improve performance using CUDA performance tips

[matthieugomez]

No description provided.

[codecov]

Codecov Report

❌ Patch coverage is 0% with 16 lines in your changes missing coverage. Please review.
✅ Project coverage is 62.17%. Comparing base (474dea9) to head (c77a035).
⚠️ Report is 4 commits behind head on master.

Files with missing lines	Patch %	Lines
ext/CUDAExt.jl	0.00%	16 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #69      +/-   ##
==========================================
- Coverage   64.92%   62.17%   -2.75%     
==========================================
  Files          11       10       -1     
  Lines         573      571       -2     
==========================================
- Hits          372      355      -17     
- Misses        201      216      +15     

☔ 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.