Now only Tesla V100 and Titan V have tensor cores. Both GPUs have 5120 cuda cores where each core can perform up to 1 single precision multiply-accumulate operation (e.g. in fp32: x += y * z) per 1 GPU clock (e.g. Tesla V100 PCIe frequency is 1.38Gz). Each tensor core perform operations on small matrices … Read more
I investigated the same question a while back. After chatting to people who have worked on FPGAs, this is what I get: FPGAs are great for realtime systems, where even 1ms of delay might be too long. This does not apply in your case; FPGAs can be very fast, espeically for well-defined digital signal processing … Read more
blockDim.x,y,z gives the number of threads in a block, in the particular direction gridDim.x,y,z gives the number of blocks in a grid, in the particular direction blockDim.x * gridDim.x gives the number of threads in a grid (in the x direction, in this case) block and grid variables can be 1, 2, or 3 dimensional. … Read more
The __syncthreads() command is a block level synchronization barrier. That means it is safe to be used when all threads in a block reach the barrier. It is also possible to use __syncthreads() in conditional code but only when all threads evaluate identically such code otherwise the execution is likely to hang or produce unintended … Read more
There is such a nice complete cuda 4.2 wrapper as ManagedCuda. You simply add C++ cuda project to your solution, which contains yours c# project, then you just add call “%VS100COMNTOOLS%vsvars32.bat” for /f %%a IN (‘dir /b “$(ProjectDir)Kernels\*.cu”‘) do nvcc -ptx -arch sm_21 -m 64 -o “$(ProjectDir)bin\Debug\%%~na_64.ptx” “$(ProjectDir)Kernels\%%~na.cu” for /f %%a IN (‘dir /b “$(ProjectDir)Kernels\*.cu”‘) … Read more
It does on NVIDIA hardware supporting compute capability 2.0 and CUDA 3.1: New language features added to CUDA C / C++ include: Support for function pointers and recursion make it easier to port many existing algorithms to Fermi GPUs http://developer.nvidia.com/object/cuda_3_1_downloads.html Function pointers: http://developer.download.nvidia.com/compute/cuda/sdk/website/CUDA_Advanced_Topics.html#FunctionPointers Recursion: I can’t find a code sample on NVIDIA’s website, but on … Read more
You will need to add the folder containing the “cl.exe” file to your path environment variable. For example: C:\Program Files\Microsoft Visual Studio 10.0\VC\bin Edit: Ok, go to My Computer -> Properties -> Advanced System Settings -> Environment Variables. Here look for “PATH” in the list, and add the path above (or whatever is the location … Read more
There are two things- nvidia drivers and cuda toolkit- which you may want to remove. If you have installed using apt-get use the following to remove the packages completely from the system: To remove cuda toolkit: sudo apt-get –purge remove “*cublas*” “cuda*” “nsight*” To remove Nvidia drivers: sudo apt-get –purge remove “*nvidia*” If you have … Read more
Here is an explanation about pitched pointer and padding in CUDA. Linear memory vs padded memory First, lets start with the reason for the existence of non linear memory. When allocating memory with cudaMalloc, the result is like an allocation with malloc, we have a contiguous memory chunk of the size specified and we can … Read more
Usually, it is /usr/local/cuda. If this is not the case, you can try to locate cuda. If you want to find directories only, run locate cuda | grep /cuda$ or find / -type d -name cuda 2>/dev/null For me, it turned out to be in /opt/cuda-7.5