https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104704
--- Comment #11 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to H.J. Lu from comment #9)
> --- pieces-memset-46.s 2022-03-02 06:44:55.845212762 -0800
> +++
> /export/build/gnu/tools-build/gcc-gitlab-debug/build-x86_64-linux/gcc/pieces-
> memset-46.s 2022-03-02 06:45:03.313188978 -0800
> @@ -8,9 +8,11 @@ foo:
> .cfi_startproc
> movq dst(%rip), %rdx
> movl $3, %eax
> - vpbroadcastb %eax, %zmm31
> - vmovdqu8 %zmm31, (%rdx)
> - vmovw %xmm31, 64(%rdx)
> + vpbroadcastb %eax, %zmm0
> + movl $771, %eax
> + movw %ax, 64(%rdx)
> + vmovdqu8 %zmm0, (%rdx)
> + vzeroupper
> ret
> .cfi_endproc
> .LFE0:
>
> gen_reg_rtx generates 2 extra instructions for pieces-memset-46.c.
It's on purpose.
;; Don't move an immediate directly to memory when the instruction
;; gets too big, or if LCP stalls are a problem for 16-bit moves.
(define_peephole2
[(match_scratch:SWI124 2 "<r>")
(set (match_operand:SWI124 0 "memory_operand")
(match_operand:SWI124 1 "immediate_operand"))]
"optimize_insn_for_speed_p ()
&& ((<MODE>mode == HImode
&& TARGET_LCP_STALL)
|| (TARGET_SPLIT_LONG_MOVES
&& get_attr_length (insn) >= ix86_cur_cost ()->large_insn))"
[(set (match_dup 2) (match_dup 1))
(set (match_dup 0) (match_dup 2))])
