Recent questions tagged GPU

0 votes

742 views

1 answer

gpu - Is the warmup code necessary when measuring CUDA kernel running time?

In page 85, professional CUDA C programming: int main() { ...... // run a warmup kernel to remove ... warmup code. Is my understanding right? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

344 views

1 answer

gpu - Simple CUDA Kernel Optimization

In the process of speeding up an application, I have a very simple kernel which does the type casting as ... memory copy will be required. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

320 views

1 answer

gpu - tensorflow running error with cublas

when I successfully install tensorflow on cluster, I immediately running mnist demo to check if it's going ... Segmentation fault (core dumped) See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

242 views

1 answer

gpu - tensorflow running error with cublas

when I successfully install tensorflow on cluster, I immediately running mnist demo to check if it's going ... Segmentation fault (core dumped) See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

316 views

1 answer

gpu - tensorflow running error with cublas

when I successfully install tensorflow on cluster, I immediately running mnist demo to check if it's going ... Segmentation fault (core dumped) See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

317 views

1 answer

gpu - tensorflow running error with cublas

when I successfully install tensorflow on cluster, I immediately running mnist demo to check if it's going ... Segmentation fault (core dumped) See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

480 views

1 answer

gpu - How to measure the execution time of every block when using CUDA?

clock() is not accurate enough. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

312 views

1 answer

gpu - How to get memory bandwidth from memory clock/memory speed

FYI, Here are the specs I got from Nvidia http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-680/ ... both measured in Gbps. Thanks! See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

280 views

1 answer

gpu - Matrix-vector multiplication in CUDA: benchmarking & performance

I'm updating my question with some new benchmarking results (I also reformulated the question to be more specific and I ... , 0, n_rows_max * sizeof(real_t)); matvec<real_t>(d...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

629 views

1 answer

gpu - CUDA runtime error (59) : device-side assert triggered

I have access to Tesla K20c, I am running ResNet50 on CIFAR10 dataset... Then I get the error as: THCudaCheck ... 265 How to resolve this error? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

256 views

1 answer

gpu - help me understand cuda

i am having some troubles understanding threads in NVIDIA gpu architecture with cuda. please could anybody clarify ... and SPs execute warps. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

495 views

1 answer

gpu - CUDA Thrust: reduce_by_key on only some values in an array, based off values in a "key" array

Let's say I have two device_vector<byte> arrays, d_keys and d_data. If d_data is, for example, a flattened 2D 3x5 ... must be a way to make it! See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

988 views

1 answer

gpu - AMD equivalent to NvOptimusEnablement

For Intel+NVIDIA dual-GPU "Optimus" setups, an application can export NvOptimusEnablement as explained in ... t know" comment. See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

430 views

1 answer

gpu - How do I use Nvidia Multi-process Service (MPS) to run multiple non-MPI CUDA applications?

Can I run non-MPI CUDA applications concurrently on NVIDIA Kepler GPUs with MPS? I'd like to do this because my ... any code example to do this? See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

Categories

Just Browsing Browsing

Most popular tags