Hi, The patch punishes reload of alternative pair of "d, Z" for movsi_internal1. The reload occurs if 'Z' doesn't match and generates an additional insn. So the memory reload should be punished.
Bootstrapped and tested on powerpc64le-linux with no regressions. Is this okay for trunk? Any recommendations? Thanks a lot. ChangeLog 2021-09-29 Haochen Gui <guih...@linux.ibm.com> gcc/ * gcc/config/rs6000/rs6000.md (movsi_internal1): disparages slightly the alternative 'Z' of "lfiwzx" when reload is needed. patch.diff diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md index 6bec2bddbde..c961f2df4a7 100644 --- a/gcc/config/rs6000/rs6000.md +++ b/gcc/config/rs6000/rs6000.md @@ -7341,7 +7341,7 @@ (define_insn "*movsi_internal1" r, *h, *h") (match_operand:SI 1 "input_operand" "r, U, - m, Z, Z, + m, ^Z, Z, r, d, v, I, L, eI, n, wa, O, wM, wB,
