|
Which tool can accurately obtain kernel performance, ncu or nsys?
|
|
2
|
93
|
March 30, 2026
|
|
Can we see warp scheduler status in pmsampling?
|
|
0
|
23
|
February 7, 2026
|
|
Difference in number of wavefronts for strided access to shared-memory and L1 cache in Ampere GPUs
|
|
3
|
1014
|
February 6, 2026
|
|
Feature request: Output to a text file format
|
|
3
|
58
|
February 17, 2026
|
|
Understanding registers information in NCU
|
|
2
|
91
|
February 2, 2026
|
|
Wrong bytes from L1/TEX cache to LRC?
|
|
2
|
91
|
March 30, 2026
|
|
Why Nsight Compute reports error about encoding?
|
|
5
|
76
|
May 30, 2026
|
|
Possible Bug in NVIDIA Nsight Compute: FMUL2 FLOP Multiplier Missing in Nsight Compute Python Rule
|
|
3
|
67
|
January 23, 2026
|
|
Restricted vs. unrestricted profiling
|
|
6
|
93
|
February 22, 2026
|
|
Investigating metrics which cause profiler to fail
|
|
1
|
54
|
January 22, 2026
|
|
Ncu CLI error: LookupError: unknown encoding: utf-8-sig on Windows 11 (Nsight Compute 2025.4)
|
|
2
|
89
|
February 21, 2026
|
|
blockIdx.y usage causes shared memory bank conflicts on Turing (RTX 2070, CUDA 12.2)
|
|
3
|
62
|
January 20, 2026
|
|
NVIDIA® Nsight™ Compute 2025.4 is now available
|
|
6
|
238
|
March 10, 2026
|
|
Can the theoretical peak value of Computed (SM) Throughput be calculated by hand?
|
|
2
|
53
|
January 29, 2026
|
|
About performance comparision
|
|
2
|
56
|
January 29, 2026
|
|
Question about memory throughout
|
|
2
|
62
|
January 29, 2026
|
|
Understanding Tensor Pipe Throughput and Throttle Stalls
|
|
4
|
296
|
January 29, 2026
|
|
Why the Compute Throughput's value is different from the actual Performance / Peak Performance
|
|
9
|
3723
|
December 31, 2025
|
|
What is the different between “SM: Pipe Tc Cycles Active [%]” and “SM: Pipe Tensor Cycles Active [%]” in nsight compute
|
|
5
|
164
|
January 6, 2026
|
|
Timelline View of Using PM Sampling to Get Tenso Core Utilitation
|
|
4
|
87
|
January 29, 2026
|
|
Is serialization unavoidable while profiling L2 cache miss rates for concurrent kernels with Nsight Compute?
|
|
2
|
74
|
December 10, 2025
|
|
Question about L1 tag stage resolution per cycle
|
|
2
|
108
|
December 9, 2025
|
|
Could you tell me how to use nsight compute with MPS and MPI program?
|
|
3
|
90
|
December 8, 2025
|
|
NCU and driver compatibility
|
|
2
|
167
|
December 5, 2025
|
|
Excessive sectors reported for LDGSTS.E
|
|
3
|
134
|
December 3, 2025
|
|
Tensor Core Flops
|
|
2
|
111
|
December 24, 2025
|
|
[Nsight Compute] [H100] Questions on L1 Bank Conflict statistic discrepancies between Details and Source pages
|
|
2
|
117
|
December 16, 2025
|
|
OptiX Shader Kernel Profiling
|
|
2
|
72
|
December 12, 2025
|
|
[Nsight Compute] [H100] Questions on L1 Bank Conflict statistic discrepancies between Details and Source pages
|
|
3
|
113
|
December 26, 2025
|
|
What's the difference between metrics of with "_realtime" and without "_realtime"?
|
|
2
|
71
|
December 26, 2025
|