/* * NOTE about '.balign 4': * * To make atomic update of patched instruction available we need to guarantee * that this instruction doesn't cross L1 cache line boundary. * * As of today we simply align instruction which can be patched by 4 byte using * ".balign 4" directive. In that case patched instruction is aligned with one * 16-bit NOP_S if this is required. * However 'align by 4' directive is much stricter than it actually required. * It's enough that our 32-bit instruction don't cross L1 cache line boundary / * L1 I$ fetch block boundary which can be achieved by using * ".bundle_align_mode" assembler directive. That will save us from adding * useless NOP_S padding in most of the cases. * * TODO: switch to ".bundle_align_mode" directive using whin it will be * supported by ARC toolchain.
*/
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.