mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 20:40:52 +07:00
5210d1e688
Hand optimised asm code for ARC700 pipeline. Originally written/optimized by Joern Rennecke Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Cc: Joern Rennecke <joern.rennecke@embecosm.com>
60 lines
1.2 KiB
ArmAsm
60 lines
1.2 KiB
ArmAsm
/*
|
|
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <asm/linkage.h>
|
|
|
|
#define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */
|
|
|
|
ARC_ENTRY memset
|
|
mov_s r4,r0
|
|
or r12,r0,r2
|
|
bmsk.f r12,r12,1
|
|
extb_s r1,r1
|
|
asl r3,r1,8
|
|
beq.d .Laligned
|
|
or_s r1,r1,r3
|
|
brls r2,SMALL,.Ltiny
|
|
add r3,r2,r0
|
|
stb r1,[r3,-1]
|
|
bclr_s r3,r3,0
|
|
stw r1,[r3,-2]
|
|
bmsk.f r12,r0,1
|
|
add_s r2,r2,r12
|
|
sub.ne r2,r2,4
|
|
stb.ab r1,[r4,1]
|
|
and r4,r4,-2
|
|
stw.ab r1,[r4,2]
|
|
and r4,r4,-4
|
|
.Laligned: ; This code address should be aligned for speed.
|
|
asl r3,r1,16
|
|
lsr.f lp_count,r2,2
|
|
or_s r1,r1,r3
|
|
lpne .Loop_end
|
|
st.ab r1,[r4,4]
|
|
.Loop_end:
|
|
j_s [blink]
|
|
|
|
.balign 4
|
|
.Ltiny:
|
|
mov.f lp_count,r2
|
|
lpne .Ltiny_end
|
|
stb.ab r1,[r4,1]
|
|
.Ltiny_end:
|
|
j_s [blink]
|
|
ARC_EXIT memset
|
|
|
|
; memzero: @r0 = mem, @r1 = size_t
|
|
; memset: @r0 = mem, @r1 = char, @r2 = size_t
|
|
|
|
ARC_ENTRY memzero
|
|
; adjust bzero args to memset args
|
|
mov r2, r1
|
|
mov r1, 0
|
|
b memset ;tail call so need to tinker with blink
|
|
ARC_EXIT memzero
|