Question

Profilers (nvvp and nvprof) not showing "Page Fault" information

score 303 · Answer 1 · 2021-11-29T12:12:01.607000

303

Views

Profilers (nvvp and nvprof) not showing "Page Fault" information

Published on 29 November 2021 at 12:12

score 334 · Answer 2 · 2020-09-09T17:06:58.820000

334

Views

Meaning of the "flop_count_sp" and "inst_fp_32" metric in CUDA Profiler

Published on 09 September 2020 at 17:06

score 587 · Answer 3 · 2020-08-18T22:08:34.027000

587

Views

NVIDIA Visual Profiler: Insufficient kernel bounds data

Published on 18 August 2020 at 22:08

score 188 · Answer 4 · 2020-03-16T07:30:40.867000

188

Views

How to stop running TensorRT server without using ctrl-c (for profiling with nvprof)

Published on 16 March 2020 at 07:30

score 271 · Answer 5 · 2019-05-14T22:54:21.283000

271

Views

Where is the boundary of start and end of CPU launch and GPU launch of Nvidia Profiling NVPROF?

Published on 14 May 2019 at 22:54

score 898 · Answer 6 · 2019-01-15T14:47:20.957000

898

Views

Why operations in two CUDA Streams are not overlapping?

Published on 15 January 2019 at 14:47

score 378 · Answer 7 · 2018-12-23T20:24:32.507000

378

Views

How can a registers-only instruction stall due to "memory dependencies"?

Published on 23 December 2018 at 20:24

score 261 · Answer 8 · 2018-11-08T18:32:50.060000

261

Views

CUDA's nvvp reports non-ideal memory access pattern, but bandwidth is almost peaking

Published on 08 November 2018 at 18:32

score 618 · Answer 9 · 2018-09-12T05:28:27.540000

618

Views

How to print api calls per thread with nvprof

Published on 12 September 2018 at 05:28

score 1.8k · Answer 10 · 2018-05-18T03:39:46.033000

1.8k

Views

Profiling arbitrary CUDA applications

Published on 18 May 2018 at 03:39

score 501 · Answer 11 · 2018-04-19T13:17:08.360000

501

Views

What does "Instruction Issued" mean in the report provided by CUDA nvvp?

Published on 19 April 2018 at 13:17

score 2.9k · Answer 12 · 2018-04-17T12:19:59.900000

2.9k

Views

How to specify nvprof "devices" option for Nvidia Visual Profiler?

Published on 17 April 2018 at 12:19

score 494 · Answer 13 · 2017-11-07T21:34:11.333000

494

Views

How to profile CUDA code on a headless node?

Published on 07 November 2017 at 21:34

score 852 · Answer 14 · 2017-10-23T23:53:20.327000

852

Views

Excessive profiler overhead with NVidia Visual Profiler

Published on 23 October 2017 at 23:53

score 1.4k · Answer 15 · 2017-07-14T02:33:18.963000

1.4k

Views

What's the difference between DtoD and PtoP memory copies?

Published on 14 July 2017 at 02:33

score 416 · Answer 16 · 2017-07-11T11:18:57.410000

416

Views

Dependency Analysis options in CUDA Profiler

Published on 11 July 2017 at 11:18

score 239 · Answer 17 · 2017-06-11T01:23:02.360000

239

Views

CUDA pointer arithmetic causes uncoalesced memory access?

Published on 11 June 2017 at 01:23

score 958 · Answer 18 · 2017-06-01T21:39:03.497000

958

Views

nsight EE and nvvp both crash during startup on Ubuntu 16.10

Published on 01 June 2017 at 21:39

score 205 · Answer 19 · 2017-05-02T13:48:49.077000

205

Views

How to interpret NVIDIA Visual Profiler analysis/recommendations?

Published on 02 May 2017 at 13:48

score 77 · Answer 20 · 2017-04-13T09:53:34.570000

77

Views

"The kernel was blocked for an uncommon reason" - what are these reasons?

Published on 13 April 2017 at 09:53

List Question

Profilers (nvvp and nvprof) not showing "Page Fault" information

Meaning of the "flop_count_sp" and "inst_fp_32" metric in CUDA Profiler

NVIDIA Visual Profiler: Insufficient kernel bounds data

How to stop running TensorRT server without using ctrl-c (for profiling with nvprof)

Where is the boundary of start and end of CPU launch and GPU launch of Nvidia Profiling NVPROF?

Why operations in two CUDA Streams are not overlapping?

How can a registers-only instruction stall due to "memory dependencies"?

CUDA's nvvp reports non-ideal memory access pattern, but bandwidth is almost peaking

How to print api calls per thread with nvprof

Profiling arbitrary CUDA applications

What does "Instruction Issued" mean in the report provided by CUDA nvvp?

How to specify nvprof "devices" option for Nvidia Visual Profiler?

How to profile CUDA code on a headless node?

Excessive profiler overhead with NVidia Visual Profiler

What's the difference between DtoD and PtoP memory copies?

Dependency Analysis options in CUDA Profiler

CUDA pointer arithmetic causes uncoalesced memory access?

nsight EE and nvvp both crash during startup on Ubuntu 16.10

How to interpret NVIDIA Visual Profiler analysis/recommendations?

"The kernel was blocked for an uncommon reason" - what are these reasons?

Trending Questions

Popular # Hahtags

Popular Questions