/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
|
/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
|
2004, 2005, 2006
|
2004, 2005, 2006
|
Free Software Foundation, Inc.
|
Free Software Foundation, Inc.
|
|
|
This file is free software; you can redistribute it and/or modify it
|
This file is free software; you can redistribute it and/or modify it
|
under the terms of the GNU General Public License as published by the
|
under the terms of the GNU General Public License as published by the
|
Free Software Foundation; either version 2, or (at your option) any
|
Free Software Foundation; either version 2, or (at your option) any
|
later version.
|
later version.
|
|
|
In addition to the permissions in the GNU General Public License, the
|
In addition to the permissions in the GNU General Public License, the
|
Free Software Foundation gives you unlimited permission to link the
|
Free Software Foundation gives you unlimited permission to link the
|
compiled version of this file into combinations with other programs,
|
compiled version of this file into combinations with other programs,
|
and to distribute those combinations without any restriction coming
|
and to distribute those combinations without any restriction coming
|
from the use of this file. (The General Public License restrictions
|
from the use of this file. (The General Public License restrictions
|
do apply in other respects; for example, they cover modification of
|
do apply in other respects; for example, they cover modification of
|
the file, and distribution when not linked into a combine
|
the file, and distribution when not linked into a combine
|
executable.)
|
executable.)
|
|
|
This file is distributed in the hope that it will be useful, but
|
This file is distributed in the hope that it will be useful, but
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
General Public License for more details.
|
General Public License for more details.
|
|
|
You should have received a copy of the GNU General Public License
|
You should have received a copy of the GNU General Public License
|
along with this program; see the file COPYING. If not, write to
|
along with this program; see the file COPYING. If not, write to
|
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
|
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
|
Boston, MA 02110-1301, USA. */
|
Boston, MA 02110-1301, USA. */
|
|
|
!! libgcc routines for the Renesas / SuperH SH CPUs.
|
!! libgcc routines for the Renesas / SuperH SH CPUs.
|
!! Contributed by Steve Chamberlain.
|
!! Contributed by Steve Chamberlain.
|
!! sac@cygnus.com
|
!! sac@cygnus.com
|
|
|
!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
|
!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
|
!! recoded in assembly by Toshiyasu Morita
|
!! recoded in assembly by Toshiyasu Morita
|
!! tm@netcom.com
|
!! tm@netcom.com
|
|
|
/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
|
/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
|
ELF local label prefixes by J"orn Rennecke
|
ELF local label prefixes by J"orn Rennecke
|
amylaar@cygnus.com */
|
amylaar@cygnus.com */
|
|
|
#include "lib1funcs.h"
|
#include "lib1funcs.h"
|
|
|
#if ! __SH5__
|
#if ! __SH5__
|
#ifdef L_ashiftrt
|
#ifdef L_ashiftrt
|
.global GLOBAL(ashiftrt_r4_0)
|
.global GLOBAL(ashiftrt_r4_0)
|
.global GLOBAL(ashiftrt_r4_1)
|
.global GLOBAL(ashiftrt_r4_1)
|
.global GLOBAL(ashiftrt_r4_2)
|
.global GLOBAL(ashiftrt_r4_2)
|
.global GLOBAL(ashiftrt_r4_3)
|
.global GLOBAL(ashiftrt_r4_3)
|
.global GLOBAL(ashiftrt_r4_4)
|
.global GLOBAL(ashiftrt_r4_4)
|
.global GLOBAL(ashiftrt_r4_5)
|
.global GLOBAL(ashiftrt_r4_5)
|
.global GLOBAL(ashiftrt_r4_6)
|
.global GLOBAL(ashiftrt_r4_6)
|
.global GLOBAL(ashiftrt_r4_7)
|
.global GLOBAL(ashiftrt_r4_7)
|
.global GLOBAL(ashiftrt_r4_8)
|
.global GLOBAL(ashiftrt_r4_8)
|
.global GLOBAL(ashiftrt_r4_9)
|
.global GLOBAL(ashiftrt_r4_9)
|
.global GLOBAL(ashiftrt_r4_10)
|
.global GLOBAL(ashiftrt_r4_10)
|
.global GLOBAL(ashiftrt_r4_11)
|
.global GLOBAL(ashiftrt_r4_11)
|
.global GLOBAL(ashiftrt_r4_12)
|
.global GLOBAL(ashiftrt_r4_12)
|
.global GLOBAL(ashiftrt_r4_13)
|
.global GLOBAL(ashiftrt_r4_13)
|
.global GLOBAL(ashiftrt_r4_14)
|
.global GLOBAL(ashiftrt_r4_14)
|
.global GLOBAL(ashiftrt_r4_15)
|
.global GLOBAL(ashiftrt_r4_15)
|
.global GLOBAL(ashiftrt_r4_16)
|
.global GLOBAL(ashiftrt_r4_16)
|
.global GLOBAL(ashiftrt_r4_17)
|
.global GLOBAL(ashiftrt_r4_17)
|
.global GLOBAL(ashiftrt_r4_18)
|
.global GLOBAL(ashiftrt_r4_18)
|
.global GLOBAL(ashiftrt_r4_19)
|
.global GLOBAL(ashiftrt_r4_19)
|
.global GLOBAL(ashiftrt_r4_20)
|
.global GLOBAL(ashiftrt_r4_20)
|
.global GLOBAL(ashiftrt_r4_21)
|
.global GLOBAL(ashiftrt_r4_21)
|
.global GLOBAL(ashiftrt_r4_22)
|
.global GLOBAL(ashiftrt_r4_22)
|
.global GLOBAL(ashiftrt_r4_23)
|
.global GLOBAL(ashiftrt_r4_23)
|
.global GLOBAL(ashiftrt_r4_24)
|
.global GLOBAL(ashiftrt_r4_24)
|
.global GLOBAL(ashiftrt_r4_25)
|
.global GLOBAL(ashiftrt_r4_25)
|
.global GLOBAL(ashiftrt_r4_26)
|
.global GLOBAL(ashiftrt_r4_26)
|
.global GLOBAL(ashiftrt_r4_27)
|
.global GLOBAL(ashiftrt_r4_27)
|
.global GLOBAL(ashiftrt_r4_28)
|
.global GLOBAL(ashiftrt_r4_28)
|
.global GLOBAL(ashiftrt_r4_29)
|
.global GLOBAL(ashiftrt_r4_29)
|
.global GLOBAL(ashiftrt_r4_30)
|
.global GLOBAL(ashiftrt_r4_30)
|
.global GLOBAL(ashiftrt_r4_31)
|
.global GLOBAL(ashiftrt_r4_31)
|
.global GLOBAL(ashiftrt_r4_32)
|
.global GLOBAL(ashiftrt_r4_32)
|
|
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_0))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_0))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_1))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_1))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_2))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_2))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_3))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_3))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_4))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_4))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_5))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_5))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_6))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_6))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_7))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_7))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_8))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_8))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_9))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_9))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_10))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_10))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_11))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_11))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_12))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_12))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_13))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_13))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_14))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_14))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_15))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_15))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_16))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_16))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_17))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_17))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_18))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_18))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_19))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_19))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_20))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_20))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_21))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_21))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_22))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_22))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_23))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_23))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_24))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_24))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_25))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_25))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_26))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_26))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_27))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_27))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_28))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_28))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_29))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_29))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_30))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_30))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_31))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_31))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_32))
|
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_32))
|
|
|
.align 1
|
.align 1
|
GLOBAL(ashiftrt_r4_32):
|
GLOBAL(ashiftrt_r4_32):
|
GLOBAL(ashiftrt_r4_31):
|
GLOBAL(ashiftrt_r4_31):
|
rotcl r4
|
rotcl r4
|
rts
|
rts
|
subc r4,r4
|
subc r4,r4
|
|
|
GLOBAL(ashiftrt_r4_30):
|
GLOBAL(ashiftrt_r4_30):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_29):
|
GLOBAL(ashiftrt_r4_29):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_28):
|
GLOBAL(ashiftrt_r4_28):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_27):
|
GLOBAL(ashiftrt_r4_27):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_26):
|
GLOBAL(ashiftrt_r4_26):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_25):
|
GLOBAL(ashiftrt_r4_25):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_24):
|
GLOBAL(ashiftrt_r4_24):
|
shlr16 r4
|
shlr16 r4
|
shlr8 r4
|
shlr8 r4
|
rts
|
rts
|
exts.b r4,r4
|
exts.b r4,r4
|
|
|
GLOBAL(ashiftrt_r4_23):
|
GLOBAL(ashiftrt_r4_23):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_22):
|
GLOBAL(ashiftrt_r4_22):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_21):
|
GLOBAL(ashiftrt_r4_21):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_20):
|
GLOBAL(ashiftrt_r4_20):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_19):
|
GLOBAL(ashiftrt_r4_19):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_18):
|
GLOBAL(ashiftrt_r4_18):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_17):
|
GLOBAL(ashiftrt_r4_17):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_16):
|
GLOBAL(ashiftrt_r4_16):
|
shlr16 r4
|
shlr16 r4
|
rts
|
rts
|
exts.w r4,r4
|
exts.w r4,r4
|
|
|
GLOBAL(ashiftrt_r4_15):
|
GLOBAL(ashiftrt_r4_15):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_14):
|
GLOBAL(ashiftrt_r4_14):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_13):
|
GLOBAL(ashiftrt_r4_13):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_12):
|
GLOBAL(ashiftrt_r4_12):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_11):
|
GLOBAL(ashiftrt_r4_11):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_10):
|
GLOBAL(ashiftrt_r4_10):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_9):
|
GLOBAL(ashiftrt_r4_9):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_8):
|
GLOBAL(ashiftrt_r4_8):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_7):
|
GLOBAL(ashiftrt_r4_7):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_6):
|
GLOBAL(ashiftrt_r4_6):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_5):
|
GLOBAL(ashiftrt_r4_5):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_4):
|
GLOBAL(ashiftrt_r4_4):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_3):
|
GLOBAL(ashiftrt_r4_3):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_2):
|
GLOBAL(ashiftrt_r4_2):
|
shar r4
|
shar r4
|
GLOBAL(ashiftrt_r4_1):
|
GLOBAL(ashiftrt_r4_1):
|
rts
|
rts
|
shar r4
|
shar r4
|
|
|
GLOBAL(ashiftrt_r4_0):
|
GLOBAL(ashiftrt_r4_0):
|
rts
|
rts
|
nop
|
nop
|
|
|
ENDFUNC(GLOBAL(ashiftrt_r4_0))
|
ENDFUNC(GLOBAL(ashiftrt_r4_0))
|
ENDFUNC(GLOBAL(ashiftrt_r4_1))
|
ENDFUNC(GLOBAL(ashiftrt_r4_1))
|
ENDFUNC(GLOBAL(ashiftrt_r4_2))
|
ENDFUNC(GLOBAL(ashiftrt_r4_2))
|
ENDFUNC(GLOBAL(ashiftrt_r4_3))
|
ENDFUNC(GLOBAL(ashiftrt_r4_3))
|
ENDFUNC(GLOBAL(ashiftrt_r4_4))
|
ENDFUNC(GLOBAL(ashiftrt_r4_4))
|
ENDFUNC(GLOBAL(ashiftrt_r4_5))
|
ENDFUNC(GLOBAL(ashiftrt_r4_5))
|
ENDFUNC(GLOBAL(ashiftrt_r4_6))
|
ENDFUNC(GLOBAL(ashiftrt_r4_6))
|
ENDFUNC(GLOBAL(ashiftrt_r4_7))
|
ENDFUNC(GLOBAL(ashiftrt_r4_7))
|
ENDFUNC(GLOBAL(ashiftrt_r4_8))
|
ENDFUNC(GLOBAL(ashiftrt_r4_8))
|
ENDFUNC(GLOBAL(ashiftrt_r4_9))
|
ENDFUNC(GLOBAL(ashiftrt_r4_9))
|
ENDFUNC(GLOBAL(ashiftrt_r4_10))
|
ENDFUNC(GLOBAL(ashiftrt_r4_10))
|
ENDFUNC(GLOBAL(ashiftrt_r4_11))
|
ENDFUNC(GLOBAL(ashiftrt_r4_11))
|
ENDFUNC(GLOBAL(ashiftrt_r4_12))
|
ENDFUNC(GLOBAL(ashiftrt_r4_12))
|
ENDFUNC(GLOBAL(ashiftrt_r4_13))
|
ENDFUNC(GLOBAL(ashiftrt_r4_13))
|
ENDFUNC(GLOBAL(ashiftrt_r4_14))
|
ENDFUNC(GLOBAL(ashiftrt_r4_14))
|
ENDFUNC(GLOBAL(ashiftrt_r4_15))
|
ENDFUNC(GLOBAL(ashiftrt_r4_15))
|
ENDFUNC(GLOBAL(ashiftrt_r4_16))
|
ENDFUNC(GLOBAL(ashiftrt_r4_16))
|
ENDFUNC(GLOBAL(ashiftrt_r4_17))
|
ENDFUNC(GLOBAL(ashiftrt_r4_17))
|
ENDFUNC(GLOBAL(ashiftrt_r4_18))
|
ENDFUNC(GLOBAL(ashiftrt_r4_18))
|
ENDFUNC(GLOBAL(ashiftrt_r4_19))
|
ENDFUNC(GLOBAL(ashiftrt_r4_19))
|
ENDFUNC(GLOBAL(ashiftrt_r4_20))
|
ENDFUNC(GLOBAL(ashiftrt_r4_20))
|
ENDFUNC(GLOBAL(ashiftrt_r4_21))
|
ENDFUNC(GLOBAL(ashiftrt_r4_21))
|
ENDFUNC(GLOBAL(ashiftrt_r4_22))
|
ENDFUNC(GLOBAL(ashiftrt_r4_22))
|
ENDFUNC(GLOBAL(ashiftrt_r4_23))
|
ENDFUNC(GLOBAL(ashiftrt_r4_23))
|
ENDFUNC(GLOBAL(ashiftrt_r4_24))
|
ENDFUNC(GLOBAL(ashiftrt_r4_24))
|
ENDFUNC(GLOBAL(ashiftrt_r4_25))
|
ENDFUNC(GLOBAL(ashiftrt_r4_25))
|
ENDFUNC(GLOBAL(ashiftrt_r4_26))
|
ENDFUNC(GLOBAL(ashiftrt_r4_26))
|
ENDFUNC(GLOBAL(ashiftrt_r4_27))
|
ENDFUNC(GLOBAL(ashiftrt_r4_27))
|
ENDFUNC(GLOBAL(ashiftrt_r4_28))
|
ENDFUNC(GLOBAL(ashiftrt_r4_28))
|
ENDFUNC(GLOBAL(ashiftrt_r4_29))
|
ENDFUNC(GLOBAL(ashiftrt_r4_29))
|
ENDFUNC(GLOBAL(ashiftrt_r4_30))
|
ENDFUNC(GLOBAL(ashiftrt_r4_30))
|
ENDFUNC(GLOBAL(ashiftrt_r4_31))
|
ENDFUNC(GLOBAL(ashiftrt_r4_31))
|
ENDFUNC(GLOBAL(ashiftrt_r4_32))
|
ENDFUNC(GLOBAL(ashiftrt_r4_32))
|
#endif
|
#endif
|
|
|
#ifdef L_ashiftrt_n
|
#ifdef L_ashiftrt_n
|
|
|
!
|
!
|
! GLOBAL(ashrsi3)
|
! GLOBAL(ashrsi3)
|
!
|
!
|
! Entry:
|
! Entry:
|
!
|
!
|
! r4: Value to shift
|
! r4: Value to shift
|
! r5: Shifts
|
! r5: Shifts
|
!
|
!
|
! Exit:
|
! Exit:
|
!
|
!
|
! r0: Result
|
! r0: Result
|
!
|
!
|
! Destroys:
|
! Destroys:
|
!
|
!
|
! (none)
|
! (none)
|
!
|
!
|
|
|
.global GLOBAL(ashrsi3)
|
.global GLOBAL(ashrsi3)
|
HIDDEN_FUNC(GLOBAL(ashrsi3))
|
HIDDEN_FUNC(GLOBAL(ashrsi3))
|
.align 2
|
.align 2
|
GLOBAL(ashrsi3):
|
GLOBAL(ashrsi3):
|
mov #31,r0
|
mov #31,r0
|
and r0,r5
|
and r0,r5
|
mova LOCAL(ashrsi3_table),r0
|
mova LOCAL(ashrsi3_table),r0
|
mov.b @(r0,r5),r5
|
mov.b @(r0,r5),r5
|
#ifdef __sh1__
|
#ifdef __sh1__
|
add r5,r0
|
add r5,r0
|
jmp @r0
|
jmp @r0
|
#else
|
#else
|
braf r5
|
braf r5
|
#endif
|
#endif
|
mov r4,r0
|
mov r4,r0
|
|
|
.align 2
|
.align 2
|
LOCAL(ashrsi3_table):
|
LOCAL(ashrsi3_table):
|
.byte LOCAL(ashrsi3_0)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_0)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_1)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_1)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_2)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_2)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_3)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_3)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_4)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_4)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_5)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_5)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_6)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_6)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_7)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_7)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_8)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_8)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_9)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_9)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_10)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_10)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_11)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_11)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_12)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_12)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_13)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_13)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_14)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_14)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_15)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_15)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_16)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_16)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_17)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_17)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_18)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_18)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_19)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_19)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_20)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_20)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_21)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_21)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_22)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_22)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_23)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_23)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_24)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_24)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_25)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_25)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_26)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_26)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_27)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_27)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_28)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_28)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_29)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_29)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_30)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_30)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_31)-LOCAL(ashrsi3_table)
|
.byte LOCAL(ashrsi3_31)-LOCAL(ashrsi3_table)
|
|
|
LOCAL(ashrsi3_31):
|
LOCAL(ashrsi3_31):
|
rotcl r0
|
rotcl r0
|
rts
|
rts
|
subc r0,r0
|
subc r0,r0
|
|
|
LOCAL(ashrsi3_30):
|
LOCAL(ashrsi3_30):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_29):
|
LOCAL(ashrsi3_29):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_28):
|
LOCAL(ashrsi3_28):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_27):
|
LOCAL(ashrsi3_27):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_26):
|
LOCAL(ashrsi3_26):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_25):
|
LOCAL(ashrsi3_25):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_24):
|
LOCAL(ashrsi3_24):
|
shlr16 r0
|
shlr16 r0
|
shlr8 r0
|
shlr8 r0
|
rts
|
rts
|
exts.b r0,r0
|
exts.b r0,r0
|
|
|
LOCAL(ashrsi3_23):
|
LOCAL(ashrsi3_23):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_22):
|
LOCAL(ashrsi3_22):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_21):
|
LOCAL(ashrsi3_21):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_20):
|
LOCAL(ashrsi3_20):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_19):
|
LOCAL(ashrsi3_19):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_18):
|
LOCAL(ashrsi3_18):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_17):
|
LOCAL(ashrsi3_17):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_16):
|
LOCAL(ashrsi3_16):
|
shlr16 r0
|
shlr16 r0
|
rts
|
rts
|
exts.w r0,r0
|
exts.w r0,r0
|
|
|
LOCAL(ashrsi3_15):
|
LOCAL(ashrsi3_15):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_14):
|
LOCAL(ashrsi3_14):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_13):
|
LOCAL(ashrsi3_13):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_12):
|
LOCAL(ashrsi3_12):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_11):
|
LOCAL(ashrsi3_11):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_10):
|
LOCAL(ashrsi3_10):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_9):
|
LOCAL(ashrsi3_9):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_8):
|
LOCAL(ashrsi3_8):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_7):
|
LOCAL(ashrsi3_7):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_6):
|
LOCAL(ashrsi3_6):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_5):
|
LOCAL(ashrsi3_5):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_4):
|
LOCAL(ashrsi3_4):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_3):
|
LOCAL(ashrsi3_3):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_2):
|
LOCAL(ashrsi3_2):
|
shar r0
|
shar r0
|
LOCAL(ashrsi3_1):
|
LOCAL(ashrsi3_1):
|
rts
|
rts
|
shar r0
|
shar r0
|
|
|
LOCAL(ashrsi3_0):
|
LOCAL(ashrsi3_0):
|
rts
|
rts
|
nop
|
nop
|
|
|
ENDFUNC(GLOBAL(ashrsi3))
|
ENDFUNC(GLOBAL(ashrsi3))
|
#endif
|
#endif
|
|
|
#ifdef L_ashiftlt
|
#ifdef L_ashiftlt
|
|
|
!
|
!
|
! GLOBAL(ashlsi3)
|
! GLOBAL(ashlsi3)
|
!
|
!
|
! Entry:
|
! Entry:
|
!
|
!
|
! r4: Value to shift
|
! r4: Value to shift
|
! r5: Shifts
|
! r5: Shifts
|
!
|
!
|
! Exit:
|
! Exit:
|
!
|
!
|
! r0: Result
|
! r0: Result
|
!
|
!
|
! Destroys:
|
! Destroys:
|
!
|
!
|
! (none)
|
! (none)
|
!
|
!
|
.global GLOBAL(ashlsi3)
|
.global GLOBAL(ashlsi3)
|
HIDDEN_FUNC(GLOBAL(ashlsi3))
|
HIDDEN_FUNC(GLOBAL(ashlsi3))
|
.align 2
|
.align 2
|
GLOBAL(ashlsi3):
|
GLOBAL(ashlsi3):
|
mov #31,r0
|
mov #31,r0
|
and r0,r5
|
and r0,r5
|
mova LOCAL(ashlsi3_table),r0
|
mova LOCAL(ashlsi3_table),r0
|
mov.b @(r0,r5),r5
|
mov.b @(r0,r5),r5
|
#ifdef __sh1__
|
#ifdef __sh1__
|
add r5,r0
|
add r5,r0
|
jmp @r0
|
jmp @r0
|
#else
|
#else
|
braf r5
|
braf r5
|
#endif
|
#endif
|
mov r4,r0
|
mov r4,r0
|
|
|
.align 2
|
.align 2
|
LOCAL(ashlsi3_table):
|
LOCAL(ashlsi3_table):
|
.byte LOCAL(ashlsi3_0)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_0)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_1)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_1)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_2)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_2)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_3)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_3)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_4)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_4)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_5)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_5)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_6)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_6)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_7)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_7)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_8)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_8)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_9)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_9)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_10)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_10)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_11)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_11)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_12)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_12)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_13)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_13)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_14)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_14)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_15)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_15)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_16)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_16)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_17)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_17)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_18)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_18)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_19)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_19)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_20)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_20)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_21)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_21)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_22)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_22)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_23)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_23)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_24)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_24)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_25)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_25)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_26)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_26)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_27)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_27)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_28)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_28)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_29)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_29)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_30)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_30)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_31)-LOCAL(ashlsi3_table)
|
.byte LOCAL(ashlsi3_31)-LOCAL(ashlsi3_table)
|
|
|
LOCAL(ashlsi3_6):
|
LOCAL(ashlsi3_6):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_4):
|
LOCAL(ashlsi3_4):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_2):
|
LOCAL(ashlsi3_2):
|
rts
|
rts
|
shll2 r0
|
shll2 r0
|
|
|
LOCAL(ashlsi3_7):
|
LOCAL(ashlsi3_7):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_5):
|
LOCAL(ashlsi3_5):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_3):
|
LOCAL(ashlsi3_3):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_1):
|
LOCAL(ashlsi3_1):
|
rts
|
rts
|
shll r0
|
shll r0
|
|
|
LOCAL(ashlsi3_14):
|
LOCAL(ashlsi3_14):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_12):
|
LOCAL(ashlsi3_12):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_10):
|
LOCAL(ashlsi3_10):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_8):
|
LOCAL(ashlsi3_8):
|
rts
|
rts
|
shll8 r0
|
shll8 r0
|
|
|
LOCAL(ashlsi3_15):
|
LOCAL(ashlsi3_15):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_13):
|
LOCAL(ashlsi3_13):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_11):
|
LOCAL(ashlsi3_11):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_9):
|
LOCAL(ashlsi3_9):
|
shll8 r0
|
shll8 r0
|
rts
|
rts
|
shll r0
|
shll r0
|
|
|
LOCAL(ashlsi3_22):
|
LOCAL(ashlsi3_22):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_20):
|
LOCAL(ashlsi3_20):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_18):
|
LOCAL(ashlsi3_18):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_16):
|
LOCAL(ashlsi3_16):
|
rts
|
rts
|
shll16 r0
|
shll16 r0
|
|
|
LOCAL(ashlsi3_23):
|
LOCAL(ashlsi3_23):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_21):
|
LOCAL(ashlsi3_21):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_19):
|
LOCAL(ashlsi3_19):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_17):
|
LOCAL(ashlsi3_17):
|
shll16 r0
|
shll16 r0
|
rts
|
rts
|
shll r0
|
shll r0
|
|
|
LOCAL(ashlsi3_30):
|
LOCAL(ashlsi3_30):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_28):
|
LOCAL(ashlsi3_28):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_26):
|
LOCAL(ashlsi3_26):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_24):
|
LOCAL(ashlsi3_24):
|
shll16 r0
|
shll16 r0
|
rts
|
rts
|
shll8 r0
|
shll8 r0
|
|
|
LOCAL(ashlsi3_31):
|
LOCAL(ashlsi3_31):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_29):
|
LOCAL(ashlsi3_29):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_27):
|
LOCAL(ashlsi3_27):
|
shll2 r0
|
shll2 r0
|
LOCAL(ashlsi3_25):
|
LOCAL(ashlsi3_25):
|
shll16 r0
|
shll16 r0
|
shll8 r0
|
shll8 r0
|
rts
|
rts
|
shll r0
|
shll r0
|
|
|
LOCAL(ashlsi3_0):
|
LOCAL(ashlsi3_0):
|
rts
|
rts
|
nop
|
nop
|
|
|
ENDFUNC(GLOBAL(ashlsi3))
|
ENDFUNC(GLOBAL(ashlsi3))
|
#endif
|
#endif
|
|
|
#ifdef L_lshiftrt
|
#ifdef L_lshiftrt
|
|
|
!
|
!
|
! GLOBAL(lshrsi3)
|
! GLOBAL(lshrsi3)
|
!
|
!
|
! Entry:
|
! Entry:
|
!
|
!
|
! r4: Value to shift
|
! r4: Value to shift
|
! r5: Shifts
|
! r5: Shifts
|
!
|
!
|
! Exit:
|
! Exit:
|
!
|
!
|
! r0: Result
|
! r0: Result
|
!
|
!
|
! Destroys:
|
! Destroys:
|
!
|
!
|
! (none)
|
! (none)
|
!
|
!
|
.global GLOBAL(lshrsi3)
|
.global GLOBAL(lshrsi3)
|
HIDDEN_FUNC(GLOBAL(lshrsi3))
|
HIDDEN_FUNC(GLOBAL(lshrsi3))
|
.align 2
|
.align 2
|
GLOBAL(lshrsi3):
|
GLOBAL(lshrsi3):
|
mov #31,r0
|
mov #31,r0
|
and r0,r5
|
and r0,r5
|
mova LOCAL(lshrsi3_table),r0
|
mova LOCAL(lshrsi3_table),r0
|
mov.b @(r0,r5),r5
|
mov.b @(r0,r5),r5
|
#ifdef __sh1__
|
#ifdef __sh1__
|
add r5,r0
|
add r5,r0
|
jmp @r0
|
jmp @r0
|
#else
|
#else
|
braf r5
|
braf r5
|
#endif
|
#endif
|
mov r4,r0
|
mov r4,r0
|
|
|
.align 2
|
.align 2
|
LOCAL(lshrsi3_table):
|
LOCAL(lshrsi3_table):
|
.byte LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)
|
.byte LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)
|
|
|
LOCAL(lshrsi3_6):
|
LOCAL(lshrsi3_6):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_4):
|
LOCAL(lshrsi3_4):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_2):
|
LOCAL(lshrsi3_2):
|
rts
|
rts
|
shlr2 r0
|
shlr2 r0
|
|
|
LOCAL(lshrsi3_7):
|
LOCAL(lshrsi3_7):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_5):
|
LOCAL(lshrsi3_5):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_3):
|
LOCAL(lshrsi3_3):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_1):
|
LOCAL(lshrsi3_1):
|
rts
|
rts
|
shlr r0
|
shlr r0
|
|
|
LOCAL(lshrsi3_14):
|
LOCAL(lshrsi3_14):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_12):
|
LOCAL(lshrsi3_12):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_10):
|
LOCAL(lshrsi3_10):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_8):
|
LOCAL(lshrsi3_8):
|
rts
|
rts
|
shlr8 r0
|
shlr8 r0
|
|
|
LOCAL(lshrsi3_15):
|
LOCAL(lshrsi3_15):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_13):
|
LOCAL(lshrsi3_13):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_11):
|
LOCAL(lshrsi3_11):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_9):
|
LOCAL(lshrsi3_9):
|
shlr8 r0
|
shlr8 r0
|
rts
|
rts
|
shlr r0
|
shlr r0
|
|
|
LOCAL(lshrsi3_22):
|
LOCAL(lshrsi3_22):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_20):
|
LOCAL(lshrsi3_20):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_18):
|
LOCAL(lshrsi3_18):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_16):
|
LOCAL(lshrsi3_16):
|
rts
|
rts
|
shlr16 r0
|
shlr16 r0
|
|
|
LOCAL(lshrsi3_23):
|
LOCAL(lshrsi3_23):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_21):
|
LOCAL(lshrsi3_21):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_19):
|
LOCAL(lshrsi3_19):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_17):
|
LOCAL(lshrsi3_17):
|
shlr16 r0
|
shlr16 r0
|
rts
|
rts
|
shlr r0
|
shlr r0
|
|
|
LOCAL(lshrsi3_30):
|
LOCAL(lshrsi3_30):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_28):
|
LOCAL(lshrsi3_28):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_26):
|
LOCAL(lshrsi3_26):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_24):
|
LOCAL(lshrsi3_24):
|
shlr16 r0
|
shlr16 r0
|
rts
|
rts
|
shlr8 r0
|
shlr8 r0
|
|
|
LOCAL(lshrsi3_31):
|
LOCAL(lshrsi3_31):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_29):
|
LOCAL(lshrsi3_29):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_27):
|
LOCAL(lshrsi3_27):
|
shlr2 r0
|
shlr2 r0
|
LOCAL(lshrsi3_25):
|
LOCAL(lshrsi3_25):
|
shlr16 r0
|
shlr16 r0
|
shlr8 r0
|
shlr8 r0
|
rts
|
rts
|
shlr r0
|
shlr r0
|
|
|
LOCAL(lshrsi3_0):
|
LOCAL(lshrsi3_0):
|
rts
|
rts
|
nop
|
nop
|
|
|
ENDFUNC(GLOBAL(lshrsi3))
|
ENDFUNC(GLOBAL(lshrsi3))
|
#endif
|
#endif
|
|
|
#ifdef L_movmem
|
#ifdef L_movmem
|
.text
|
.text
|
.balign 4
|
.balign 4
|
.global GLOBAL(movmem)
|
.global GLOBAL(movmem)
|
HIDDEN_FUNC(GLOBAL(movmem))
|
HIDDEN_FUNC(GLOBAL(movmem))
|
HIDDEN_ALIAS(movstr,movmem)
|
HIDDEN_ALIAS(movstr,movmem)
|
/* This would be a lot simpler if r6 contained the byte count
|
/* This would be a lot simpler if r6 contained the byte count
|
minus 64, and we wouldn't be called here for a byte count of 64. */
|
minus 64, and we wouldn't be called here for a byte count of 64. */
|
GLOBAL(movmem):
|
GLOBAL(movmem):
|
sts.l pr,@-r15
|
sts.l pr,@-r15
|
shll2 r6
|
shll2 r6
|
bsr GLOBAL(movmemSI52+2)
|
bsr GLOBAL(movmemSI52+2)
|
mov.l @(48,r5),r0
|
mov.l @(48,r5),r0
|
.balign 4
|
.balign 4
|
LOCAL(movmem_loop): /* Reached with rts */
|
LOCAL(movmem_loop): /* Reached with rts */
|
mov.l @(60,r5),r0
|
mov.l @(60,r5),r0
|
add #-64,r6
|
add #-64,r6
|
mov.l r0,@(60,r4)
|
mov.l r0,@(60,r4)
|
tst r6,r6
|
tst r6,r6
|
mov.l @(56,r5),r0
|
mov.l @(56,r5),r0
|
bt LOCAL(movmem_done)
|
bt LOCAL(movmem_done)
|
mov.l r0,@(56,r4)
|
mov.l r0,@(56,r4)
|
cmp/pl r6
|
cmp/pl r6
|
mov.l @(52,r5),r0
|
mov.l @(52,r5),r0
|
add #64,r5
|
add #64,r5
|
mov.l r0,@(52,r4)
|
mov.l r0,@(52,r4)
|
add #64,r4
|
add #64,r4
|
bt GLOBAL(movmemSI52)
|
bt GLOBAL(movmemSI52)
|
! done all the large groups, do the remainder
|
! done all the large groups, do the remainder
|
! jump to movmem+
|
! jump to movmem+
|
mova GLOBAL(movmemSI4)+4,r0
|
mova GLOBAL(movmemSI4)+4,r0
|
add r6,r0
|
add r6,r0
|
jmp @r0
|
jmp @r0
|
LOCAL(movmem_done): ! share slot insn, works out aligned.
|
LOCAL(movmem_done): ! share slot insn, works out aligned.
|
lds.l @r15+,pr
|
lds.l @r15+,pr
|
mov.l r0,@(56,r4)
|
mov.l r0,@(56,r4)
|
mov.l @(52,r5),r0
|
mov.l @(52,r5),r0
|
rts
|
rts
|
mov.l r0,@(52,r4)
|
mov.l r0,@(52,r4)
|
.balign 4
|
.balign 4
|
! ??? We need aliases movstr* for movmem* for the older libraries. These
|
! ??? We need aliases movstr* for movmem* for the older libraries. These
|
! aliases will be removed at the some point in the future.
|
! aliases will be removed at the some point in the future.
|
.global GLOBAL(movmemSI64)
|
.global GLOBAL(movmemSI64)
|
HIDDEN_FUNC(GLOBAL(movmemSI64))
|
HIDDEN_FUNC(GLOBAL(movmemSI64))
|
HIDDEN_ALIAS(movstrSI64,movmemSI64)
|
HIDDEN_ALIAS(movstrSI64,movmemSI64)
|
GLOBAL(movmemSI64):
|
GLOBAL(movmemSI64):
|
mov.l @(60,r5),r0
|
mov.l @(60,r5),r0
|
mov.l r0,@(60,r4)
|
mov.l r0,@(60,r4)
|
.global GLOBAL(movmemSI60)
|
.global GLOBAL(movmemSI60)
|
HIDDEN_FUNC(GLOBAL(movmemSI60))
|
HIDDEN_FUNC(GLOBAL(movmemSI60))
|
HIDDEN_ALIAS(movstrSI60,movmemSI60)
|
HIDDEN_ALIAS(movstrSI60,movmemSI60)
|
GLOBAL(movmemSI60):
|
GLOBAL(movmemSI60):
|
mov.l @(56,r5),r0
|
mov.l @(56,r5),r0
|
mov.l r0,@(56,r4)
|
mov.l r0,@(56,r4)
|
.global GLOBAL(movmemSI56)
|
.global GLOBAL(movmemSI56)
|
HIDDEN_FUNC(GLOBAL(movmemSI56))
|
HIDDEN_FUNC(GLOBAL(movmemSI56))
|
HIDDEN_ALIAS(movstrSI56,movmemSI56)
|
HIDDEN_ALIAS(movstrSI56,movmemSI56)
|
GLOBAL(movmemSI56):
|
GLOBAL(movmemSI56):
|
mov.l @(52,r5),r0
|
mov.l @(52,r5),r0
|
mov.l r0,@(52,r4)
|
mov.l r0,@(52,r4)
|
.global GLOBAL(movmemSI52)
|
.global GLOBAL(movmemSI52)
|
HIDDEN_FUNC(GLOBAL(movmemSI52))
|
HIDDEN_FUNC(GLOBAL(movmemSI52))
|
HIDDEN_ALIAS(movstrSI52,movmemSI52)
|
HIDDEN_ALIAS(movstrSI52,movmemSI52)
|
GLOBAL(movmemSI52):
|
GLOBAL(movmemSI52):
|
mov.l @(48,r5),r0
|
mov.l @(48,r5),r0
|
mov.l r0,@(48,r4)
|
mov.l r0,@(48,r4)
|
.global GLOBAL(movmemSI48)
|
.global GLOBAL(movmemSI48)
|
HIDDEN_FUNC(GLOBAL(movmemSI48))
|
HIDDEN_FUNC(GLOBAL(movmemSI48))
|
HIDDEN_ALIAS(movstrSI48,movmemSI48)
|
HIDDEN_ALIAS(movstrSI48,movmemSI48)
|
GLOBAL(movmemSI48):
|
GLOBAL(movmemSI48):
|
mov.l @(44,r5),r0
|
mov.l @(44,r5),r0
|
mov.l r0,@(44,r4)
|
mov.l r0,@(44,r4)
|
.global GLOBAL(movmemSI44)
|
.global GLOBAL(movmemSI44)
|
HIDDEN_FUNC(GLOBAL(movmemSI44))
|
HIDDEN_FUNC(GLOBAL(movmemSI44))
|
HIDDEN_ALIAS(movstrSI44,movmemSI44)
|
HIDDEN_ALIAS(movstrSI44,movmemSI44)
|
GLOBAL(movmemSI44):
|
GLOBAL(movmemSI44):
|
mov.l @(40,r5),r0
|
mov.l @(40,r5),r0
|
mov.l r0,@(40,r4)
|
mov.l r0,@(40,r4)
|
.global GLOBAL(movmemSI40)
|
.global GLOBAL(movmemSI40)
|
HIDDEN_FUNC(GLOBAL(movmemSI40))
|
HIDDEN_FUNC(GLOBAL(movmemSI40))
|
HIDDEN_ALIAS(movstrSI40,movmemSI40)
|
HIDDEN_ALIAS(movstrSI40,movmemSI40)
|
GLOBAL(movmemSI40):
|
GLOBAL(movmemSI40):
|
mov.l @(36,r5),r0
|
mov.l @(36,r5),r0
|
mov.l r0,@(36,r4)
|
mov.l r0,@(36,r4)
|
.global GLOBAL(movmemSI36)
|
.global GLOBAL(movmemSI36)
|
HIDDEN_FUNC(GLOBAL(movmemSI36))
|
HIDDEN_FUNC(GLOBAL(movmemSI36))
|
HIDDEN_ALIAS(movstrSI36,movmemSI36)
|
HIDDEN_ALIAS(movstrSI36,movmemSI36)
|
GLOBAL(movmemSI36):
|
GLOBAL(movmemSI36):
|
mov.l @(32,r5),r0
|
mov.l @(32,r5),r0
|
mov.l r0,@(32,r4)
|
mov.l r0,@(32,r4)
|
.global GLOBAL(movmemSI32)
|
.global GLOBAL(movmemSI32)
|
HIDDEN_FUNC(GLOBAL(movmemSI32))
|
HIDDEN_FUNC(GLOBAL(movmemSI32))
|
HIDDEN_ALIAS(movstrSI32,movmemSI32)
|
HIDDEN_ALIAS(movstrSI32,movmemSI32)
|
GLOBAL(movmemSI32):
|
GLOBAL(movmemSI32):
|
mov.l @(28,r5),r0
|
mov.l @(28,r5),r0
|
mov.l r0,@(28,r4)
|
mov.l r0,@(28,r4)
|
.global GLOBAL(movmemSI28)
|
.global GLOBAL(movmemSI28)
|
HIDDEN_FUNC(GLOBAL(movmemSI28))
|
HIDDEN_FUNC(GLOBAL(movmemSI28))
|
HIDDEN_ALIAS(movstrSI28,movmemSI28)
|
HIDDEN_ALIAS(movstrSI28,movmemSI28)
|
GLOBAL(movmemSI28):
|
GLOBAL(movmemSI28):
|
mov.l @(24,r5),r0
|
mov.l @(24,r5),r0
|
mov.l r0,@(24,r4)
|
mov.l r0,@(24,r4)
|
.global GLOBAL(movmemSI24)
|
.global GLOBAL(movmemSI24)
|
HIDDEN_FUNC(GLOBAL(movmemSI24))
|
HIDDEN_FUNC(GLOBAL(movmemSI24))
|
HIDDEN_ALIAS(movstrSI24,movmemSI24)
|
HIDDEN_ALIAS(movstrSI24,movmemSI24)
|
GLOBAL(movmemSI24):
|
GLOBAL(movmemSI24):
|
mov.l @(20,r5),r0
|
mov.l @(20,r5),r0
|
mov.l r0,@(20,r4)
|
mov.l r0,@(20,r4)
|
.global GLOBAL(movmemSI20)
|
.global GLOBAL(movmemSI20)
|
HIDDEN_FUNC(GLOBAL(movmemSI20))
|
HIDDEN_FUNC(GLOBAL(movmemSI20))
|
HIDDEN_ALIAS(movstrSI20,movmemSI20)
|
HIDDEN_ALIAS(movstrSI20,movmemSI20)
|
GLOBAL(movmemSI20):
|
GLOBAL(movmemSI20):
|
mov.l @(16,r5),r0
|
mov.l @(16,r5),r0
|
mov.l r0,@(16,r4)
|
mov.l r0,@(16,r4)
|
.global GLOBAL(movmemSI16)
|
.global GLOBAL(movmemSI16)
|
HIDDEN_FUNC(GLOBAL(movmemSI16))
|
HIDDEN_FUNC(GLOBAL(movmemSI16))
|
HIDDEN_ALIAS(movstrSI16,movmemSI16)
|
HIDDEN_ALIAS(movstrSI16,movmemSI16)
|
GLOBAL(movmemSI16):
|
GLOBAL(movmemSI16):
|
mov.l @(12,r5),r0
|
mov.l @(12,r5),r0
|
mov.l r0,@(12,r4)
|
mov.l r0,@(12,r4)
|
.global GLOBAL(movmemSI12)
|
.global GLOBAL(movmemSI12)
|
HIDDEN_FUNC(GLOBAL(movmemSI12))
|
HIDDEN_FUNC(GLOBAL(movmemSI12))
|
HIDDEN_ALIAS(movstrSI12,movmemSI12)
|
HIDDEN_ALIAS(movstrSI12,movmemSI12)
|
GLOBAL(movmemSI12):
|
GLOBAL(movmemSI12):
|
mov.l @(8,r5),r0
|
mov.l @(8,r5),r0
|
mov.l r0,@(8,r4)
|
mov.l r0,@(8,r4)
|
.global GLOBAL(movmemSI8)
|
.global GLOBAL(movmemSI8)
|
HIDDEN_FUNC(GLOBAL(movmemSI8))
|
HIDDEN_FUNC(GLOBAL(movmemSI8))
|
HIDDEN_ALIAS(movstrSI8,movmemSI8)
|
HIDDEN_ALIAS(movstrSI8,movmemSI8)
|
GLOBAL(movmemSI8):
|
GLOBAL(movmemSI8):
|
mov.l @(4,r5),r0
|
mov.l @(4,r5),r0
|
mov.l r0,@(4,r4)
|
mov.l r0,@(4,r4)
|
.global GLOBAL(movmemSI4)
|
.global GLOBAL(movmemSI4)
|
HIDDEN_FUNC(GLOBAL(movmemSI4))
|
HIDDEN_FUNC(GLOBAL(movmemSI4))
|
HIDDEN_ALIAS(movstrSI4,movmemSI4)
|
HIDDEN_ALIAS(movstrSI4,movmemSI4)
|
GLOBAL(movmemSI4):
|
GLOBAL(movmemSI4):
|
mov.l @(0,r5),r0
|
mov.l @(0,r5),r0
|
rts
|
rts
|
mov.l r0,@(0,r4)
|
mov.l r0,@(0,r4)
|
|
|
ENDFUNC(GLOBAL(movmemSI64))
|
ENDFUNC(GLOBAL(movmemSI64))
|
ENDFUNC(GLOBAL(movmemSI60))
|
ENDFUNC(GLOBAL(movmemSI60))
|
ENDFUNC(GLOBAL(movmemSI56))
|
ENDFUNC(GLOBAL(movmemSI56))
|
ENDFUNC(GLOBAL(movmemSI52))
|
ENDFUNC(GLOBAL(movmemSI52))
|
ENDFUNC(GLOBAL(movmemSI48))
|
ENDFUNC(GLOBAL(movmemSI48))
|
ENDFUNC(GLOBAL(movmemSI44))
|
ENDFUNC(GLOBAL(movmemSI44))
|
ENDFUNC(GLOBAL(movmemSI40))
|
ENDFUNC(GLOBAL(movmemSI40))
|
ENDFUNC(GLOBAL(movmemSI36))
|
ENDFUNC(GLOBAL(movmemSI36))
|
ENDFUNC(GLOBAL(movmemSI32))
|
ENDFUNC(GLOBAL(movmemSI32))
|
ENDFUNC(GLOBAL(movmemSI28))
|
ENDFUNC(GLOBAL(movmemSI28))
|
ENDFUNC(GLOBAL(movmemSI24))
|
ENDFUNC(GLOBAL(movmemSI24))
|
ENDFUNC(GLOBAL(movmemSI20))
|
ENDFUNC(GLOBAL(movmemSI20))
|
ENDFUNC(GLOBAL(movmemSI16))
|
ENDFUNC(GLOBAL(movmemSI16))
|
ENDFUNC(GLOBAL(movmemSI12))
|
ENDFUNC(GLOBAL(movmemSI12))
|
ENDFUNC(GLOBAL(movmemSI8))
|
ENDFUNC(GLOBAL(movmemSI8))
|
ENDFUNC(GLOBAL(movmemSI4))
|
ENDFUNC(GLOBAL(movmemSI4))
|
ENDFUNC(GLOBAL(movmem))
|
ENDFUNC(GLOBAL(movmem))
|
#endif
|
#endif
|
|
|
#ifdef L_movmem_i4
|
#ifdef L_movmem_i4
|
.text
|
.text
|
.global GLOBAL(movmem_i4_even)
|
.global GLOBAL(movmem_i4_even)
|
.global GLOBAL(movmem_i4_odd)
|
.global GLOBAL(movmem_i4_odd)
|
.global GLOBAL(movmemSI12_i4)
|
.global GLOBAL(movmemSI12_i4)
|
|
|
HIDDEN_FUNC(GLOBAL(movmem_i4_even))
|
HIDDEN_FUNC(GLOBAL(movmem_i4_even))
|
HIDDEN_FUNC(GLOBAL(movmem_i4_odd))
|
HIDDEN_FUNC(GLOBAL(movmem_i4_odd))
|
HIDDEN_FUNC(GLOBAL(movmemSI12_i4))
|
HIDDEN_FUNC(GLOBAL(movmemSI12_i4))
|
|
|
HIDDEN_ALIAS(movstr_i4_even,movmem_i4_even)
|
HIDDEN_ALIAS(movstr_i4_even,movmem_i4_even)
|
HIDDEN_ALIAS(movstr_i4_odd,movmem_i4_odd)
|
HIDDEN_ALIAS(movstr_i4_odd,movmem_i4_odd)
|
HIDDEN_ALIAS(movstrSI12_i4,movmemSI12_i4)
|
HIDDEN_ALIAS(movstrSI12_i4,movmemSI12_i4)
|
|
|
.p2align 5
|
.p2align 5
|
L_movmem_2mod4_end:
|
L_movmem_2mod4_end:
|
mov.l r0,@(16,r4)
|
mov.l r0,@(16,r4)
|
rts
|
rts
|
mov.l r1,@(20,r4)
|
mov.l r1,@(20,r4)
|
|
|
.p2align 2
|
.p2align 2
|
|
|
GLOBAL(movmem_i4_even):
|
GLOBAL(movmem_i4_even):
|
mov.l @r5+,r0
|
mov.l @r5+,r0
|
bra L_movmem_start_even
|
bra L_movmem_start_even
|
mov.l @r5+,r1
|
mov.l @r5+,r1
|
|
|
GLOBAL(movmem_i4_odd):
|
GLOBAL(movmem_i4_odd):
|
mov.l @r5+,r1
|
mov.l @r5+,r1
|
add #-4,r4
|
add #-4,r4
|
mov.l @r5+,r2
|
mov.l @r5+,r2
|
mov.l @r5+,r3
|
mov.l @r5+,r3
|
mov.l r1,@(4,r4)
|
mov.l r1,@(4,r4)
|
mov.l r2,@(8,r4)
|
mov.l r2,@(8,r4)
|
|
|
L_movmem_loop:
|
L_movmem_loop:
|
mov.l r3,@(12,r4)
|
mov.l r3,@(12,r4)
|
dt r6
|
dt r6
|
mov.l @r5+,r0
|
mov.l @r5+,r0
|
bt/s L_movmem_2mod4_end
|
bt/s L_movmem_2mod4_end
|
mov.l @r5+,r1
|
mov.l @r5+,r1
|
add #16,r4
|
add #16,r4
|
L_movmem_start_even:
|
L_movmem_start_even:
|
mov.l @r5+,r2
|
mov.l @r5+,r2
|
mov.l @r5+,r3
|
mov.l @r5+,r3
|
mov.l r0,@r4
|
mov.l r0,@r4
|
dt r6
|
dt r6
|
mov.l r1,@(4,r4)
|
mov.l r1,@(4,r4)
|
bf/s L_movmem_loop
|
bf/s L_movmem_loop
|
mov.l r2,@(8,r4)
|
mov.l r2,@(8,r4)
|
rts
|
rts
|
mov.l r3,@(12,r4)
|
mov.l r3,@(12,r4)
|
|
|
ENDFUNC(GLOBAL(movmem_i4_even))
|
ENDFUNC(GLOBAL(movmem_i4_even))
|
ENDFUNC(GLOBAL(movmem_i4_odd))
|
ENDFUNC(GLOBAL(movmem_i4_odd))
|
|
|
.p2align 4
|
.p2align 4
|
GLOBAL(movmemSI12_i4):
|
GLOBAL(movmemSI12_i4):
|
mov.l @r5,r0
|
mov.l @r5,r0
|
mov.l @(4,r5),r1
|
mov.l @(4,r5),r1
|
mov.l @(8,r5),r2
|
mov.l @(8,r5),r2
|
mov.l r0,@r4
|
mov.l r0,@r4
|
mov.l r1,@(4,r4)
|
mov.l r1,@(4,r4)
|
rts
|
rts
|
mov.l r2,@(8,r4)
|
mov.l r2,@(8,r4)
|
|
|
ENDFUNC(GLOBAL(movmemSI12_i4))
|
ENDFUNC(GLOBAL(movmemSI12_i4))
|
#endif
|
#endif
|
|
|
#ifdef L_mulsi3
|
#ifdef L_mulsi3
|
|
|
|
|
.global GLOBAL(mulsi3)
|
.global GLOBAL(mulsi3)
|
HIDDEN_FUNC(GLOBAL(mulsi3))
|
HIDDEN_FUNC(GLOBAL(mulsi3))
|
|
|
! r4 = aabb
|
! r4 = aabb
|
! r5 = ccdd
|
! r5 = ccdd
|
! r0 = aabb*ccdd via partial products
|
! r0 = aabb*ccdd via partial products
|
!
|
!
|
! if aa == 0 and cc = 0
|
! if aa == 0 and cc = 0
|
! r0 = bb*dd
|
! r0 = bb*dd
|
!
|
!
|
! else
|
! else
|
! aa = bb*dd + (aa*dd*65536) + (cc*bb*65536)
|
! aa = bb*dd + (aa*dd*65536) + (cc*bb*65536)
|
!
|
!
|
|
|
GLOBAL(mulsi3):
|
GLOBAL(mulsi3):
|
mulu.w r4,r5 ! multiply the lsws macl=bb*dd
|
mulu.w r4,r5 ! multiply the lsws macl=bb*dd
|
mov r5,r3 ! r3 = ccdd
|
mov r5,r3 ! r3 = ccdd
|
swap.w r4,r2 ! r2 = bbaa
|
swap.w r4,r2 ! r2 = bbaa
|
xtrct r2,r3 ! r3 = aacc
|
xtrct r2,r3 ! r3 = aacc
|
tst r3,r3 ! msws zero ?
|
tst r3,r3 ! msws zero ?
|
bf hiset
|
bf hiset
|
rts ! yes - then we have the answer
|
rts ! yes - then we have the answer
|
sts macl,r0
|
sts macl,r0
|
|
|
hiset: sts macl,r0 ! r0 = bb*dd
|
hiset: sts macl,r0 ! r0 = bb*dd
|
mulu.w r2,r5 ! brewing macl = aa*dd
|
mulu.w r2,r5 ! brewing macl = aa*dd
|
sts macl,r1
|
sts macl,r1
|
mulu.w r3,r4 ! brewing macl = cc*bb
|
mulu.w r3,r4 ! brewing macl = cc*bb
|
sts macl,r2
|
sts macl,r2
|
add r1,r2
|
add r1,r2
|
shll16 r2
|
shll16 r2
|
rts
|
rts
|
add r2,r0
|
add r2,r0
|
|
|
ENDFUNC(GLOBAL(mulsi3))
|
ENDFUNC(GLOBAL(mulsi3))
|
#endif
|
#endif
|
#endif /* ! __SH5__ */
|
#endif /* ! __SH5__ */
|
#ifdef L_sdivsi3_i4
|
#ifdef L_sdivsi3_i4
|
.title "SH DIVIDE"
|
.title "SH DIVIDE"
|
!! 4 byte integer Divide code for the Renesas SH
|
!! 4 byte integer Divide code for the Renesas SH
|
#ifdef __SH4__
|
#ifdef __SH4__
|
!! args in r4 and r5, result in fpul, clobber dr0, dr2
|
!! args in r4 and r5, result in fpul, clobber dr0, dr2
|
|
|
.global GLOBAL(sdivsi3_i4)
|
.global GLOBAL(sdivsi3_i4)
|
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
|
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
|
GLOBAL(sdivsi3_i4):
|
GLOBAL(sdivsi3_i4):
|
lds r4,fpul
|
lds r4,fpul
|
float fpul,dr0
|
float fpul,dr0
|
lds r5,fpul
|
lds r5,fpul
|
float fpul,dr2
|
float fpul,dr2
|
fdiv dr2,dr0
|
fdiv dr2,dr0
|
rts
|
rts
|
ftrc dr0,fpul
|
ftrc dr0,fpul
|
|
|
ENDFUNC(GLOBAL(sdivsi3_i4))
|
ENDFUNC(GLOBAL(sdivsi3_i4))
|
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || (defined (__SH5__) && ! defined __SH4_NOFPU__)
|
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || (defined (__SH5__) && ! defined __SH4_NOFPU__)
|
!! args in r4 and r5, result in fpul, clobber r2, dr0, dr2
|
!! args in r4 and r5, result in fpul, clobber r2, dr0, dr2
|
|
|
#if ! __SH5__ || __SH5__ == 32
|
#if ! __SH5__ || __SH5__ == 32
|
#if __SH5__
|
#if __SH5__
|
.mode SHcompact
|
.mode SHcompact
|
#endif
|
#endif
|
.global GLOBAL(sdivsi3_i4)
|
.global GLOBAL(sdivsi3_i4)
|
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
|
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
|
GLOBAL(sdivsi3_i4):
|
GLOBAL(sdivsi3_i4):
|
sts.l fpscr,@-r15
|
sts.l fpscr,@-r15
|
mov #8,r2
|
mov #8,r2
|
swap.w r2,r2
|
swap.w r2,r2
|
lds r2,fpscr
|
lds r2,fpscr
|
lds r4,fpul
|
lds r4,fpul
|
float fpul,dr0
|
float fpul,dr0
|
lds r5,fpul
|
lds r5,fpul
|
float fpul,dr2
|
float fpul,dr2
|
fdiv dr2,dr0
|
fdiv dr2,dr0
|
ftrc dr0,fpul
|
ftrc dr0,fpul
|
rts
|
rts
|
lds.l @r15+,fpscr
|
lds.l @r15+,fpscr
|
|
|
ENDFUNC(GLOBAL(sdivsi3_i4))
|
ENDFUNC(GLOBAL(sdivsi3_i4))
|
#endif /* ! __SH5__ || __SH5__ == 32 */
|
#endif /* ! __SH5__ || __SH5__ == 32 */
|
#endif /* ! __SH4__ */
|
#endif /* ! __SH4__ */
|
#endif
|
#endif
|
|
|
#ifdef L_sdivsi3
|
#ifdef L_sdivsi3
|
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
|
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
|
sh2e/sh3e code. */
|
sh2e/sh3e code. */
|
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
|
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
|
!!
|
!!
|
!! Steve Chamberlain
|
!! Steve Chamberlain
|
!! sac@cygnus.com
|
!! sac@cygnus.com
|
!!
|
!!
|
!!
|
!!
|
|
|
!! args in r4 and r5, result in r0 clobber r1, r2, r3, and t bit
|
!! args in r4 and r5, result in r0 clobber r1, r2, r3, and t bit
|
|
|
.global GLOBAL(sdivsi3)
|
.global GLOBAL(sdivsi3)
|
#if __SHMEDIA__
|
#if __SHMEDIA__
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
#else
|
#else
|
.text
|
.text
|
#endif
|
#endif
|
.align 2
|
.align 2
|
#if 0
|
#if 0
|
/* The assembly code that follows is a hand-optimized version of the C
|
/* The assembly code that follows is a hand-optimized version of the C
|
code that follows. Note that the registers that are modified are
|
code that follows. Note that the registers that are modified are
|
exactly those listed as clobbered in the patterns divsi3_i1 and
|
exactly those listed as clobbered in the patterns divsi3_i1 and
|
divsi3_i1_media.
|
divsi3_i1_media.
|
|
|
int __sdivsi3 (i, j)
|
int __sdivsi3 (i, j)
|
int i, j;
|
int i, j;
|
{
|
{
|
register unsigned long long r18 asm ("r18");
|
register unsigned long long r18 asm ("r18");
|
register unsigned long long r19 asm ("r19");
|
register unsigned long long r19 asm ("r19");
|
register unsigned long long r0 asm ("r0") = 0;
|
register unsigned long long r0 asm ("r0") = 0;
|
register unsigned long long r1 asm ("r1") = 1;
|
register unsigned long long r1 asm ("r1") = 1;
|
register int r2 asm ("r2") = i >> 31;
|
register int r2 asm ("r2") = i >> 31;
|
register int r3 asm ("r3") = j >> 31;
|
register int r3 asm ("r3") = j >> 31;
|
|
|
r2 = r2 ? r2 : r1;
|
r2 = r2 ? r2 : r1;
|
r3 = r3 ? r3 : r1;
|
r3 = r3 ? r3 : r1;
|
r18 = i * r2;
|
r18 = i * r2;
|
r19 = j * r3;
|
r19 = j * r3;
|
r2 *= r3;
|
r2 *= r3;
|
|
|
r19 <<= 31;
|
r19 <<= 31;
|
r1 <<= 31;
|
r1 <<= 31;
|
do
|
do
|
if (r18 >= r19)
|
if (r18 >= r19)
|
r0 |= r1, r18 -= r19;
|
r0 |= r1, r18 -= r19;
|
while (r19 >>= 1, r1 >>= 1);
|
while (r19 >>= 1, r1 >>= 1);
|
|
|
return r2 * (int)r0;
|
return r2 * (int)r0;
|
}
|
}
|
*/
|
*/
|
GLOBAL(sdivsi3):
|
GLOBAL(sdivsi3):
|
pt/l LOCAL(sdivsi3_dontadd), tr2
|
pt/l LOCAL(sdivsi3_dontadd), tr2
|
pt/l LOCAL(sdivsi3_loop), tr1
|
pt/l LOCAL(sdivsi3_loop), tr1
|
ptabs/l r18, tr0
|
ptabs/l r18, tr0
|
movi 0, r0
|
movi 0, r0
|
movi 1, r1
|
movi 1, r1
|
shari.l r4, 31, r2
|
shari.l r4, 31, r2
|
shari.l r5, 31, r3
|
shari.l r5, 31, r3
|
cmveq r2, r1, r2
|
cmveq r2, r1, r2
|
cmveq r3, r1, r3
|
cmveq r3, r1, r3
|
muls.l r4, r2, r18
|
muls.l r4, r2, r18
|
muls.l r5, r3, r19
|
muls.l r5, r3, r19
|
muls.l r2, r3, r2
|
muls.l r2, r3, r2
|
shlli r19, 31, r19
|
shlli r19, 31, r19
|
shlli r1, 31, r1
|
shlli r1, 31, r1
|
LOCAL(sdivsi3_loop):
|
LOCAL(sdivsi3_loop):
|
bgtu r19, r18, tr2
|
bgtu r19, r18, tr2
|
or r0, r1, r0
|
or r0, r1, r0
|
sub r18, r19, r18
|
sub r18, r19, r18
|
LOCAL(sdivsi3_dontadd):
|
LOCAL(sdivsi3_dontadd):
|
shlri r1, 1, r1
|
shlri r1, 1, r1
|
shlri r19, 1, r19
|
shlri r19, 1, r19
|
bnei r1, 0, tr1
|
bnei r1, 0, tr1
|
muls.l r0, r2, r0
|
muls.l r0, r2, r0
|
add.l r0, r63, r0
|
add.l r0, r63, r0
|
blink tr0, r63
|
blink tr0, r63
|
#elif 0 /* ! 0 */
|
#elif 0 /* ! 0 */
|
// inputs: r4,r5
|
// inputs: r4,r5
|
// clobbered: r1,r2,r3,r18,r19,r20,r21,r25,tr0
|
// clobbered: r1,r2,r3,r18,r19,r20,r21,r25,tr0
|
// result in r0
|
// result in r0
|
GLOBAL(sdivsi3):
|
GLOBAL(sdivsi3):
|
// can create absolute value without extra latency,
|
// can create absolute value without extra latency,
|
// but dependent on proper sign extension of inputs:
|
// but dependent on proper sign extension of inputs:
|
// shari.l r5,31,r2
|
// shari.l r5,31,r2
|
// xor r5,r2,r20
|
// xor r5,r2,r20
|
// sub r20,r2,r20 // r20 is now absolute value of r5, zero-extended.
|
// sub r20,r2,r20 // r20 is now absolute value of r5, zero-extended.
|
shari.l r5,31,r2
|
shari.l r5,31,r2
|
ori r2,1,r2
|
ori r2,1,r2
|
muls.l r5,r2,r20 // r20 is now absolute value of r5, zero-extended.
|
muls.l r5,r2,r20 // r20 is now absolute value of r5, zero-extended.
|
movi 0xffffffffffffbb0c,r19 // shift count eqiv 76
|
movi 0xffffffffffffbb0c,r19 // shift count eqiv 76
|
shari.l r4,31,r3
|
shari.l r4,31,r3
|
nsb r20,r0
|
nsb r20,r0
|
shlld r20,r0,r25
|
shlld r20,r0,r25
|
shlri r25,48,r25
|
shlri r25,48,r25
|
sub r19,r25,r1
|
sub r19,r25,r1
|
mmulfx.w r1,r1,r2
|
mmulfx.w r1,r1,r2
|
mshflo.w r1,r63,r1
|
mshflo.w r1,r63,r1
|
// If r4 was to be used in-place instead of r21, could use this sequence
|
// If r4 was to be used in-place instead of r21, could use this sequence
|
// to compute absolute:
|
// to compute absolute:
|
// sub r63,r4,r19 // compute absolute value of r4
|
// sub r63,r4,r19 // compute absolute value of r4
|
// shlri r4,32,r3 // into lower 32 bit of r4, keeping
|
// shlri r4,32,r3 // into lower 32 bit of r4, keeping
|
// mcmv r19,r3,r4 // the sign in the upper 32 bits intact.
|
// mcmv r19,r3,r4 // the sign in the upper 32 bits intact.
|
ori r3,1,r3
|
ori r3,1,r3
|
mmulfx.w r25,r2,r2
|
mmulfx.w r25,r2,r2
|
sub r19,r0,r0
|
sub r19,r0,r0
|
muls.l r4,r3,r21
|
muls.l r4,r3,r21
|
msub.w r1,r2,r2
|
msub.w r1,r2,r2
|
addi r2,-2,r1
|
addi r2,-2,r1
|
mulu.l r21,r1,r19
|
mulu.l r21,r1,r19
|
mmulfx.w r2,r2,r2
|
mmulfx.w r2,r2,r2
|
shlli r1,15,r1
|
shlli r1,15,r1
|
shlrd r19,r0,r19
|
shlrd r19,r0,r19
|
mulu.l r19,r20,r3
|
mulu.l r19,r20,r3
|
mmacnfx.wl r25,r2,r1
|
mmacnfx.wl r25,r2,r1
|
ptabs r18,tr0
|
ptabs r18,tr0
|
sub r21,r3,r25
|
sub r21,r3,r25
|
|
|
mulu.l r25,r1,r2
|
mulu.l r25,r1,r2
|
addi r0,14,r0
|
addi r0,14,r0
|
xor r4,r5,r18
|
xor r4,r5,r18
|
shlrd r2,r0,r2
|
shlrd r2,r0,r2
|
mulu.l r2,r20,r3
|
mulu.l r2,r20,r3
|
add r19,r2,r19
|
add r19,r2,r19
|
shari.l r18,31,r18
|
shari.l r18,31,r18
|
sub r25,r3,r25
|
sub r25,r3,r25
|
|
|
mulu.l r25,r1,r2
|
mulu.l r25,r1,r2
|
sub r25,r20,r25
|
sub r25,r20,r25
|
add r19,r18,r19
|
add r19,r18,r19
|
shlrd r2,r0,r2
|
shlrd r2,r0,r2
|
mulu.l r2,r20,r3
|
mulu.l r2,r20,r3
|
addi r25,1,r25
|
addi r25,1,r25
|
add r19,r2,r19
|
add r19,r2,r19
|
|
|
cmpgt r25,r3,r25
|
cmpgt r25,r3,r25
|
add.l r19,r25,r0
|
add.l r19,r25,r0
|
xor r0,r18,r0
|
xor r0,r18,r0
|
blink tr0,r63
|
blink tr0,r63
|
#else /* ! 0 && ! 0 */
|
#else /* ! 0 && ! 0 */
|
|
|
// inputs: r4,r5
|
// inputs: r4,r5
|
// clobbered: r1,r18,r19,r20,r21,r25,tr0
|
// clobbered: r1,r18,r19,r20,r21,r25,tr0
|
// result in r0
|
// result in r0
|
HIDDEN_FUNC(GLOBAL(sdivsi3_2))
|
HIDDEN_FUNC(GLOBAL(sdivsi3_2))
|
#ifndef __pic__
|
#ifndef __pic__
|
FUNC(GLOBAL(sdivsi3))
|
FUNC(GLOBAL(sdivsi3))
|
GLOBAL(sdivsi3): /* this is the shcompact entry point */
|
GLOBAL(sdivsi3): /* this is the shcompact entry point */
|
// The special SHmedia entry point sdivsi3_1 prevents accidental linking
|
// The special SHmedia entry point sdivsi3_1 prevents accidental linking
|
// with the SHcompact implementation, which clobbers tr1 / tr2.
|
// with the SHcompact implementation, which clobbers tr1 / tr2.
|
.global GLOBAL(sdivsi3_1)
|
.global GLOBAL(sdivsi3_1)
|
GLOBAL(sdivsi3_1):
|
GLOBAL(sdivsi3_1):
|
.global GLOBAL(div_table_internal)
|
.global GLOBAL(div_table_internal)
|
movi (GLOBAL(div_table_internal) >> 16) & 65535, r20
|
movi (GLOBAL(div_table_internal) >> 16) & 65535, r20
|
shori GLOBAL(div_table_internal) & 65535, r20
|
shori GLOBAL(div_table_internal) & 65535, r20
|
#endif
|
#endif
|
.global GLOBAL(sdivsi3_2)
|
.global GLOBAL(sdivsi3_2)
|
// div_table in r20
|
// div_table in r20
|
// clobbered: r1,r18,r19,r21,r25,tr0
|
// clobbered: r1,r18,r19,r21,r25,tr0
|
GLOBAL(sdivsi3_2):
|
GLOBAL(sdivsi3_2):
|
nsb r5, r1
|
nsb r5, r1
|
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
|
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
|
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
|
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
|
ldx.ub r20, r21, r19 // u0.8
|
ldx.ub r20, r21, r19 // u0.8
|
shari r25, 32, r25 // normalize to s2.30
|
shari r25, 32, r25 // normalize to s2.30
|
shlli r21, 1, r21
|
shlli r21, 1, r21
|
muls.l r25, r19, r19 // s2.38
|
muls.l r25, r19, r19 // s2.38
|
ldx.w r20, r21, r21 // s2.14
|
ldx.w r20, r21, r21 // s2.14
|
ptabs r18, tr0
|
ptabs r18, tr0
|
shari r19, 24, r19 // truncate to s2.14
|
shari r19, 24, r19 // truncate to s2.14
|
sub r21, r19, r19 // some 11 bit inverse in s1.14
|
sub r21, r19, r19 // some 11 bit inverse in s1.14
|
muls.l r19, r19, r21 // u0.28
|
muls.l r19, r19, r21 // u0.28
|
sub r63, r1, r1
|
sub r63, r1, r1
|
addi r1, 92, r1
|
addi r1, 92, r1
|
muls.l r25, r21, r18 // s2.58
|
muls.l r25, r21, r18 // s2.58
|
shlli r19, 45, r19 // multiply by two and convert to s2.58
|
shlli r19, 45, r19 // multiply by two and convert to s2.58
|
/* bubble */
|
/* bubble */
|
sub r19, r18, r18
|
sub r19, r18, r18
|
shari r18, 28, r18 // some 22 bit inverse in s1.30
|
shari r18, 28, r18 // some 22 bit inverse in s1.30
|
muls.l r18, r25, r0 // s2.60
|
muls.l r18, r25, r0 // s2.60
|
muls.l r18, r4, r25 // s32.30
|
muls.l r18, r4, r25 // s32.30
|
/* bubble */
|
/* bubble */
|
shari r0, 16, r19 // s-16.44
|
shari r0, 16, r19 // s-16.44
|
muls.l r19, r18, r19 // s-16.74
|
muls.l r19, r18, r19 // s-16.74
|
shari r25, 63, r0
|
shari r25, 63, r0
|
shari r4, 14, r18 // s19.-14
|
shari r4, 14, r18 // s19.-14
|
shari r19, 30, r19 // s-16.44
|
shari r19, 30, r19 // s-16.44
|
muls.l r19, r18, r19 // s15.30
|
muls.l r19, r18, r19 // s15.30
|
xor r21, r0, r21 // You could also use the constant 1 << 27.
|
xor r21, r0, r21 // You could also use the constant 1 << 27.
|
add r21, r25, r21
|
add r21, r25, r21
|
sub r21, r19, r21
|
sub r21, r19, r21
|
shard r21, r1, r21
|
shard r21, r1, r21
|
sub r21, r0, r0
|
sub r21, r0, r0
|
blink tr0, r63
|
blink tr0, r63
|
#ifndef __pic__
|
#ifndef __pic__
|
ENDFUNC(GLOBAL(sdivsi3))
|
ENDFUNC(GLOBAL(sdivsi3))
|
#endif
|
#endif
|
ENDFUNC(GLOBAL(sdivsi3_2))
|
ENDFUNC(GLOBAL(sdivsi3_2))
|
#endif
|
#endif
|
#elif defined __SHMEDIA__
|
#elif defined __SHMEDIA__
|
/* m5compact-nofpu */
|
/* m5compact-nofpu */
|
// clobbered: r18,r19,r20,r21,r25,tr0,tr1,tr2
|
// clobbered: r18,r19,r20,r21,r25,tr0,tr1,tr2
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
FUNC(GLOBAL(sdivsi3))
|
FUNC(GLOBAL(sdivsi3))
|
GLOBAL(sdivsi3):
|
GLOBAL(sdivsi3):
|
pt/l LOCAL(sdivsi3_dontsub), tr0
|
pt/l LOCAL(sdivsi3_dontsub), tr0
|
pt/l LOCAL(sdivsi3_loop), tr1
|
pt/l LOCAL(sdivsi3_loop), tr1
|
ptabs/l r18,tr2
|
ptabs/l r18,tr2
|
shari.l r4,31,r18
|
shari.l r4,31,r18
|
shari.l r5,31,r19
|
shari.l r5,31,r19
|
xor r4,r18,r20
|
xor r4,r18,r20
|
xor r5,r19,r21
|
xor r5,r19,r21
|
sub.l r20,r18,r20
|
sub.l r20,r18,r20
|
sub.l r21,r19,r21
|
sub.l r21,r19,r21
|
xor r18,r19,r19
|
xor r18,r19,r19
|
shlli r21,32,r25
|
shlli r21,32,r25
|
addi r25,-1,r21
|
addi r25,-1,r21
|
addz.l r20,r63,r20
|
addz.l r20,r63,r20
|
LOCAL(sdivsi3_loop):
|
LOCAL(sdivsi3_loop):
|
shlli r20,1,r20
|
shlli r20,1,r20
|
bgeu/u r21,r20,tr0
|
bgeu/u r21,r20,tr0
|
sub r20,r21,r20
|
sub r20,r21,r20
|
LOCAL(sdivsi3_dontsub):
|
LOCAL(sdivsi3_dontsub):
|
addi.l r25,-1,r25
|
addi.l r25,-1,r25
|
bnei r25,-32,tr1
|
bnei r25,-32,tr1
|
xor r20,r19,r20
|
xor r20,r19,r20
|
sub.l r20,r19,r0
|
sub.l r20,r19,r0
|
blink tr2,r63
|
blink tr2,r63
|
ENDFUNC(GLOBAL(sdivsi3))
|
ENDFUNC(GLOBAL(sdivsi3))
|
#else /* ! __SHMEDIA__ */
|
#else /* ! __SHMEDIA__ */
|
FUNC(GLOBAL(sdivsi3))
|
FUNC(GLOBAL(sdivsi3))
|
GLOBAL(sdivsi3):
|
GLOBAL(sdivsi3):
|
mov r4,r1
|
mov r4,r1
|
mov r5,r0
|
mov r5,r0
|
|
|
tst r0,r0
|
tst r0,r0
|
bt div0
|
bt div0
|
mov #0,r2
|
mov #0,r2
|
div0s r2,r1
|
div0s r2,r1
|
subc r3,r3
|
subc r3,r3
|
subc r2,r1
|
subc r2,r1
|
div0s r0,r3
|
div0s r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
div1 r0,r3
|
div1 r0,r3
|
rotcl r1
|
rotcl r1
|
addc r2,r1
|
addc r2,r1
|
rts
|
rts
|
mov r1,r0
|
mov r1,r0
|
|
|
|
|
div0: rts
|
div0: rts
|
mov #0,r0
|
mov #0,r0
|
|
|
ENDFUNC(GLOBAL(sdivsi3))
|
ENDFUNC(GLOBAL(sdivsi3))
|
#endif /* ! __SHMEDIA__ */
|
#endif /* ! __SHMEDIA__ */
|
#endif /* ! __SH4__ */
|
#endif /* ! __SH4__ */
|
#endif
|
#endif
|
#ifdef L_udivsi3_i4
|
#ifdef L_udivsi3_i4
|
|
|
.title "SH DIVIDE"
|
.title "SH DIVIDE"
|
!! 4 byte integer Divide code for the Renesas SH
|
!! 4 byte integer Divide code for the Renesas SH
|
#ifdef __SH4__
|
#ifdef __SH4__
|
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4,
|
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4,
|
!! and t bit
|
!! and t bit
|
|
|
.global GLOBAL(udivsi3_i4)
|
.global GLOBAL(udivsi3_i4)
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
GLOBAL(udivsi3_i4):
|
GLOBAL(udivsi3_i4):
|
mov #1,r1
|
mov #1,r1
|
cmp/hi r1,r5
|
cmp/hi r1,r5
|
bf trivial
|
bf trivial
|
rotr r1
|
rotr r1
|
xor r1,r4
|
xor r1,r4
|
lds r4,fpul
|
lds r4,fpul
|
mova L1,r0
|
mova L1,r0
|
#ifdef FMOVD_WORKS
|
#ifdef FMOVD_WORKS
|
fmov.d @r0+,dr4
|
fmov.d @r0+,dr4
|
#else
|
#else
|
fmov.s @r0+,DR40
|
fmov.s @r0+,DR40
|
fmov.s @r0,DR41
|
fmov.s @r0,DR41
|
#endif
|
#endif
|
float fpul,dr0
|
float fpul,dr0
|
xor r1,r5
|
xor r1,r5
|
lds r5,fpul
|
lds r5,fpul
|
float fpul,dr2
|
float fpul,dr2
|
fadd dr4,dr0
|
fadd dr4,dr0
|
fadd dr4,dr2
|
fadd dr4,dr2
|
fdiv dr2,dr0
|
fdiv dr2,dr0
|
rts
|
rts
|
ftrc dr0,fpul
|
ftrc dr0,fpul
|
|
|
trivial:
|
trivial:
|
rts
|
rts
|
lds r4,fpul
|
lds r4,fpul
|
|
|
.align 2
|
.align 2
|
#ifdef FMOVD_WORKS
|
#ifdef FMOVD_WORKS
|
.align 3 ! make double below 8 byte aligned.
|
.align 3 ! make double below 8 byte aligned.
|
#endif
|
#endif
|
L1:
|
L1:
|
.double 2147483648
|
.double 2147483648
|
|
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
#elif defined (__SH5__) && ! defined (__SH4_NOFPU__)
|
#elif defined (__SH5__) && ! defined (__SH4_NOFPU__)
|
#if ! __SH5__ || __SH5__ == 32
|
#if ! __SH5__ || __SH5__ == 32
|
!! args in r4 and r5, result in fpul, clobber r20, r21, dr0, fr33
|
!! args in r4 and r5, result in fpul, clobber r20, r21, dr0, fr33
|
.mode SHmedia
|
.mode SHmedia
|
.global GLOBAL(udivsi3_i4)
|
.global GLOBAL(udivsi3_i4)
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
GLOBAL(udivsi3_i4):
|
GLOBAL(udivsi3_i4):
|
addz.l r4,r63,r20
|
addz.l r4,r63,r20
|
addz.l r5,r63,r21
|
addz.l r5,r63,r21
|
fmov.qd r20,dr0
|
fmov.qd r20,dr0
|
fmov.qd r21,dr32
|
fmov.qd r21,dr32
|
ptabs r18,tr0
|
ptabs r18,tr0
|
float.qd dr0,dr0
|
float.qd dr0,dr0
|
float.qd dr32,dr32
|
float.qd dr32,dr32
|
fdiv.d dr0,dr32,dr0
|
fdiv.d dr0,dr32,dr0
|
ftrc.dq dr0,dr32
|
ftrc.dq dr0,dr32
|
fmov.s fr33,fr32
|
fmov.s fr33,fr32
|
blink tr0,r63
|
blink tr0,r63
|
|
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
#endif /* ! __SH5__ || __SH5__ == 32 */
|
#endif /* ! __SH5__ || __SH5__ == 32 */
|
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
|
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
|
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
|
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
|
|
|
.global GLOBAL(udivsi3_i4)
|
.global GLOBAL(udivsi3_i4)
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
|
GLOBAL(udivsi3_i4):
|
GLOBAL(udivsi3_i4):
|
mov #1,r1
|
mov #1,r1
|
cmp/hi r1,r5
|
cmp/hi r1,r5
|
bf trivial
|
bf trivial
|
sts.l fpscr,@-r15
|
sts.l fpscr,@-r15
|
mova L1,r0
|
mova L1,r0
|
lds.l @r0+,fpscr
|
lds.l @r0+,fpscr
|
rotr r1
|
rotr r1
|
xor r1,r4
|
xor r1,r4
|
lds r4,fpul
|
lds r4,fpul
|
#ifdef FMOVD_WORKS
|
#ifdef FMOVD_WORKS
|
fmov.d @r0+,dr4
|
fmov.d @r0+,dr4
|
#else
|
#else
|
fmov.s @r0+,DR40
|
fmov.s @r0+,DR40
|
fmov.s @r0,DR41
|
fmov.s @r0,DR41
|
#endif
|
#endif
|
float fpul,dr0
|
float fpul,dr0
|
xor r1,r5
|
xor r1,r5
|
lds r5,fpul
|
lds r5,fpul
|
float fpul,dr2
|
float fpul,dr2
|
fadd dr4,dr0
|
fadd dr4,dr0
|
fadd dr4,dr2
|
fadd dr4,dr2
|
fdiv dr2,dr0
|
fdiv dr2,dr0
|
ftrc dr0,fpul
|
ftrc dr0,fpul
|
rts
|
rts
|
lds.l @r15+,fpscr
|
lds.l @r15+,fpscr
|
|
|
#ifdef FMOVD_WORKS
|
#ifdef FMOVD_WORKS
|
.align 3 ! make double below 8 byte aligned.
|
.align 3 ! make double below 8 byte aligned.
|
#endif
|
#endif
|
trivial:
|
trivial:
|
rts
|
rts
|
lds r4,fpul
|
lds r4,fpul
|
|
|
.align 2
|
.align 2
|
L1:
|
L1:
|
#ifndef FMOVD_WORKS
|
#ifndef FMOVD_WORKS
|
.long 0x80000
|
.long 0x80000
|
#else
|
#else
|
.long 0x180000
|
.long 0x180000
|
#endif
|
#endif
|
.double 2147483648
|
.double 2147483648
|
|
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
ENDFUNC(GLOBAL(udivsi3_i4))
|
#endif /* ! __SH4__ */
|
#endif /* ! __SH4__ */
|
#endif
|
#endif
|
|
|
#ifdef L_udivsi3
|
#ifdef L_udivsi3
|
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
|
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
|
sh2e/sh3e code. */
|
sh2e/sh3e code. */
|
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
|
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
|
|
|
!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
|
!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
|
.global GLOBAL(udivsi3)
|
.global GLOBAL(udivsi3)
|
HIDDEN_FUNC(GLOBAL(udivsi3))
|
HIDDEN_FUNC(GLOBAL(udivsi3))
|
|
|
#if __SHMEDIA__
|
#if __SHMEDIA__
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
#else
|
#else
|
.text
|
.text
|
#endif
|
#endif
|
.align 2
|
.align 2
|
#if 0
|
#if 0
|
/* The assembly code that follows is a hand-optimized version of the C
|
/* The assembly code that follows is a hand-optimized version of the C
|
code that follows. Note that the registers that are modified are
|
code that follows. Note that the registers that are modified are
|
exactly those listed as clobbered in the patterns udivsi3_i1 and
|
exactly those listed as clobbered in the patterns udivsi3_i1 and
|
udivsi3_i1_media.
|
udivsi3_i1_media.
|
|
|
unsigned
|
unsigned
|
__udivsi3 (i, j)
|
__udivsi3 (i, j)
|
unsigned i, j;
|
unsigned i, j;
|
{
|
{
|
register unsigned long long r0 asm ("r0") = 0;
|
register unsigned long long r0 asm ("r0") = 0;
|
register unsigned long long r18 asm ("r18") = 1;
|
register unsigned long long r18 asm ("r18") = 1;
|
register unsigned long long r4 asm ("r4") = i;
|
register unsigned long long r4 asm ("r4") = i;
|
register unsigned long long r19 asm ("r19") = j;
|
register unsigned long long r19 asm ("r19") = j;
|
|
|
r19 <<= 31;
|
r19 <<= 31;
|
r18 <<= 31;
|
r18 <<= 31;
|
do
|
do
|
if (r4 >= r19)
|
if (r4 >= r19)
|
r0 |= r18, r4 -= r19;
|
r0 |= r18, r4 -= r19;
|
while (r19 >>= 1, r18 >>= 1);
|
while (r19 >>= 1, r18 >>= 1);
|
|
|
return r0;
|
return r0;
|
}
|
}
|
*/
|
*/
|
GLOBAL(udivsi3):
|
GLOBAL(udivsi3):
|
pt/l LOCAL(udivsi3_dontadd), tr2
|
pt/l LOCAL(udivsi3_dontadd), tr2
|
pt/l LOCAL(udivsi3_loop), tr1
|
pt/l LOCAL(udivsi3_loop), tr1
|
ptabs/l r18, tr0
|
ptabs/l r18, tr0
|
movi 0, r0
|
movi 0, r0
|
movi 1, r18
|
movi 1, r18
|
addz.l r5, r63, r19
|
addz.l r5, r63, r19
|
addz.l r4, r63, r4
|
addz.l r4, r63, r4
|
shlli r19, 31, r19
|
shlli r19, 31, r19
|
shlli r18, 31, r18
|
shlli r18, 31, r18
|
LOCAL(udivsi3_loop):
|
LOCAL(udivsi3_loop):
|
bgtu r19, r4, tr2
|
bgtu r19, r4, tr2
|
or r0, r18, r0
|
or r0, r18, r0
|
sub r4, r19, r4
|
sub r4, r19, r4
|
LOCAL(udivsi3_dontadd):
|
LOCAL(udivsi3_dontadd):
|
shlri r18, 1, r18
|
shlri r18, 1, r18
|
shlri r19, 1, r19
|
shlri r19, 1, r19
|
bnei r18, 0, tr1
|
bnei r18, 0, tr1
|
blink tr0, r63
|
blink tr0, r63
|
#else
|
#else
|
GLOBAL(udivsi3):
|
GLOBAL(udivsi3):
|
// inputs: r4,r5
|
// inputs: r4,r5
|
// clobbered: r18,r19,r20,r21,r22,r25,tr0
|
// clobbered: r18,r19,r20,r21,r22,r25,tr0
|
// result in r0.
|
// result in r0.
|
addz.l r5,r63,r22
|
addz.l r5,r63,r22
|
nsb r22,r0
|
nsb r22,r0
|
shlld r22,r0,r25
|
shlld r22,r0,r25
|
shlri r25,48,r25
|
shlri r25,48,r25
|
movi 0xffffffffffffbb0c,r20 // shift count eqiv 76
|
movi 0xffffffffffffbb0c,r20 // shift count eqiv 76
|
sub r20,r25,r21
|
sub r20,r25,r21
|
mmulfx.w r21,r21,r19
|
mmulfx.w r21,r21,r19
|
mshflo.w r21,r63,r21
|
mshflo.w r21,r63,r21
|
ptabs r18,tr0
|
ptabs r18,tr0
|
mmulfx.w r25,r19,r19
|
mmulfx.w r25,r19,r19
|
sub r20,r0,r0
|
sub r20,r0,r0
|
/* bubble */
|
/* bubble */
|
msub.w r21,r19,r19
|
msub.w r21,r19,r19
|
addi r19,-2,r21 /* It would be nice for scheduling to do this add to r21
|
addi r19,-2,r21 /* It would be nice for scheduling to do this add to r21
|
before the msub.w, but we need a different value for
|
before the msub.w, but we need a different value for
|
r19 to keep errors under control. */
|
r19 to keep errors under control. */
|
mulu.l r4,r21,r18
|
mulu.l r4,r21,r18
|
mmulfx.w r19,r19,r19
|
mmulfx.w r19,r19,r19
|
shlli r21,15,r21
|
shlli r21,15,r21
|
shlrd r18,r0,r18
|
shlrd r18,r0,r18
|
mulu.l r18,r22,r20
|
mulu.l r18,r22,r20
|
mmacnfx.wl r25,r19,r21
|
mmacnfx.wl r25,r19,r21
|
/* bubble */
|
/* bubble */
|
sub r4,r20,r25
|
sub r4,r20,r25
|
|
|
mulu.l r25,r21,r19
|
mulu.l r25,r21,r19
|
addi r0,14,r0
|
addi r0,14,r0
|
/* bubble */
|
/* bubble */
|
shlrd r19,r0,r19
|
shlrd r19,r0,r19
|
mulu.l r19,r22,r20
|
mulu.l r19,r22,r20
|
add r18,r19,r18
|
add r18,r19,r18
|
/* bubble */
|
/* bubble */
|
sub.l r25,r20,r25
|
sub.l r25,r20,r25
|
|
|
mulu.l r25,r21,r19
|
mulu.l r25,r21,r19
|
addz.l r25,r63,r25
|
addz.l r25,r63,r25
|
sub r25,r22,r25
|
sub r25,r22,r25
|
shlrd r19,r0,r19
|
shlrd r19,r0,r19
|
mulu.l r19,r22,r20
|
mulu.l r19,r22,r20
|
addi r25,1,r25
|
addi r25,1,r25
|
add r18,r19,r18
|
add r18,r19,r18
|
|
|
cmpgt r25,r20,r25
|
cmpgt r25,r20,r25
|
add.l r18,r25,r0
|
add.l r18,r25,r0
|
blink tr0,r63
|
blink tr0,r63
|
#endif
|
#endif
|
#elif defined (__SHMEDIA__)
|
#elif defined (__SHMEDIA__)
|
/* m5compact-nofpu - more emphasis on code size than on speed, but don't
|
/* m5compact-nofpu - more emphasis on code size than on speed, but don't
|
ignore speed altogether - div1 needs 9 cycles, subc 7 and rotcl 4.
|
ignore speed altogether - div1 needs 9 cycles, subc 7 and rotcl 4.
|
So use a short shmedia loop. */
|
So use a short shmedia loop. */
|
// clobbered: r20,r21,r25,tr0,tr1,tr2
|
// clobbered: r20,r21,r25,tr0,tr1,tr2
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
GLOBAL(udivsi3):
|
GLOBAL(udivsi3):
|
pt/l LOCAL(udivsi3_dontsub), tr0
|
pt/l LOCAL(udivsi3_dontsub), tr0
|
pt/l LOCAL(udivsi3_loop), tr1
|
pt/l LOCAL(udivsi3_loop), tr1
|
ptabs/l r18,tr2
|
ptabs/l r18,tr2
|
shlli r5,32,r25
|
shlli r5,32,r25
|
addi r25,-1,r21
|
addi r25,-1,r21
|
addz.l r4,r63,r20
|
addz.l r4,r63,r20
|
LOCAL(udivsi3_loop):
|
LOCAL(udivsi3_loop):
|
shlli r20,1,r20
|
shlli r20,1,r20
|
bgeu/u r21,r20,tr0
|
bgeu/u r21,r20,tr0
|
sub r20,r21,r20
|
sub r20,r21,r20
|
LOCAL(udivsi3_dontsub):
|
LOCAL(udivsi3_dontsub):
|
addi.l r25,-1,r25
|
addi.l r25,-1,r25
|
bnei r25,-32,tr1
|
bnei r25,-32,tr1
|
add.l r20,r63,r0
|
add.l r20,r63,r0
|
blink tr2,r63
|
blink tr2,r63
|
#else /* ! defined (__SHMEDIA__) */
|
#else /* ! defined (__SHMEDIA__) */
|
LOCAL(div8):
|
LOCAL(div8):
|
div1 r5,r4
|
div1 r5,r4
|
LOCAL(div7):
|
LOCAL(div7):
|
div1 r5,r4; div1 r5,r4; div1 r5,r4
|
div1 r5,r4; div1 r5,r4; div1 r5,r4
|
div1 r5,r4; div1 r5,r4; div1 r5,r4; rts; div1 r5,r4
|
div1 r5,r4; div1 r5,r4; div1 r5,r4; rts; div1 r5,r4
|
|
|
LOCAL(divx4):
|
LOCAL(divx4):
|
div1 r5,r4; rotcl r0
|
div1 r5,r4; rotcl r0
|
div1 r5,r4; rotcl r0
|
div1 r5,r4; rotcl r0
|
div1 r5,r4; rotcl r0
|
div1 r5,r4; rotcl r0
|
rts; div1 r5,r4
|
rts; div1 r5,r4
|
|
|
GLOBAL(udivsi3):
|
GLOBAL(udivsi3):
|
sts.l pr,@-r15
|
sts.l pr,@-r15
|
extu.w r5,r0
|
extu.w r5,r0
|
cmp/eq r5,r0
|
cmp/eq r5,r0
|
#ifdef __sh1__
|
#ifdef __sh1__
|
bf LOCAL(large_divisor)
|
bf LOCAL(large_divisor)
|
#else
|
#else
|
bf/s LOCAL(large_divisor)
|
bf/s LOCAL(large_divisor)
|
#endif
|
#endif
|
div0u
|
div0u
|
swap.w r4,r0
|
swap.w r4,r0
|
shlr16 r4
|
shlr16 r4
|
bsr LOCAL(div8)
|
bsr LOCAL(div8)
|
shll16 r5
|
shll16 r5
|
bsr LOCAL(div7)
|
bsr LOCAL(div7)
|
div1 r5,r4
|
div1 r5,r4
|
xtrct r4,r0
|
xtrct r4,r0
|
xtrct r0,r4
|
xtrct r0,r4
|
bsr LOCAL(div8)
|
bsr LOCAL(div8)
|
swap.w r4,r4
|
swap.w r4,r4
|
bsr LOCAL(div7)
|
bsr LOCAL(div7)
|
div1 r5,r4
|
div1 r5,r4
|
lds.l @r15+,pr
|
lds.l @r15+,pr
|
xtrct r4,r0
|
xtrct r4,r0
|
swap.w r0,r0
|
swap.w r0,r0
|
rotcl r0
|
rotcl r0
|
rts
|
rts
|
shlr16 r5
|
shlr16 r5
|
|
|
LOCAL(large_divisor):
|
LOCAL(large_divisor):
|
#ifdef __sh1__
|
#ifdef __sh1__
|
div0u
|
div0u
|
#endif
|
#endif
|
mov #0,r0
|
mov #0,r0
|
xtrct r4,r0
|
xtrct r4,r0
|
xtrct r0,r4
|
xtrct r0,r4
|
bsr LOCAL(divx4)
|
bsr LOCAL(divx4)
|
rotcl r0
|
rotcl r0
|
bsr LOCAL(divx4)
|
bsr LOCAL(divx4)
|
rotcl r0
|
rotcl r0
|
bsr LOCAL(divx4)
|
bsr LOCAL(divx4)
|
rotcl r0
|
rotcl r0
|
bsr LOCAL(divx4)
|
bsr LOCAL(divx4)
|
rotcl r0
|
rotcl r0
|
lds.l @r15+,pr
|
lds.l @r15+,pr
|
rts
|
rts
|
rotcl r0
|
rotcl r0
|
|
|
ENDFUNC(GLOBAL(udivsi3))
|
ENDFUNC(GLOBAL(udivsi3))
|
#endif /* ! __SHMEDIA__ */
|
#endif /* ! __SHMEDIA__ */
|
#endif /* __SH4__ */
|
#endif /* __SH4__ */
|
#endif /* L_udivsi3 */
|
#endif /* L_udivsi3 */
|
|
|
#ifdef L_udivdi3
|
#ifdef L_udivdi3
|
#ifdef __SHMEDIA__
|
#ifdef __SHMEDIA__
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
.global GLOBAL(udivdi3)
|
.global GLOBAL(udivdi3)
|
FUNC(GLOBAL(udivdi3))
|
FUNC(GLOBAL(udivdi3))
|
GLOBAL(udivdi3):
|
GLOBAL(udivdi3):
|
HIDDEN_ALIAS(udivdi3_internal,udivdi3)
|
HIDDEN_ALIAS(udivdi3_internal,udivdi3)
|
shlri r3,1,r4
|
shlri r3,1,r4
|
nsb r4,r22
|
nsb r4,r22
|
shlld r3,r22,r6
|
shlld r3,r22,r6
|
shlri r6,49,r5
|
shlri r6,49,r5
|
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
|
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
|
sub r21,r5,r1
|
sub r21,r5,r1
|
mmulfx.w r1,r1,r4
|
mmulfx.w r1,r1,r4
|
mshflo.w r1,r63,r1
|
mshflo.w r1,r63,r1
|
sub r63,r22,r20 // r63 == 64 % 64
|
sub r63,r22,r20 // r63 == 64 % 64
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
pta LOCAL(large_divisor),tr0
|
pta LOCAL(large_divisor),tr0
|
addi r20,32,r9
|
addi r20,32,r9
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
madd.w r1,r1,r1
|
madd.w r1,r1,r1
|
mmulfx.w r1,r1,r4
|
mmulfx.w r1,r1,r4
|
shlri r6,32,r7
|
shlri r6,32,r7
|
bgt/u r9,r63,tr0 // large_divisor
|
bgt/u r9,r63,tr0 // large_divisor
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
shlri r2,32+14,r19
|
shlri r2,32+14,r19
|
addi r22,-31,r0
|
addi r22,-31,r0
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
|
|
mulu.l r1,r7,r4
|
mulu.l r1,r7,r4
|
addi r1,-3,r5
|
addi r1,-3,r5
|
mulu.l r5,r19,r5
|
mulu.l r5,r19,r5
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
the case may be, %0000000000000000 000.11111111111, still */
|
the case may be, %0000000000000000 000.11111111111, still */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
mulu.l r5,r3,r8
|
mulu.l r5,r3,r8
|
mshalds.l r1,r21,r1
|
mshalds.l r1,r21,r1
|
shari r4,26,r4
|
shari r4,26,r4
|
shlld r8,r0,r8
|
shlld r8,r0,r8
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
sub r2,r8,r2
|
sub r2,r8,r2
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
|
|
|
shlri r2,22,r21
|
shlri r2,22,r21
|
mulu.l r21,r1,r21
|
mulu.l r21,r1,r21
|
shlld r5,r0,r8
|
shlld r5,r0,r8
|
addi r20,30-22,r0
|
addi r20,30-22,r0
|
shlrd r21,r0,r21
|
shlrd r21,r0,r21
|
mulu.l r21,r3,r5
|
mulu.l r21,r3,r5
|
add r8,r21,r8
|
add r8,r21,r8
|
mcmpgt.l r21,r63,r21 // See Note 1
|
mcmpgt.l r21,r63,r21 // See Note 1
|
addi r20,30,r0
|
addi r20,30,r0
|
mshfhi.l r63,r21,r21
|
mshfhi.l r63,r21,r21
|
sub r2,r5,r2
|
sub r2,r5,r2
|
andc r2,r21,r2
|
andc r2,r21,r2
|
|
|
/* small divisor: need a third divide step */
|
/* small divisor: need a third divide step */
|
mulu.l r2,r1,r7
|
mulu.l r2,r1,r7
|
ptabs r18,tr0
|
ptabs r18,tr0
|
addi r2,1,r2
|
addi r2,1,r2
|
shlrd r7,r0,r7
|
shlrd r7,r0,r7
|
mulu.l r7,r3,r5
|
mulu.l r7,r3,r5
|
add r8,r7,r8
|
add r8,r7,r8
|
sub r2,r3,r2
|
sub r2,r3,r2
|
cmpgt r2,r5,r5
|
cmpgt r2,r5,r5
|
add r8,r5,r2
|
add r8,r5,r2
|
/* could test r3 here to check for divide by zero. */
|
/* could test r3 here to check for divide by zero. */
|
blink tr0,r63
|
blink tr0,r63
|
|
|
LOCAL(large_divisor):
|
LOCAL(large_divisor):
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
shlrd r2,r9,r25
|
shlrd r2,r9,r25
|
shlri r25,32,r8
|
shlri r25,32,r8
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
|
|
mulu.l r1,r7,r4
|
mulu.l r1,r7,r4
|
addi r1,-3,r5
|
addi r1,-3,r5
|
mulu.l r5,r8,r5
|
mulu.l r5,r8,r5
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
the case may be, %0000000000000000 000.11111111111, still */
|
the case may be, %0000000000000000 000.11111111111, still */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
shlri r5,14-1,r8
|
shlri r5,14-1,r8
|
mulu.l r8,r7,r5
|
mulu.l r8,r7,r5
|
mshalds.l r1,r21,r1
|
mshalds.l r1,r21,r1
|
shari r4,26,r4
|
shari r4,26,r4
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
sub r25,r5,r25
|
sub r25,r5,r25
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
|
|
|
shlri r25,22,r21
|
shlri r25,22,r21
|
mulu.l r21,r1,r21
|
mulu.l r21,r1,r21
|
pta LOCAL(no_lo_adj),tr0
|
pta LOCAL(no_lo_adj),tr0
|
addi r22,32,r0
|
addi r22,32,r0
|
shlri r21,40,r21
|
shlri r21,40,r21
|
mulu.l r21,r7,r5
|
mulu.l r21,r7,r5
|
add r8,r21,r8
|
add r8,r21,r8
|
shlld r2,r0,r2
|
shlld r2,r0,r2
|
sub r25,r5,r25
|
sub r25,r5,r25
|
bgtu/u r7,r25,tr0 // no_lo_adj
|
bgtu/u r7,r25,tr0 // no_lo_adj
|
addi r8,1,r8
|
addi r8,1,r8
|
sub r25,r7,r25
|
sub r25,r7,r25
|
LOCAL(no_lo_adj):
|
LOCAL(no_lo_adj):
|
mextr4 r2,r25,r2
|
mextr4 r2,r25,r2
|
|
|
/* large_divisor: only needs a few adjustments. */
|
/* large_divisor: only needs a few adjustments. */
|
mulu.l r8,r6,r5
|
mulu.l r8,r6,r5
|
ptabs r18,tr0
|
ptabs r18,tr0
|
/* bubble */
|
/* bubble */
|
cmpgtu r5,r2,r5
|
cmpgtu r5,r2,r5
|
sub r8,r5,r2
|
sub r8,r5,r2
|
blink tr0,r63
|
blink tr0,r63
|
ENDFUNC(GLOBAL(udivdi3))
|
ENDFUNC(GLOBAL(udivdi3))
|
/* Note 1: To shift the result of the second divide stage so that the result
|
/* Note 1: To shift the result of the second divide stage so that the result
|
always fits into 32 bits, yet we still reduce the rest sufficiently
|
always fits into 32 bits, yet we still reduce the rest sufficiently
|
would require a lot of instructions to do the shifts just right. Using
|
would require a lot of instructions to do the shifts just right. Using
|
the full 64 bit shift result to multiply with the divisor would require
|
the full 64 bit shift result to multiply with the divisor would require
|
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
|
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
|
Fortunately, if the upper 32 bits of the shift result are nonzero, we
|
Fortunately, if the upper 32 bits of the shift result are nonzero, we
|
know that the rest after taking this partial result into account will
|
know that the rest after taking this partial result into account will
|
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
|
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
|
upper 32 bits of the partial result are nonzero. */
|
upper 32 bits of the partial result are nonzero. */
|
#endif /* __SHMEDIA__ */
|
#endif /* __SHMEDIA__ */
|
#endif /* L_udivdi3 */
|
#endif /* L_udivdi3 */
|
|
|
#ifdef L_divdi3
|
#ifdef L_divdi3
|
#ifdef __SHMEDIA__
|
#ifdef __SHMEDIA__
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
.global GLOBAL(divdi3)
|
.global GLOBAL(divdi3)
|
FUNC(GLOBAL(divdi3))
|
FUNC(GLOBAL(divdi3))
|
GLOBAL(divdi3):
|
GLOBAL(divdi3):
|
pta GLOBAL(udivdi3_internal),tr0
|
pta GLOBAL(udivdi3_internal),tr0
|
shari r2,63,r22
|
shari r2,63,r22
|
shari r3,63,r23
|
shari r3,63,r23
|
xor r2,r22,r2
|
xor r2,r22,r2
|
xor r3,r23,r3
|
xor r3,r23,r3
|
sub r2,r22,r2
|
sub r2,r22,r2
|
sub r3,r23,r3
|
sub r3,r23,r3
|
beq/u r22,r23,tr0
|
beq/u r22,r23,tr0
|
ptabs r18,tr1
|
ptabs r18,tr1
|
blink tr0,r18
|
blink tr0,r18
|
sub r63,r2,r2
|
sub r63,r2,r2
|
blink tr1,r63
|
blink tr1,r63
|
ENDFUNC(GLOBAL(divdi3))
|
ENDFUNC(GLOBAL(divdi3))
|
#endif /* __SHMEDIA__ */
|
#endif /* __SHMEDIA__ */
|
#endif /* L_divdi3 */
|
#endif /* L_divdi3 */
|
|
|
#ifdef L_umoddi3
|
#ifdef L_umoddi3
|
#ifdef __SHMEDIA__
|
#ifdef __SHMEDIA__
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
.global GLOBAL(umoddi3)
|
.global GLOBAL(umoddi3)
|
FUNC(GLOBAL(umoddi3))
|
FUNC(GLOBAL(umoddi3))
|
GLOBAL(umoddi3):
|
GLOBAL(umoddi3):
|
HIDDEN_ALIAS(umoddi3_internal,umoddi3)
|
HIDDEN_ALIAS(umoddi3_internal,umoddi3)
|
shlri r3,1,r4
|
shlri r3,1,r4
|
nsb r4,r22
|
nsb r4,r22
|
shlld r3,r22,r6
|
shlld r3,r22,r6
|
shlri r6,49,r5
|
shlri r6,49,r5
|
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
|
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
|
sub r21,r5,r1
|
sub r21,r5,r1
|
mmulfx.w r1,r1,r4
|
mmulfx.w r1,r1,r4
|
mshflo.w r1,r63,r1
|
mshflo.w r1,r63,r1
|
sub r63,r22,r20 // r63 == 64 % 64
|
sub r63,r22,r20 // r63 == 64 % 64
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
pta LOCAL(large_divisor),tr0
|
pta LOCAL(large_divisor),tr0
|
addi r20,32,r9
|
addi r20,32,r9
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
madd.w r1,r1,r1
|
madd.w r1,r1,r1
|
mmulfx.w r1,r1,r4
|
mmulfx.w r1,r1,r4
|
shlri r6,32,r7
|
shlri r6,32,r7
|
bgt/u r9,r63,tr0 // large_divisor
|
bgt/u r9,r63,tr0 // large_divisor
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
shlri r2,32+14,r19
|
shlri r2,32+14,r19
|
addi r22,-31,r0
|
addi r22,-31,r0
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
|
|
mulu.l r1,r7,r4
|
mulu.l r1,r7,r4
|
addi r1,-3,r5
|
addi r1,-3,r5
|
mulu.l r5,r19,r5
|
mulu.l r5,r19,r5
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
the case may be, %0000000000000000 000.11111111111, still */
|
the case may be, %0000000000000000 000.11111111111, still */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
mulu.l r5,r3,r5
|
mulu.l r5,r3,r5
|
mshalds.l r1,r21,r1
|
mshalds.l r1,r21,r1
|
shari r4,26,r4
|
shari r4,26,r4
|
shlld r5,r0,r5
|
shlld r5,r0,r5
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
sub r2,r5,r2
|
sub r2,r5,r2
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
|
|
|
shlri r2,22,r21
|
shlri r2,22,r21
|
mulu.l r21,r1,r21
|
mulu.l r21,r1,r21
|
addi r20,30-22,r0
|
addi r20,30-22,r0
|
/* bubble */ /* could test r3 here to check for divide by zero. */
|
/* bubble */ /* could test r3 here to check for divide by zero. */
|
shlrd r21,r0,r21
|
shlrd r21,r0,r21
|
mulu.l r21,r3,r5
|
mulu.l r21,r3,r5
|
mcmpgt.l r21,r63,r21 // See Note 1
|
mcmpgt.l r21,r63,r21 // See Note 1
|
addi r20,30,r0
|
addi r20,30,r0
|
mshfhi.l r63,r21,r21
|
mshfhi.l r63,r21,r21
|
sub r2,r5,r2
|
sub r2,r5,r2
|
andc r2,r21,r2
|
andc r2,r21,r2
|
|
|
/* small divisor: need a third divide step */
|
/* small divisor: need a third divide step */
|
mulu.l r2,r1,r7
|
mulu.l r2,r1,r7
|
ptabs r18,tr0
|
ptabs r18,tr0
|
sub r2,r3,r8 /* re-use r8 here for rest - r3 */
|
sub r2,r3,r8 /* re-use r8 here for rest - r3 */
|
shlrd r7,r0,r7
|
shlrd r7,r0,r7
|
mulu.l r7,r3,r5
|
mulu.l r7,r3,r5
|
/* bubble */
|
/* bubble */
|
addi r8,1,r7
|
addi r8,1,r7
|
cmpgt r7,r5,r7
|
cmpgt r7,r5,r7
|
cmvne r7,r8,r2
|
cmvne r7,r8,r2
|
sub r2,r5,r2
|
sub r2,r5,r2
|
blink tr0,r63
|
blink tr0,r63
|
|
|
LOCAL(large_divisor):
|
LOCAL(large_divisor):
|
mmulfx.w r5,r4,r4
|
mmulfx.w r5,r4,r4
|
shlrd r2,r9,r25
|
shlrd r2,r9,r25
|
shlri r25,32,r8
|
shlri r25,32,r8
|
msub.w r1,r4,r1
|
msub.w r1,r4,r1
|
|
|
mulu.l r1,r7,r4
|
mulu.l r1,r7,r4
|
addi r1,-3,r5
|
addi r1,-3,r5
|
mulu.l r5,r8,r5
|
mulu.l r5,r8,r5
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
|
the case may be, %0000000000000000 000.11111111111, still */
|
the case may be, %0000000000000000 000.11111111111, still */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
muls.l r1,r4,r4 /* leaving at least one sign bit. */
|
shlri r5,14-1,r8
|
shlri r5,14-1,r8
|
mulu.l r8,r7,r5
|
mulu.l r8,r7,r5
|
mshalds.l r1,r21,r1
|
mshalds.l r1,r21,r1
|
shari r4,26,r4
|
shari r4,26,r4
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
|
sub r25,r5,r25
|
sub r25,r5,r25
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
|
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
|
|
|
shlri r25,22,r21
|
shlri r25,22,r21
|
mulu.l r21,r1,r21
|
mulu.l r21,r1,r21
|
pta LOCAL(no_lo_adj),tr0
|
pta LOCAL(no_lo_adj),tr0
|
addi r22,32,r0
|
addi r22,32,r0
|
shlri r21,40,r21
|
shlri r21,40,r21
|
mulu.l r21,r7,r5
|
mulu.l r21,r7,r5
|
add r8,r21,r8
|
add r8,r21,r8
|
shlld r2,r0,r2
|
shlld r2,r0,r2
|
sub r25,r5,r25
|
sub r25,r5,r25
|
bgtu/u r7,r25,tr0 // no_lo_adj
|
bgtu/u r7,r25,tr0 // no_lo_adj
|
addi r8,1,r8
|
addi r8,1,r8
|
sub r25,r7,r25
|
sub r25,r7,r25
|
LOCAL(no_lo_adj):
|
LOCAL(no_lo_adj):
|
mextr4 r2,r25,r2
|
mextr4 r2,r25,r2
|
|
|
/* large_divisor: only needs a few adjustments. */
|
/* large_divisor: only needs a few adjustments. */
|
mulu.l r8,r6,r5
|
mulu.l r8,r6,r5
|
ptabs r18,tr0
|
ptabs r18,tr0
|
add r2,r6,r7
|
add r2,r6,r7
|
cmpgtu r5,r2,r8
|
cmpgtu r5,r2,r8
|
cmvne r8,r7,r2
|
cmvne r8,r7,r2
|
sub r2,r5,r2
|
sub r2,r5,r2
|
shlrd r2,r22,r2
|
shlrd r2,r22,r2
|
blink tr0,r63
|
blink tr0,r63
|
ENDFUNC(GLOBAL(umoddi3))
|
ENDFUNC(GLOBAL(umoddi3))
|
/* Note 1: To shift the result of the second divide stage so that the result
|
/* Note 1: To shift the result of the second divide stage so that the result
|
always fits into 32 bits, yet we still reduce the rest sufficiently
|
always fits into 32 bits, yet we still reduce the rest sufficiently
|
would require a lot of instructions to do the shifts just right. Using
|
would require a lot of instructions to do the shifts just right. Using
|
the full 64 bit shift result to multiply with the divisor would require
|
the full 64 bit shift result to multiply with the divisor would require
|
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
|
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
|
Fortunately, if the upper 32 bits of the shift result are nonzero, we
|
Fortunately, if the upper 32 bits of the shift result are nonzero, we
|
know that the rest after taking this partial result into account will
|
know that the rest after taking this partial result into account will
|
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
|
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
|
upper 32 bits of the partial result are nonzero. */
|
upper 32 bits of the partial result are nonzero. */
|
#endif /* __SHMEDIA__ */
|
#endif /* __SHMEDIA__ */
|
#endif /* L_umoddi3 */
|
#endif /* L_umoddi3 */
|
|
|
#ifdef L_moddi3
|
#ifdef L_moddi3
|
#ifdef __SHMEDIA__
|
#ifdef __SHMEDIA__
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
.global GLOBAL(moddi3)
|
.global GLOBAL(moddi3)
|
FUNC(GLOBAL(moddi3))
|
FUNC(GLOBAL(moddi3))
|
GLOBAL(moddi3):
|
GLOBAL(moddi3):
|
pta GLOBAL(umoddi3_internal),tr0
|
pta GLOBAL(umoddi3_internal),tr0
|
shari r2,63,r22
|
shari r2,63,r22
|
shari r3,63,r23
|
shari r3,63,r23
|
xor r2,r22,r2
|
xor r2,r22,r2
|
xor r3,r23,r3
|
xor r3,r23,r3
|
sub r2,r22,r2
|
sub r2,r22,r2
|
sub r3,r23,r3
|
sub r3,r23,r3
|
beq/u r22,r63,tr0
|
beq/u r22,r63,tr0
|
ptabs r18,tr1
|
ptabs r18,tr1
|
blink tr0,r18
|
blink tr0,r18
|
sub r63,r2,r2
|
sub r63,r2,r2
|
blink tr1,r63
|
blink tr1,r63
|
ENDFUNC(GLOBAL(moddi3))
|
ENDFUNC(GLOBAL(moddi3))
|
#endif /* __SHMEDIA__ */
|
#endif /* __SHMEDIA__ */
|
#endif /* L_moddi3 */
|
#endif /* L_moddi3 */
|
|
|
#ifdef L_set_fpscr
|
#ifdef L_set_fpscr
|
#if !defined (__SH2A_NOFPU__)
|
#if !defined (__SH2A_NOFPU__)
|
#if defined (__SH2E__) || defined (__SH2A__) || defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || __SH5__ == 32
|
#if defined (__SH2E__) || defined (__SH2A__) || defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || __SH5__ == 32
|
#ifdef __SH5__
|
#ifdef __SH5__
|
.mode SHcompact
|
.mode SHcompact
|
#endif
|
#endif
|
.global GLOBAL(set_fpscr)
|
.global GLOBAL(set_fpscr)
|
HIDDEN_FUNC(GLOBAL(set_fpscr))
|
HIDDEN_FUNC(GLOBAL(set_fpscr))
|
GLOBAL(set_fpscr):
|
GLOBAL(set_fpscr):
|
lds r4,fpscr
|
lds r4,fpscr
|
#ifdef __PIC__
|
#ifdef __PIC__
|
mov.l r12,@-r15
|
mov.l r12,@-r15
|
mova LOCAL(set_fpscr_L0),r0
|
mova LOCAL(set_fpscr_L0),r0
|
mov.l LOCAL(set_fpscr_L0),r12
|
mov.l LOCAL(set_fpscr_L0),r12
|
add r0,r12
|
add r0,r12
|
mov.l LOCAL(set_fpscr_L1),r0
|
mov.l LOCAL(set_fpscr_L1),r0
|
mov.l @(r0,r12),r1
|
mov.l @(r0,r12),r1
|
mov.l @r15+,r12
|
mov.l @r15+,r12
|
#else
|
#else
|
mov.l LOCAL(set_fpscr_L1),r1
|
mov.l LOCAL(set_fpscr_L1),r1
|
#endif
|
#endif
|
swap.w r4,r0
|
swap.w r4,r0
|
or #24,r0
|
or #24,r0
|
#ifndef FMOVD_WORKS
|
#ifndef FMOVD_WORKS
|
xor #16,r0
|
xor #16,r0
|
#endif
|
#endif
|
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
|
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
|
swap.w r0,r3
|
swap.w r0,r3
|
mov.l r3,@(4,r1)
|
mov.l r3,@(4,r1)
|
#else /* defined (__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
|
#else /* defined (__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
|
swap.w r0,r2
|
swap.w r0,r2
|
mov.l r2,@r1
|
mov.l r2,@r1
|
#endif
|
#endif
|
#ifndef FMOVD_WORKS
|
#ifndef FMOVD_WORKS
|
xor #8,r0
|
xor #8,r0
|
#else
|
#else
|
xor #24,r0
|
xor #24,r0
|
#endif
|
#endif
|
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
|
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
|
swap.w r0,r2
|
swap.w r0,r2
|
rts
|
rts
|
mov.l r2,@r1
|
mov.l r2,@r1
|
#else /* defined(__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
|
#else /* defined(__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
|
swap.w r0,r3
|
swap.w r0,r3
|
rts
|
rts
|
mov.l r3,@(4,r1)
|
mov.l r3,@(4,r1)
|
#endif
|
#endif
|
.align 2
|
.align 2
|
#ifdef __PIC__
|
#ifdef __PIC__
|
LOCAL(set_fpscr_L0):
|
LOCAL(set_fpscr_L0):
|
.long _GLOBAL_OFFSET_TABLE_
|
.long _GLOBAL_OFFSET_TABLE_
|
LOCAL(set_fpscr_L1):
|
LOCAL(set_fpscr_L1):
|
.long GLOBAL(fpscr_values@GOT)
|
.long GLOBAL(fpscr_values@GOT)
|
#else
|
#else
|
LOCAL(set_fpscr_L1):
|
LOCAL(set_fpscr_L1):
|
.long GLOBAL(fpscr_values)
|
.long GLOBAL(fpscr_values)
|
#endif
|
#endif
|
|
|
ENDFUNC(GLOBAL(set_fpscr))
|
ENDFUNC(GLOBAL(set_fpscr))
|
#ifndef NO_FPSCR_VALUES
|
#ifndef NO_FPSCR_VALUES
|
#ifdef __ELF__
|
#ifdef __ELF__
|
.comm GLOBAL(fpscr_values),8,4
|
.comm GLOBAL(fpscr_values),8,4
|
#else
|
#else
|
.comm GLOBAL(fpscr_values),8
|
.comm GLOBAL(fpscr_values),8
|
#endif /* ELF */
|
#endif /* ELF */
|
#endif /* NO_FPSCR_VALUES */
|
#endif /* NO_FPSCR_VALUES */
|
#endif /* SH2E / SH3E / SH4 */
|
#endif /* SH2E / SH3E / SH4 */
|
#endif /* __SH2A_NOFPU__ */
|
#endif /* __SH2A_NOFPU__ */
|
#endif /* L_set_fpscr */
|
#endif /* L_set_fpscr */
|
#ifdef L_ic_invalidate
|
#ifdef L_ic_invalidate
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.align 2
|
.align 2
|
.global GLOBAL(init_trampoline)
|
.global GLOBAL(init_trampoline)
|
HIDDEN_FUNC(GLOBAL(init_trampoline))
|
HIDDEN_FUNC(GLOBAL(init_trampoline))
|
GLOBAL(init_trampoline):
|
GLOBAL(init_trampoline):
|
st.l r0,8,r2
|
st.l r0,8,r2
|
#ifdef __LITTLE_ENDIAN__
|
#ifdef __LITTLE_ENDIAN__
|
movi 9,r20
|
movi 9,r20
|
shori 0x402b,r20
|
shori 0x402b,r20
|
shori 0xd101,r20
|
shori 0xd101,r20
|
shori 0xd002,r20
|
shori 0xd002,r20
|
#else
|
#else
|
movi 0xffffffffffffd002,r20
|
movi 0xffffffffffffd002,r20
|
shori 0xd101,r20
|
shori 0xd101,r20
|
shori 0x402b,r20
|
shori 0x402b,r20
|
shori 9,r20
|
shori 9,r20
|
#endif
|
#endif
|
st.q r0,0,r20
|
st.q r0,0,r20
|
st.l r0,12,r3
|
st.l r0,12,r3
|
ENDFUNC(GLOBAL(init_trampoline))
|
ENDFUNC(GLOBAL(init_trampoline))
|
.global GLOBAL(ic_invalidate)
|
.global GLOBAL(ic_invalidate)
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
GLOBAL(ic_invalidate):
|
GLOBAL(ic_invalidate):
|
ocbwb r0,0
|
ocbwb r0,0
|
synco
|
synco
|
icbi r0, 0
|
icbi r0, 0
|
ptabs r18, tr0
|
ptabs r18, tr0
|
synci
|
synci
|
blink tr0, r63
|
blink tr0, r63
|
ENDFUNC(GLOBAL(ic_invalidate))
|
ENDFUNC(GLOBAL(ic_invalidate))
|
#elif defined(__SH4A__)
|
#elif defined(__SH4A__)
|
.global GLOBAL(ic_invalidate)
|
.global GLOBAL(ic_invalidate)
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
GLOBAL(ic_invalidate):
|
GLOBAL(ic_invalidate):
|
ocbwb @r4
|
ocbwb @r4
|
synco
|
synco
|
rts
|
rts
|
icbi @r4
|
icbi @r4
|
ENDFUNC(GLOBAL(ic_invalidate))
|
ENDFUNC(GLOBAL(ic_invalidate))
|
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
|
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
|
/* For system code, we use ic_invalidate_line_i, but user code
|
/* For system code, we use ic_invalidate_line_i, but user code
|
needs a different mechanism. A kernel call is generally not
|
needs a different mechanism. A kernel call is generally not
|
available, and it would also be slow. Different SH4 variants use
|
available, and it would also be slow. Different SH4 variants use
|
different sizes and associativities of the Icache. We use a small
|
different sizes and associativities of the Icache. We use a small
|
bit of dispatch code that can be put hidden in every shared object,
|
bit of dispatch code that can be put hidden in every shared object,
|
which calls the actual processor-specific invalidation code in a
|
which calls the actual processor-specific invalidation code in a
|
separate module.
|
separate module.
|
Or if you have operating system support, the OS could mmap the
|
Or if you have operating system support, the OS could mmap the
|
procesor-specific code from a single page, since it is highly
|
procesor-specific code from a single page, since it is highly
|
repetitive. */
|
repetitive. */
|
.global GLOBAL(ic_invalidate)
|
.global GLOBAL(ic_invalidate)
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
HIDDEN_FUNC(GLOBAL(ic_invalidate))
|
GLOBAL(ic_invalidate):
|
GLOBAL(ic_invalidate):
|
mov.l 0f,r1
|
mov.l 0f,r1
|
#ifdef __pic__
|
#ifdef __pic__
|
mova 0f,r0
|
mova 0f,r0
|
mov.l 1f,r2
|
mov.l 1f,r2
|
add r1,r0
|
add r1,r0
|
mov.l @(r0,r2),r1
|
mov.l @(r0,r2),r1
|
#endif
|
#endif
|
ocbwb @r4
|
ocbwb @r4
|
mov.l @(8,r1),r0
|
mov.l @(8,r1),r0
|
sub r1,r4
|
sub r1,r4
|
and r4,r0
|
and r4,r0
|
add r1,r0
|
add r1,r0
|
jmp @r0
|
jmp @r0
|
mov.l @(4,r1),r0
|
mov.l @(4,r1),r0
|
#ifndef __pic__
|
#ifndef __pic__
|
0: .long GLOBAL(ic_invalidate_array)
|
0: .long GLOBAL(ic_invalidate_array)
|
#else /* __pic__ */
|
#else /* __pic__ */
|
.global GLOBAL(ic_invalidate_array)
|
.global GLOBAL(ic_invalidate_array)
|
/* ??? Why won't the assembler allow to add these two constants? */
|
/* ??? Why won't the assembler allow to add these two constants? */
|
0: .long _GLOBAL_OFFSET_TABLE_
|
0: .long _GLOBAL_OFFSET_TABLE_
|
1: .long GLOBAL(ic_invalidate_array)@GOT
|
1: .long GLOBAL(ic_invalidate_array)@GOT
|
ENDFUNC(GLOBAL(ic_invalidate))
|
ENDFUNC(GLOBAL(ic_invalidate))
|
#endif /* __pic__ */
|
#endif /* __pic__ */
|
#endif /* SH4 */
|
#endif /* SH4 */
|
#endif /* L_ic_invalidate */
|
#endif /* L_ic_invalidate */
|
|
|
#ifdef L_ic_invalidate_array
|
#ifdef L_ic_invalidate_array
|
#if defined(__SH4A__) || (defined (__FORCE_SH4A__) && (defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))))
|
#if defined(__SH4A__) || (defined (__FORCE_SH4A__) && (defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))))
|
.global GLOBAL(ic_invalidate_array)
|
.global GLOBAL(ic_invalidate_array)
|
/* This is needed when an SH4 dso with trampolines is used on SH4A. */
|
/* This is needed when an SH4 dso with trampolines is used on SH4A. */
|
.global GLOBAL(ic_invalidate_array)
|
.global GLOBAL(ic_invalidate_array)
|
FUNC(GLOBAL(ic_invalidate_array))
|
FUNC(GLOBAL(ic_invalidate_array))
|
GLOBAL(ic_invalidate_array):
|
GLOBAL(ic_invalidate_array):
|
add r1,r4
|
add r1,r4
|
synco
|
synco
|
rts
|
rts
|
icbi @r4
|
icbi @r4
|
.long 0
|
.long 0
|
ENDFUNC(GLOBAL(ic_invalidate_array))
|
ENDFUNC(GLOBAL(ic_invalidate_array))
|
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
|
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
|
.global GLOBAL(ic_invalidate_array)
|
.global GLOBAL(ic_invalidate_array)
|
.p2align 5
|
.p2align 5
|
FUNC(GLOBAL(ic_invalidate_array))
|
FUNC(GLOBAL(ic_invalidate_array))
|
/* This must be aligned to the beginning of a cache line. */
|
/* This must be aligned to the beginning of a cache line. */
|
GLOBAL(ic_invalidate_array):
|
GLOBAL(ic_invalidate_array):
|
#ifndef WAYS
|
#ifndef WAYS
|
#define WAYS 4
|
#define WAYS 4
|
#define WAY_SIZE 0x4000
|
#define WAY_SIZE 0x4000
|
#endif
|
#endif
|
#if WAYS == 1
|
#if WAYS == 1
|
.rept WAY_SIZE * WAYS / 32
|
.rept WAY_SIZE * WAYS / 32
|
rts
|
rts
|
nop
|
nop
|
.rept 7
|
.rept 7
|
.long WAY_SIZE - 32
|
.long WAY_SIZE - 32
|
.endr
|
.endr
|
.endr
|
.endr
|
#elif WAYS <= 6
|
#elif WAYS <= 6
|
.rept WAY_SIZE * WAYS / 32
|
.rept WAY_SIZE * WAYS / 32
|
braf r0
|
braf r0
|
add #-8,r0
|
add #-8,r0
|
.long WAY_SIZE + 8
|
.long WAY_SIZE + 8
|
.long WAY_SIZE - 32
|
.long WAY_SIZE - 32
|
.rept WAYS-2
|
.rept WAYS-2
|
braf r0
|
braf r0
|
nop
|
nop
|
.endr
|
.endr
|
.rept 7 - WAYS
|
.rept 7 - WAYS
|
rts
|
rts
|
nop
|
nop
|
.endr
|
.endr
|
.endr
|
.endr
|
#else /* WAYS > 6 */
|
#else /* WAYS > 6 */
|
/* This variant needs two different pages for mmap-ing. */
|
/* This variant needs two different pages for mmap-ing. */
|
.rept WAYS-1
|
.rept WAYS-1
|
.rept WAY_SIZE / 32
|
.rept WAY_SIZE / 32
|
braf r0
|
braf r0
|
nop
|
nop
|
.long WAY_SIZE
|
.long WAY_SIZE
|
.rept 6
|
.rept 6
|
.long WAY_SIZE - 32
|
.long WAY_SIZE - 32
|
.endr
|
.endr
|
.endr
|
.endr
|
.endr
|
.endr
|
.rept WAY_SIZE / 32
|
.rept WAY_SIZE / 32
|
rts
|
rts
|
.rept 15
|
.rept 15
|
nop
|
nop
|
.endr
|
.endr
|
.endr
|
.endr
|
#endif /* WAYS */
|
#endif /* WAYS */
|
ENDFUNC(GLOBAL(ic_invalidate_array))
|
ENDFUNC(GLOBAL(ic_invalidate_array))
|
#endif /* SH4 */
|
#endif /* SH4 */
|
#endif /* L_ic_invalidate_array */
|
#endif /* L_ic_invalidate_array */
|
|
|
#if defined (__SH5__) && __SH5__ == 32
|
#if defined (__SH5__) && __SH5__ == 32
|
#ifdef L_shcompact_call_trampoline
|
#ifdef L_shcompact_call_trampoline
|
.section .rodata
|
.section .rodata
|
.align 1
|
.align 1
|
LOCAL(ct_main_table):
|
LOCAL(ct_main_table):
|
.word LOCAL(ct_r2_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r2_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r2_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r2_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r2_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r2_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r3_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r4_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_fp) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r5_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r6_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r7_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r8_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_fph) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_fpl) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_ld) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_ret_wide) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_ret_wide) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_call_func) - datalabel LOCAL(ct_main_label)
|
.word LOCAL(ct_call_func) - datalabel LOCAL(ct_main_label)
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32, "ax"
|
.section .text..SHmedia32, "ax"
|
.align 2
|
.align 2
|
|
|
/* This function loads 64-bit general-purpose registers from the
|
/* This function loads 64-bit general-purpose registers from the
|
stack, from a memory address contained in them or from an FP
|
stack, from a memory address contained in them or from an FP
|
register, according to a cookie passed in r1. Its execution
|
register, according to a cookie passed in r1. Its execution
|
time is linear on the number of registers that actually have
|
time is linear on the number of registers that actually have
|
to be copied. See sh.h for details on the actual bit pattern.
|
to be copied. See sh.h for details on the actual bit pattern.
|
|
|
The function to be called is passed in r0. If a 32-bit return
|
The function to be called is passed in r0. If a 32-bit return
|
value is expected, the actual function will be tail-called,
|
value is expected, the actual function will be tail-called,
|
otherwise the return address will be stored in r10 (that the
|
otherwise the return address will be stored in r10 (that the
|
caller should expect to be clobbered) and the return value
|
caller should expect to be clobbered) and the return value
|
will be expanded into r2/r3 upon return. */
|
will be expanded into r2/r3 upon return. */
|
|
|
.global GLOBAL(GCC_shcompact_call_trampoline)
|
.global GLOBAL(GCC_shcompact_call_trampoline)
|
FUNC(GLOBAL(GCC_shcompact_call_trampoline))
|
FUNC(GLOBAL(GCC_shcompact_call_trampoline))
|
GLOBAL(GCC_shcompact_call_trampoline):
|
GLOBAL(GCC_shcompact_call_trampoline):
|
ptabs/l r0, tr0 /* Prepare to call the actual function. */
|
ptabs/l r0, tr0 /* Prepare to call the actual function. */
|
movi ((datalabel LOCAL(ct_main_table) - 31 * 2) >> 16) & 65535, r0
|
movi ((datalabel LOCAL(ct_main_table) - 31 * 2) >> 16) & 65535, r0
|
pt/l LOCAL(ct_loop), tr1
|
pt/l LOCAL(ct_loop), tr1
|
addz.l r1, r63, r1
|
addz.l r1, r63, r1
|
shori ((datalabel LOCAL(ct_main_table) - 31 * 2)) & 65535, r0
|
shori ((datalabel LOCAL(ct_main_table) - 31 * 2)) & 65535, r0
|
LOCAL(ct_loop):
|
LOCAL(ct_loop):
|
nsb r1, r28
|
nsb r1, r28
|
shlli r28, 1, r29
|
shlli r28, 1, r29
|
ldx.w r0, r29, r30
|
ldx.w r0, r29, r30
|
LOCAL(ct_main_label):
|
LOCAL(ct_main_label):
|
ptrel/l r30, tr2
|
ptrel/l r30, tr2
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r2_fp): /* Copy r2 from an FP register. */
|
LOCAL(ct_r2_fp): /* Copy r2 from an FP register. */
|
/* It must be dr0, so just do it. */
|
/* It must be dr0, so just do it. */
|
fmov.dq dr0, r2
|
fmov.dq dr0, r2
|
movi 7, r30
|
movi 7, r30
|
shlli r30, 29, r31
|
shlli r30, 29, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r3_fp): /* Copy r3 from an FP register. */
|
LOCAL(ct_r3_fp): /* Copy r3 from an FP register. */
|
/* It is either dr0 or dr2. */
|
/* It is either dr0 or dr2. */
|
movi 7, r30
|
movi 7, r30
|
shlri r1, 26, r32
|
shlri r1, 26, r32
|
shlli r30, 26, r31
|
shlli r30, 26, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
fmov.dq dr0, r3
|
fmov.dq dr0, r3
|
beqi/l r32, 4, tr1
|
beqi/l r32, 4, tr1
|
fmov.dq dr2, r3
|
fmov.dq dr2, r3
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r4_fp): /* Copy r4 from an FP register. */
|
LOCAL(ct_r4_fp): /* Copy r4 from an FP register. */
|
shlri r1, 23 - 3, r34
|
shlri r1, 23 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r4_fp_copy) - datalabel LOCAL(ct_r4_fp_base), r32
|
addi r33, LOCAL(ct_r4_fp_copy) - datalabel LOCAL(ct_r4_fp_base), r32
|
LOCAL(ct_r4_fp_base):
|
LOCAL(ct_r4_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7, r30
|
movi 7, r30
|
shlli r30, 23, r31
|
shlli r30, 23, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r4_fp_copy):
|
LOCAL(ct_r4_fp_copy):
|
fmov.dq dr0, r4
|
fmov.dq dr0, r4
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r4
|
fmov.dq dr2, r4
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r4
|
fmov.dq dr4, r4
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r5_fp): /* Copy r5 from an FP register. */
|
LOCAL(ct_r5_fp): /* Copy r5 from an FP register. */
|
shlri r1, 20 - 3, r34
|
shlri r1, 20 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r5_fp_copy) - datalabel LOCAL(ct_r5_fp_base), r32
|
addi r33, LOCAL(ct_r5_fp_copy) - datalabel LOCAL(ct_r5_fp_base), r32
|
LOCAL(ct_r5_fp_base):
|
LOCAL(ct_r5_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7, r30
|
movi 7, r30
|
shlli r30, 20, r31
|
shlli r30, 20, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r5_fp_copy):
|
LOCAL(ct_r5_fp_copy):
|
fmov.dq dr0, r5
|
fmov.dq dr0, r5
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r5
|
fmov.dq dr2, r5
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r5
|
fmov.dq dr4, r5
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr6, r5
|
fmov.dq dr6, r5
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r6_fph): /* Copy r6 from a high FP register. */
|
LOCAL(ct_r6_fph): /* Copy r6 from a high FP register. */
|
/* It must be dr8. */
|
/* It must be dr8. */
|
fmov.dq dr8, r6
|
fmov.dq dr8, r6
|
movi 15, r30
|
movi 15, r30
|
shlli r30, 16, r31
|
shlli r30, 16, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r6_fpl): /* Copy r6 from a low FP register. */
|
LOCAL(ct_r6_fpl): /* Copy r6 from a low FP register. */
|
shlri r1, 16 - 3, r34
|
shlri r1, 16 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r6_fp_copy) - datalabel LOCAL(ct_r6_fp_base), r32
|
addi r33, LOCAL(ct_r6_fp_copy) - datalabel LOCAL(ct_r6_fp_base), r32
|
LOCAL(ct_r6_fp_base):
|
LOCAL(ct_r6_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7, r30
|
movi 7, r30
|
shlli r30, 16, r31
|
shlli r30, 16, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r6_fp_copy):
|
LOCAL(ct_r6_fp_copy):
|
fmov.dq dr0, r6
|
fmov.dq dr0, r6
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r6
|
fmov.dq dr2, r6
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r6
|
fmov.dq dr4, r6
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr6, r6
|
fmov.dq dr6, r6
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r7_fph): /* Copy r7 from a high FP register. */
|
LOCAL(ct_r7_fph): /* Copy r7 from a high FP register. */
|
/* It is either dr8 or dr10. */
|
/* It is either dr8 or dr10. */
|
movi 15 << 12, r31
|
movi 15 << 12, r31
|
shlri r1, 12, r32
|
shlri r1, 12, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
fmov.dq dr8, r7
|
fmov.dq dr8, r7
|
beqi/l r32, 8, tr1
|
beqi/l r32, 8, tr1
|
fmov.dq dr10, r7
|
fmov.dq dr10, r7
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r7_fpl): /* Copy r7 from a low FP register. */
|
LOCAL(ct_r7_fpl): /* Copy r7 from a low FP register. */
|
shlri r1, 12 - 3, r34
|
shlri r1, 12 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r7_fp_copy) - datalabel LOCAL(ct_r7_fp_base), r32
|
addi r33, LOCAL(ct_r7_fp_copy) - datalabel LOCAL(ct_r7_fp_base), r32
|
LOCAL(ct_r7_fp_base):
|
LOCAL(ct_r7_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7 << 12, r31
|
movi 7 << 12, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r7_fp_copy):
|
LOCAL(ct_r7_fp_copy):
|
fmov.dq dr0, r7
|
fmov.dq dr0, r7
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r7
|
fmov.dq dr2, r7
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r7
|
fmov.dq dr4, r7
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr6, r7
|
fmov.dq dr6, r7
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r8_fph): /* Copy r8 from a high FP register. */
|
LOCAL(ct_r8_fph): /* Copy r8 from a high FP register. */
|
/* It is either dr8 or dr10. */
|
/* It is either dr8 or dr10. */
|
movi 15 << 8, r31
|
movi 15 << 8, r31
|
andi r1, 1 << 8, r32
|
andi r1, 1 << 8, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
fmov.dq dr8, r8
|
fmov.dq dr8, r8
|
beq/l r32, r63, tr1
|
beq/l r32, r63, tr1
|
fmov.dq dr10, r8
|
fmov.dq dr10, r8
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r8_fpl): /* Copy r8 from a low FP register. */
|
LOCAL(ct_r8_fpl): /* Copy r8 from a low FP register. */
|
shlri r1, 8 - 3, r34
|
shlri r1, 8 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r8_fp_copy) - datalabel LOCAL(ct_r8_fp_base), r32
|
addi r33, LOCAL(ct_r8_fp_copy) - datalabel LOCAL(ct_r8_fp_base), r32
|
LOCAL(ct_r8_fp_base):
|
LOCAL(ct_r8_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7 << 8, r31
|
movi 7 << 8, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r8_fp_copy):
|
LOCAL(ct_r8_fp_copy):
|
fmov.dq dr0, r8
|
fmov.dq dr0, r8
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r8
|
fmov.dq dr2, r8
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r8
|
fmov.dq dr4, r8
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr6, r8
|
fmov.dq dr6, r8
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r9_fph): /* Copy r9 from a high FP register. */
|
LOCAL(ct_r9_fph): /* Copy r9 from a high FP register. */
|
/* It is either dr8 or dr10. */
|
/* It is either dr8 or dr10. */
|
movi 15 << 4, r31
|
movi 15 << 4, r31
|
andi r1, 1 << 4, r32
|
andi r1, 1 << 4, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
fmov.dq dr8, r9
|
fmov.dq dr8, r9
|
beq/l r32, r63, tr1
|
beq/l r32, r63, tr1
|
fmov.dq dr10, r9
|
fmov.dq dr10, r9
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r9_fpl): /* Copy r9 from a low FP register. */
|
LOCAL(ct_r9_fpl): /* Copy r9 from a low FP register. */
|
shlri r1, 4 - 3, r34
|
shlri r1, 4 - 3, r34
|
andi r34, 3 << 3, r33
|
andi r34, 3 << 3, r33
|
addi r33, LOCAL(ct_r9_fp_copy) - datalabel LOCAL(ct_r9_fp_base), r32
|
addi r33, LOCAL(ct_r9_fp_copy) - datalabel LOCAL(ct_r9_fp_base), r32
|
LOCAL(ct_r9_fp_base):
|
LOCAL(ct_r9_fp_base):
|
ptrel/l r32, tr2
|
ptrel/l r32, tr2
|
movi 7 << 4, r31
|
movi 7 << 4, r31
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r9_fp_copy):
|
LOCAL(ct_r9_fp_copy):
|
fmov.dq dr0, r9
|
fmov.dq dr0, r9
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr2, r9
|
fmov.dq dr2, r9
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr4, r9
|
fmov.dq dr4, r9
|
blink tr1, r63
|
blink tr1, r63
|
fmov.dq dr6, r9
|
fmov.dq dr6, r9
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r2_ld): /* Copy r2 from a memory address. */
|
LOCAL(ct_r2_ld): /* Copy r2 from a memory address. */
|
pt/l LOCAL(ct_r2_load), tr2
|
pt/l LOCAL(ct_r2_load), tr2
|
movi 3, r30
|
movi 3, r30
|
shlli r30, 29, r31
|
shlli r30, 29, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r2, 8, r3
|
addi.l r2, 8, r3
|
ldx.q r2, r63, r2
|
ldx.q r2, r63, r2
|
/* Fall through. */
|
/* Fall through. */
|
LOCAL(ct_r3_ld): /* Copy r3 from a memory address. */
|
LOCAL(ct_r3_ld): /* Copy r3 from a memory address. */
|
pt/l LOCAL(ct_r3_load), tr2
|
pt/l LOCAL(ct_r3_load), tr2
|
movi 3, r30
|
movi 3, r30
|
shlli r30, 26, r31
|
shlli r30, 26, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r3, 8, r4
|
addi.l r3, 8, r4
|
ldx.q r3, r63, r3
|
ldx.q r3, r63, r3
|
LOCAL(ct_r4_ld): /* Copy r4 from a memory address. */
|
LOCAL(ct_r4_ld): /* Copy r4 from a memory address. */
|
pt/l LOCAL(ct_r4_load), tr2
|
pt/l LOCAL(ct_r4_load), tr2
|
movi 3, r30
|
movi 3, r30
|
shlli r30, 23, r31
|
shlli r30, 23, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r4, 8, r5
|
addi.l r4, 8, r5
|
ldx.q r4, r63, r4
|
ldx.q r4, r63, r4
|
LOCAL(ct_r5_ld): /* Copy r5 from a memory address. */
|
LOCAL(ct_r5_ld): /* Copy r5 from a memory address. */
|
pt/l LOCAL(ct_r5_load), tr2
|
pt/l LOCAL(ct_r5_load), tr2
|
movi 3, r30
|
movi 3, r30
|
shlli r30, 20, r31
|
shlli r30, 20, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r5, 8, r6
|
addi.l r5, 8, r6
|
ldx.q r5, r63, r5
|
ldx.q r5, r63, r5
|
LOCAL(ct_r6_ld): /* Copy r6 from a memory address. */
|
LOCAL(ct_r6_ld): /* Copy r6 from a memory address. */
|
pt/l LOCAL(ct_r6_load), tr2
|
pt/l LOCAL(ct_r6_load), tr2
|
movi 3 << 16, r31
|
movi 3 << 16, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r6, 8, r7
|
addi.l r6, 8, r7
|
ldx.q r6, r63, r6
|
ldx.q r6, r63, r6
|
LOCAL(ct_r7_ld): /* Copy r7 from a memory address. */
|
LOCAL(ct_r7_ld): /* Copy r7 from a memory address. */
|
pt/l LOCAL(ct_r7_load), tr2
|
pt/l LOCAL(ct_r7_load), tr2
|
movi 3 << 12, r31
|
movi 3 << 12, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r7, 8, r8
|
addi.l r7, 8, r8
|
ldx.q r7, r63, r7
|
ldx.q r7, r63, r7
|
LOCAL(ct_r8_ld): /* Copy r8 from a memory address. */
|
LOCAL(ct_r8_ld): /* Copy r8 from a memory address. */
|
pt/l LOCAL(ct_r8_load), tr2
|
pt/l LOCAL(ct_r8_load), tr2
|
movi 3 << 8, r31
|
movi 3 << 8, r31
|
and r1, r31, r32
|
and r1, r31, r32
|
andc r1, r31, r1
|
andc r1, r31, r1
|
beq/l r31, r32, tr2
|
beq/l r31, r32, tr2
|
addi.l r8, 8, r9
|
addi.l r8, 8, r9
|
ldx.q r8, r63, r8
|
ldx.q r8, r63, r8
|
LOCAL(ct_r9_ld): /* Copy r9 from a memory address. */
|
LOCAL(ct_r9_ld): /* Copy r9 from a memory address. */
|
pt/l LOCAL(ct_check_tramp), tr2
|
pt/l LOCAL(ct_check_tramp), tr2
|
ldx.q r9, r63, r9
|
ldx.q r9, r63, r9
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_r2_load):
|
LOCAL(ct_r2_load):
|
ldx.q r2, r63, r2
|
ldx.q r2, r63, r2
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r3_load):
|
LOCAL(ct_r3_load):
|
ldx.q r3, r63, r3
|
ldx.q r3, r63, r3
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r4_load):
|
LOCAL(ct_r4_load):
|
ldx.q r4, r63, r4
|
ldx.q r4, r63, r4
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r5_load):
|
LOCAL(ct_r5_load):
|
ldx.q r5, r63, r5
|
ldx.q r5, r63, r5
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r6_load):
|
LOCAL(ct_r6_load):
|
ldx.q r6, r63, r6
|
ldx.q r6, r63, r6
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r7_load):
|
LOCAL(ct_r7_load):
|
ldx.q r7, r63, r7
|
ldx.q r7, r63, r7
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r8_load):
|
LOCAL(ct_r8_load):
|
ldx.q r8, r63, r8
|
ldx.q r8, r63, r8
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r2_pop): /* Pop r2 from the stack. */
|
LOCAL(ct_r2_pop): /* Pop r2 from the stack. */
|
movi 1, r30
|
movi 1, r30
|
ldx.q r15, r63, r2
|
ldx.q r15, r63, r2
|
shlli r30, 29, r31
|
shlli r30, 29, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r3_pop): /* Pop r3 from the stack. */
|
LOCAL(ct_r3_pop): /* Pop r3 from the stack. */
|
movi 1, r30
|
movi 1, r30
|
ldx.q r15, r63, r3
|
ldx.q r15, r63, r3
|
shlli r30, 26, r31
|
shlli r30, 26, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r4_pop): /* Pop r4 from the stack. */
|
LOCAL(ct_r4_pop): /* Pop r4 from the stack. */
|
movi 1, r30
|
movi 1, r30
|
ldx.q r15, r63, r4
|
ldx.q r15, r63, r4
|
shlli r30, 23, r31
|
shlli r30, 23, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r5_pop): /* Pop r5 from the stack. */
|
LOCAL(ct_r5_pop): /* Pop r5 from the stack. */
|
movi 1, r30
|
movi 1, r30
|
ldx.q r15, r63, r5
|
ldx.q r15, r63, r5
|
shlli r30, 20, r31
|
shlli r30, 20, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r6_pop): /* Pop r6 from the stack. */
|
LOCAL(ct_r6_pop): /* Pop r6 from the stack. */
|
movi 1, r30
|
movi 1, r30
|
ldx.q r15, r63, r6
|
ldx.q r15, r63, r6
|
shlli r30, 16, r31
|
shlli r30, 16, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r7_pop): /* Pop r7 from the stack. */
|
LOCAL(ct_r7_pop): /* Pop r7 from the stack. */
|
ldx.q r15, r63, r7
|
ldx.q r15, r63, r7
|
movi 1 << 12, r31
|
movi 1 << 12, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_r8_pop): /* Pop r8 from the stack. */
|
LOCAL(ct_r8_pop): /* Pop r8 from the stack. */
|
ldx.q r15, r63, r8
|
ldx.q r15, r63, r8
|
movi 1 << 8, r31
|
movi 1 << 8, r31
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
andc r1, r31, r1
|
andc r1, r31, r1
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ct_pop_seq): /* Pop a sequence of registers off the stack. */
|
LOCAL(ct_pop_seq): /* Pop a sequence of registers off the stack. */
|
andi r1, 7 << 1, r30
|
andi r1, 7 << 1, r30
|
movi (LOCAL(ct_end_of_pop_seq) >> 16) & 65535, r32
|
movi (LOCAL(ct_end_of_pop_seq) >> 16) & 65535, r32
|
shlli r30, 2, r31
|
shlli r30, 2, r31
|
shori LOCAL(ct_end_of_pop_seq) & 65535, r32
|
shori LOCAL(ct_end_of_pop_seq) & 65535, r32
|
sub.l r32, r31, r33
|
sub.l r32, r31, r33
|
ptabs/l r33, tr2
|
ptabs/l r33, tr2
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ct_start_of_pop_seq): /* Beginning of pop sequence. */
|
LOCAL(ct_start_of_pop_seq): /* Beginning of pop sequence. */
|
ldx.q r15, r63, r3
|
ldx.q r15, r63, r3
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
ldx.q r15, r63, r4
|
ldx.q r15, r63, r4
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
ldx.q r15, r63, r5
|
ldx.q r15, r63, r5
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
ldx.q r15, r63, r6
|
ldx.q r15, r63, r6
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
ldx.q r15, r63, r7
|
ldx.q r15, r63, r7
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
ldx.q r15, r63, r8
|
ldx.q r15, r63, r8
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
LOCAL(ct_r9_pop): /* Pop r9 from the stack. */
|
LOCAL(ct_r9_pop): /* Pop r9 from the stack. */
|
ldx.q r15, r63, r9
|
ldx.q r15, r63, r9
|
addi.l r15, 8, r15
|
addi.l r15, 8, r15
|
LOCAL(ct_end_of_pop_seq): /* Label used to compute first pop instruction. */
|
LOCAL(ct_end_of_pop_seq): /* Label used to compute first pop instruction. */
|
LOCAL(ct_check_tramp): /* Check whether we need a trampoline. */
|
LOCAL(ct_check_tramp): /* Check whether we need a trampoline. */
|
pt/u LOCAL(ct_ret_wide), tr2
|
pt/u LOCAL(ct_ret_wide), tr2
|
andi r1, 1, r1
|
andi r1, 1, r1
|
bne/u r1, r63, tr2
|
bne/u r1, r63, tr2
|
LOCAL(ct_call_func): /* Just branch to the function. */
|
LOCAL(ct_call_func): /* Just branch to the function. */
|
blink tr0, r63
|
blink tr0, r63
|
LOCAL(ct_ret_wide): /* Call the function, so that we can unpack its
|
LOCAL(ct_ret_wide): /* Call the function, so that we can unpack its
|
64-bit return value. */
|
64-bit return value. */
|
add.l r18, r63, r10
|
add.l r18, r63, r10
|
blink tr0, r18
|
blink tr0, r18
|
ptabs r10, tr0
|
ptabs r10, tr0
|
#if __LITTLE_ENDIAN__
|
#if __LITTLE_ENDIAN__
|
shari r2, 32, r3
|
shari r2, 32, r3
|
add.l r2, r63, r2
|
add.l r2, r63, r2
|
#else
|
#else
|
add.l r2, r63, r3
|
add.l r2, r63, r3
|
shari r2, 32, r2
|
shari r2, 32, r2
|
#endif
|
#endif
|
blink tr0, r63
|
blink tr0, r63
|
|
|
ENDFUNC(GLOBAL(GCC_shcompact_call_trampoline))
|
ENDFUNC(GLOBAL(GCC_shcompact_call_trampoline))
|
#endif /* L_shcompact_call_trampoline */
|
#endif /* L_shcompact_call_trampoline */
|
|
|
#ifdef L_shcompact_return_trampoline
|
#ifdef L_shcompact_return_trampoline
|
/* This function does the converse of the code in `ret_wide'
|
/* This function does the converse of the code in `ret_wide'
|
above. It is tail-called by SHcompact functions returning
|
above. It is tail-called by SHcompact functions returning
|
64-bit non-floating-point values, to pack the 32-bit values in
|
64-bit non-floating-point values, to pack the 32-bit values in
|
r2 and r3 into r2. */
|
r2 and r3 into r2. */
|
|
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32, "ax"
|
.section .text..SHmedia32, "ax"
|
.align 2
|
.align 2
|
.global GLOBAL(GCC_shcompact_return_trampoline)
|
.global GLOBAL(GCC_shcompact_return_trampoline)
|
HIDDEN_FUNC(GLOBAL(GCC_shcompact_return_trampoline))
|
HIDDEN_FUNC(GLOBAL(GCC_shcompact_return_trampoline))
|
GLOBAL(GCC_shcompact_return_trampoline):
|
GLOBAL(GCC_shcompact_return_trampoline):
|
ptabs/l r18, tr0
|
ptabs/l r18, tr0
|
#if __LITTLE_ENDIAN__
|
#if __LITTLE_ENDIAN__
|
addz.l r2, r63, r2
|
addz.l r2, r63, r2
|
shlli r3, 32, r3
|
shlli r3, 32, r3
|
#else
|
#else
|
addz.l r3, r63, r3
|
addz.l r3, r63, r3
|
shlli r2, 32, r2
|
shlli r2, 32, r2
|
#endif
|
#endif
|
or r3, r2, r2
|
or r3, r2, r2
|
blink tr0, r63
|
blink tr0, r63
|
|
|
ENDFUNC(GLOBAL(GCC_shcompact_return_trampoline))
|
ENDFUNC(GLOBAL(GCC_shcompact_return_trampoline))
|
#endif /* L_shcompact_return_trampoline */
|
#endif /* L_shcompact_return_trampoline */
|
|
|
#ifdef L_shcompact_incoming_args
|
#ifdef L_shcompact_incoming_args
|
.section .rodata
|
.section .rodata
|
.align 1
|
.align 1
|
LOCAL(ia_main_table):
|
LOCAL(ia_main_table):
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r2_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r2_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r2_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r2_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r3_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r3_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r3_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r3_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r4_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r4_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r4_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r4_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r5_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r5_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r5_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r5_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r6_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r6_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r6_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r6_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r7_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r7_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r7_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r7_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r8_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r8_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r8_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r8_push) - datalabel LOCAL(ia_main_label)
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word 1 /* Invalid, just loop */
|
.word LOCAL(ia_r9_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r9_ld) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
|
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
|
.mode SHmedia
|
.mode SHmedia
|
.section .text..SHmedia32, "ax"
|
.section .text..SHmedia32, "ax"
|
.align 2
|
.align 2
|
|
|
/* This function stores 64-bit general-purpose registers back in
|
/* This function stores 64-bit general-purpose registers back in
|
the stack, and loads the address in which each register
|
the stack, and loads the address in which each register
|
was stored into itself. The lower 32 bits of r17 hold the address
|
was stored into itself. The lower 32 bits of r17 hold the address
|
to begin storing, and the upper 32 bits of r17 hold the cookie.
|
to begin storing, and the upper 32 bits of r17 hold the cookie.
|
Its execution time is linear on the
|
Its execution time is linear on the
|
number of registers that actually have to be copied, and it is
|
number of registers that actually have to be copied, and it is
|
optimized for structures larger than 64 bits, as opposed to
|
optimized for structures larger than 64 bits, as opposed to
|
individual `long long' arguments. See sh.h for details on the
|
individual `long long' arguments. See sh.h for details on the
|
actual bit pattern. */
|
actual bit pattern. */
|
|
|
.global GLOBAL(GCC_shcompact_incoming_args)
|
.global GLOBAL(GCC_shcompact_incoming_args)
|
FUNC(GLOBAL(GCC_shcompact_incoming_args))
|
FUNC(GLOBAL(GCC_shcompact_incoming_args))
|
GLOBAL(GCC_shcompact_incoming_args):
|
GLOBAL(GCC_shcompact_incoming_args):
|
ptabs/l r18, tr0 /* Prepare to return. */
|
ptabs/l r18, tr0 /* Prepare to return. */
|
shlri r17, 32, r0 /* Load the cookie. */
|
shlri r17, 32, r0 /* Load the cookie. */
|
movi ((datalabel LOCAL(ia_main_table) - 31 * 2) >> 16) & 65535, r43
|
movi ((datalabel LOCAL(ia_main_table) - 31 * 2) >> 16) & 65535, r43
|
pt/l LOCAL(ia_loop), tr1
|
pt/l LOCAL(ia_loop), tr1
|
add.l r17, r63, r17
|
add.l r17, r63, r17
|
shori ((datalabel LOCAL(ia_main_table) - 31 * 2)) & 65535, r43
|
shori ((datalabel LOCAL(ia_main_table) - 31 * 2)) & 65535, r43
|
LOCAL(ia_loop):
|
LOCAL(ia_loop):
|
nsb r0, r36
|
nsb r0, r36
|
shlli r36, 1, r37
|
shlli r36, 1, r37
|
ldx.w r43, r37, r38
|
ldx.w r43, r37, r38
|
LOCAL(ia_main_label):
|
LOCAL(ia_main_label):
|
ptrel/l r38, tr2
|
ptrel/l r38, tr2
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ia_r2_ld): /* Store r2 and load its address. */
|
LOCAL(ia_r2_ld): /* Store r2 and load its address. */
|
movi 3, r38
|
movi 3, r38
|
shlli r38, 29, r39
|
shlli r38, 29, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r2
|
stx.q r17, r63, r2
|
add.l r17, r63, r2
|
add.l r17, r63, r2
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r3_ld): /* Store r3 and load its address. */
|
LOCAL(ia_r3_ld): /* Store r3 and load its address. */
|
movi 3, r38
|
movi 3, r38
|
shlli r38, 26, r39
|
shlli r38, 26, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r3
|
stx.q r17, r63, r3
|
add.l r17, r63, r3
|
add.l r17, r63, r3
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r4_ld): /* Store r4 and load its address. */
|
LOCAL(ia_r4_ld): /* Store r4 and load its address. */
|
movi 3, r38
|
movi 3, r38
|
shlli r38, 23, r39
|
shlli r38, 23, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r4
|
stx.q r17, r63, r4
|
add.l r17, r63, r4
|
add.l r17, r63, r4
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r5_ld): /* Store r5 and load its address. */
|
LOCAL(ia_r5_ld): /* Store r5 and load its address. */
|
movi 3, r38
|
movi 3, r38
|
shlli r38, 20, r39
|
shlli r38, 20, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r5
|
stx.q r17, r63, r5
|
add.l r17, r63, r5
|
add.l r17, r63, r5
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r6_ld): /* Store r6 and load its address. */
|
LOCAL(ia_r6_ld): /* Store r6 and load its address. */
|
movi 3, r38
|
movi 3, r38
|
shlli r38, 16, r39
|
shlli r38, 16, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r6
|
stx.q r17, r63, r6
|
add.l r17, r63, r6
|
add.l r17, r63, r6
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r7_ld): /* Store r7 and load its address. */
|
LOCAL(ia_r7_ld): /* Store r7 and load its address. */
|
movi 3 << 12, r39
|
movi 3 << 12, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r7
|
stx.q r17, r63, r7
|
add.l r17, r63, r7
|
add.l r17, r63, r7
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r8_ld): /* Store r8 and load its address. */
|
LOCAL(ia_r8_ld): /* Store r8 and load its address. */
|
movi 3 << 8, r39
|
movi 3 << 8, r39
|
and r0, r39, r40
|
and r0, r39, r40
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r8
|
stx.q r17, r63, r8
|
add.l r17, r63, r8
|
add.l r17, r63, r8
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
beq/u r39, r40, tr1
|
beq/u r39, r40, tr1
|
LOCAL(ia_r9_ld): /* Store r9 and load its address. */
|
LOCAL(ia_r9_ld): /* Store r9 and load its address. */
|
stx.q r17, r63, r9
|
stx.q r17, r63, r9
|
add.l r17, r63, r9
|
add.l r17, r63, r9
|
blink tr0, r63
|
blink tr0, r63
|
LOCAL(ia_r2_push): /* Push r2 onto the stack. */
|
LOCAL(ia_r2_push): /* Push r2 onto the stack. */
|
movi 1, r38
|
movi 1, r38
|
shlli r38, 29, r39
|
shlli r38, 29, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r2
|
stx.q r17, r63, r2
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r3_push): /* Push r3 onto the stack. */
|
LOCAL(ia_r3_push): /* Push r3 onto the stack. */
|
movi 1, r38
|
movi 1, r38
|
shlli r38, 26, r39
|
shlli r38, 26, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r3
|
stx.q r17, r63, r3
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r4_push): /* Push r4 onto the stack. */
|
LOCAL(ia_r4_push): /* Push r4 onto the stack. */
|
movi 1, r38
|
movi 1, r38
|
shlli r38, 23, r39
|
shlli r38, 23, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r4
|
stx.q r17, r63, r4
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r5_push): /* Push r5 onto the stack. */
|
LOCAL(ia_r5_push): /* Push r5 onto the stack. */
|
movi 1, r38
|
movi 1, r38
|
shlli r38, 20, r39
|
shlli r38, 20, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r5
|
stx.q r17, r63, r5
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r6_push): /* Push r6 onto the stack. */
|
LOCAL(ia_r6_push): /* Push r6 onto the stack. */
|
movi 1, r38
|
movi 1, r38
|
shlli r38, 16, r39
|
shlli r38, 16, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r6
|
stx.q r17, r63, r6
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r7_push): /* Push r7 onto the stack. */
|
LOCAL(ia_r7_push): /* Push r7 onto the stack. */
|
movi 1 << 12, r39
|
movi 1 << 12, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r7
|
stx.q r17, r63, r7
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_r8_push): /* Push r8 onto the stack. */
|
LOCAL(ia_r8_push): /* Push r8 onto the stack. */
|
movi 1 << 8, r39
|
movi 1 << 8, r39
|
andc r0, r39, r0
|
andc r0, r39, r0
|
stx.q r17, r63, r8
|
stx.q r17, r63, r8
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
blink tr1, r63
|
blink tr1, r63
|
LOCAL(ia_push_seq): /* Push a sequence of registers onto the stack. */
|
LOCAL(ia_push_seq): /* Push a sequence of registers onto the stack. */
|
andi r0, 7 << 1, r38
|
andi r0, 7 << 1, r38
|
movi (LOCAL(ia_end_of_push_seq) >> 16) & 65535, r40
|
movi (LOCAL(ia_end_of_push_seq) >> 16) & 65535, r40
|
shlli r38, 2, r39
|
shlli r38, 2, r39
|
shori LOCAL(ia_end_of_push_seq) & 65535, r40
|
shori LOCAL(ia_end_of_push_seq) & 65535, r40
|
sub.l r40, r39, r41
|
sub.l r40, r39, r41
|
ptabs/l r41, tr2
|
ptabs/l r41, tr2
|
blink tr2, r63
|
blink tr2, r63
|
LOCAL(ia_stack_of_push_seq): /* Beginning of push sequence. */
|
LOCAL(ia_stack_of_push_seq): /* Beginning of push sequence. */
|
stx.q r17, r63, r3
|
stx.q r17, r63, r3
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
stx.q r17, r63, r4
|
stx.q r17, r63, r4
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
stx.q r17, r63, r5
|
stx.q r17, r63, r5
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
stx.q r17, r63, r6
|
stx.q r17, r63, r6
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
stx.q r17, r63, r7
|
stx.q r17, r63, r7
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
stx.q r17, r63, r8
|
stx.q r17, r63, r8
|
addi.l r17, 8, r17
|
addi.l r17, 8, r17
|
LOCAL(ia_r9_push): /* Push r9 onto the stack. */
|
LOCAL(ia_r9_push): /* Push r9 onto the stack. */
|
stx.q r17, r63, r9
|
stx.q r17, r63, r9
|
LOCAL(ia_return): /* Return. */
|
LOCAL(ia_return): /* Return. */
|
blink tr0, r63
|
blink tr0, r63
|
LOCAL(ia_end_of_push_seq): /* Label used to compute the first push instruction. */
|
LOCAL(ia_end_of_push_seq): /* Label used to compute the first push instruction. */
|
ENDFUNC(GLOBAL(GCC_shcompact_incoming_args))
|
ENDFUNC(GLOBAL(GCC_shcompact_incoming_args))
|
#endif /* L_shcompact_incoming_args */
|
#endif /* L_shcompact_incoming_args */
|
#endif
|
#endif
|
#if __SH5__
|
#if __SH5__
|
#ifdef L_nested_trampoline
|
#ifdef L_nested_trampoline
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
#else
|
#else
|
.text
|
.text
|
#endif
|
#endif
|
.align 3 /* It is copied in units of 8 bytes in SHmedia mode. */
|
.align 3 /* It is copied in units of 8 bytes in SHmedia mode. */
|
.global GLOBAL(GCC_nested_trampoline)
|
.global GLOBAL(GCC_nested_trampoline)
|
HIDDEN_FUNC(GLOBAL(GCC_nested_trampoline))
|
HIDDEN_FUNC(GLOBAL(GCC_nested_trampoline))
|
GLOBAL(GCC_nested_trampoline):
|
GLOBAL(GCC_nested_trampoline):
|
.mode SHmedia
|
.mode SHmedia
|
ptrel/u r63, tr0
|
ptrel/u r63, tr0
|
gettr tr0, r0
|
gettr tr0, r0
|
#if __SH5__ == 64
|
#if __SH5__ == 64
|
ld.q r0, 24, r1
|
ld.q r0, 24, r1
|
#else
|
#else
|
ld.l r0, 24, r1
|
ld.l r0, 24, r1
|
#endif
|
#endif
|
ptabs/l r1, tr1
|
ptabs/l r1, tr1
|
#if __SH5__ == 64
|
#if __SH5__ == 64
|
ld.q r0, 32, r1
|
ld.q r0, 32, r1
|
#else
|
#else
|
ld.l r0, 28, r1
|
ld.l r0, 28, r1
|
#endif
|
#endif
|
blink tr1, r63
|
blink tr1, r63
|
|
|
ENDFUNC(GLOBAL(GCC_nested_trampoline))
|
ENDFUNC(GLOBAL(GCC_nested_trampoline))
|
#endif /* L_nested_trampoline */
|
#endif /* L_nested_trampoline */
|
#endif /* __SH5__ */
|
#endif /* __SH5__ */
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
#ifdef L_push_pop_shmedia_regs
|
#ifdef L_push_pop_shmedia_regs
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
.mode SHmedia
|
.mode SHmedia
|
.align 2
|
.align 2
|
#ifndef __SH4_NOFPU__
|
#ifndef __SH4_NOFPU__
|
.global GLOBAL(GCC_push_shmedia_regs)
|
.global GLOBAL(GCC_push_shmedia_regs)
|
FUNC(GLOBAL(GCC_push_shmedia_regs))
|
FUNC(GLOBAL(GCC_push_shmedia_regs))
|
GLOBAL(GCC_push_shmedia_regs):
|
GLOBAL(GCC_push_shmedia_regs):
|
addi.l r15, -14*8, r15
|
addi.l r15, -14*8, r15
|
fst.d r15, 13*8, dr62
|
fst.d r15, 13*8, dr62
|
fst.d r15, 12*8, dr60
|
fst.d r15, 12*8, dr60
|
fst.d r15, 11*8, dr58
|
fst.d r15, 11*8, dr58
|
fst.d r15, 10*8, dr56
|
fst.d r15, 10*8, dr56
|
fst.d r15, 9*8, dr54
|
fst.d r15, 9*8, dr54
|
fst.d r15, 8*8, dr52
|
fst.d r15, 8*8, dr52
|
fst.d r15, 7*8, dr50
|
fst.d r15, 7*8, dr50
|
fst.d r15, 6*8, dr48
|
fst.d r15, 6*8, dr48
|
fst.d r15, 5*8, dr46
|
fst.d r15, 5*8, dr46
|
fst.d r15, 4*8, dr44
|
fst.d r15, 4*8, dr44
|
fst.d r15, 3*8, dr42
|
fst.d r15, 3*8, dr42
|
fst.d r15, 2*8, dr40
|
fst.d r15, 2*8, dr40
|
fst.d r15, 1*8, dr38
|
fst.d r15, 1*8, dr38
|
fst.d r15, 0*8, dr36
|
fst.d r15, 0*8, dr36
|
#else /* ! __SH4_NOFPU__ */
|
#else /* ! __SH4_NOFPU__ */
|
.global GLOBAL(GCC_push_shmedia_regs_nofpu)
|
.global GLOBAL(GCC_push_shmedia_regs_nofpu)
|
FUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
|
FUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
|
GLOBAL(GCC_push_shmedia_regs_nofpu):
|
GLOBAL(GCC_push_shmedia_regs_nofpu):
|
#endif /* ! __SH4_NOFPU__ */
|
#endif /* ! __SH4_NOFPU__ */
|
ptabs/l r18, tr0
|
ptabs/l r18, tr0
|
addi.l r15, -27*8, r15
|
addi.l r15, -27*8, r15
|
gettr tr7, r62
|
gettr tr7, r62
|
gettr tr6, r61
|
gettr tr6, r61
|
gettr tr5, r60
|
gettr tr5, r60
|
st.q r15, 26*8, r62
|
st.q r15, 26*8, r62
|
st.q r15, 25*8, r61
|
st.q r15, 25*8, r61
|
st.q r15, 24*8, r60
|
st.q r15, 24*8, r60
|
st.q r15, 23*8, r59
|
st.q r15, 23*8, r59
|
st.q r15, 22*8, r58
|
st.q r15, 22*8, r58
|
st.q r15, 21*8, r57
|
st.q r15, 21*8, r57
|
st.q r15, 20*8, r56
|
st.q r15, 20*8, r56
|
st.q r15, 19*8, r55
|
st.q r15, 19*8, r55
|
st.q r15, 18*8, r54
|
st.q r15, 18*8, r54
|
st.q r15, 17*8, r53
|
st.q r15, 17*8, r53
|
st.q r15, 16*8, r52
|
st.q r15, 16*8, r52
|
st.q r15, 15*8, r51
|
st.q r15, 15*8, r51
|
st.q r15, 14*8, r50
|
st.q r15, 14*8, r50
|
st.q r15, 13*8, r49
|
st.q r15, 13*8, r49
|
st.q r15, 12*8, r48
|
st.q r15, 12*8, r48
|
st.q r15, 11*8, r47
|
st.q r15, 11*8, r47
|
st.q r15, 10*8, r46
|
st.q r15, 10*8, r46
|
st.q r15, 9*8, r45
|
st.q r15, 9*8, r45
|
st.q r15, 8*8, r44
|
st.q r15, 8*8, r44
|
st.q r15, 7*8, r35
|
st.q r15, 7*8, r35
|
st.q r15, 6*8, r34
|
st.q r15, 6*8, r34
|
st.q r15, 5*8, r33
|
st.q r15, 5*8, r33
|
st.q r15, 4*8, r32
|
st.q r15, 4*8, r32
|
st.q r15, 3*8, r31
|
st.q r15, 3*8, r31
|
st.q r15, 2*8, r30
|
st.q r15, 2*8, r30
|
st.q r15, 1*8, r29
|
st.q r15, 1*8, r29
|
st.q r15, 0*8, r28
|
st.q r15, 0*8, r28
|
blink tr0, r63
|
blink tr0, r63
|
#ifndef __SH4_NOFPU__
|
#ifndef __SH4_NOFPU__
|
ENDFUNC(GLOBAL(GCC_push_shmedia_regs))
|
ENDFUNC(GLOBAL(GCC_push_shmedia_regs))
|
#else
|
#else
|
ENDFUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
|
ENDFUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
|
#endif
|
#endif
|
#ifndef __SH4_NOFPU__
|
#ifndef __SH4_NOFPU__
|
.global GLOBAL(GCC_pop_shmedia_regs)
|
.global GLOBAL(GCC_pop_shmedia_regs)
|
FUNC(GLOBAL(GCC_pop_shmedia_regs))
|
FUNC(GLOBAL(GCC_pop_shmedia_regs))
|
GLOBAL(GCC_pop_shmedia_regs):
|
GLOBAL(GCC_pop_shmedia_regs):
|
pt .L0, tr1
|
pt .L0, tr1
|
movi 41*8, r0
|
movi 41*8, r0
|
fld.d r15, 40*8, dr62
|
fld.d r15, 40*8, dr62
|
fld.d r15, 39*8, dr60
|
fld.d r15, 39*8, dr60
|
fld.d r15, 38*8, dr58
|
fld.d r15, 38*8, dr58
|
fld.d r15, 37*8, dr56
|
fld.d r15, 37*8, dr56
|
fld.d r15, 36*8, dr54
|
fld.d r15, 36*8, dr54
|
fld.d r15, 35*8, dr52
|
fld.d r15, 35*8, dr52
|
fld.d r15, 34*8, dr50
|
fld.d r15, 34*8, dr50
|
fld.d r15, 33*8, dr48
|
fld.d r15, 33*8, dr48
|
fld.d r15, 32*8, dr46
|
fld.d r15, 32*8, dr46
|
fld.d r15, 31*8, dr44
|
fld.d r15, 31*8, dr44
|
fld.d r15, 30*8, dr42
|
fld.d r15, 30*8, dr42
|
fld.d r15, 29*8, dr40
|
fld.d r15, 29*8, dr40
|
fld.d r15, 28*8, dr38
|
fld.d r15, 28*8, dr38
|
fld.d r15, 27*8, dr36
|
fld.d r15, 27*8, dr36
|
blink tr1, r63
|
blink tr1, r63
|
#else /* ! __SH4_NOFPU__ */
|
#else /* ! __SH4_NOFPU__ */
|
.global GLOBAL(GCC_pop_shmedia_regs_nofpu)
|
.global GLOBAL(GCC_pop_shmedia_regs_nofpu)
|
FUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
|
FUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
|
GLOBAL(GCC_pop_shmedia_regs_nofpu):
|
GLOBAL(GCC_pop_shmedia_regs_nofpu):
|
#endif /* ! __SH4_NOFPU__ */
|
#endif /* ! __SH4_NOFPU__ */
|
movi 27*8, r0
|
movi 27*8, r0
|
.L0:
|
.L0:
|
ptabs r18, tr0
|
ptabs r18, tr0
|
ld.q r15, 26*8, r62
|
ld.q r15, 26*8, r62
|
ld.q r15, 25*8, r61
|
ld.q r15, 25*8, r61
|
ld.q r15, 24*8, r60
|
ld.q r15, 24*8, r60
|
ptabs r62, tr7
|
ptabs r62, tr7
|
ptabs r61, tr6
|
ptabs r61, tr6
|
ptabs r60, tr5
|
ptabs r60, tr5
|
ld.q r15, 23*8, r59
|
ld.q r15, 23*8, r59
|
ld.q r15, 22*8, r58
|
ld.q r15, 22*8, r58
|
ld.q r15, 21*8, r57
|
ld.q r15, 21*8, r57
|
ld.q r15, 20*8, r56
|
ld.q r15, 20*8, r56
|
ld.q r15, 19*8, r55
|
ld.q r15, 19*8, r55
|
ld.q r15, 18*8, r54
|
ld.q r15, 18*8, r54
|
ld.q r15, 17*8, r53
|
ld.q r15, 17*8, r53
|
ld.q r15, 16*8, r52
|
ld.q r15, 16*8, r52
|
ld.q r15, 15*8, r51
|
ld.q r15, 15*8, r51
|
ld.q r15, 14*8, r50
|
ld.q r15, 14*8, r50
|
ld.q r15, 13*8, r49
|
ld.q r15, 13*8, r49
|
ld.q r15, 12*8, r48
|
ld.q r15, 12*8, r48
|
ld.q r15, 11*8, r47
|
ld.q r15, 11*8, r47
|
ld.q r15, 10*8, r46
|
ld.q r15, 10*8, r46
|
ld.q r15, 9*8, r45
|
ld.q r15, 9*8, r45
|
ld.q r15, 8*8, r44
|
ld.q r15, 8*8, r44
|
ld.q r15, 7*8, r35
|
ld.q r15, 7*8, r35
|
ld.q r15, 6*8, r34
|
ld.q r15, 6*8, r34
|
ld.q r15, 5*8, r33
|
ld.q r15, 5*8, r33
|
ld.q r15, 4*8, r32
|
ld.q r15, 4*8, r32
|
ld.q r15, 3*8, r31
|
ld.q r15, 3*8, r31
|
ld.q r15, 2*8, r30
|
ld.q r15, 2*8, r30
|
ld.q r15, 1*8, r29
|
ld.q r15, 1*8, r29
|
ld.q r15, 0*8, r28
|
ld.q r15, 0*8, r28
|
add.l r15, r0, r15
|
add.l r15, r0, r15
|
blink tr0, r63
|
blink tr0, r63
|
|
|
#ifndef __SH4_NOFPU__
|
#ifndef __SH4_NOFPU__
|
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs))
|
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs))
|
#else
|
#else
|
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
|
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
|
#endif
|
#endif
|
#endif /* __SH5__ == 32 */
|
#endif /* __SH5__ == 32 */
|
#endif /* L_push_pop_shmedia_regs */
|
#endif /* L_push_pop_shmedia_regs */
|
|
|
#ifdef L_div_table
|
#ifdef L_div_table
|
#if __SH5__
|
#if __SH5__
|
#if defined(__pic__) && defined(__SHMEDIA__)
|
#if defined(__pic__) && defined(__SHMEDIA__)
|
.global GLOBAL(sdivsi3)
|
.global GLOBAL(sdivsi3)
|
FUNC(GLOBAL(sdivsi3))
|
FUNC(GLOBAL(sdivsi3))
|
#if __SH5__ == 32
|
#if __SH5__ == 32
|
.section .text..SHmedia32,"ax"
|
.section .text..SHmedia32,"ax"
|
#else
|
#else
|
.text
|
.text
|
#endif
|
#endif
|
#if 0
|
#if 0
|
/* ??? FIXME: Presumably due to a linker bug, exporting data symbols
|
/* ??? FIXME: Presumably due to a linker bug, exporting data symbols
|
in a text section does not work (at least for shared libraries):
|
in a text section does not work (at least for shared libraries):
|
the linker sets the LSB of the address as if this was SHmedia code. */
|
the linker sets the LSB of the address as if this was SHmedia code. */
|
#define TEXT_DATA_BUG
|
#define TEXT_DATA_BUG
|
#endif
|
#endif
|
.align 2
|
.align 2
|
// inputs: r4,r5
|
// inputs: r4,r5
|
// clobbered: r1,r18,r19,r20,r21,r25,tr0
|
// clobbered: r1,r18,r19,r20,r21,r25,tr0
|
// result in r0
|
// result in r0
|
.global GLOBAL(sdivsi3)
|
.global GLOBAL(sdivsi3)
|
GLOBAL(sdivsi3):
|
GLOBAL(sdivsi3):
|
#ifdef TEXT_DATA_BUG
|
#ifdef TEXT_DATA_BUG
|
ptb datalabel Local_div_table,tr0
|
ptb datalabel Local_div_table,tr0
|
#else
|
#else
|
ptb GLOBAL(div_table_internal),tr0
|
ptb GLOBAL(div_table_internal),tr0
|
#endif
|
#endif
|
nsb r5, r1
|
nsb r5, r1
|
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
|
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
|
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
|
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
|
/* bubble */
|
/* bubble */
|
gettr tr0,r20
|
gettr tr0,r20
|
ldx.ub r20, r21, r19 // u0.8
|
ldx.ub r20, r21, r19 // u0.8
|
shari r25, 32, r25 // normalize to s2.30
|
shari r25, 32, r25 // normalize to s2.30
|
shlli r21, 1, r21
|
shlli r21, 1, r21
|
muls.l r25, r19, r19 // s2.38
|
muls.l r25, r19, r19 // s2.38
|
ldx.w r20, r21, r21 // s2.14
|
ldx.w r20, r21, r21 // s2.14
|
ptabs r18, tr0
|
ptabs r18, tr0
|
shari r19, 24, r19 // truncate to s2.14
|
shari r19, 24, r19 // truncate to s2.14
|
sub r21, r19, r19 // some 11 bit inverse in s1.14
|
sub r21, r19, r19 // some 11 bit inverse in s1.14
|
muls.l r19, r19, r21 // u0.28
|
muls.l r19, r19, r21 // u0.28
|
sub r63, r1, r1
|
sub r63, r1, r1
|
addi r1, 92, r1
|
addi r1, 92, r1
|
muls.l r25, r21, r18 // s2.58
|
muls.l r25, r21, r18 // s2.58
|
shlli r19, 45, r19 // multiply by two and convert to s2.58
|
shlli r19, 45, r19 // multiply by two and convert to s2.58
|
/* bubble */
|
/* bubble */
|
sub r19, r18, r18
|
sub r19, r18, r18
|
shari r18, 28, r18 // some 22 bit inverse in s1.30
|
shari r18, 28, r18 // some 22 bit inverse in s1.30
|
muls.l r18, r25, r0 // s2.60
|
muls.l r18, r25, r0 // s2.60
|
muls.l r18, r4, r25 // s32.30
|
muls.l r18, r4, r25 // s32.30
|
/* bubble */
|
/* bubble */
|
shari r0, 16, r19 // s-16.44
|
shari r0, 16, r19 // s-16.44
|
muls.l r19, r18, r19 // s-16.74
|
muls.l r19, r18, r19 // s-16.74
|
shari r25, 63, r0
|
shari r25, 63, r0
|
shari r4, 14, r18 // s19.-14
|
shari r4, 14, r18 // s19.-14
|
shari r19, 30, r19 // s-16.44
|
shari r19, 30, r19 // s-16.44
|
muls.l r19, r18, r19 // s15.30
|
muls.l r19, r18, r19 // s15.30
|
xor r21, r0, r21 // You could also use the constant 1 << 27.
|
xor r21, r0, r21 // You could also use the constant 1 << 27.
|
add r21, r25, r21
|
add r21, r25, r21
|
sub r21, r19, r21
|
sub r21, r19, r21
|
shard r21, r1, r21
|
shard r21, r1, r21
|
sub r21, r0, r0
|
sub r21, r0, r0
|
blink tr0, r63
|
blink tr0, r63
|
ENDFUNC(GLOBAL(sdivsi3))
|
ENDFUNC(GLOBAL(sdivsi3))
|
/* This table has been generated by divtab.c .
|
/* This table has been generated by divtab.c .
|
Defects for bias -330:
|
Defects for bias -330:
|
Max defect: 6.081536e-07 at -1.000000e+00
|
Max defect: 6.081536e-07 at -1.000000e+00
|
Min defect: 2.849516e-08 at 1.030651e+00
|
Min defect: 2.849516e-08 at 1.030651e+00
|
Max 2nd step defect: 9.606539e-12 at -1.000000e+00
|
Max 2nd step defect: 9.606539e-12 at -1.000000e+00
|
Min 2nd step defect: 0.000000e+00 at 0.000000e+00
|
Min 2nd step defect: 0.000000e+00 at 0.000000e+00
|
Defect at 1: 1.238659e-07
|
Defect at 1: 1.238659e-07
|
Defect at -2: 1.061708e-07 */
|
Defect at -2: 1.061708e-07 */
|
#else /* ! __pic__ || ! __SHMEDIA__ */
|
#else /* ! __pic__ || ! __SHMEDIA__ */
|
.section .rodata
|
.section .rodata
|
#endif /* __pic__ */
|
#endif /* __pic__ */
|
#if defined(TEXT_DATA_BUG) && defined(__pic__) && defined(__SHMEDIA__)
|
#if defined(TEXT_DATA_BUG) && defined(__pic__) && defined(__SHMEDIA__)
|
.balign 2
|
.balign 2
|
.type Local_div_table,@object
|
.type Local_div_table,@object
|
.size Local_div_table,128
|
.size Local_div_table,128
|
/* negative division constants */
|
/* negative division constants */
|
.word -16638
|
.word -16638
|
.word -17135
|
.word -17135
|
.word -17737
|
.word -17737
|
.word -18433
|
.word -18433
|
.word -19103
|
.word -19103
|
.word -19751
|
.word -19751
|
.word -20583
|
.word -20583
|
.word -21383
|
.word -21383
|
.word -22343
|
.word -22343
|
.word -23353
|
.word -23353
|
.word -24407
|
.word -24407
|
.word -25582
|
.word -25582
|
.word -26863
|
.word -26863
|
.word -28382
|
.word -28382
|
.word -29965
|
.word -29965
|
.word -31800
|
.word -31800
|
/* negative division factors */
|
/* negative division factors */
|
.byte 66
|
.byte 66
|
.byte 70
|
.byte 70
|
.byte 75
|
.byte 75
|
.byte 81
|
.byte 81
|
.byte 87
|
.byte 87
|
.byte 93
|
.byte 93
|
.byte 101
|
.byte 101
|
.byte 109
|
.byte 109
|
.byte 119
|
.byte 119
|
.byte 130
|
.byte 130
|
.byte 142
|
.byte 142
|
.byte 156
|
.byte 156
|
.byte 172
|
.byte 172
|
.byte 192
|
.byte 192
|
.byte 214
|
.byte 214
|
.byte 241
|
.byte 241
|
.skip 16
|
.skip 16
|
Local_div_table:
|
Local_div_table:
|
.skip 16
|
.skip 16
|
/* positive division factors */
|
/* positive division factors */
|
.byte 241
|
.byte 241
|
.byte 214
|
.byte 214
|
.byte 192
|
.byte 192
|
.byte 172
|
.byte 172
|
.byte 156
|
.byte 156
|
.byte 142
|
.byte 142
|
.byte 130
|
.byte 130
|
.byte 119
|
.byte 119
|
.byte 109
|
.byte 109
|
.byte 101
|
.byte 101
|
.byte 93
|
.byte 93
|
.byte 87
|
.byte 87
|
.byte 81
|
.byte 81
|
.byte 75
|
.byte 75
|
.byte 70
|
.byte 70
|
.byte 66
|
.byte 66
|
/* positive division constants */
|
/* positive division constants */
|
.word 31801
|
.word 31801
|
.word 29966
|
.word 29966
|
.word 28383
|
.word 28383
|
.word 26864
|
.word 26864
|
.word 25583
|
.word 25583
|
.word 24408
|
.word 24408
|
.word 23354
|
.word 23354
|
.word 22344
|
.word 22344
|
.word 21384
|
.word 21384
|
.word 20584
|
.word 20584
|
.word 19752
|
.word 19752
|
.word 19104
|
.word 19104
|
.word 18434
|
.word 18434
|
.word 17738
|
.word 17738
|
.word 17136
|
.word 17136
|
.word 16639
|
.word 16639
|
.section .rodata
|
.section .rodata
|
#endif /* TEXT_DATA_BUG */
|
#endif /* TEXT_DATA_BUG */
|
.balign 2
|
.balign 2
|
.type GLOBAL(div_table),@object
|
.type GLOBAL(div_table),@object
|
.size GLOBAL(div_table),128
|
.size GLOBAL(div_table),128
|
/* negative division constants */
|
/* negative division constants */
|
.word -16638
|
.word -16638
|
.word -17135
|
.word -17135
|
.word -17737
|
.word -17737
|
.word -18433
|
.word -18433
|
.word -19103
|
.word -19103
|
.word -19751
|
.word -19751
|
.word -20583
|
.word -20583
|
.word -21383
|
.word -21383
|
.word -22343
|
.word -22343
|
.word -23353
|
.word -23353
|
.word -24407
|
.word -24407
|
.word -25582
|
.word -25582
|
.word -26863
|
.word -26863
|
.word -28382
|
.word -28382
|
.word -29965
|
.word -29965
|
.word -31800
|
.word -31800
|
/* negative division factors */
|
/* negative division factors */
|
.byte 66
|
.byte 66
|
.byte 70
|
.byte 70
|
.byte 75
|
.byte 75
|
.byte 81
|
.byte 81
|
.byte 87
|
.byte 87
|
.byte 93
|
.byte 93
|
.byte 101
|
.byte 101
|
.byte 109
|
.byte 109
|
.byte 119
|
.byte 119
|
.byte 130
|
.byte 130
|
.byte 142
|
.byte 142
|
.byte 156
|
.byte 156
|
.byte 172
|
.byte 172
|
.byte 192
|
.byte 192
|
.byte 214
|
.byte 214
|
.byte 241
|
.byte 241
|
.skip 16
|
.skip 16
|
.global GLOBAL(div_table)
|
.global GLOBAL(div_table)
|
GLOBAL(div_table):
|
GLOBAL(div_table):
|
HIDDEN_ALIAS(div_table_internal,div_table)
|
HIDDEN_ALIAS(div_table_internal,div_table)
|
.skip 16
|
.skip 16
|
/* positive division factors */
|
/* positive division factors */
|
.byte 241
|
.byte 241
|
.byte 214
|
.byte 214
|
.byte 192
|
.byte 192
|
.byte 172
|
.byte 172
|
.byte 156
|
.byte 156
|
.byte 142
|
.byte 142
|
.byte 130
|
.byte 130
|
.byte 119
|
.byte 119
|
.byte 109
|
.byte 109
|
.byte 101
|
.byte 101
|
.byte 93
|
.byte 93
|
.byte 87
|
.byte 87
|
.byte 81
|
.byte 81
|
.byte 75
|
.byte 75
|
.byte 70
|
.byte 70
|
.byte 66
|
.byte 66
|
/* positive division constants */
|
/* positive division constants */
|
.word 31801
|
.word 31801
|
.word 29966
|
.word 29966
|
.word 28383
|
.word 28383
|
.word 26864
|
.word 26864
|
.word 25583
|
.word 25583
|
.word 24408
|
.word 24408
|
.word 23354
|
.word 23354
|
.word 22344
|
.word 22344
|
.word 21384
|
.word 21384
|
.word 20584
|
.word 20584
|
.word 19752
|
.word 19752
|
.word 19104
|
.word 19104
|
.word 18434
|
.word 18434
|
.word 17738
|
.word 17738
|
.word 17136
|
.word 17136
|
.word 16639
|
.word 16639
|
|
|
#elif defined (__SH3__) || defined (__SH3E__) || defined (__SH4__) || defined (__SH4_SINGLE__) || defined (__SH4_SINGLE_ONLY__) || defined (__SH4_NOFPU__)
|
#elif defined (__SH3__) || defined (__SH3E__) || defined (__SH4__) || defined (__SH4_SINGLE__) || defined (__SH4_SINGLE_ONLY__) || defined (__SH4_NOFPU__)
|
/* This code used shld, thus is not suitable for SH1 / SH2. */
|
/* This code used shld, thus is not suitable for SH1 / SH2. */
|
|
|
/* Signed / unsigned division without use of FPU, optimized for SH4.
|
/* Signed / unsigned division without use of FPU, optimized for SH4.
|
Uses a lookup table for divisors in the range -128 .. +128, and
|
Uses a lookup table for divisors in the range -128 .. +128, and
|
div1 with case distinction for larger divisors in three more ranges.
|
div1 with case distinction for larger divisors in three more ranges.
|
The code is lumped together with the table to allow the use of mova. */
|
The code is lumped together with the table to allow the use of mova. */
|
#ifdef __LITTLE_ENDIAN__
|
#ifdef __LITTLE_ENDIAN__
|
#define L_LSB 0
|
#define L_LSB 0
|
#define L_LSWMSB 1
|
#define L_LSWMSB 1
|
#define L_MSWLSB 2
|
#define L_MSWLSB 2
|
#else
|
#else
|
#define L_LSB 3
|
#define L_LSB 3
|
#define L_LSWMSB 2
|
#define L_LSWMSB 2
|
#define L_MSWLSB 1
|
#define L_MSWLSB 1
|
#endif
|
#endif
|
|
|
.balign 4
|
.balign 4
|
.global GLOBAL(udivsi3_i4i)
|
.global GLOBAL(udivsi3_i4i)
|
FUNC(GLOBAL(udivsi3_i4i))
|
FUNC(GLOBAL(udivsi3_i4i))
|
GLOBAL(udivsi3_i4i):
|
GLOBAL(udivsi3_i4i):
|
mov.w LOCAL(c128_w), r1
|
mov.w LOCAL(c128_w), r1
|
div0u
|
div0u
|
mov r4,r0
|
mov r4,r0
|
shlr8 r0
|
shlr8 r0
|
cmp/hi r1,r5
|
cmp/hi r1,r5
|
extu.w r5,r1
|
extu.w r5,r1
|
bf LOCAL(udiv_le128)
|
bf LOCAL(udiv_le128)
|
cmp/eq r5,r1
|
cmp/eq r5,r1
|
bf LOCAL(udiv_ge64k)
|
bf LOCAL(udiv_ge64k)
|
shlr r0
|
shlr r0
|
mov r5,r1
|
mov r5,r1
|
shll16 r5
|
shll16 r5
|
mov.l r4,@-r15
|
mov.l r4,@-r15
|
div1 r5,r0
|
div1 r5,r0
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
bra LOCAL(udiv_25)
|
bra LOCAL(udiv_25)
|
div1 r5,r0
|
div1 r5,r0
|
|
|
LOCAL(div_le128):
|
LOCAL(div_le128):
|
mova LOCAL(div_table_ix),r0
|
mova LOCAL(div_table_ix),r0
|
bra LOCAL(div_le128_2)
|
bra LOCAL(div_le128_2)
|
mov.b @(r0,r5),r1
|
mov.b @(r0,r5),r1
|
LOCAL(udiv_le128):
|
LOCAL(udiv_le128):
|
mov.l r4,@-r15
|
mov.l r4,@-r15
|
mova LOCAL(div_table_ix),r0
|
mova LOCAL(div_table_ix),r0
|
mov.b @(r0,r5),r1
|
mov.b @(r0,r5),r1
|
mov.l r5,@-r15
|
mov.l r5,@-r15
|
LOCAL(div_le128_2):
|
LOCAL(div_le128_2):
|
mova LOCAL(div_table_inv),r0
|
mova LOCAL(div_table_inv),r0
|
mov.l @(r0,r1),r1
|
mov.l @(r0,r1),r1
|
mov r5,r0
|
mov r5,r0
|
tst #0xfe,r0
|
tst #0xfe,r0
|
mova LOCAL(div_table_clz),r0
|
mova LOCAL(div_table_clz),r0
|
dmulu.l r1,r4
|
dmulu.l r1,r4
|
mov.b @(r0,r5),r1
|
mov.b @(r0,r5),r1
|
bt/s LOCAL(div_by_1)
|
bt/s LOCAL(div_by_1)
|
mov r4,r0
|
mov r4,r0
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
sts mach,r0
|
sts mach,r0
|
/* clrt */
|
/* clrt */
|
addc r4,r0
|
addc r4,r0
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
rotcr r0
|
rotcr r0
|
rts
|
rts
|
shld r1,r0
|
shld r1,r0
|
|
|
LOCAL(div_by_1_neg):
|
LOCAL(div_by_1_neg):
|
neg r4,r0
|
neg r4,r0
|
LOCAL(div_by_1):
|
LOCAL(div_by_1):
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
rts
|
rts
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
|
|
LOCAL(div_ge64k):
|
LOCAL(div_ge64k):
|
bt/s LOCAL(div_r8)
|
bt/s LOCAL(div_r8)
|
div0u
|
div0u
|
shll8 r5
|
shll8 r5
|
bra LOCAL(div_ge64k_2)
|
bra LOCAL(div_ge64k_2)
|
div1 r5,r0
|
div1 r5,r0
|
LOCAL(udiv_ge64k):
|
LOCAL(udiv_ge64k):
|
cmp/hi r0,r5
|
cmp/hi r0,r5
|
mov r5,r1
|
mov r5,r1
|
bt LOCAL(udiv_r8)
|
bt LOCAL(udiv_r8)
|
shll8 r5
|
shll8 r5
|
mov.l r4,@-r15
|
mov.l r4,@-r15
|
div1 r5,r0
|
div1 r5,r0
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
LOCAL(div_ge64k_2):
|
LOCAL(div_ge64k_2):
|
div1 r5,r0
|
div1 r5,r0
|
mov.l LOCAL(zero_l),r1
|
mov.l LOCAL(zero_l),r1
|
.rept 4
|
.rept 4
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
div1 r5,r0
|
div1 r5,r0
|
mov.w LOCAL(m256_w),r1
|
mov.w LOCAL(m256_w),r1
|
div1 r5,r0
|
div1 r5,r0
|
mov.b r0,@(L_LSWMSB,r15)
|
mov.b r0,@(L_LSWMSB,r15)
|
xor r4,r0
|
xor r4,r0
|
and r1,r0
|
and r1,r0
|
bra LOCAL(div_ge64k_end)
|
bra LOCAL(div_ge64k_end)
|
xor r4,r0
|
xor r4,r0
|
|
|
LOCAL(div_r8):
|
LOCAL(div_r8):
|
shll16 r4
|
shll16 r4
|
bra LOCAL(div_r8_2)
|
bra LOCAL(div_r8_2)
|
shll8 r4
|
shll8 r4
|
LOCAL(udiv_r8):
|
LOCAL(udiv_r8):
|
mov.l r4,@-r15
|
mov.l r4,@-r15
|
shll16 r4
|
shll16 r4
|
clrt
|
clrt
|
shll8 r4
|
shll8 r4
|
mov.l r5,@-r15
|
mov.l r5,@-r15
|
LOCAL(div_r8_2):
|
LOCAL(div_r8_2):
|
rotcl r4
|
rotcl r4
|
mov r0,r1
|
mov r0,r1
|
div1 r5,r1
|
div1 r5,r1
|
mov r4,r0
|
mov r4,r0
|
rotcl r0
|
rotcl r0
|
mov r5,r4
|
mov r5,r4
|
div1 r5,r1
|
div1 r5,r1
|
.rept 5
|
.rept 5
|
rotcl r0; div1 r5,r1
|
rotcl r0; div1 r5,r1
|
.endr
|
.endr
|
rotcl r0
|
rotcl r0
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
div1 r4,r1
|
div1 r4,r1
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
rts
|
rts
|
rotcl r0
|
rotcl r0
|
|
|
ENDFUNC(GLOBAL(udivsi3_i4i))
|
ENDFUNC(GLOBAL(udivsi3_i4i))
|
|
|
.global GLOBAL(sdivsi3_i4i)
|
.global GLOBAL(sdivsi3_i4i)
|
FUNC(GLOBAL(sdivsi3_i4i))
|
FUNC(GLOBAL(sdivsi3_i4i))
|
/* This is link-compatible with a GLOBAL(sdivsi3) call,
|
/* This is link-compatible with a GLOBAL(sdivsi3) call,
|
but we effectively clobber only r1. */
|
but we effectively clobber only r1. */
|
GLOBAL(sdivsi3_i4i):
|
GLOBAL(sdivsi3_i4i):
|
mov.l r4,@-r15
|
mov.l r4,@-r15
|
cmp/pz r5
|
cmp/pz r5
|
mov.w LOCAL(c128_w), r1
|
mov.w LOCAL(c128_w), r1
|
bt/s LOCAL(pos_divisor)
|
bt/s LOCAL(pos_divisor)
|
cmp/pz r4
|
cmp/pz r4
|
mov.l r5,@-r15
|
mov.l r5,@-r15
|
neg r5,r5
|
neg r5,r5
|
bt/s LOCAL(neg_result)
|
bt/s LOCAL(neg_result)
|
cmp/hi r1,r5
|
cmp/hi r1,r5
|
neg r4,r4
|
neg r4,r4
|
LOCAL(pos_result):
|
LOCAL(pos_result):
|
extu.w r5,r0
|
extu.w r5,r0
|
bf LOCAL(div_le128)
|
bf LOCAL(div_le128)
|
cmp/eq r5,r0
|
cmp/eq r5,r0
|
mov r4,r0
|
mov r4,r0
|
shlr8 r0
|
shlr8 r0
|
bf/s LOCAL(div_ge64k)
|
bf/s LOCAL(div_ge64k)
|
cmp/hi r0,r5
|
cmp/hi r0,r5
|
div0u
|
div0u
|
shll16 r5
|
shll16 r5
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
LOCAL(udiv_25):
|
LOCAL(udiv_25):
|
mov.l LOCAL(zero_l),r1
|
mov.l LOCAL(zero_l),r1
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
div1 r5,r0
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
.rept 3
|
.rept 3
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.b r0,@(L_MSWLSB,r15)
|
mov.b r0,@(L_MSWLSB,r15)
|
xtrct r4,r0
|
xtrct r4,r0
|
swap.w r0,r0
|
swap.w r0,r0
|
.rept 8
|
.rept 8
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.b r0,@(L_LSWMSB,r15)
|
mov.b r0,@(L_LSWMSB,r15)
|
LOCAL(div_ge64k_end):
|
LOCAL(div_ge64k_end):
|
.rept 8
|
.rept 8
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
|
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
|
extu.b r0,r0
|
extu.b r0,r0
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
or r4,r0
|
or r4,r0
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
rts
|
rts
|
rotcl r0
|
rotcl r0
|
|
|
LOCAL(div_le128_neg):
|
LOCAL(div_le128_neg):
|
tst #0xfe,r0
|
tst #0xfe,r0
|
mova LOCAL(div_table_ix),r0
|
mova LOCAL(div_table_ix),r0
|
mov.b @(r0,r5),r1
|
mov.b @(r0,r5),r1
|
mova LOCAL(div_table_inv),r0
|
mova LOCAL(div_table_inv),r0
|
bt/s LOCAL(div_by_1_neg)
|
bt/s LOCAL(div_by_1_neg)
|
mov.l @(r0,r1),r1
|
mov.l @(r0,r1),r1
|
mova LOCAL(div_table_clz),r0
|
mova LOCAL(div_table_clz),r0
|
dmulu.l r1,r4
|
dmulu.l r1,r4
|
mov.b @(r0,r5),r1
|
mov.b @(r0,r5),r1
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
sts mach,r0
|
sts mach,r0
|
/* clrt */
|
/* clrt */
|
addc r4,r0
|
addc r4,r0
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
rotcr r0
|
rotcr r0
|
shld r1,r0
|
shld r1,r0
|
rts
|
rts
|
neg r0,r0
|
neg r0,r0
|
|
|
LOCAL(pos_divisor):
|
LOCAL(pos_divisor):
|
mov.l r5,@-r15
|
mov.l r5,@-r15
|
bt/s LOCAL(pos_result)
|
bt/s LOCAL(pos_result)
|
cmp/hi r1,r5
|
cmp/hi r1,r5
|
neg r4,r4
|
neg r4,r4
|
LOCAL(neg_result):
|
LOCAL(neg_result):
|
extu.w r5,r0
|
extu.w r5,r0
|
bf LOCAL(div_le128_neg)
|
bf LOCAL(div_le128_neg)
|
cmp/eq r5,r0
|
cmp/eq r5,r0
|
mov r4,r0
|
mov r4,r0
|
shlr8 r0
|
shlr8 r0
|
bf/s LOCAL(div_ge64k_neg)
|
bf/s LOCAL(div_ge64k_neg)
|
cmp/hi r0,r5
|
cmp/hi r0,r5
|
div0u
|
div0u
|
mov.l LOCAL(zero_l),r1
|
mov.l LOCAL(zero_l),r1
|
shll16 r5
|
shll16 r5
|
div1 r5,r0
|
div1 r5,r0
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
.rept 7
|
.rept 7
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.b r0,@(L_MSWLSB,r15)
|
mov.b r0,@(L_MSWLSB,r15)
|
xtrct r4,r0
|
xtrct r4,r0
|
swap.w r0,r0
|
swap.w r0,r0
|
.rept 8
|
.rept 8
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.b r0,@(L_LSWMSB,r15)
|
mov.b r0,@(L_LSWMSB,r15)
|
LOCAL(div_ge64k_neg_end):
|
LOCAL(div_ge64k_neg_end):
|
.rept 8
|
.rept 8
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
|
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
|
extu.b r0,r1
|
extu.b r0,r1
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
or r4,r1
|
or r4,r1
|
LOCAL(div_r8_neg_end):
|
LOCAL(div_r8_neg_end):
|
mov.l @r15+,r4
|
mov.l @r15+,r4
|
rotcl r1
|
rotcl r1
|
rts
|
rts
|
neg r1,r0
|
neg r1,r0
|
|
|
LOCAL(div_ge64k_neg):
|
LOCAL(div_ge64k_neg):
|
bt/s LOCAL(div_r8_neg)
|
bt/s LOCAL(div_r8_neg)
|
div0u
|
div0u
|
shll8 r5
|
shll8 r5
|
mov.l LOCAL(zero_l),r1
|
mov.l LOCAL(zero_l),r1
|
.rept 6
|
.rept 6
|
div1 r5,r0
|
div1 r5,r0
|
.endr
|
.endr
|
mov.l r1,@-r15
|
mov.l r1,@-r15
|
div1 r5,r0
|
div1 r5,r0
|
mov.w LOCAL(m256_w),r1
|
mov.w LOCAL(m256_w),r1
|
div1 r5,r0
|
div1 r5,r0
|
mov.b r0,@(L_LSWMSB,r15)
|
mov.b r0,@(L_LSWMSB,r15)
|
xor r4,r0
|
xor r4,r0
|
and r1,r0
|
and r1,r0
|
bra LOCAL(div_ge64k_neg_end)
|
bra LOCAL(div_ge64k_neg_end)
|
xor r4,r0
|
xor r4,r0
|
|
|
LOCAL(c128_w):
|
LOCAL(c128_w):
|
.word 128
|
.word 128
|
|
|
LOCAL(div_r8_neg):
|
LOCAL(div_r8_neg):
|
clrt
|
clrt
|
shll16 r4
|
shll16 r4
|
mov r4,r1
|
mov r4,r1
|
shll8 r1
|
shll8 r1
|
mov r5,r4
|
mov r5,r4
|
.rept 7
|
.rept 7
|
rotcl r1; div1 r5,r0
|
rotcl r1; div1 r5,r0
|
.endr
|
.endr
|
mov.l @r15+,r5
|
mov.l @r15+,r5
|
rotcl r1
|
rotcl r1
|
bra LOCAL(div_r8_neg_end)
|
bra LOCAL(div_r8_neg_end)
|
div1 r4,r0
|
div1 r4,r0
|
|
|
LOCAL(m256_w):
|
LOCAL(m256_w):
|
.word 0xff00
|
.word 0xff00
|
/* This table has been generated by divtab-sh4.c. */
|
/* This table has been generated by divtab-sh4.c. */
|
.balign 4
|
.balign 4
|
LOCAL(div_table_clz):
|
LOCAL(div_table_clz):
|
.byte 0
|
.byte 0
|
.byte 1
|
.byte 1
|
.byte 0
|
.byte 0
|
.byte -1
|
.byte -1
|
.byte -1
|
.byte -1
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -2
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -3
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -4
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -5
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
.byte -6
|
/* Lookup table translating positive divisor to index into table of
|
/* Lookup table translating positive divisor to index into table of
|
normalized inverse. N.B. the '0' entry is also the last entry of the
|
normalized inverse. N.B. the '0' entry is also the last entry of the
|
previous table, and causes an unaligned access for division by zero. */
|
previous table, and causes an unaligned access for division by zero. */
|
LOCAL(div_table_ix):
|
LOCAL(div_table_ix):
|
.byte -6
|
.byte -6
|
.byte -128
|
.byte -128
|
.byte -128
|
.byte -128
|
.byte 0
|
.byte 0
|
.byte -128
|
.byte -128
|
.byte -64
|
.byte -64
|
.byte 0
|
.byte 0
|
.byte 64
|
.byte 64
|
.byte -128
|
.byte -128
|
.byte -96
|
.byte -96
|
.byte -64
|
.byte -64
|
.byte -32
|
.byte -32
|
.byte 0
|
.byte 0
|
.byte 32
|
.byte 32
|
.byte 64
|
.byte 64
|
.byte 96
|
.byte 96
|
.byte -128
|
.byte -128
|
.byte -112
|
.byte -112
|
.byte -96
|
.byte -96
|
.byte -80
|
.byte -80
|
.byte -64
|
.byte -64
|
.byte -48
|
.byte -48
|
.byte -32
|
.byte -32
|
.byte -16
|
.byte -16
|
.byte 0
|
.byte 0
|
.byte 16
|
.byte 16
|
.byte 32
|
.byte 32
|
.byte 48
|
.byte 48
|
.byte 64
|
.byte 64
|
.byte 80
|
.byte 80
|
.byte 96
|
.byte 96
|
.byte 112
|
.byte 112
|
.byte -128
|
.byte -128
|
.byte -120
|
.byte -120
|
.byte -112
|
.byte -112
|
.byte -104
|
.byte -104
|
.byte -96
|
.byte -96
|
.byte -88
|
.byte -88
|
.byte -80
|
.byte -80
|
.byte -72
|
.byte -72
|
.byte -64
|
.byte -64
|
.byte -56
|
.byte -56
|
.byte -48
|
.byte -48
|
.byte -40
|
.byte -40
|
.byte -32
|
.byte -32
|
.byte -24
|
.byte -24
|
.byte -16
|
.byte -16
|
.byte -8
|
.byte -8
|
.byte 0
|
.byte 0
|
.byte 8
|
.byte 8
|
.byte 16
|
.byte 16
|
.byte 24
|
.byte 24
|
.byte 32
|
.byte 32
|
.byte 40
|
.byte 40
|
.byte 48
|
.byte 48
|
.byte 56
|
.byte 56
|
.byte 64
|
.byte 64
|
.byte 72
|
.byte 72
|
.byte 80
|
.byte 80
|
.byte 88
|
.byte 88
|
.byte 96
|
.byte 96
|
.byte 104
|
.byte 104
|
.byte 112
|
.byte 112
|
.byte 120
|
.byte 120
|
.byte -128
|
.byte -128
|
.byte -124
|
.byte -124
|
.byte -120
|
.byte -120
|
.byte -116
|
.byte -116
|
.byte -112
|
.byte -112
|
.byte -108
|
.byte -108
|
.byte -104
|
.byte -104
|
.byte -100
|
.byte -100
|
.byte -96
|
.byte -96
|
.byte -92
|
.byte -92
|
.byte -88
|
.byte -88
|
.byte -84
|
.byte -84
|
.byte -80
|
.byte -80
|
.byte -76
|
.byte -76
|
.byte -72
|
.byte -72
|
.byte -68
|
.byte -68
|
.byte -64
|
.byte -64
|
.byte -60
|
.byte -60
|
.byte -56
|
.byte -56
|
.byte -52
|
.byte -52
|
.byte -48
|
.byte -48
|
.byte -44
|
.byte -44
|
.byte -40
|
.byte -40
|
.byte -36
|
.byte -36
|
.byte -32
|
.byte -32
|
.byte -28
|
.byte -28
|
.byte -24
|
.byte -24
|
.byte -20
|
.byte -20
|
.byte -16
|
.byte -16
|
.byte -12
|
.byte -12
|
.byte -8
|
.byte -8
|
.byte -4
|
.byte -4
|
.byte 0
|
.byte 0
|
.byte 4
|
.byte 4
|
.byte 8
|
.byte 8
|
.byte 12
|
.byte 12
|
.byte 16
|
.byte 16
|
.byte 20
|
.byte 20
|
.byte 24
|
.byte 24
|
.byte 28
|
.byte 28
|
.byte 32
|
.byte 32
|
.byte 36
|
.byte 36
|
.byte 40
|
.byte 40
|
.byte 44
|
.byte 44
|
.byte 48
|
.byte 48
|
.byte 52
|
.byte 52
|
.byte 56
|
.byte 56
|
.byte 60
|
.byte 60
|
.byte 64
|
.byte 64
|
.byte 68
|
.byte 68
|
.byte 72
|
.byte 72
|
.byte 76
|
.byte 76
|
.byte 80
|
.byte 80
|
.byte 84
|
.byte 84
|
.byte 88
|
.byte 88
|
.byte 92
|
.byte 92
|
.byte 96
|
.byte 96
|
.byte 100
|
.byte 100
|
.byte 104
|
.byte 104
|
.byte 108
|
.byte 108
|
.byte 112
|
.byte 112
|
.byte 116
|
.byte 116
|
.byte 120
|
.byte 120
|
.byte 124
|
.byte 124
|
.byte -128
|
.byte -128
|
/* 1/64 .. 1/127, normalized. There is an implicit leading 1 in bit 32. */
|
/* 1/64 .. 1/127, normalized. There is an implicit leading 1 in bit 32. */
|
.balign 4
|
.balign 4
|
LOCAL(zero_l):
|
LOCAL(zero_l):
|
.long 0x0
|
.long 0x0
|
.long 0xF81F81F9
|
.long 0xF81F81F9
|
.long 0xF07C1F08
|
.long 0xF07C1F08
|
.long 0xE9131AC0
|
.long 0xE9131AC0
|
.long 0xE1E1E1E2
|
.long 0xE1E1E1E2
|
.long 0xDAE6076C
|
.long 0xDAE6076C
|
.long 0xD41D41D5
|
.long 0xD41D41D5
|
.long 0xCD856891
|
.long 0xCD856891
|
.long 0xC71C71C8
|
.long 0xC71C71C8
|
.long 0xC0E07039
|
.long 0xC0E07039
|
.long 0xBACF914D
|
.long 0xBACF914D
|
.long 0xB4E81B4F
|
.long 0xB4E81B4F
|
.long 0xAF286BCB
|
.long 0xAF286BCB
|
.long 0xA98EF607
|
.long 0xA98EF607
|
.long 0xA41A41A5
|
.long 0xA41A41A5
|
.long 0x9EC8E952
|
.long 0x9EC8E952
|
.long 0x9999999A
|
.long 0x9999999A
|
.long 0x948B0FCE
|
.long 0x948B0FCE
|
.long 0x8F9C18FA
|
.long 0x8F9C18FA
|
.long 0x8ACB90F7
|
.long 0x8ACB90F7
|
.long 0x86186187
|
.long 0x86186187
|
.long 0x81818182
|
.long 0x81818182
|
.long 0x7D05F418
|
.long 0x7D05F418
|
.long 0x78A4C818
|
.long 0x78A4C818
|
.long 0x745D1746
|
.long 0x745D1746
|
.long 0x702E05C1
|
.long 0x702E05C1
|
.long 0x6C16C16D
|
.long 0x6C16C16D
|
.long 0x68168169
|
.long 0x68168169
|
.long 0x642C8591
|
.long 0x642C8591
|
.long 0x60581606
|
.long 0x60581606
|
.long 0x5C9882BA
|
.long 0x5C9882BA
|
.long 0x58ED2309
|
.long 0x58ED2309
|
LOCAL(div_table_inv):
|
LOCAL(div_table_inv):
|
.long 0x55555556
|
.long 0x55555556
|
.long 0x51D07EAF
|
.long 0x51D07EAF
|
.long 0x4E5E0A73
|
.long 0x4E5E0A73
|
.long 0x4AFD6A06
|
.long 0x4AFD6A06
|
.long 0x47AE147B
|
.long 0x47AE147B
|
.long 0x446F8657
|
.long 0x446F8657
|
.long 0x41414142
|
.long 0x41414142
|
.long 0x3E22CBCF
|
.long 0x3E22CBCF
|
.long 0x3B13B13C
|
.long 0x3B13B13C
|
.long 0x38138139
|
.long 0x38138139
|
.long 0x3521CFB3
|
.long 0x3521CFB3
|
.long 0x323E34A3
|
.long 0x323E34A3
|
.long 0x2F684BDB
|
.long 0x2F684BDB
|
.long 0x2C9FB4D9
|
.long 0x2C9FB4D9
|
.long 0x29E4129F
|
.long 0x29E4129F
|
.long 0x27350B89
|
.long 0x27350B89
|
.long 0x24924925
|
.long 0x24924925
|
.long 0x21FB7813
|
.long 0x21FB7813
|
.long 0x1F7047DD
|
.long 0x1F7047DD
|
.long 0x1CF06ADB
|
.long 0x1CF06ADB
|
.long 0x1A7B9612
|
.long 0x1A7B9612
|
.long 0x18118119
|
.long 0x18118119
|
.long 0x15B1E5F8
|
.long 0x15B1E5F8
|
.long 0x135C8114
|
.long 0x135C8114
|
.long 0x11111112
|
.long 0x11111112
|
.long 0xECF56BF
|
.long 0xECF56BF
|
.long 0xC9714FC
|
.long 0xC9714FC
|
.long 0xA6810A7
|
.long 0xA6810A7
|
.long 0x8421085
|
.long 0x8421085
|
.long 0x624DD30
|
.long 0x624DD30
|
.long 0x4104105
|
.long 0x4104105
|
.long 0x2040811
|
.long 0x2040811
|
/* maximum error: 0.987342 scaled: 0.921875*/
|
/* maximum error: 0.987342 scaled: 0.921875*/
|
|
|
ENDFUNC(GLOBAL(sdivsi3_i4i))
|
ENDFUNC(GLOBAL(sdivsi3_i4i))
|
#endif /* SH3 / SH4 */
|
#endif /* SH3 / SH4 */
|
|
|
#endif /* L_div_table */
|
#endif /* L_div_table */
|
|
|
#ifdef L_udiv_qrnnd_16
|
#ifdef L_udiv_qrnnd_16
|
#if !__SHMEDIA__
|
#if !__SHMEDIA__
|
HIDDEN_FUNC(GLOBAL(udiv_qrnnd_16))
|
HIDDEN_FUNC(GLOBAL(udiv_qrnnd_16))
|
/* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */
|
/* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */
|
/* n1 < d, but n1 might be larger than d1. */
|
/* n1 < d, but n1 might be larger than d1. */
|
.global GLOBAL(udiv_qrnnd_16)
|
.global GLOBAL(udiv_qrnnd_16)
|
.balign 8
|
.balign 8
|
GLOBAL(udiv_qrnnd_16):
|
GLOBAL(udiv_qrnnd_16):
|
div0u
|
div0u
|
cmp/hi r6,r0
|
cmp/hi r6,r0
|
bt .Lots
|
bt .Lots
|
.rept 16
|
.rept 16
|
div1 r6,r0
|
div1 r6,r0
|
.endr
|
.endr
|
extu.w r0,r1
|
extu.w r0,r1
|
bt 0f
|
bt 0f
|
add r6,r0
|
add r6,r0
|
0: rotcl r1
|
0: rotcl r1
|
mulu.w r1,r5
|
mulu.w r1,r5
|
xtrct r4,r0
|
xtrct r4,r0
|
swap.w r0,r0
|
swap.w r0,r0
|
sts macl,r2
|
sts macl,r2
|
cmp/hs r2,r0
|
cmp/hs r2,r0
|
sub r2,r0
|
sub r2,r0
|
bt 0f
|
bt 0f
|
addc r5,r0
|
addc r5,r0
|
add #-1,r1
|
add #-1,r1
|
bt 0f
|
bt 0f
|
1: add #-1,r1
|
1: add #-1,r1
|
rts
|
rts
|
add r5,r0
|
add r5,r0
|
.balign 8
|
.balign 8
|
.Lots:
|
.Lots:
|
sub r5,r0
|
sub r5,r0
|
swap.w r4,r1
|
swap.w r4,r1
|
xtrct r0,r1
|
xtrct r0,r1
|
clrt
|
clrt
|
mov r1,r0
|
mov r1,r0
|
addc r5,r0
|
addc r5,r0
|
mov #-1,r1
|
mov #-1,r1
|
SL1(bf, 1b,
|
SL1(bf, 1b,
|
shlr16 r1)
|
shlr16 r1)
|
0: rts
|
0: rts
|
nop
|
nop
|
ENDFUNC(GLOBAL(udiv_qrnnd_16))
|
ENDFUNC(GLOBAL(udiv_qrnnd_16))
|
#endif /* !__SHMEDIA__ */
|
#endif /* !__SHMEDIA__ */
|
#endif /* L_udiv_qrnnd_16 */
|
#endif /* L_udiv_qrnnd_16 */
|
|
|
