https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119010
--- Comment #15 from GCC Commits <cvs-commit at gcc dot gnu.org> --- The master branch has been updated by Richard Biener <rgue...@gcc.gnu.org>: https://gcc.gnu.org/g:4903e49b2fe321b1479dce4d3c4e2c2ae297298f commit r15-9052-g4903e49b2fe321b1479dce4d3c4e2c2ae297298f Author: Richard Biener <rguent...@suse.de> Date: Thu Mar 27 09:04:38 2025 +0100 target/119010 - fixup zn4zn5 reservation for move from const_vector movv8si_internal uses sselog1 and V4SFmode for an instruction like (insn 363 2437 371 97 (set (reg:V8SI 46 xmm10 [1125]) (const_vector:V8SI [ (const_int 0 [0]) repeated x8 ])) "ComputeNonbondedUtil.C":185:21 2402 {movv8si_internal} this wasn't catched by the existing znver4_sse_log1 reservation, I think the znver automaton catches this with the generic (define_insn_reservation "znver1_sse_log1" 1 (and (eq_attr "cpu" "znver1,znver2,znver3") (and (eq_attr "type" "sselog1") (eq_attr "memory" "none"))) "znver1-direct,znver1-fp1|znver1-fp2") which does not look at the mode at all. The zn4zn5 automaton lacks this and instead has separated store and load-store reservations in odd ways. The following renames the store one and introduces a none variant. PR target/119010 * config/i386/zn4zn5.md (znver4_sse_log1): Rename to znver4_sse_log1_store. (znver5_sse_log1): Rename to znver5_sse_log1_store. (znver4_sse_log1): New memory-less variant.
