It was added an example of interaction of CUDA C with MATLAB, based on the K nearest neighbours algorithm. under code_examples/KNN svn folder.
CUDA toolkit 4.0 RC into Repository, under root/files directory. It contains:
new linux driver (32 & 64 bits);
bunch of .txt's and .pdf's explaining releases and news;
Apart from linux drivers (which has both versions), It was added only 32 bit versions of cuda toolkit and cuda sdk, and even cuda toolkit it's only for ubuntu. if you need to other platforms or operating systems, feel free to ask. it's available for all of them. This is so, because it is an exaustive work to put all possible files in svn.
The CUDA Toolkit 4.0 Release Candidate (RC) will be available to all CUDA Registered Developers later this week. New Features are:
Easier Application Porting
- Share GPUs across multiple threads
- Use all GPUs in the system concurrently from a single host thread
- No-copy pinning of system memory, a faster alternative to cudaMallocHost()
- C++ new/delete and support for virtual functions
- Support for inline PTX assembly
- Thrust library of templated performance primitives such as sort, reduce, etc.
- NVIDIA Performance Primitives (NPP) library for image/video processing
- Layered Textures for working with same size/format textures at larger sizes and higher performance
Faster Multi-GPU Programming
- Unified Virtual Addressing
- GPUDirect v2.0 support for Peer-to-Peer Communication
New & Improved Developer Tools
- Automated Performance Analysis in Visual Profiler
- C++ debugging in cuda-gdb
- GPU binary disassembler for Fermi architecture (cuobjdump)
Foi adicionada a biblioteca cuPrintf ao repositório, na pasta libs. Serve para ajudar a fazer debug ao vosso código em CUDA.
Also available in: Atom