You are reading a single comment by @Gordon and its replies. Click here to read the full conversation.
  • Just to add, I had a quick look at this, and I replaced the spiFlashReadWrite with a spiFlashRead which also avoided a memset as well - it reduces the exceution time from 8.79 to 8.58. Might not seem like much but there's a lot of other overhead for those calculations!

    • You can turn on GCC's -O3 for single functions, so I gave that a try, and it actually unrolls the loop anyway. It actually stopped Bangle.js being able to read from flash - so it turns out you can go too fast!
    • Using GCC's -O2 for the functions instead of the standard (-Os for size) actually made things slower!
About

Avatar for Gordon @Gordon started