Made huge progress today on J-core SPI/MMC performance, but Linux is still about 1/3 to 1/2 the speed of bare-metal code reading SD card...
...and it seems to be just a matter of all the layers of crap the kernel puts you through for each 512-byte transfer block. :-(
-
-
I still don't understand why block 2 of a multiblock transfer doesn't start immediately after block 1 finishes, but some 20k cycles later...
-
@RichFelker sounds *just like* Linux networking.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.