nvidia
Cuda Different Memory Allocations
I am developing a small application using CUDA. i have a huge 2d array (won\'t fit on shared memory) in which threads in开发者_高级运维 all blocks will read from constantly at random places.[详细]
2023-01-29 09:24 分类:问答Stuck on why my OpenCL kernel won't execute with particular parameters
I have an OpenCL kernel that I run in JOCL and it passes all my JUnit tests. I ported my code into C++ so I could profile the kernel under the same conditions. The driver works fine in all cases excep[详细]
2023-01-28 12:39 分类:问答nVidia CUDA on GPU with PCI interface
Do you have any experience working with CUDA on an enabled GPU that uses the PCI interface (as oppose开发者_如何转开发d to PCIe)? Does it work?I cannot see a reason why it wouldn\'t work, and a quick[详细]
2023-01-27 16:43 分类:问答NVIDIA首发DX12终极版驱动:仅支持RTX 20系列?
微软日前正式发布DX12.Ultimate终极版(也可以理解为DX12_2),新增支持DXR1.1光线追踪、可变速着色率VRSTier1/2)、网格着色器、样板反馈等高级特性,集成到Windows1004、XboxSeriesX中。[详细]
2023-01-27 07:33 分类:问答NVIDIA年度驱动秒翻车:强制安装GeForce Experience?
NVIDIA今天发布了GeForce 436.02版显卡驱动,作为科隆游戏展特别版(GamescomSpecial)开发者_JS百科,它带来了最高23%的游戏性能提升,并支持超低延迟、图像锐化、整数缩放、30位色彩等四大全新特性,并支持更多G-Sy[详细]
2023-01-24 22:27 分类:问答Confused about profiling results from my OpenCL kernel (DSP Window Function)
I completed a Window Function kernel in OpenCL. Basically a window function just applies a set of coefficients over another set of numbers piece by piece (Wikipedia explains it better). I was able to[详细]
2023-01-24 10:12 分类:问答Should I create multiple OpenCL kernels to avoid conditional statements?
In OpenCL, I have a kernel that needs to operate on complex and real data. I could put a conditional statement in that calls the right line of code to handle this, or I could have two kernels that I c[详细]
2023-01-24 05:10 分类:问答How many memory latency cycles per memory access type in OpenCL/CUDA?
I looked through the programming guide and best practices guide and it mentioned that Global Memory access takes 400-600 cycles. I did not see much on the other memory types like texture cache, consta[详细]
2023-01-23 06:37 分类:问答CUDA Matrix multiplication breaks for large matrices
I have the following matrix multiplication code, implemented using CUDA 3.2 and VS 2008. I am running on Windows server 2008 r2 enterprise. I am running a Nvidia GTX 480. The following code works fine[详细]
2023-01-22 23:07 分类:问答CL_OUT_OF_RESOURCES for 2 millions floats with 1GB VRAM?
It seems like 2 million floats should be no big deal, only 8MBs of 1GB of GPU RAM. I am able to allocate that much at times and sometimes more than that with no trouble. I get CL_OUT_OF_RESOURCES when[详细]
2023-01-21 21:42 分类:问答