Porting and Optimizing ARM for ARM Embedded Linux

Issues when porting or developing an application for ARM Embedded Linux
”Get as much better performance, with the smallest memory footprint”
Similar to any platform for the code to be portable it should

• Program according to standards
• Use intrinsics

and should not

• Use inline, embedded assembly
• Use Toolchain specific things.

Neon Architecture

What is NEON

ARM NEON technology is a 128 bit SIMD (Single Instruction, Multiple Data)
architecture extension for the ARM CortexTM-A series processors, designed to provide flexible and powerful acceleration for intensive multimedia applications, thereby delivering a significantly enhanced user experience.

Some of the benefits…

• Aligned and unaligned data access allows for efficient vectorization of SIMD operations.
• Support for both integer and floating point operations
• Tight coupling to the ARM core provides a single instruction stream and a unified view of memory, presenting a single development platform target with a simpler tool flow.
• The large NEON register file with its multiple views enables efficient handling of data and minimizes access to memory, enhancing data throughput performance.

Reference:

Portability and Optimizations of GNU Applications for ARM Embedded Linux – http://tree.celinuxforum.org/CelfPubWiki/ELCEurope2008Presentations?action=AttachFile&do=get&target=ARM_EmbeddedLinux_Apps_Port.pdf