How to perform Integer SIMD operations on an iPad A4 processor?

I feel the need for speed. Dual for loops kills iPad performance. I need a SIMD. How to perform integer SIMD operations on an iPad A4 processor?

Thanks,
Doug

+4
source share
2 answers

To get the maximum speed, you will need to write ARM assembly language code that uses the NEON SIMD operations because C compilers do not usually make very good SIMD code, so handwriting is very important. I have a brief introduction here: http://www.shervinemami.co.cc/iphoneAssembly.html

Note that the iPad A4 uses an ARMv7-A processor, so the reference guide for NEON SIMD instructions is: http://infocenter.arm.com/help/topic/com.arm.doc.ddi0406b/index.html (but its 2000 pages longer and requires an understanding of the assembly code and possibly SIMD in general!).

+4
source

NEON instruction set, intrinsics reference

I could never find good documentation that they are all really. But you pick it up pretty quickly if you have SSE exposure

+5
source

All Articles