Question

Intercepting cuda memory management related APIs in cuda11.7 and encountering invalid device context (201) errors

score 167 · Answer 1 · 2023-11-18T04:44:23.983000

167

Views

Intercepting cuda memory management related APIs in cuda11.7 and encountering invalid device context (201) errors

Published on 18 November 2023 at 04:44

score 76 · Answer 2 · 2023-02-07T21:59:38.757000

76

Views

Do CUDA 3D memory copy parameters need to be kept alive?

Published on 07 February 2023 at 21:59

score 334 · Answer 3 · 2022-12-26T09:15:16.237000

334

Views

What are the new unique-id's for CUDA streams and contexts useful for?

Published on 26 December 2022 at 09:15

score 237 · Answer 4 · 2022-10-08T12:58:43.400000

237

Views

Does cuMemcpy "care" about the current context?

Published on 08 October 2022 at 12:58

score 570 · Answer 5 · 2022-01-19T08:08:51.903000

570

Views

cuMemAlloc'ing memory in one CUDA context, and freeing it in another - why does this succeed?

Published on 19 January 2022 at 08:08

score 257 · Answer 6 · 2021-10-21T13:48:33.947000

257

Views

Fine grained Kernel scheduling with MPS

Published on 21 October 2021 at 13:48

score 1.4k · Answer 7 · 2021-02-03T20:59:36.583000

1.4k

Views

Missing symbol: cuDevicePrimaryCtxRelease vs cuDevicePrimaryCtxRelease_v2

Published on 03 February 2021 at 20:59

score 3.3k · Answer 8 · 2020-07-13T14:07:16.580000

3.3k

Views

What does cudaSetDevice() do to a CUDA device's context stack?

Published on 13 July 2020 at 14:07

score 606 · Answer 9 · 2020-07-12T22:55:54.570000

606

Views

How can I determine whether a CUDA context is the primary one - cheaply?

Published on 12 July 2020 at 22:55

score 2.2k · Answer 10 · 2020-04-30T10:35:14.857000

2.2k

Views

When is a primary CUDA context destroyed by the Runtime API?

Published on 30 April 2020 at 10:35

score 1.1k · Answer 11 · 2019-12-19T14:21:53.067000

1.1k

Views

How to reduce CUDA context size (Multi-Process Service)

Published on 19 December 2019 at 14:21

score 901 · Answer 12 · 2019-11-12T07:23:36.890000

901

Views

get memory usage on cuda context

Published on 12 November 2019 at 07:23

score 2.2k · Answer 13 · 2019-11-07T11:00:29.920000

2.2k

Views

Can multiple processes share one CUDA context?

Published on 07 November 2019 at 11:00

score 4k · Answer 14 · 2019-05-27T16:08:49.520000

4k

Views

Reset Cuda Context after exception

Published on 27 May 2019 at 16:08

score 244 · Answer 15 · 2019-04-01T21:46:36.700000

244

Views

cuCtxGetApiVersion value differs from other version management calls

Published on 01 April 2019 at 21:46

score 46 · Answer 16 · 2018-04-27T15:54:38.677000

46

Views

Do failed CUDA memory allocations require a cudaDeviceReset call?

Published on 27 April 2018 at 15:54

score 1.6k · Answer 17 · 2018-02-08T01:19:39.663000

1.6k

Views

How to implement handles for a CUDA driver API library?

Published on 08 February 2018 at 01:19

score 2.4k · Answer 18 · 2018-01-25T13:58:53.690000

2.4k

Views

Is cuDevicePrimaryCtxRetain() used for having persistent CUDA context objects between multiple processes?

Published on 25 January 2018 at 13:58

score 584 · Answer 19 · 2017-11-23T20:29:38.600000

584

Views

Why are OpenGL and CUDA contexts memory greedy?

Published on 23 November 2017 at 20:29

score 152 · Answer 20 · 2017-09-07T19:36:08.507000

152

Views

CUDA context was created on a GPU that is not currently debuggable

Published on 07 September 2017 at 19:36

List Question

Intercepting cuda memory management related APIs in cuda11.7 and encountering invalid device context (201) errors

Do CUDA 3D memory copy parameters need to be kept alive?

What are the new unique-id's for CUDA streams and contexts useful for?

Does cuMemcpy "care" about the current context?

cuMemAlloc'ing memory in one CUDA context, and freeing it in another - why does this succeed?

Fine grained Kernel scheduling with MPS

Missing symbol: cuDevicePrimaryCtxRelease vs cuDevicePrimaryCtxRelease_v2

What does cudaSetDevice() do to a CUDA device's context stack?

How can I determine whether a CUDA context is the primary one - cheaply?

When is a primary CUDA context destroyed by the Runtime API?

How to reduce CUDA context size (Multi-Process Service)

get memory usage on cuda context

Can multiple processes share one CUDA context?

Reset Cuda Context after exception

cuCtxGetApiVersion value differs from other version management calls

Do failed CUDA memory allocations require a cudaDeviceReset call?

How to implement handles for a CUDA driver API library?

Is cuDevicePrimaryCtxRetain() used for having persistent CUDA context objects between multiple processes?

Why are OpenGL and CUDA contexts memory greedy?

CUDA context was created on a GPU that is not currently debuggable

Trending Questions

Popular # Hahtags

Popular Questions