-/* Copyright (C) 1994, 1995 Free Software Foundation, Inc.
+/* Copyright (C) 1994, 95, 97, 98, 1999, 2000 Free Software Foundation, Inc.
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
In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
-compiled version of this file with other programs, and to distribute
-those programs without any restriction coming from the use of this
-file. (The General Public License restrictions do apply in other
-respects; for example, they cover modification of the file, and
-distribution when not linked into another program.)
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file. (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
This file is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
-/* As a special exception, if you link this library with other files,
- some of which are compiled with GCC, to produce an executable,
- this library does not by itself cause the resulting executable
- to be covered by the GNU General Public License.
- This exception does not however invalidate any other reasons why
- the executable file might be covered by the GNU General Public License. */
-
-
!! libgcc1 routines for the Hitachi SH cpu.
!! Contributed by Steve Chamberlain.
!! sac@cygnus.com
!! recoded in assembly by Toshiyasu Morita
!! tm@netcom.com
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+ ELF local label prefixes by J"orn Rennecke
+ amylaar@cygnus.com */
+
+#ifdef __ELF__
+#define LOCAL(X) .L_##X
+#else
+#define LOCAL(X) L_##X
+#endif
+
+#ifdef __linux__
+#define GLOBAL(X) __##X
+#endif
+
+#ifndef GLOBAL
+#define GLOBAL(X) ___##X
+#endif
+
#ifdef L_ashiftrt
- .global ___ashiftrt_r4_0
- .global ___ashiftrt_r4_1
- .global ___ashiftrt_r4_2
- .global ___ashiftrt_r4_3
- .global ___ashiftrt_r4_4
- .global ___ashiftrt_r4_5
- .global ___ashiftrt_r4_6
- .global ___ashiftrt_r4_7
- .global ___ashiftrt_r4_8
- .global ___ashiftrt_r4_9
- .global ___ashiftrt_r4_10
- .global ___ashiftrt_r4_11
- .global ___ashiftrt_r4_12
- .global ___ashiftrt_r4_13
- .global ___ashiftrt_r4_14
- .global ___ashiftrt_r4_15
- .global ___ashiftrt_r4_16
- .global ___ashiftrt_r4_17
- .global ___ashiftrt_r4_18
- .global ___ashiftrt_r4_19
- .global ___ashiftrt_r4_20
- .global ___ashiftrt_r4_21
- .global ___ashiftrt_r4_22
- .global ___ashiftrt_r4_23
- .global ___ashiftrt_r4_24
- .global ___ashiftrt_r4_25
- .global ___ashiftrt_r4_26
- .global ___ashiftrt_r4_27
- .global ___ashiftrt_r4_28
- .global ___ashiftrt_r4_29
- .global ___ashiftrt_r4_30
- .global ___ashiftrt_r4_31
- .global ___ashiftrt_r4_32
+ .global GLOBAL(ashiftrt_r4_0)
+ .global GLOBAL(ashiftrt_r4_1)
+ .global GLOBAL(ashiftrt_r4_2)
+ .global GLOBAL(ashiftrt_r4_3)
+ .global GLOBAL(ashiftrt_r4_4)
+ .global GLOBAL(ashiftrt_r4_5)
+ .global GLOBAL(ashiftrt_r4_6)
+ .global GLOBAL(ashiftrt_r4_7)
+ .global GLOBAL(ashiftrt_r4_8)
+ .global GLOBAL(ashiftrt_r4_9)
+ .global GLOBAL(ashiftrt_r4_10)
+ .global GLOBAL(ashiftrt_r4_11)
+ .global GLOBAL(ashiftrt_r4_12)
+ .global GLOBAL(ashiftrt_r4_13)
+ .global GLOBAL(ashiftrt_r4_14)
+ .global GLOBAL(ashiftrt_r4_15)
+ .global GLOBAL(ashiftrt_r4_16)
+ .global GLOBAL(ashiftrt_r4_17)
+ .global GLOBAL(ashiftrt_r4_18)
+ .global GLOBAL(ashiftrt_r4_19)
+ .global GLOBAL(ashiftrt_r4_20)
+ .global GLOBAL(ashiftrt_r4_21)
+ .global GLOBAL(ashiftrt_r4_22)
+ .global GLOBAL(ashiftrt_r4_23)
+ .global GLOBAL(ashiftrt_r4_24)
+ .global GLOBAL(ashiftrt_r4_25)
+ .global GLOBAL(ashiftrt_r4_26)
+ .global GLOBAL(ashiftrt_r4_27)
+ .global GLOBAL(ashiftrt_r4_28)
+ .global GLOBAL(ashiftrt_r4_29)
+ .global GLOBAL(ashiftrt_r4_30)
+ .global GLOBAL(ashiftrt_r4_31)
+ .global GLOBAL(ashiftrt_r4_32)
.align 1
-___ashiftrt_r4_32:
-___ashiftrt_r4_31:
+GLOBAL(ashiftrt_r4_32):
+GLOBAL(ashiftrt_r4_31):
rotcl r4
rts
subc r4,r4
-___ashiftrt_r4_30:
+GLOBAL(ashiftrt_r4_30):
shar r4
-___ashiftrt_r4_29:
+GLOBAL(ashiftrt_r4_29):
shar r4
-___ashiftrt_r4_28:
+GLOBAL(ashiftrt_r4_28):
shar r4
-___ashiftrt_r4_27:
+GLOBAL(ashiftrt_r4_27):
shar r4
-___ashiftrt_r4_26:
+GLOBAL(ashiftrt_r4_26):
shar r4
-___ashiftrt_r4_25:
+GLOBAL(ashiftrt_r4_25):
shar r4
-___ashiftrt_r4_24:
+GLOBAL(ashiftrt_r4_24):
shlr16 r4
shlr8 r4
rts
exts.b r4,r4
-___ashiftrt_r4_23:
+GLOBAL(ashiftrt_r4_23):
shar r4
-___ashiftrt_r4_22:
+GLOBAL(ashiftrt_r4_22):
shar r4
-___ashiftrt_r4_21:
+GLOBAL(ashiftrt_r4_21):
shar r4
-___ashiftrt_r4_20:
+GLOBAL(ashiftrt_r4_20):
shar r4
-___ashiftrt_r4_19:
+GLOBAL(ashiftrt_r4_19):
shar r4
-___ashiftrt_r4_18:
+GLOBAL(ashiftrt_r4_18):
shar r4
-___ashiftrt_r4_17:
+GLOBAL(ashiftrt_r4_17):
shar r4
-___ashiftrt_r4_16:
+GLOBAL(ashiftrt_r4_16):
shlr16 r4
rts
exts.w r4,r4
-___ashiftrt_r4_15:
+GLOBAL(ashiftrt_r4_15):
shar r4
-___ashiftrt_r4_14:
+GLOBAL(ashiftrt_r4_14):
shar r4
-___ashiftrt_r4_13:
+GLOBAL(ashiftrt_r4_13):
shar r4
-___ashiftrt_r4_12:
+GLOBAL(ashiftrt_r4_12):
shar r4
-___ashiftrt_r4_11:
+GLOBAL(ashiftrt_r4_11):
shar r4
-___ashiftrt_r4_10:
+GLOBAL(ashiftrt_r4_10):
shar r4
-___ashiftrt_r4_9:
+GLOBAL(ashiftrt_r4_9):
shar r4
-___ashiftrt_r4_8:
+GLOBAL(ashiftrt_r4_8):
shar r4
-___ashiftrt_r4_7:
+GLOBAL(ashiftrt_r4_7):
shar r4
-___ashiftrt_r4_6:
+GLOBAL(ashiftrt_r4_6):
shar r4
-___ashiftrt_r4_5:
+GLOBAL(ashiftrt_r4_5):
shar r4
-___ashiftrt_r4_4:
+GLOBAL(ashiftrt_r4_4):
shar r4
-___ashiftrt_r4_3:
+GLOBAL(ashiftrt_r4_3):
shar r4
-___ashiftrt_r4_2:
+GLOBAL(ashiftrt_r4_2):
shar r4
-___ashiftrt_r4_1:
+GLOBAL(ashiftrt_r4_1):
rts
shar r4
-___ashiftrt_r4_0:
+GLOBAL(ashiftrt_r4_0):
rts
nop
#endif
#ifdef L_ashiftrt_n
!
-! ___ashrsi3
+! GLOBAL(ashrsi3)
!
! Entry:
!
! (none)
!
- .global ___ashrsi3
+ .global GLOBAL(ashrsi3)
.align 2
-___ashrsi3:
+GLOBAL(ashrsi3):
mov #31,r0
- cmp/hi r0,r5
- bt L_ashrsi3_31
- mova L_ashrsi3_table,r0
+ and r0,r5
+ mova LOCAL(ashrsi3_table),r0
mov.b @(r0,r5),r5
- add r5,r0 ! Change to braf when gas is fixed
+#ifdef __sh1__
+ add r5,r0
jmp @r0
+#else
+ braf r5
+#endif
mov r4,r0
-L_ashrsi3_table:
- .byte L_ashrsi3_0-L_ashrsi3_table
- .byte L_ashrsi3_1-L_ashrsi3_table
- .byte L_ashrsi3_2-L_ashrsi3_table
- .byte L_ashrsi3_3-L_ashrsi3_table
- .byte L_ashrsi3_4-L_ashrsi3_table
- .byte L_ashrsi3_5-L_ashrsi3_table
- .byte L_ashrsi3_6-L_ashrsi3_table
- .byte L_ashrsi3_7-L_ashrsi3_table
- .byte L_ashrsi3_8-L_ashrsi3_table
- .byte L_ashrsi3_9-L_ashrsi3_table
- .byte L_ashrsi3_10-L_ashrsi3_table
- .byte L_ashrsi3_11-L_ashrsi3_table
- .byte L_ashrsi3_12-L_ashrsi3_table
- .byte L_ashrsi3_13-L_ashrsi3_table
- .byte L_ashrsi3_14-L_ashrsi3_table
- .byte L_ashrsi3_15-L_ashrsi3_table
- .byte L_ashrsi3_16-L_ashrsi3_table
- .byte L_ashrsi3_17-L_ashrsi3_table
- .byte L_ashrsi3_18-L_ashrsi3_table
- .byte L_ashrsi3_19-L_ashrsi3_table
- .byte L_ashrsi3_20-L_ashrsi3_table
- .byte L_ashrsi3_21-L_ashrsi3_table
- .byte L_ashrsi3_22-L_ashrsi3_table
- .byte L_ashrsi3_23-L_ashrsi3_table
- .byte L_ashrsi3_24-L_ashrsi3_table
- .byte L_ashrsi3_25-L_ashrsi3_table
- .byte L_ashrsi3_26-L_ashrsi3_table
- .byte L_ashrsi3_27-L_ashrsi3_table
- .byte L_ashrsi3_28-L_ashrsi3_table
- .byte L_ashrsi3_29-L_ashrsi3_table
- .byte L_ashrsi3_30-L_ashrsi3_table
- .byte L_ashrsi3_31-L_ashrsi3_table
-
-L_ashrsi3_31:
+ .align 2
+LOCAL(ashrsi3_table):
+ .byte LOCAL(ashrsi3_0)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_1)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_2)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_3)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_4)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_5)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_6)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_7)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_8)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_9)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_10)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_11)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_12)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_13)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_14)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_15)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_16)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_17)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_18)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_19)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_20)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_21)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_22)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_23)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_24)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_25)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_26)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_27)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_28)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_29)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_30)-LOCAL(ashrsi3_table)
+ .byte LOCAL(ashrsi3_31)-LOCAL(ashrsi3_table)
+
+LOCAL(ashrsi3_31):
rotcl r0
rts
subc r0,r0
-L_ashrsi3_30:
+LOCAL(ashrsi3_30):
shar r0
-L_ashrsi3_29:
+LOCAL(ashrsi3_29):
shar r0
-L_ashrsi3_28:
+LOCAL(ashrsi3_28):
shar r0
-L_ashrsi3_27:
+LOCAL(ashrsi3_27):
shar r0
-L_ashrsi3_26:
+LOCAL(ashrsi3_26):
shar r0
-L_ashrsi3_25:
+LOCAL(ashrsi3_25):
shar r0
-L_ashrsi3_24:
+LOCAL(ashrsi3_24):
shlr16 r0
shlr8 r0
rts
exts.b r0,r0
-L_ashrsi3_23:
+LOCAL(ashrsi3_23):
shar r0
-L_ashrsi3_22:
+LOCAL(ashrsi3_22):
shar r0
-L_ashrsi3_21:
+LOCAL(ashrsi3_21):
shar r0
-L_ashrsi3_20:
+LOCAL(ashrsi3_20):
shar r0
-L_ashrsi3_19:
+LOCAL(ashrsi3_19):
shar r0
-L_ashrsi3_18:
+LOCAL(ashrsi3_18):
shar r0
-L_ashrsi3_17:
+LOCAL(ashrsi3_17):
shar r0
-L_ashrsi3_16:
+LOCAL(ashrsi3_16):
shlr16 r0
rts
exts.w r0,r0
-L_ashrsi3_15:
+LOCAL(ashrsi3_15):
shar r0
-L_ashrsi3_14:
+LOCAL(ashrsi3_14):
shar r0
-L_ashrsi3_13:
+LOCAL(ashrsi3_13):
shar r0
-L_ashrsi3_12:
+LOCAL(ashrsi3_12):
shar r0
-L_ashrsi3_11:
+LOCAL(ashrsi3_11):
shar r0
-L_ashrsi3_10:
+LOCAL(ashrsi3_10):
shar r0
-L_ashrsi3_9:
+LOCAL(ashrsi3_9):
shar r0
-L_ashrsi3_8:
+LOCAL(ashrsi3_8):
shar r0
-L_ashrsi3_7:
+LOCAL(ashrsi3_7):
shar r0
-L_ashrsi3_6:
+LOCAL(ashrsi3_6):
shar r0
-L_ashrsi3_5:
+LOCAL(ashrsi3_5):
shar r0
-L_ashrsi3_4:
+LOCAL(ashrsi3_4):
shar r0
-L_ashrsi3_3:
+LOCAL(ashrsi3_3):
shar r0
-L_ashrsi3_2:
+LOCAL(ashrsi3_2):
shar r0
-L_ashrsi3_1:
+LOCAL(ashrsi3_1):
rts
shar r0
-L_ashrsi3_0:
+LOCAL(ashrsi3_0):
rts
nop
#ifdef L_ashiftlt
!
-! ___ashlsi3
+! GLOBAL(ashlsi3)
!
! Entry:
!
!
! (none)
!
- .global ___ashlsi3
+ .global GLOBAL(ashlsi3)
.align 2
-___ashlsi3:
+GLOBAL(ashlsi3):
mov #31,r0
- cmp/hi r0,r5
- bt L_ashlsi3_32
- mova L_ashlsi3_table,r0
+ and r0,r5
+ mova LOCAL(ashlsi3_table),r0
mov.b @(r0,r5),r5
- add r5,r0 ! Change to braf when gas is fixed
+#ifdef __sh1__
+ add r5,r0
jmp @r0
+#else
+ braf r5
+#endif
mov r4,r0
-L_ashlsi3_table:
- .byte L_ashlsi3_0-L_ashlsi3_table
- .byte L_ashlsi3_1-L_ashlsi3_table
- .byte L_ashlsi3_2-L_ashlsi3_table
- .byte L_ashlsi3_3-L_ashlsi3_table
- .byte L_ashlsi3_4-L_ashlsi3_table
- .byte L_ashlsi3_5-L_ashlsi3_table
- .byte L_ashlsi3_6-L_ashlsi3_table
- .byte L_ashlsi3_7-L_ashlsi3_table
- .byte L_ashlsi3_8-L_ashlsi3_table
- .byte L_ashlsi3_9-L_ashlsi3_table
- .byte L_ashlsi3_10-L_ashlsi3_table
- .byte L_ashlsi3_11-L_ashlsi3_table
- .byte L_ashlsi3_12-L_ashlsi3_table
- .byte L_ashlsi3_13-L_ashlsi3_table
- .byte L_ashlsi3_14-L_ashlsi3_table
- .byte L_ashlsi3_15-L_ashlsi3_table
- .byte L_ashlsi3_16-L_ashlsi3_table
- .byte L_ashlsi3_17-L_ashlsi3_table
- .byte L_ashlsi3_18-L_ashlsi3_table
- .byte L_ashlsi3_19-L_ashlsi3_table
- .byte L_ashlsi3_20-L_ashlsi3_table
- .byte L_ashlsi3_21-L_ashlsi3_table
- .byte L_ashlsi3_22-L_ashlsi3_table
- .byte L_ashlsi3_23-L_ashlsi3_table
- .byte L_ashlsi3_24-L_ashlsi3_table
- .byte L_ashlsi3_25-L_ashlsi3_table
- .byte L_ashlsi3_26-L_ashlsi3_table
- .byte L_ashlsi3_27-L_ashlsi3_table
- .byte L_ashlsi3_28-L_ashlsi3_table
- .byte L_ashlsi3_29-L_ashlsi3_table
- .byte L_ashlsi3_30-L_ashlsi3_table
- .byte L_ashlsi3_31-L_ashlsi3_table
-
-L_ashlsi3_6:
+ .align 2
+LOCAL(ashlsi3_table):
+ .byte LOCAL(ashlsi3_0)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_1)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_2)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_3)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_4)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_5)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_6)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_7)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_8)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_9)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_10)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_11)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_12)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_13)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_14)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_15)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_16)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_17)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_18)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_19)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_20)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_21)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_22)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_23)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_24)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_25)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_26)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_27)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_28)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_29)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_30)-LOCAL(ashlsi3_table)
+ .byte LOCAL(ashlsi3_31)-LOCAL(ashlsi3_table)
+
+LOCAL(ashlsi3_6):
shll2 r0
-L_ashlsi3_4:
+LOCAL(ashlsi3_4):
shll2 r0
-L_ashlsi3_2:
+LOCAL(ashlsi3_2):
rts
shll2 r0
-L_ashlsi3_7:
+LOCAL(ashlsi3_7):
shll2 r0
-L_ashlsi3_5:
+LOCAL(ashlsi3_5):
shll2 r0
-L_ashlsi3_3:
+LOCAL(ashlsi3_3):
shll2 r0
-L_ashlsi3_1:
+LOCAL(ashlsi3_1):
rts
shll r0
-L_ashlsi3_14:
+LOCAL(ashlsi3_14):
shll2 r0
-L_ashlsi3_12:
+LOCAL(ashlsi3_12):
shll2 r0
-L_ashlsi3_10:
+LOCAL(ashlsi3_10):
shll2 r0
-L_ashlsi3_8:
+LOCAL(ashlsi3_8):
rts
shll8 r0
-L_ashlsi3_15:
+LOCAL(ashlsi3_15):
shll2 r0
-L_ashlsi3_13:
+LOCAL(ashlsi3_13):
shll2 r0
-L_ashlsi3_11:
+LOCAL(ashlsi3_11):
shll2 r0
-L_ashlsi3_9:
+LOCAL(ashlsi3_9):
shll8 r0
rts
shll r0
-L_ashlsi3_22:
+LOCAL(ashlsi3_22):
shll2 r0
-L_ashlsi3_20:
+LOCAL(ashlsi3_20):
shll2 r0
-L_ashlsi3_18:
+LOCAL(ashlsi3_18):
shll2 r0
-L_ashlsi3_16:
+LOCAL(ashlsi3_16):
rts
shll16 r0
-L_ashlsi3_23:
+LOCAL(ashlsi3_23):
shll2 r0
-L_ashlsi3_21:
+LOCAL(ashlsi3_21):
shll2 r0
-L_ashlsi3_19:
+LOCAL(ashlsi3_19):
shll2 r0
-L_ashlsi3_17:
+LOCAL(ashlsi3_17):
shll16 r0
rts
shll r0
-L_ashlsi3_30:
+LOCAL(ashlsi3_30):
shll2 r0
-L_ashlsi3_28:
+LOCAL(ashlsi3_28):
shll2 r0
-L_ashlsi3_26:
+LOCAL(ashlsi3_26):
shll2 r0
-L_ashlsi3_24:
+LOCAL(ashlsi3_24):
shll16 r0
rts
shll8 r0
-L_ashlsi3_31:
+LOCAL(ashlsi3_31):
shll2 r0
-L_ashlsi3_29:
+LOCAL(ashlsi3_29):
shll2 r0
-L_ashlsi3_27:
+LOCAL(ashlsi3_27):
shll2 r0
-L_ashlsi3_25:
+LOCAL(ashlsi3_25):
shll16 r0
shll8 r0
rts
shll r0
-L_ashlsi3_32:
- rts
- mov #0,r0
-
-L_ashlsi3_0:
+LOCAL(ashlsi3_0):
rts
nop
#ifdef L_lshiftrt
!
-! ___lshrsi3
+! GLOBAL(lshrsi3)
!
! Entry:
!
!
! (none)
!
- .global ___lshrsi3
+ .global GLOBAL(lshrsi3)
.align 2
-___lshrsi3:
+GLOBAL(lshrsi3):
mov #31,r0
- cmp/hi r0,r5
- bt L_lshrsi3_32
- mova L_lshrsi3_table,r0
+ and r0,r5
+ mova LOCAL(lshrsi3_table),r0
mov.b @(r0,r5),r5
- add r5,r0 ! Change to braf when gas is fixed
+#ifdef __sh1__
+ add r5,r0
jmp @r0
+#else
+ braf r5
+#endif
mov r4,r0
-L_lshrsi3_table:
- .byte L_lshrsi3_0-L_lshrsi3_table
- .byte L_lshrsi3_1-L_lshrsi3_table
- .byte L_lshrsi3_2-L_lshrsi3_table
- .byte L_lshrsi3_3-L_lshrsi3_table
- .byte L_lshrsi3_4-L_lshrsi3_table
- .byte L_lshrsi3_5-L_lshrsi3_table
- .byte L_lshrsi3_6-L_lshrsi3_table
- .byte L_lshrsi3_7-L_lshrsi3_table
- .byte L_lshrsi3_8-L_lshrsi3_table
- .byte L_lshrsi3_9-L_lshrsi3_table
- .byte L_lshrsi3_10-L_lshrsi3_table
- .byte L_lshrsi3_11-L_lshrsi3_table
- .byte L_lshrsi3_12-L_lshrsi3_table
- .byte L_lshrsi3_13-L_lshrsi3_table
- .byte L_lshrsi3_14-L_lshrsi3_table
- .byte L_lshrsi3_15-L_lshrsi3_table
- .byte L_lshrsi3_16-L_lshrsi3_table
- .byte L_lshrsi3_17-L_lshrsi3_table
- .byte L_lshrsi3_18-L_lshrsi3_table
- .byte L_lshrsi3_19-L_lshrsi3_table
- .byte L_lshrsi3_20-L_lshrsi3_table
- .byte L_lshrsi3_21-L_lshrsi3_table
- .byte L_lshrsi3_22-L_lshrsi3_table
- .byte L_lshrsi3_23-L_lshrsi3_table
- .byte L_lshrsi3_24-L_lshrsi3_table
- .byte L_lshrsi3_25-L_lshrsi3_table
- .byte L_lshrsi3_26-L_lshrsi3_table
- .byte L_lshrsi3_27-L_lshrsi3_table
- .byte L_lshrsi3_28-L_lshrsi3_table
- .byte L_lshrsi3_29-L_lshrsi3_table
- .byte L_lshrsi3_30-L_lshrsi3_table
- .byte L_lshrsi3_31-L_lshrsi3_table
-
-L_lshrsi3_6:
+ .align 2
+LOCAL(lshrsi3_table):
+ .byte LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
+ .byte LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)
+
+LOCAL(lshrsi3_6):
shlr2 r0
-L_lshrsi3_4:
+LOCAL(lshrsi3_4):
shlr2 r0
-L_lshrsi3_2:
+LOCAL(lshrsi3_2):
rts
shlr2 r0
-L_lshrsi3_7:
+LOCAL(lshrsi3_7):
shlr2 r0
-L_lshrsi3_5:
+LOCAL(lshrsi3_5):
shlr2 r0
-L_lshrsi3_3:
+LOCAL(lshrsi3_3):
shlr2 r0
-L_lshrsi3_1:
+LOCAL(lshrsi3_1):
rts
shlr r0
-L_lshrsi3_14:
+LOCAL(lshrsi3_14):
shlr2 r0
-L_lshrsi3_12:
+LOCAL(lshrsi3_12):
shlr2 r0
-L_lshrsi3_10:
+LOCAL(lshrsi3_10):
shlr2 r0
-L_lshrsi3_8:
+LOCAL(lshrsi3_8):
rts
shlr8 r0
-L_lshrsi3_15:
+LOCAL(lshrsi3_15):
shlr2 r0
-L_lshrsi3_13:
+LOCAL(lshrsi3_13):
shlr2 r0
-L_lshrsi3_11:
+LOCAL(lshrsi3_11):
shlr2 r0
-L_lshrsi3_9:
+LOCAL(lshrsi3_9):
shlr8 r0
rts
shlr r0
-L_lshrsi3_22:
+LOCAL(lshrsi3_22):
shlr2 r0
-L_lshrsi3_20:
+LOCAL(lshrsi3_20):
shlr2 r0
-L_lshrsi3_18:
+LOCAL(lshrsi3_18):
shlr2 r0
-L_lshrsi3_16:
+LOCAL(lshrsi3_16):
rts
shlr16 r0
-L_lshrsi3_23:
+LOCAL(lshrsi3_23):
shlr2 r0
-L_lshrsi3_21:
+LOCAL(lshrsi3_21):
shlr2 r0
-L_lshrsi3_19:
+LOCAL(lshrsi3_19):
shlr2 r0
-L_lshrsi3_17:
+LOCAL(lshrsi3_17):
shlr16 r0
rts
shlr r0
-L_lshrsi3_30:
+LOCAL(lshrsi3_30):
shlr2 r0
-L_lshrsi3_28:
+LOCAL(lshrsi3_28):
shlr2 r0
-L_lshrsi3_26:
+LOCAL(lshrsi3_26):
shlr2 r0
-L_lshrsi3_24:
+LOCAL(lshrsi3_24):
shlr16 r0
rts
shlr8 r0
-L_lshrsi3_31:
+LOCAL(lshrsi3_31):
shlr2 r0
-L_lshrsi3_29:
+LOCAL(lshrsi3_29):
shlr2 r0
-L_lshrsi3_27:
+LOCAL(lshrsi3_27):
shlr2 r0
-L_lshrsi3_25:
+LOCAL(lshrsi3_25):
shlr16 r0
shlr8 r0
rts
shlr r0
-L_lshrsi3_32:
- rts
- mov #0,r0
-
-L_lshrsi3_0:
+LOCAL(lshrsi3_0):
rts
nop
! jump to movstr+
done:
add #64,r5
- mova ___movstrSI0,r0
+ mova GLOBAL(movstrSI0),r0
shll2 r6
add r6,r0
jmp @r0
add #64,r4
.align 4
- .global ___movstrSI64
-___movstrSI64:
+ .global GLOBAL(movstrSI64)
+GLOBAL(movstrSI64):
mov.l @(60,r5),r0
mov.l r0,@(60,r4)
- .global ___movstrSI60
-___movstrSI60:
+ .global GLOBAL(movstrSI60)
+GLOBAL(movstrSI60):
mov.l @(56,r5),r0
mov.l r0,@(56,r4)
- .global ___movstrSI56
-___movstrSI56:
+ .global GLOBAL(movstrSI56)
+GLOBAL(movstrSI56):
mov.l @(52,r5),r0
mov.l r0,@(52,r4)
- .global ___movstrSI52
-___movstrSI52:
+ .global GLOBAL(movstrSI52)
+GLOBAL(movstrSI52):
mov.l @(48,r5),r0
mov.l r0,@(48,r4)
- .global ___movstrSI48
-___movstrSI48:
+ .global GLOBAL(movstrSI48)
+GLOBAL(movstrSI48):
mov.l @(44,r5),r0
mov.l r0,@(44,r4)
- .global ___movstrSI44
-___movstrSI44:
+ .global GLOBAL(movstrSI44)
+GLOBAL(movstrSI44):
mov.l @(40,r5),r0
mov.l r0,@(40,r4)
- .global ___movstrSI40
-___movstrSI40:
+ .global GLOBAL(movstrSI40)
+GLOBAL(movstrSI40):
mov.l @(36,r5),r0
mov.l r0,@(36,r4)
- .global ___movstrSI36
-___movstrSI36:
+ .global GLOBAL(movstrSI36)
+GLOBAL(movstrSI36):
mov.l @(32,r5),r0
mov.l r0,@(32,r4)
- .global ___movstrSI32
-___movstrSI32:
+ .global GLOBAL(movstrSI32)
+GLOBAL(movstrSI32):
mov.l @(28,r5),r0
mov.l r0,@(28,r4)
- .global ___movstrSI28
-___movstrSI28:
+ .global GLOBAL(movstrSI28)
+GLOBAL(movstrSI28):
mov.l @(24,r5),r0
mov.l r0,@(24,r4)
- .global ___movstrSI24
-___movstrSI24:
+ .global GLOBAL(movstrSI24)
+GLOBAL(movstrSI24):
mov.l @(20,r5),r0
mov.l r0,@(20,r4)
- .global ___movstrSI20
-___movstrSI20:
+ .global GLOBAL(movstrSI20)
+GLOBAL(movstrSI20):
mov.l @(16,r5),r0
mov.l r0,@(16,r4)
- .global ___movstrSI16
-___movstrSI16:
+ .global GLOBAL(movstrSI16)
+GLOBAL(movstrSI16):
mov.l @(12,r5),r0
mov.l r0,@(12,r4)
- .global ___movstrSI12
-___movstrSI12:
+ .global GLOBAL(movstrSI12)
+GLOBAL(movstrSI12):
mov.l @(8,r5),r0
mov.l r0,@(8,r4)
- .global ___movstrSI8
-___movstrSI8:
+ .global GLOBAL(movstrSI8)
+GLOBAL(movstrSI8):
mov.l @(4,r5),r0
mov.l r0,@(4,r4)
- .global ___movstrSI4
-___movstrSI4:
+ .global GLOBAL(movstrSI4)
+GLOBAL(movstrSI4):
mov.l @(0,r5),r0
mov.l r0,@(0,r4)
-___movstrSI0:
+GLOBAL(movstrSI0):
rts
- or r0,r0,r0
+ nop
.align 4
- .global ___movstr
-___movstr:
+ .global GLOBAL(movstr)
+GLOBAL(movstr):
mov.l @(60,r5),r0
mov.l r0,@(60,r4)
bf done
add #64,r5
- bra ___movstr
+ bra GLOBAL(movstr)
add #64,r4
#endif
+#ifdef L_movstr_i4
+#if defined(__SH4__) || defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || defined(__SH4_NOFPU__)
+ .text
+ .global GLOBAL(movstr_i4_even)
+ .global GLOBAL(movstr_i4_odd)
+ .global GLOBAL(movstrSI12_i4)
+
+ .p2align 5
+L_movstr_2mod4_end:
+ mov.l r0,@(16,r4)
+ rts
+ mov.l r1,@(20,r4)
+
+ .p2align 2
+
+GLOBAL(movstr_i4_odd):
+ mov.l @r5+,r1
+ add #-4,r4
+ mov.l @r5+,r2
+ mov.l @r5+,r3
+ mov.l r1,@(4,r4)
+ mov.l r2,@(8,r4)
+
+L_movstr_loop:
+ mov.l r3,@(12,r4)
+ dt r6
+ mov.l @r5+,r0
+ bt/s L_movstr_2mod4_end
+ mov.l @r5+,r1
+ add #16,r4
+L_movstr_start_even:
+ mov.l @r5+,r2
+ mov.l @r5+,r3
+ mov.l r0,@r4
+ dt r6
+ mov.l r1,@(4,r4)
+ bf/s L_movstr_loop
+ mov.l r2,@(8,r4)
+ rts
+ mov.l r3,@(12,r4)
+
+GLOBAL(movstr_i4_even):
+ mov.l @r5+,r0
+ bra L_movstr_start_even
+ mov.l @r5+,r1
+
+ .p2align 4
+GLOBAL(movstrSI12_i4):
+ mov.l @r5,r0
+ mov.l @(4,r5),r1
+ mov.l @(8,r5),r2
+ mov.l r0,@r4
+ mov.l r1,@(4,r4)
+ rts
+ mov.l r2,@(8,r4)
+#endif /* ! __SH4__ */
+#endif
+
#ifdef L_mulsi3
- .global ___mulsi3
+ .global GLOBAL(mulsi3)
! r4 = aabb
! r5 = ccdd
! aa = bb*dd + (aa*dd*65536) + (cc*bb*65536)
!
-___mulsi3:
+GLOBAL(mulsi3):
mulu r4,r5 ! multiply the lsws macl=bb*dd
mov r5,r3 ! r3 = ccdd
swap.w r4,r2 ! r2 = bbaa
sts macl,r0
hiset: sts macl,r0 ! r0 = bb*dd
- mulu r2,r5 | brewing macl = aa*dd
+ mulu r2,r5 ! brewing macl = aa*dd
sts macl,r1
- mulu r3,r4 | brewing macl = cc*bb
+ mulu r3,r4 ! brewing macl = cc*bb
sts macl,r2
add r1,r2
shll16 r2
#endif
-#ifdef L_sdivsi3
+#ifdef L_sdivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Hitachi SH
+#ifdef __SH4__
+!! args in r4 and r5, result in fpul, clobber dr0, dr2
+
+ .global GLOBAL(sdivsi3_i4)
+GLOBAL(sdivsi3_i4):
+ lds r4,fpul
+ float fpul,dr0
+ lds r5,fpul
+ float fpul,dr2
+ fdiv dr2,dr0
+ rts
+ ftrc dr0,fpul
+
+#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
+!! args in r4 and r5, result in fpul, clobber r2, dr0, dr2
+
+ .global GLOBAL(sdivsi3_i4)
+GLOBAL(sdivsi3_i4):
+ sts.l fpscr,@-r15
+ mov #8,r2
+ swap.w r2,r2
+ lds r2,fpscr
+ lds r4,fpul
+ float fpul,dr0
+ lds r5,fpul
+ float fpul,dr2
+ fdiv dr2,dr0
+ ftrc dr0,fpul
+ rts
+ lds.l @r15+,fpscr
+
+#endif /* ! __SH4__ */
+#endif
+
+#ifdef L_sdivsi3
+/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
+ sh3e code. */
+#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!!
!! Steve Chamberlain
!! sac@cygnus.com
!! args in r4 and r5, result in r0 clobber r1,r2,r3
- .global ___sdivsi3
-___sdivsi3:
+ .global GLOBAL(sdivsi3)
+GLOBAL(sdivsi3):
mov r4,r1
mov r5,r0
div0: rts
mov #0,r0
+#endif /* ! __SH4__ */
#endif
-#ifdef L_udivsi3
+#ifdef L_udivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Hitachi SH
+#ifdef __SH4__
+!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
+
+ .global GLOBAL(udivsi3_i4)
+GLOBAL(udivsi3_i4):
+ mov #1,r1
+ cmp/hi r1,r5
+ bf trivial
+ rotr r1
+ xor r1,r4
+ lds r4,fpul
+ mova L1,r0
+#ifdef FMOVD_WORKS
+ fmov.d @r0+,dr4
+#else
+#ifdef __LITTLE_ENDIAN__
+ fmov.s @r0+,fr5
+ fmov.s @r0,fr4
+#else
+ fmov.s @r0+,fr4
+ fmov.s @r0,fr5
+#endif
+#endif
+ float fpul,dr0
+ xor r1,r5
+ lds r5,fpul
+ float fpul,dr2
+ fadd dr4,dr0
+ fadd dr4,dr2
+ fdiv dr2,dr0
+ rts
+ ftrc dr0,fpul
+
+trivial:
+ rts
+ lds r4,fpul
+
+ .align 2
+#ifdef FMOVD_WORKS
+ .align 3 ! make double below 8 byte aligned.
+#endif
+L1:
+ .double 2147483648
+
+#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
+!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
+
+ .global GLOBAL(udivsi3_i4)
+GLOBAL(udivsi3_i4):
+ mov #1,r1
+ cmp/hi r1,r5
+ bf trivial
+ sts.l fpscr,@-r15
+ mova L1,r0
+ lds.l @r0+,fpscr
+ rotr r1
+ xor r1,r4
+ lds r4,fpul
+#ifdef FMOVD_WORKS
+ fmov.d @r0+,dr4
+#else
+#ifdef __LITTLE_ENDIAN__
+ fmov.s @r0+,fr5
+ fmov.s @r0,fr4
+#else
+ fmov.s @r0+,fr4
+ fmov.s @r0,fr5
+#endif
+#endif
+ float fpul,dr0
+ xor r1,r5
+ lds r5,fpul
+ float fpul,dr2
+ fadd dr4,dr0
+ fadd dr4,dr2
+ fdiv dr2,dr0
+ ftrc dr0,fpul
+ rts
+ lds.l @r15+,fpscr
+
+#ifdef FMOVD_WORKS
+ .align 3 ! make double below 8 byte aligned.
+#endif
+trivial:
+ rts
+ lds r4,fpul
+
+ .align 2
+L1:
+#ifndef FMOVD_WORKS
+ .long 0x80000
+#else
+ .long 0x180000
+#endif
+ .double 2147483648
+
+#endif /* ! __SH4__ */
+#endif
+
+#ifdef L_udivsi3
+/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
+ sh3e code. */
+#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!!
!! Steve Chamberlain
!! sac@cygnus.com
!!
!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
- .global ___udivsi3
+ .global GLOBAL(udivsi3)
-___udivsi3:
+GLOBAL(udivsi3):
longway:
mov #0,r0
div0u
ret: rts
mov r4,r0
+#endif /* __SH4__ */
+#endif
+#ifdef L_set_fpscr
+#if defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__)
+ .global GLOBAL(set_fpscr)
+GLOBAL(set_fpscr):
+ lds r4,fpscr
+ mov.l LOCAL(set_fpscr_L1),r1
+ swap.w r4,r0
+ or #24,r0
+#ifndef FMOVD_WORKS
+ xor #16,r0
+#endif
+#if defined(__SH4__)
+ swap.w r0,r3
+ mov.l r3,@(4,r1)
+#else /* defined(__SH3E__) || defined(__SH4_SINGLE*__) */
+ swap.w r0,r2
+ mov.l r2,@r1
#endif
+#ifndef FMOVD_WORKS
+ xor #8,r0
+#else
+ xor #24,r0
+#endif
+#if defined(__SH4__)
+ swap.w r0,r2
+ rts
+ mov.l r2,@r1
+#else /* defined(__SH3E__) || defined(__SH4_SINGLE*__) */
+ swap.w r0,r3
+ rts
+ mov.l r3,@(4,r1)
+#endif
+ .align 2
+LOCAL(set_fpscr_L1):
+ .long GLOBAL(fpscr_values)
+#ifdef __ELF__
+ .comm GLOBAL(fpscr_values),8,4
+#else
+ .comm GLOBAL(fpscr_values),8
+#endif /* ELF */
+#endif /* SH3E / SH4 */
+#endif /* L_set_fpscr */
+#ifdef L_ic_invalidate
+#if defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__)
+ .global GLOBAL(ic_invalidate)
+GLOBAL(ic_invalidate):
+ ocbwb @r4
+ mova 0f,r0
+ mov.w 1f,r1
+ sub r0,r4
+ and r1,r4
+ add #4,r4
+ braf r4
+ nop
+1:
+ .short 0x1fe0
+ nop
+0:
+ .rept 2048
+ rts
+ nop
+ .endr
+#endif /* SH4 */
+#endif /* L_ic_invalidate */