apitrace VS tracy

You have several tools, this can be done by printing debug messages using extensions such as KHR_debug, or using specific tools which will inject themselves between your OpenGL calls and your driver such as apitrace or RenderDoc. I recommend running your program in RenderDoc regularly even if everything seems to work fine as it may help you catch some subtle bugs.

That said, the profiling situation for non-NV users is not completely hopeless. You can still use API timer queries to get an idea of how long events take on the device. Tracy also supports GPU profiling, but I suspect it's just a fancy way of inserting timer queries. apitrace also claims to support profiling OpenGL apps, but I'd be wary of overhead as it's doing a lot of other things besides profiling.

At first I thought Feral probably used it accidentally, but this thread about the symbol's use in apitrace seems to shed some light:

I don't see anything wrong with your code, altough I'm not familiar with Avalonia or Silk. I suggest you try to use apitrace for (a probably long and painful day) debugging it.

I get that it's hard to debug without direct access, but isn't there some dump or log that they could generate and provide? Maybe something like using apitrace?

Pierre-Eric Pelloux-Prayer @pepp · 6 months ago Developer https://github.com/apitrace/apitrace/blob/master/docs/USAGE.markdown is the basic doc. For Steam games I usually go to the game's folder (probably $HOME/.steam/steam/steamapps/common/Indivisible) and try to run the game with apitrace (apitrace trace indivisible-executable). It should print a line to indicate where the trace file is written to (apitrace: tracing to somefile.trace.

i don't really think there is _anything_ that comes even close to tracy https://github.com/wolfpld/tracy.

on top of this, given google's penchant for dumping projects aka abandonware, this would be an easy pass.

The RemedyBG debugger (https://remedybg.handmade.network/) and the Tracy profiler (https://github.com/wolfpld/tracy) both use Dear ImGui and so far I've only read high praise from people who used those tools compared to the 'established' alternatives.

For tools like this, programmers are also just "normal users", and from the developer side, I'm sure they evaluated various alternatives with all their pros and cons before settling for Dear ImGui.

Not the person you asked, but generally you might want to look at "frame-based" profilers. These are typically used in video games, but the concept is general, and can apply to other applications. The "frame" could also be something like a request or transaction being processed. I like Tracy[1], myself.

Another latency metric that you'll see, often w/respect to web apps and microservices is "P99" and similar. This is the amount of time in which 99% of requests get their response. For a higher percentile, you get a better idea of worst-case performance.

[1] https://github.com/wolfpld/tracy

I've not actually used Superluminal, but I use Tracy for similar reasons. It's free though (and, importantly, open source).

For profiling, you can check tracy.

You could try Tracy

There is no such thing as overengineering in fun projects, so I've also adopted Tracy as profiling solution. Works quite nice and gonna save me plenty of times in the future debugging performance spikes on badly optimized math heavy operations.

I know about tools such as tracing, jaeger or tracy. While having a complete tracing could be a potential solution, these tools don't work with no_std.