Splits LDM and STM instructions perfoming large numbers of register transfers into multiple LDM or STM instructions, to help reduce interrupt latency on some ARM systems.
--split_ldm is selected, the maximum number of register transfers for
STM instruction is limited to:
Five, for all
LDMs that do not load the PC.
LDMs that load the PC.
Where register transfers beyond these limits are required, multiple
STM instructions are used.
--split_ldm option can reduce interrupt latency on ARM systems
Do not have a cache or a write buffer, for example, a cacheless ARM7TDMI.
Use zero-wait-state, 32-bit memory.
--split_ldm increases code size and decreases performance
STM instructions are split
by default when
--split_ldm is used. However, the compiler might
subsequently recombine the separate instructions into an
STM instructions are split when
--split_ldm is used.
Some target hardware does not benefit from code built with
--split_ldm. For example:
It has no significant benefit for cached systems, or for processors with a write
It has no benefit for systems with non zero-wait-state memory, or for systems
with slow peripheral devices. Interrupt latency in such systems is determined by the
number of cycles required for the slowest memory or peripheral access. Typically,
this is much greater than the latency introduced by multiple register