--- /dev/null 2004-02-02 20:32:13.000000000 +0000
-+++ sysdeps/arm/memcpy.S 2004-03-20 13:25:27.000000000 +0000
-@@ -0,0 +1,241 @@
-+/*
-+ * Optimized memcpy implementation for ARM processors
-+ *
-+ * Author: Nicolas Pitre
-+ * Created: Dec 23, 2003
-+ * Copyright: (C) MontaVista Software, Inc.
-+ *
-+ * This file is free software; you can redistribute it and/or
-+ * modify it under the terms of the GNU Lesser General Public
-+ * License as published by the Free Software Foundation; either
-+ * version 2.1 of the License, or (at your option) any later version.
-+ *
-+ * This file is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
-+ * Lesser General Public License for more details.
-+ */
-+
-+#include <sysdep.h>
-+
-+
-+/*
-+ * Endian independent macros for shifting bytes within registers.
-+ */
-+#ifndef __ARMEB__
-+#define pull lsr
-+#define push lsl
-+#else
-+#define pull lsl
-+#define push lsr
-+#endif
-+
-+/*
-+ * Enable data preload for architectures that support it (ARMv5 and above)
-+ */
-+#if defined(__ARM_ARCH_5__) || \
-+ defined(__ARM_ARCH_5T__) || \
-+ defined(__ARM_ARCH_5TE__)
-+#define PLD(code...) code
-+#else
-+#define PLD(code...)
-+#endif
-+
-+
-+/* char * memcpy (char *dst, const char *src) */
-+
-+ENTRY(memcpy)
-+ subs r2, r2, #4
-+ stmfd sp!, {r0, r4, lr}
-+ blt 7f
-+ ands ip, r0, #3
-+ PLD( pld [r1, #0] )
-+ bne 8f
-+ ands ip, r1, #3
-+ bne 9f
-+
-+1: subs r2, r2, #4
-+ blt 6f
-+ subs r2, r2, #8
-+ blt 5f
-+ subs r2, r2, #16
-+ blt 4f
-+
-+ PLD( subs r2, r2, #65 )
-+ stmfd sp!, {r5 - r8}
-+ PLD( blt 3f )
-+ PLD( pld [r1, #32] )
-+
-+ PLD( @ cache alignment )
-+ PLD( ands ip, r1, #31 )
-+ PLD( pld [r1, #64] )
-+ PLD( beq 2f )
-+ PLD( rsb ip, ip, #32 )
-+ PLD( cmp r2, ip )
-+ PLD( pld [r1, #96] )
-+ PLD( blt 2f )
-+ PLD( cmp ip, #16 )
-+ PLD( sub r2, r2, ip )
-+ PLD( ldmgeia r1!, {r3 - r6} )
-+ PLD( stmgeia r0!, {r3 - r6} )
-+ PLD( beq 2f )
-+ PLD( and ip, ip, #15 )
-+ PLD( cmp ip, #8 )
-+ PLD( ldr r3, [r1], #4 )
-+ PLD( ldrge r4, [r1], #4 )
-+ PLD( ldrgt r5, [r1], #4 )
-+ PLD( str r3, [r0], #4 )
-+ PLD( strge r4, [r0], #4 )
-+ PLD( strgt r5, [r0], #4 )
-+
-+2: PLD( pld [r1, #96] )
-+3: ldmia r1!, {r3 - r8, ip, lr}
-+ subs r2, r2, #32
-+ stmia r0!, {r3 - r8, ip, lr}
-+ bge 2b
-+ PLD( cmn r2, #65 )
-+ PLD( bge 3b )
-+ PLD( add r2, r2, #65 )
-+ tst r2, #31
-+ ldmfd sp!, {r5 - r8}
-+ ldmeqfd sp!, {r0, r4, pc}
-+
-+ tst r2, #16
-+4: ldmneia r1!, {r3, r4, ip, lr}
-+ stmneia r0!, {r3, r4, ip, lr}
-+
-+ tst r2, #8
-+5: ldmneia r1!, {r3, r4}
-+ stmneia r0!, {r3, r4}
-+
-+ tst r2, #4
-+6: ldrne r3, [r1], #4
-+ strne r3, [r0], #4
-+
-+7: ands r2, r2, #3
-+ ldmeqfd sp!, {r0, r4, pc}
-+
-+ cmp r2, #2
-+ ldrb r3, [r1], #1
-+ ldrgeb r4, [r1], #1
-+ ldrgtb ip, [r1]
-+ strb r3, [r0], #1
-+ strgeb r4, [r0], #1
-+ strgtb ip, [r0]
-+ ldmfd sp!, {r0, r4, pc}
-+
-+8: rsb ip, ip, #4
-+ cmp ip, #2
-+ ldrb r3, [r1], #1
-+ ldrgeb r4, [r1], #1
-+ ldrgtb lr, [r1], #1
-+ strb r3, [r0], #1
-+ strgeb r4, [r0], #1
-+ strgtb lr, [r0], #1
-+ subs r2, r2, ip
-+ blt 7b
-+ ands ip, r1, #3
-+ beq 1b
-+
-+9: bic r1, r1, #3
-+ cmp ip, #2
-+ ldr lr, [r1], #4
-+ beq 17f
-+ bgt 18f
-+
-+
-+ .macro forward_copy_shift pull push
-+
-+ cmp r2, #12
-+ PLD( pld [r1, #0] )
-+ blt 15f
-+ subs r2, r2, #28
-+ stmfd sp!, {r5 - r9}
-+ blt 13f
-+
-+ PLD( subs r2, r2, #97 )
-+ PLD( blt 12f )
-+ PLD( pld [r1, #32] )
-+
-+ PLD( @ cache alignment )
-+ PLD( rsb ip, r1, #36 )
-+ PLD( pld [r1, #64] )
-+ PLD( ands ip, ip, #31 )
-+ PLD( pld [r1, #96] )
-+ PLD( beq 11f )
-+ PLD( cmp r2, ip )
-+ PLD( pld [r1, #128] )
-+ PLD( blt 11f )
-+ PLD( sub r2, r2, ip )
-+10: PLD( mov r3, lr, pull #\pull )
-+ PLD( ldr lr, [r1], #4 )
-+ PLD( subs ip, ip, #4 )
-+ PLD( orr r3, r3, lr, push #\push )
-+ PLD( str r3, [r0], #4 )
-+ PLD( bgt 10b )
-+
-+11: PLD( pld [r1, #128] )
-+12: mov r3, lr, pull #\pull
-+ ldmia r1!, {r4 - r9, ip, lr}
-+ subs r2, r2, #32
-+ orr r3, r3, r4, push #\push
-+ mov r4, r4, pull #\pull
-+ orr r4, r4, r5, push #\push
-+ mov r5, r5, pull #\pull
-+ orr r5, r5, r6, push #\push
-+ mov r6, r6, pull #\pull
-+ orr r6, r6, r7, push #\push
-+ mov r7, r7, pull #\pull
-+ orr r7, r7, r8, push #\push
-+ mov r8, r8, pull #\pull
-+ orr r8, r8, r9, push #\push
-+ mov r9, r9, pull #\pull
-+ orr r9, r9, ip, push #\push
-+ mov ip, ip, pull #\pull
-+ orr ip, ip, lr, push #\push
-+ stmia r0!, {r3 - r9, ip}
-+ bge 11b
-+ PLD( cmn r2, #97 )
-+ PLD( bge 12b )
-+ PLD( add r2, r2, #97 )
-+ cmn r2, #16
-+ blt 14f
-+13: mov r3, lr, pull #\pull
-+ ldmia r1!, {r4 - r6, lr}
-+ sub r2, r2, #16
-+ orr r3, r3, r4, push #\push
-+ mov r4, r4, pull #\pull
-+ orr r4, r4, r5, push #\push
-+ mov r5, r5, pull #\pull
-+ orr r5, r5, r6, push #\push
-+ mov r6, r6, pull #\pull
-+ orr r6, r6, lr, push #\push
-+ stmia r0!, {r3 - r6}
-+14: adds r2, r2, #28
-+ ldmfd sp!, {r5 - r9}
-+ blt 16f
-+15: mov r3, lr, pull #\pull
-+ ldr lr, [r1], #4
-+ subs r2, r2, #4
-+ orr r3, r3, lr, push #\push
-+ str r3, [r0], #4
-+ bge 15b
-+16:
-+ .endm
-+
-+
-+ forward_copy_shift pull=8 push=24
-+ sub r1, r1, #3
-+ b 7b
-+
-+17: forward_copy_shift pull=16 push=16
-+ sub r1, r1, #2
-+ b 7b
-+
-+18: forward_copy_shift pull=24 push=8
-+ sub r1, r1, #1
-+ b 7b
-+
-+ .size memcpy, . - memcpy
-+END(memcpy)
-+libc_hidden_builtin_def (memcpy)
---- /dev/null 2004-02-02 20:32:13.000000000 +0000
+++ sysdeps/arm/memmove.S 2004-03-20 18:37:23.000000000 +0000
@@ -0,0 +1,251 @@
+/*
+
+ .size bcopy, . - bcopy
+END(bcopy)
+
+--- /dev/null 2004-02-02 20:32:13.000000000 +0000
++++ sysdeps/arm/memcpy.S 2004-05-02 14:33:22.000000000 +0100
+@@ -0,0 +1,242 @@
++/*
++ * Optimized memcpy implementation for ARM processors
++ *
++ * Author: Nicolas Pitre
++ * Created: Dec 23, 2003
++ * Copyright: (C) MontaVista Software, Inc.
++ *
++ * This file is free software; you can redistribute it and/or
++ * modify it under the terms of the GNU Lesser General Public
++ * License as published by the Free Software Foundation; either
++ * version 2.1 of the License, or (at your option) any later version.
++ *
++ * This file is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
++ * Lesser General Public License for more details.
++ */
++
++#include <sysdep.h>
++
++
++/*
++ * Endian independent macros for shifting bytes within registers.
++ */
++#ifndef __ARMEB__
++#define pull lsr
++#define push lsl
++#else
++#define pull lsl
++#define push lsr
++#endif
++
++/*
++ * Enable data preload for architectures that support it (ARMv5 and above)
++ */
++#if defined(__ARM_ARCH_5__) || \
++ defined(__ARM_ARCH_5T__) || \
++ defined(__ARM_ARCH_5TE__)
++#define PLD(code...) code
++#else
++#define PLD(code...)
++#endif
++
++
++/* char * memcpy (char *dst, const char *src) */
++
++ENTRY(memcpy)
++ subs r2, r2, #4
++ stmfd sp!, {r0, r4, lr}
++ blt 7f
++ ands ip, r0, #3
++ PLD( pld [r1, #0] )
++ bne 8f
++ ands ip, r1, #3
++ bne 9f
++
++1: subs r2, r2, #4
++ blt 6f
++ subs r2, r2, #8
++ blt 5f
++ subs r2, r2, #16
++ blt 4f
++
++ PLD( subs r2, r2, #65 )
++ stmfd sp!, {r5 - r8}
++ PLD( blt 3f )
++ PLD( pld [r1, #32] )
++
++ PLD( @ cache alignment )
++ PLD( ands ip, r1, #31 )
++ PLD( pld [r1, #64] )
++ PLD( beq 2f )
++ PLD( rsb ip, ip, #32 )
++ PLD( cmp r2, ip )
++ PLD( pld [r1, #96] )
++ PLD( blt 2f )
++ PLD( cmp ip, #16 )
++ PLD( sub r2, r2, ip )
++ PLD( ldmgeia r1!, {r3 - r6} )
++ PLD( stmgeia r0!, {r3 - r6} )
++ PLD( beq 2f )
++ PLD( and ip, ip, #15 )
++ PLD( cmp ip, #8 )
++ PLD( ldr r3, [r1], #4 )
++ PLD( ldrge r4, [r1], #4 )
++ PLD( ldrgt r5, [r1], #4 )
++ PLD( str r3, [r0], #4 )
++ PLD( strge r4, [r0], #4 )
++ PLD( strgt r5, [r0], #4 )
++
++2: PLD( pld [r1, #96] )
++3: ldmia r1!, {r3 - r8, ip, lr}
++ subs r2, r2, #32
++ stmia r0!, {r3 - r8, ip, lr}
++ bge 2b
++ PLD( cmn r2, #65 )
++ PLD( bge 3b )
++ PLD( add r2, r2, #65 )
++ tst r2, #31
++ ldmfd sp!, {r5 - r8}
++ ldmeqfd sp!, {r0, r4, pc}
++
++ tst r2, #16
++4: ldmneia r1!, {r3, r4, ip, lr}
++ stmneia r0!, {r3, r4, ip, lr}
++
++ tst r2, #8
++5: ldmneia r1!, {r3, r4}
++ stmneia r0!, {r3, r4}
++
++ tst r2, #4
++6: ldrne r3, [r1], #4
++ strne r3, [r0], #4
++
++7: ands r2, r2, #3
++ ldmeqfd sp!, {r0, r4, pc}
++
++ cmp r2, #2
++ ldrb r3, [r1], #1
++ ldrgeb r4, [r1], #1
++ ldrgtb ip, [r1]
++ strb r3, [r0], #1
++ strgeb r4, [r0], #1
++ strgtb ip, [r0]
++ ldmfd sp!, {r0, r4, pc}
++
++8: rsb ip, ip, #4
++ cmp ip, #2
++ ldrb r3, [r1], #1
++ ldrgeb r4, [r1], #1
++ ldrgtb lr, [r1], #1
++ strb r3, [r0], #1
++ strgeb r4, [r0], #1
++ strgtb lr, [r0], #1
++ subs r2, r2, ip
++ blt 7b
++ ands ip, r1, #3
++ beq 1b
++
++9: bic r1, r1, #3
++ cmp ip, #2
++ ldr lr, [r1], #4
++ beq 17f
++ bgt 18f
++
++
++ .macro forward_copy_shift pull push
++
++ cmp r2, #12
++ PLD( pld [r1, #0] )
++ blt 15f
++ subs r2, r2, #28
++ stmfd sp!, {r5 - r9}
++ blt 13f
++
++ PLD( subs r2, r2, #97 )
++ PLD( blt 12f )
++ PLD( pld [r1, #32] )
++
++ PLD( @ cache alignment )
++ PLD( rsb ip, r1, #36 )
++ PLD( pld [r1, #64] )
++ PLD( ands ip, ip, #31 )
++ PLD( pld [r1, #96] )
++ PLD( beq 11f )
++ PLD( cmp r2, ip )
++ PLD( pld [r1, #128] )
++ PLD( blt 11f )
++ PLD( sub r2, r2, ip )
++10: PLD( mov r3, lr, pull #\pull )
++ PLD( ldr lr, [r1], #4 )
++ PLD( subs ip, ip, #4 )
++ PLD( orr r3, r3, lr, push #\push )
++ PLD( str r3, [r0], #4 )
++ PLD( bgt 10b )
++
++11: PLD( pld [r1, #128] )
++12: mov r3, lr, pull #\pull
++ ldmia r1!, {r4 - r9, ip, lr}
++ subs r2, r2, #32
++ orr r3, r3, r4, push #\push
++ mov r4, r4, pull #\pull
++ orr r4, r4, r5, push #\push
++ mov r5, r5, pull #\pull
++ orr r5, r5, r6, push #\push
++ mov r6, r6, pull #\pull
++ orr r6, r6, r7, push #\push
++ mov r7, r7, pull #\pull
++ orr r7, r7, r8, push #\push
++ mov r8, r8, pull #\pull
++ orr r8, r8, r9, push #\push
++ mov r9, r9, pull #\pull
++ orr r9, r9, ip, push #\push
++ mov ip, ip, pull #\pull
++ orr ip, ip, lr, push #\push
++ stmia r0!, {r3 - r9, ip}
++ bge 11b
++ PLD( cmn r2, #97 )
++ PLD( bge 12b )
++ PLD( add r2, r2, #97 )
++ cmn r2, #16
++ blt 14f
++13: mov r3, lr, pull #\pull
++ ldmia r1!, {r4 - r6, lr}
++ sub r2, r2, #16
++ orr r3, r3, r4, push #\push
++ mov r4, r4, pull #\pull
++ orr r4, r4, r5, push #\push
++ mov r5, r5, pull #\pull
++ orr r5, r5, r6, push #\push
++ mov r6, r6, pull #\pull
++ orr r6, r6, lr, push #\push
++ stmia r0!, {r3 - r6}
++14: adds r2, r2, #28
++ ldmfd sp!, {r5 - r9}
++ blt 16f
++15: mov r3, lr, pull #\pull
++ ldr lr, [r1], #4
++ subs r2, r2, #4
++ orr r3, r3, lr, push #\push
++ str r3, [r0], #4
++ bge 15b
++16:
++ .endm
++
++
++ forward_copy_shift pull=8 push=24
++ sub r1, r1, #3
++ b 7b
++
++17: forward_copy_shift pull=16 push=16
++ sub r1, r1, #2
++ b 7b
++
++18: forward_copy_shift pull=24 push=8
++ sub r1, r1, #1
++ b 7b
++
++ .size memcpy, . - memcpy
++END(memcpy)
++libc_hidden_builtin_def (memcpy)
++
git.openpandora.org / openembedded.git / commitdiff