The following testcase ICEs on armv7hl-linux-gnueabi.
try_combine is called on:
(gdb) p debug_rtx (i3)
(insn 20 12 22 2 (set (mem/c:SI (plus:SI (reg/f:SI 102 sfp)
(const_int -4 [0xfffffffffffffffc])) [1 x+0 S4 A32])
(reg:SI 125)) "pr94291.c":7:8 241 {*arm_movsi_insn}
(expr_list:REG_DEAD (reg:SI 125)
(nil)))
(gdb) p debug_rtx (i2)
(insn 12 7 20 2 (parallel [
(set (reg:CC 100 cc)
(compare:CC (reg:SI 121 [ <retval> ])
(const_int 0 [0])))
(set (reg:SI 125)
(reg:SI 121 [ <retval> ]))
]) "pr94291.c":7:8 248 {*movsi_compare0}
(expr_list:REG_UNUSED (reg:CC 100 cc)
(nil)))
and tries to recognize cc = r121 cmp 0; [sfp-4] = r121 parallel,
but that isn't recognized, so it splits it into two: split_i2i3
[sfp-4] = r121 followed by cc = r121 cmp 0 which is recognized, but
ICEs because the code below insist that the SET_DEST of newi2pat
(or first set in PARALLEL thereof) must be a REG or SUBREG of REG,
but it is a MEM in this case. I don't see any condition that would
guarantee that, perhaps for the swap_i2i3 case it was somehow guaranteed.
As the code just wants to update LOG_LINKS and LOG_LINKS are only for
registers, not for MEM or anything else, the patch just doesn't update those
if it isn't a REG or SUBREG of REG.
2020-04-07 Jakub Jelinek <jakub@redhat.com>
PR rtl-optimization/94291
PR rtl-optimization/84169
* combine.c (try_combine): For split_i2i3, don't assume SET_DEST
must be a REG or SUBREG of REG; if it is not one of these, don't
update LOG_LINKs.
* gcc.dg/pr94291.c: New test.
