There are a number of very old threads on CUDA so I'm starting a new one rather than resurrecting an old one. Does anyone here have any experience setting up and developing in CUDA on a Windows platform? I know that there is a system that can be set up with Visual Studio/CUDA that uses the nvidia hardware but I am hoping to find something for AMD/Radeon. I have found something called [ocelot](https://code.google.com/archive/p/gpuocelot/) that supposedly works with AMD/Radeon (which I have on my laptop) but there are issues: 1. It has the smell of abandonment (hasn't been updated since 2013) …

Member Avatar
Member Avatar
+0 forum 11

I've been editing on a (windows based) desktop and now want and need to transition to notebook computers. I've been assured that notebook computers are now showing specs that can rival any desktop based system (if you have the $$$). Specially HP's Z-Book series which is built with video and content creation in mind. However, due to budget constraints I am looking at the Acer Aspire V17 Nitro Black Edition as a possible candidate. It sports a fast i7 processor, with 16GB RAM and an Nvidia GTX-860M video card. My question is that do the more compact M-series of Nvidia …

Member Avatar
Member Avatar
+0 forum 1

Hi everyone, I am writing some PDE code, and I am just starting to think about parallelizing it. The code is extremely parallelizable by both CUDA (at the lowest level) and regular threading at the higher level. Specifically, I am coding a matrix multiply, and the matrix is banded, so the multiply is just a sum over the bands of some vector operations. In my optimistic mind, I imagine I could run the band multiplications in parallel by putting them in separate threads, and adding the results later. But I also thought that I could do the vector operations in …

Member Avatar
Member Avatar
+0 forum 1

HI I am trying to make a dll file that performs its tasks using CUDA library. Here is a simple version of my code: CUDADll.cu ` #include <iostream> #include "cuda.h" #include "cuda_runtime.h" #include "device_launch_parameters.h" __global__ void test(int a, int b, int* c) { *c = a+b; } extern "C" __declspec(dllexport) int sumTEst(int a, int b) { int c = 0; test<<<1,1>>>(a, b, &c); return c; } Inline Code Example Here ` When I compile this file, there is no problem. But when I build the project which has only file above, an error occurs: Error 1 error LNK1561: entry point …

Member Avatar
Member Avatar
+0 forum 2

[ATTACH=RIGHT]17139[/ATTACH]NVIDIA's CUDA parallel computer architecture is picking up steam and quickly becoming one of the de-facto solution for producing high-end video content. When time is money, companies such as Industrial Light & Magic, and Adobe, cannot always cram every feature or pixel into the finished product. Most consumers might not realize that production technology is a major player in the race for quality, but NVIDIA's Quadro and Tesla product lines, coupled with the CUDA architecture, will determine the future of video as we know it. Jon Peddie Research is a leading research firm for the multimedia industry and Mr. Peddie …

Member Avatar
Member Avatar
+3 forum 1

Hi, I am implementing an applicaiton which uses CPU but having a problem about allocating in GPU memory. Above all, my work environment is Windows 7 Visual Studio 2010 NVIDIA Quadro NVS 290 (256MB) When I run a piece of CUDA code: cudaMemGetInfo(&freeMem, &totalMem); I get 256MB of total memory and only 3-10MB of free memory. Because there is not much free space, my application can't successfully allocate in GPU memory mostly - outOfMemory error keeps being thrown. After crazy googling, I found out Windows 7 already allocated about 95% of GPU memory for its theme manager and others.But I …

Member Avatar
Member Avatar
+0 forum 1

[B]ATI Takes the Lead[/B] [ATTACH=RIGHT]16273[/ATTACH]After a long stretch of dominance, NVIDIA has fallen behind ATI in discrete GPU shipments. According to Mercury Research, ATI claims 51% of the market, and NVIDIA has slipped to, you guessed it, 49%. NVIDIA was the leader this time last year with 59% market share, illustrating about-face in overall shipments. ATI also took the 2nd place position from NVIDIA in the integrated GPU market (IGP), pulling in 24.5% compared to NVIDIA's 19.8%. Intel has traditionally led the pack, and clocked in last quarter at a healthy 54% of IGP shipments. These are no doubt tough …

Member Avatar
+1 forum 0

I have heard you can efficiently use your GPU to do fast floating point calculations. This can be done using OpenGL but you may have to use the library in an unorthodox way or graphics card toolkits such as CUDA (by nVidia) which I guess is Graphics card specific. Does anyone have an experience in this and an opinion on the best tools available now. Thanks!

Member Avatar
Member Avatar
+0 forum 1

I have heard you can efficiently use your GPU to do fast floating point calculations. This can be done using OpenGL but you may have to use the library in an unorthodox way or graphics card toolkits such as CUDA (by nVidia) which I guess is Graphics card specific. Does anyone have an experience in this and an opinion on the best tools available now. Thanks!

Member Avatar
+0 forum 0

[ATTACH=right]15788[/ATTACH]High-end video accelerator tools now make password recovery twentyfold faster than the current top of the line quad-core CPUs. Unlike current recovery tools, such as those offered by Intel, [URL="http://www.nvidia.com/object/fermi_architecture.html"]these new Fermi-based video boards[/URL] exceed benchmark speeds of even previous NVIDIA Tesla solutions based on the previous-generation chipsets. CPUs will still prevail, but GPUs found in modern video cards such as NVIDIA GTX 480 are becoming the new standard. Depending on applications, CUDA-based GPUs can contribute more to the total performance of the PC than the central processing unit. In some applications, their role is greater than the role of …

Member Avatar
+0 forum 0

The End.