25 is here with CUDA 5.5 support, dynamic parallelism support and a new Cudafying process (backward compatible, but internally new with some new more flexible overloads that can take advantage of new system). Finally we have changed the commercial licenses so we can better support paying customers. You can see the new structure here. For those that were planning on purchasing under the old system then if you send an email before 7 September we can still supply at old prices (Single Developer €149, 5 Developer €499).
10 July 2013: We're working on a new more flexible way of Cudafying, dynamic parallelism support and will revamp the commercial licenses. There will be a new systems of licenses - more expensive actually but with clearer tiered benefits in a model familiar to many software tools.
12 June 2013: How to use a Xilinx FPGA evaluation board, a Mini-ITX motherboard, Intel Core CPU and a fast SSD to make a low cost data acquisition processing system with OpenCL support. Low Cost, High Performance FPGA and GPGPU Based Data Acquisition System
08 May 2013: An article called "Why use FPGAs for data acquisition systems?" has been posted in the new blog of this website. It's a good question considering that FPGAs are relatively tough to work with. But the sheer performance and relatively low price of new FPGA daughter cards makes the extra effort worthwhile.
07 May 2013: Version 1.22 of CUDAfy is the first official release with support for OpenCL. There are a bunch of bug fixes and other new features like integer intrinsics and code insertion.