Question

use NCU with tensorRT, but got No kernels were profiled

score 133 · Answer 1 · 2024-12-30 02:59:37

133

Views

use NCU with tensorRT, but got No kernels were profiled

Published on 30 December 2024 at 02:59

score 2.3k · Answer 2 · 2024-12-30 03:04:40

2.3k

Views

ncu-ui won't run: Could not load the Qt platform plugin "xcb" in "" even though it was found

Published on 30 December 2024 at 03:04

score 433 · Answer 3 · 2024-12-30 02:55:51

433

Views

nsight-compute does nothing upon invocation

Published on 30 December 2024 at 02:55

score 197 · Answer 4 · 2024-12-30 02:55:12

197

Views

NSight Compute - get total number of samples?

Published on 30 December 2024 at 02:55

score 3.5k · Answer 5 · 2024-12-30 03:05:50

3.5k

Views

How to profile in CUDA application with compute capability 7.x? Is metric "dram_read_throughput" valid in Nsight Compute?

Published on 30 December 2024 at 03:05

score 834 · Answer 6 · 2024-12-30 02:57:34

834

Views

Port forwarding to avoid the need for certificate

Published on 30 December 2024 at 02:57

score 814 · Answer 7 · 2024-12-30 03:03:13

814

Views

What does NSight Compute show for a stall reason that isn't "supported"?

Published on 30 December 2024 at 03:03

score 3.6k · Answer 8 · 2025-01-06 00:24:20

3.6k

Views

What are the "long" and "short" scoreboards w.r.t. MIO/L1TEX?

Published on 06 January 2025 at 00:24

score 342 · Answer 9 · 2024-12-30 03:03:12

342

Views

Can I skip ahead to profile a specific invocation of a specific kernel?

Published on 30 December 2024 at 03:03

score 2.6k · Answer 10 · 2024-12-30 03:02:05

2.6k

Views

Nsight Compute says: "Profiling is not supported on this device" - why?

Published on 30 December 2024 at 03:02

score 1.5k · Answer 11 · 2024-12-30 02:54:16

1.5k

Views

When does MIO Throttle stall happen?

Published on 30 December 2024 at 02:54

score 501 · Answer 12 · 2024-12-30 03:01:00

501

Views

Shared memory loads not registered when using Tensor Cores

Published on 30 December 2024 at 03:01

score 766 · Answer 13 · 2024-12-30 03:03:12

766

Views

Which GPU execution dependencies have fixed latency (causing 'Wait' stalls)?

Published on 30 December 2024 at 03:03

score 628 · Answer 14 · 2024-12-30 02:57:33

628

Views

Using ncu to profile pagefault in unified memory

Published on 30 December 2024 at 02:57

score 96 · Answer 15 · 2024-12-30 02:55:11

96

Views

Unbalanced Memory Read & Write in CUDA

Published on 30 December 2024 at 02:55

score 199 · Answer 16 · 2024-12-30 02:52:49

199

Views

CUDA math function register usage

Published on 30 December 2024 at 02:52

score 335 · Answer 17 · 2024-12-30 02:57:33

335

Views

Roofline Model with CUDA Manual vs. Nsight Compute

Published on 30 December 2024 at 02:57

score 2.1k · Answer 18 · 2024-12-30 03:04:39

2.1k

Views

CUDA : How to detect shared memory bank conflict on device with compute capabiliy >= 7.2?

Published on 30 December 2024 at 03:04

score 473 · Answer 19 · 2024-12-30 02:58:41

473

Views

Optimizing CalculateConvolutionOutputTensor__im2col

Published on 30 December 2024 at 02:58

score 1.2k · Answer 20 · 2024-12-30 02:57:31

1.2k

Views

Python & Tensorflow & CUDA Environment Setup Problems

Published on 30 December 2024 at 02:57

List Question

use NCU with tensorRT, but got No kernels were profiled

ncu-ui won't run: Could not load the Qt platform plugin "xcb" in "" even though it was found

nsight-compute does nothing upon invocation

NSight Compute - get total number of samples?

How to profile in CUDA application with compute capability 7.x? Is metric "dram_read_throughput" valid in Nsight Compute?

Port forwarding to avoid the need for certificate

What does NSight Compute show for a stall reason that isn't "supported"?

What are the "long" and "short" scoreboards w.r.t. MIO/L1TEX?

Can I skip ahead to profile a specific invocation of a specific kernel?

Nsight Compute says: "Profiling is not supported on this device" - why?

When does MIO Throttle stall happen?

Shared memory loads not registered when using Tensor Cores

Which GPU execution dependencies have fixed latency (causing 'Wait' stalls)?

Using ncu to profile pagefault in unified memory

Unbalanced Memory Read & Write in CUDA

CUDA math function register usage

Roofline Model with CUDA Manual vs. Nsight Compute

CUDA : How to detect shared memory bank conflict on device with compute capabiliy >= 7.2?

Optimizing CalculateConvolutionOutputTensor__im2col

Python & Tensorflow & CUDA Environment Setup Problems

Trending Questions

Popular # Hahtags

Popular Questions