perf: add a FFT 32 codelet to fuse first 5 stages

[smu160]

No description provided.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 95.89322% with 20 lines in your changes missing coverage. Please review.
✅ Project coverage is 98.59%. Comparing base (3fc78e0) to head (8e3a968).

Files with missing lines	Patch %	Lines
src/kernels/codelets.rs	95.80%	20 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #101      +/-   ##
==========================================
- Coverage   99.79%   98.59%   -1.20%     
==========================================
  Files           8        9       +1     
  Lines        1438     1923     +485     
==========================================
+ Hits         1435     1896     +461     
- Misses          3       27      +24     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Shnatsel]

Apple M2 benchmarks: https://gist.github.com/smu160/181d0d68d7cede9913de0d0a58b6c005

Zen4 benchmarks: https://gist.github.com/Shnatsel/8d17ca71eb6548e2d1ec289b5628ec71