Use all of Unity 6's profiling tools in the smartest and most efficient way (Part 1)

I have read the new book about profiling so you can dive immediately into what interests you the most.

I had a lot of experience with Unity Profiler before, so I am excited about the new Unity 6 profiling book.
I skimmed it for you to highlight all the new stuff I found interesting and worth special attention.
Feel free to dive deeper into any point by searching for the text in the book:
- With the new Highlights module in Unity 6, it’s easy to determine whether your application is CPU- or GPU-bound on all platforms.
- Locating recurring memory allocations over application lifetime.
- Establish a profiling methodology: The flow chart below illustrates the initial profiling process with the sections following it providing detailed information on each step.
- Common pitfalls for main thread bottleneck
- Common pitfalls for render thread bottlenecks
- Common pitfalls for worker thread bottlenecks
- You can use the Flow Events feature in the Timeline view of the CPU Usage Profiler module to investigate when jobs are scheduled and when their results are expected by the main thread.

- Expensive fragment shaders caused by:
- Branching logic inside shader code
Note: I saw multiple posts that demystify it for modern desktop GPUs, so validate every claim for your particular case

- A general tip to combat device thermal issues over extended play times is to leave a frame idle time of around 35%.

Profile Analyzer tips:
- Drill into user scripts (ignoring Unity Engine API levels) by selecting a Depth level of 4.
After filtering to this level and looking at the Unity Profiler in Timeline mode, you can correlate the call stack depth to make a selection here – Monobehaviour scripts will appear in blue on the fourth level down. This is a quick way to see if your specific logic
and gameplay scripts are taxing by themselves without any other “noise.”
- Filter data in the same way for other areas of the Unity engine, such as animators or engine physics.
- On the right side in the Frame Summary section, you’ll find the highlighted method’s
performance range histogram. Hover over the Max Frame number (the exact frame in which max timing was found) to get a clickable link to view the frame selection in the Unity Profiler. Use this view to analyze other factors that potentially contribute to the
high maximum frame time.

- If you have a widescreen or two monitors available it can be useful to open the Profile Analyzer and the Unity Profiler side by side. This setup enables you to double-click a frame in the Profile Analyzer to automatically select the same frame in the Unity Profiler, from where you can further investigate it using the Timeline or Hierarchy views.

- Common sense, but I’ve never seen it before in any docs and with a concrete
percentage.

DRAM access is typically a power-hungry operation on mobile devices.
Arm’s optimization advice for graphics content on mobile devices says that LPDDR4 memory access costs approximately 100 picojoules per byte.
Reduce the number of memory access operations per frame by:
- Reducing frame rate
- Reducing display resolution where possible
- Using simpler meshes with reduced vertex count and attribute precision
- Using texture compression and mipmapping

Allocation call stacks provide a quick way to discover managed memory allocations in your code.
These will provide the call stack detail you need at less overhead compared to what deep profiling would normally add, and they can be enabled on the fly using the standard Profiler.