Quick answer: Compare CPU main-thread time against GPU time in the Profiler; if lowering resolution recovers frame rate you are GPU-bound, if it does not you are CPU-bound, then profile only that side.
Optimizing the CPU when you are GPU-bound buys you nothing, and vice versa. Before touching code you need to know which processor is the limiter. Two quick measurements answer it definitively, and then all your effort goes to the half that matters.
How to find the bottleneck
1. Compare CPU and GPU time in the Profiler
Enable the GPU module and read both the main-thread CPU time and the GPU time per frame. Whichever is consistently higher and tracks your frame time is the bottleneck.
2. Run the resolution test
Drop the render resolution to a quarter and watch the frame rate. If it jumps up you are GPU-bound (fewer pixels = faster); if it barely moves the GPU was idle and you are CPU-bound.
3. Check for the gpu wait marker
A CPU thread sitting in Gfx.WaitForPresent or a GPU stalled waiting on the CPU each tells the opposite story. The thread that waits is the one with spare capacity; the thread it waits on is the limiter.
4. Profile only the limiting side
Once you know which it is, dig in: GPU-bound means overdraw, fillrate, and shader cost; CPU-bound means scripts, physics, and draw-call submission. You stop wasting effort on the half that was never the problem.
Catching the ones you can't reproduce
The hardest version of this to fix is the one you can't reproduce — it only happens on a player's hardware, OS, driver, or save state, under conditions that simply aren't present on your machine. A report that says “it crashed” or “it froze” gives you nothing to act on, so the bug survives release after release while quietly costing you players.
Automatic error capture closes that gap. Each failure arrives with its full stack trace, the device and OS, the build number, and a breadcrumb trail of what the player did right before it broke, so even a failure you have never seen becomes a specific, reproducible issue. Fold identical failures into one signature ranked by how many players each hits, and your worklist sorts itself worst-first instead of arriving as a stream of vague complaints.
This is where a tool like Bugnet earns its place. Its SDK captures every error automatically with the full stack trace plus device, OS, memory, build, and game-state context, folds duplicates into one grouped issue with an occurrence count, and ties each to the build it first appeared on — so you fix the problem that hurts the most players first and confirm it is gone when its signature disappears from the next release.
A crash you can name from its stack trace is a crash you can usually fix in minutes.