StackOverflow Questions for Tag: cuda-graphs

Weimin Chan

Reputation: 337

CUDA graph cudaKernelNodeParams kernelParams

c++cudacuda-graphs

Score: 0

Answers: 2

Mengli Cheng

Reputation: 37

cudagraph launch cored when use nsys profiling

tensorflowtensorflow-xlacuda-graphs

Score: 0

Answers: 0

Photos

Reputation: 41

CUDA Graph Execution Taking Longer Than Original Kernel Launch Loop

cudacuda-streamscuda-graphs

Score: 1

Answers: 1

Photos

Reputation: 41

How to Use CUDA Graphs with Interdependent Streams and Dynamic Parameters?

cudacuda-streamscuda-graphs

Score: 1

Answers: 2

Kostis

Reputation: 457

Call graphs for CUDA

cudacall-graphcuda-graphs

Score: 4

Answers: 2

user9684153

Reputation: 1

Behavior of cudaGraphInstantiateFlagUseNodePriority

cudacuda-graphs

Score: 0

Answers: 1

surabax

Reputation: 15

Is it possible to execute more than one CUDA graph's host execution node in different streams concurrently?

cudasynchronizationgpgpucuda-streamscuda-graphs

Score: 0

Answers: 1

Raul

Reputation: 41

Catching an exception thrown from a callback in cudaLaunchHostFunc

c++exceptioncudacuda-graphs

Score: 3

Answers: 1

einpoklum

Reputation: 131385

What should I set the flags field of CUDA_BATCH_MEM_OP_NODE_PARAMS?

cudacuda-drivercuda-graphs

Score: 0

Answers: 1

einpoklum

Reputation: 131385

What type should be pointed to for the result of cuDeviceGetGraphMemAttribute()?

memory-managementcudatype-erasurecuda-drivercuda-graphs

Score: 0

Answers: 1

einpoklum

Reputation: 131385

How can I tell whether a copy-node search failed, or whether my node or graph are invalid?

error-handlingcudaerror-codecuda-drivercuda-graphs

Score: 0

Answers: 1

Jackson

Reputation: 1

CUDA graph does not run as expected

cudacuda-graphs

Score: -1

Answers: 1

M46f988b814

Reputation: 31

simple cuda graph example doesn't product expected result

c++cudacuda-graphs

Score: 0

Answers: 1

kingwales

Reputation: 139

Error with a captured CUDA graph and asynchronous memory allocations in a loop

cudacuda-graphs

Score: 0

Answers: 1

Abator Abetor

Reputation: 2588

cudaGraph: Multi-threaded stream capturing causes errors only when run in cuda-memcheck

c++cudacuda-graphs

Score: 1

Answers: 2

skm

Reputation: 5649

CUDA Graph Problem: Results not computed for the first iteration

cudafftcufftcuda-graphs

Score: 0

Answers: 1

einpoklum

Reputation: 131385

What is the use of task graphs in CUDA 10?

cudacuda-graphs

Score: 1

Answers: 5

Cos_ma

Reputation: 75

CUDA graph stream capture with thrust::reduce

cudathrustcuda-streamscuda-graphs

Score: 0

Answers: 1

MSalters

Reputation: 179779

How do the nodes in a CUDA graph connect?

cudacuda-graphs

Score: 4

Answers: 1

Jakub Mitura

Reputation: 83

Using a loop in a CUDA graph

cudagpunvidiaschedulingcuda-graphs

Score: 1

Answers: 1

PreviousPage 1Next

StackOverflow Questions for Tag: cuda-graphs

CUDA graph cudaKernelNodeParams kernelParams

cudagraph launch cored when use nsys profiling

CUDA Graph Execution Taking Longer Than Original Kernel Launch Loop

How to Use CUDA Graphs with Interdependent Streams and Dynamic Parameters?

Call graphs for CUDA

Behavior of cudaGraphInstantiateFlagUseNodePriority

Is it possible to execute more than one CUDA graph&#39;s host execution node in different streams concurrently?

Catching an exception thrown from a callback in cudaLaunchHostFunc

What should I set the flags field of CUDA_BATCH_MEM_OP_NODE_PARAMS?

What type should be pointed to for the result of cuDeviceGetGraphMemAttribute()?

How can I tell whether a copy-node search failed, or whether my node or graph are invalid?

CUDA graph does not run as expected

simple cuda graph example doesn&#39;t product expected result

Error with a captured CUDA graph and asynchronous memory allocations in a loop

cudaGraph: Multi-threaded stream capturing causes errors only when run in cuda-memcheck

CUDA Graph Problem: Results not computed for the first iteration

What is the use of task graphs in CUDA 10?

CUDA graph stream capture with thrust::reduce

How do the nodes in a CUDA graph connect?

Using a loop in a CUDA graph

Is it possible to execute more than one CUDA graph's host execution node in different streams concurrently?

simple cuda graph example doesn't product expected result