https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114835
Bug ID: 114835 Summary: AVR popcountqi2 is not fast&small as can be Product: gcc Version: 13.2.1 Status: UNCONFIRMED Severity: normal Priority: P3 Component: target Assignee: unassigned at gcc dot gnu.org Reporter: WolfgaNg.Hospital at arcor dot de Target Milestone: --- Created attachment 58025 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=58025&action=edit AVR assembly code for __popcountqi2 For 8-bit AVRs, the current 16-instruction __popcountqi2 uses 6 ADC instructions to establish the number of bits set in a byte. In "Bit Twiddling Hacks", Sean E. Anderson presents several approaches to this; "parallel/sideways addition" can be coded with one instruction&cycle less. When establishing the "popcount" of an uint8_t, I've seen GCC to widen the value to "half int" and use __popcountqi2 twice.