Skip to content

Commit a085bbb

Browse files
authored
Consistently capitalize Nsight. (#2541)
[only docs]
1 parent 842d19f commit a085bbb

File tree

1 file changed

+20
-20
lines changed

1 file changed

+20
-20
lines changed

docs/src/development/profiling.md

Lines changed: 20 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -155,19 +155,19 @@ to a mode where it merely activates an external profiler and does not do perform
155155
profiling itself. In case the detection does not work, this mode can be forcibly activated
156156
by passing `external=true` to `CUDA.@profile`.
157157
158-
NVIDIA provides two tools for profiling CUDA applications: NSight Systems and NSight Compute
158+
NVIDIA provides two tools for profiling CUDA applications: Nsight Systems and Nsight Compute
159159
for respectively timeline profiling and more detailed kernel analysis. Both tools are
160160
well-integrated with the Julia GPU packages, and make it possible to iteratively profile
161161
without having to restart Julia.
162162
163163
#### NVIDIA Nsight Systems
164164
165-
Generally speaking, the first external profiler you should use is NSight Systems, as it will
165+
Generally speaking, the first external profiler you should use is Nsight Systems, as it will
166166
give you a high-level overview of your application's performance characteristics. After
167167
downloading and installing the tool (a version might have been installed alongside with the
168168
CUDA toolkit, but it is recommended to download and install the latest version from the
169169
NVIDIA website), you need to launch Julia from the command-line, wrapped by the `nsys`
170-
utility from NSight Systems:
170+
utility from Nsight Systems:
171171
172172
```
173173
$ nsys launch julia
@@ -209,7 +209,7 @@ You can open the resulting `.qdrep` file with `nsight-sys`:
209209
210210
!!! info
211211
212-
If NSight Systems does not capture any kernel launch, even though you have used
212+
If Nsight Systems does not capture any kernel launch, even though you have used
213213
`CUDA.@profile`, try starting `nsys` with `--trace cuda`.
214214
215215
#### NVIDIA Nsight Compute
@@ -243,7 +243,7 @@ to the running session by selecting it in the list in the `Attach` pane:
243243
244244
!["NVIDIA Nsight Compute - Attaching to a session"](nsight_compute-attach.png)
245245
246-
Note that this even works with remote systems, i.e., you can have NSight Compute connect
246+
Note that this even works with remote systems, i.e., you can have Nsight Compute connect
247247
over ssh to a remote system where you run Julia under `ncu`.
248248
249249
Once you've successfully attached to a Julia process, you will see that the tool has stopped
@@ -277,26 +277,26 @@ the API calls that have been made:
277277
!["NVIDIA Nsight Compute - API inspection"](nsight_compute-api.png)
278278
279279
280-
#### Troubleshooting NSight Compute
280+
#### Troubleshooting Nsight Compute
281281
282-
If you're running into issues, make sure you're using the same version of NSight Compute on
282+
If you're running into issues, make sure you're using the same version of Nsight Compute on
283283
the host and the device, and make sure it's the latest version available. You do not need
284-
administrative permissions to install NSight Compute, the `runfile` downloaded from the
284+
administrative permissions to install Nsight Compute, the `runfile` downloaded from the
285285
NVIDIA home page can be executed as a regular user.
286286
287287
##### Kernel sources only report `File not found`
288288
289-
When profiling a remote application, NSight Compute will not be able to find the sources of
289+
When profiling a remote application, Nsight Compute will not be able to find the sources of
290290
kernels, and instead show `File not found` errors in the Source view. Although it is
291-
possible to point NSight Compute to a local version of the remote file, it is recommended
291+
possible to point Nsight Compute to a local version of the remote file, it is recommended
292292
to enable "Auto-Resolve Remote Source File" in the global Profile preferences (Tools menu
293293
-> Preferences). With that option set to "Yes", clicking the "Resolve" button will
294294
automatically download and use the remote version of the requested source file.
295295
296296
##### `Could not load library "libpcre2-8`
297297
298-
This is caused by an incompatibility between Julia and NSight Compute, and should be fixed
299-
in the latest versions of NSight Compute. If it's not possible to upgrade, the following
298+
This is caused by an incompatibility between Julia and Nsight Compute, and should be fixed
299+
in the latest versions of Nsight Compute. If it's not possible to upgrade, the following
300300
workaround may help:
301301
302302
```
@@ -305,28 +305,28 @@ LD_LIBRARY_PATH=$(/path/to/julia -e 'println(joinpath(Sys.BINDIR, Base.LIBDIR, "
305305
306306
##### The Julia process is not listed in the "Attach" tab
307307
308-
Make sure that the port that is used by NSight Compute (49152 by default) is accessible via
308+
Make sure that the port that is used by Nsight Compute (49152 by default) is accessible via
309309
ssh. To verify this, you can also try forwarding the port manually:
310310
311311
```
312312
ssh user@host.com -L 49152:localhost:49152
313313
```
314314
315-
Then, in the "Connect to process" window of NSight Compute, add a connection to `localhost`
315+
Then, in the "Connect to process" window of Nsight Compute, add a connection to `localhost`
316316
instead of the remote host.
317317
318318
If SSH complains with `Address already in use`, that means the port is already in use. If
319319
you're using VSCode, try closing all instances as VSCode might automatically forward the
320-
port when launching NSight Compute in a terminal within VSCode.
320+
port when launching Nsight Compute in a terminal within VSCode.
321321
322-
##### Julia in NSight Compute only shows the Julia logo, not the REPL prompt
322+
##### Julia in Nsight Compute only shows the Julia logo, not the REPL prompt
323323
324-
In some versions of NSight Compute, you might have to start Julia without the `--project`
324+
In some versions of Nsight Compute, you might have to start Julia without the `--project`
325325
option and switch the environment from inside Julia.
326326
327327
##### "Disconnected from the application" once I click "Resume"
328328
329-
Make sure that everything is precompiled before starting Julia with NSight Compute,
329+
Make sure that everything is precompiled before starting Julia with Nsight Compute,
330330
otherwise you end up profiling the precompilation process instead of your actual
331331
application.
332332
@@ -348,7 +348,7 @@ The `nvidia.ko` kernel module needs to be reloaded after changing this configura
348348
your system may require regenerating the initramfs or even a reboot. Refer to your
349349
distribution's documentation for details.
350350
351-
##### NSight Compute breaks on various API calls
351+
##### Nsight Compute breaks on various API calls
352352
353353
Make sure `Break On API Error` is disabled in the `Debug` menu, as CUDA.jl purposefully
354354
triggers some API errors as part of its normal operation.
@@ -378,7 +378,7 @@ For more details, refer to the documentation of the NVTX.jl package.
378378
379379
## Compiler options
380380
381-
Some tools, like NSight Systems Compute, also make it possible to do source-level profiling.
381+
Some tools, like Nsight Systems Compute, also make it possible to do source-level profiling.
382382
CUDA.jl will by default emit the necessary source line information, which you can disable by
383383
launching Julia with `-g0`. Conversely, launching with `-g2` will emit additional debug
384384
information, which can be useful in combination with tools like `cuda-gdb`, but might hurt

0 commit comments

Comments
 (0)