MTuner VS PresentMon

I would really love to have some memory profiler that is capable of dealing of huge amount of data and allocations, robust and stable with stack traces on allocations. Similar to https://github.com/milostosic/MTuner

For memory profiling, MTuner is a good tool (worked much better for me than Visual Studio's memory profiler), and it's even open source.

Remotery - https://github.com/Celtoys/Remotery

Visual Studio's built-in profiler is an ok sampling profiler. It doesn't give you a nice multi-thread view which is a huge advantage to a span based profiler.

MTuner is quite nice for debugging memory usage. Which is another gaping hole in the Rust ecosystem. https://github.com/milostosic/mtuner

Lots of tools generate data in a format viewable by the Chrome trace viewer. I think Chrome's tracer viewer is not great. Maybe someday someone will create a viewer for the format that's good. I get cranky when large traces don't render at 60fps. Web-based viewers are almost all very very slow and it makes me sad.

Use PresentMon to figure out if it's a CPU or GPU issue. (GPUBusy)

EDIT - Intel's Presentmon has a "gpu busy" metric kinda designed to tell you if the gpu is waiting on the rest of the system and it's platform independent so should work with amd/nvidia stuff. https://game.intel.com/story/intel-presentmon/

You can also check the presentation latency with PresentMon

Borderless for DX12 and Vulkan games has no input delay. In fact those APIs don't have exclusive fullscreen support anymore. Why would the engineers who designed those get rid of "exclusive fullscreen" support if it wasn't useful? In fact most new games which offer a "fullscreen" option are faking it, you can use PresentMon to see which DXGI presentation mode is being used.

This behaviour can be monitored using PresentMon (best used on a second display) as well. This new DXGI layer would appear as Composed: Flip, Hardware: Independent Flip, or Hardware Composed: Independent Flip, while classic methods would appear as Hardware: Legacy Flip (if FSE was engaged) or Composed: Copy with GPU GDI.