1 files changed, 217 insertions, 0 deletions
diff --git a/firmware/target/sh/memcpy-sh.S b/firmware/target/sh/memcpy-sh.S
new file mode 100755
index 0000000000..0b5e086be9
--- /dev/null
+++ b/firmware/target/sh/memcpy-sh.S
@@ -0,0 +1,217 @@
+/***************************************************************************
+ *             __________               __   ___.
+ *   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
+ *   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
+ *   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
+ *   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
+ *                     \/            \/     \/    \/            \/
+ * $Id$
+ *
+ * Copyright (C) 2004-2005 by Jens Arnold
+ *
+ * All files in this archive are subject to the GNU General Public License.
+ * See the file COPYING in the source tree root for full license agreement.
+ *
+ * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
+ * KIND, either express or implied.
+ *
+ ****************************************************************************/
+#include "config.h"
+    .section    .icode,"ax",@progbits
+    .align      2
+    .global     _memcpy
+    .global     ___memcpy_fwd_entry
+    .type       _memcpy,@function
+/* Copies <length> bytes of data in memory from <source> to <dest>
+ * This version is optimized for speed
+ *
+ * arguments:
+ *  r4 - destination address
+ *  r5 - source address
+ *  r6 - length
+ *
+ * return value:
+ *  r0 - destination address (like ANSI version)
+ *
+ * register usage:
+ *  r0 - data / scratch
+ *  r1 - 2nd data / scratch
+ *  r2 - scratch
+ *  r3 - first long bound / adjusted end address (only if >= 11 bytes)
+ *  r4 - current dest address
+ *  r5 - current source address
+ *  r6 - source end address
+ *  r7 - stored dest start address
+ *
+ * The instruction order is devised in a way to utilize the pipelining
+ * of the SH1 to the max. The routine also tries to utilize fast page mode.
+ */
+_memcpy:
+    mov     r4,r7       /* store dest for returning */
+___memcpy_fwd_entry:
+    add     #-8,r4      /* offset for early increment (max. 2 longs) */
+    mov     #11,r0
+    cmp/hs  r0,r6       /* at least 11 bytes to copy? (ensures 2 aligned longs) */
+    add     r5,r6       /* r6 = source_end */
+    bf      .start_b2   /* no: jump directly to byte loop */
+    
+    mov     #3,r0
+    neg     r5,r3
+    and     r0,r3       /* r3 = (4 - align_offset) % 4 */
+    tst     r3,r3       /* already aligned? */
+    bt      .end_b1     /* yes: skip leading byte loop */
+    
+    add     r5,r3       /* r3 = first source long bound */
+    /* leading byte loop: copies 0..3 bytes */
+.loop_b1:
+    mov.b   @r5+,r0     /* load byte & increment source addr */
+    add     #1,r4       /* increment dest addr */
+    mov.b   r0,@(7,r4)  /* store byte */
+    cmp/hi  r5,r3       /* runs r5 up to first long bound */
+    bt      .loop_b1
+    /* now r5 is always at a long boundary */
+    /* -> memory reading is done in longs for all dest alignments */
+    /* selector for main copy loop */
+.end_b1:
+    mov     #3,r1
+    and     r4,r1       /* r1 = dest alignment offset */
+    mova    .jmptab,r0
+    mov.b   @(r0,r1),r1 /* select appropriate main loop */
+    add     r0,r1
+    mov     r6,r3       /* move end address to r3 */
+    jmp     @r1         /* and jump to it */
+    add     #-7,r3      /* adjust end addr for main loops doing 2 longs/pass */
+    
+    /** main loops, copying 2 longs per pass to profit from fast page mode **/
+    /* long aligned destination (fastest) */
+    .align  2
+.loop_do0:
+    mov.l   @r5+,r1     /* load first long & increment source addr */
+    add     #16,r4      /* increment dest addr & account for decrementing stores */
+    mov.l   @r5+,r0     /* load second long & increment source addr */
+    cmp/hi  r5,r3       /* runs r5 up to last or second last long bound */
+    mov.l   r0,@-r4     /* store second long */
+    mov.l   r1,@-r4     /* store first long; NOT ALIGNED - no speed loss here! */
+    bt      .loop_do0
+           
+    add     #4,r3       /* readjust end address */
+    cmp/hi  r5,r3       /* one long left? */
+    bf      .start_b2   /* no, jump to trailing byte loop */
+    
+    mov.l   @r5+,r0     /* load last long & increment source addr */
+    add     #4,r4       /* increment dest addr */
+    bra     .start_b2   /* jump to trailing byte loop */
+    mov.l   r0,@(4,r4)  /* store last long */
+    /* word aligned destination (long + 2) */
+    .align  2
+.loop_do2:
+    mov.l   @r5+,r1     /* load first long & increment source addr */
+    add     #16,r4      /* increment dest addr */
+    mov.l   @r5+,r0     /* load second long & increment source addr */
+    cmp/hi  r5,r3       /* runs r5 up to last or second last long bound */
+    mov.w   r0,@-r4     /* store low word of second long */
+    xtrct   r1,r0       /* extract low word of first long & high word of second long */
+    mov.l   r0,@-r4     /* and store as long */
+    swap.w  r1,r0       /* get high word of first long */
+    mov.w   r0,@-r4     /* and store it */
+    bt      .loop_do2
+    add     #4,r3       /* readjust end address */
+    cmp/hi  r5,r3       /* one long left? */
+    bf      .start_b2   /* no, jump to trailing byte loop */
+    mov.l   @r5+,r0     /* load last long & increment source addr */
+    add     #4,r4       /* increment dest addr */
+    mov.w   r0,@(6,r4)  /* store low word */
+    shlr16  r0          /* get high word */
+    bra     .start_b2   /* jump to trailing byte loop */
+    mov.w   r0,@(4,r4)  /* and store it */
+    /* jumptable for loop selector */
+    .align  2
+.jmptab:
+    .byte   .loop_do0 - .jmptab  /* placed in the middle because the SH1 */
+    .byte   .loop_do1 - .jmptab  /* loads bytes sign-extended. Otherwise */
+    .byte   .loop_do2 - .jmptab  /* the last loop would be out of reach */
+    .byte   .loop_do3 - .jmptab  /* of the offset range. */
+    /* byte aligned destination (long + 1) */
+    .align  2
+.loop_do1:
+    mov.l   @r5+,r1     /* load first long & increment source addr */
+    add     #16,r4      /* increment dest addr */
+    mov.l   @r5+,r0     /* load second long & increment source addr */
+    cmp/hi  r5,r3       /* runs r5 up to last or second last long bound */
+    mov.b   r0,@-r4     /* store low byte of second long */
+    shlr8   r0          /* get upper 3 bytes */
+    mov     r1,r2       /* copy first long */
+    shll16  r2          /* move low byte of first long all the way up, .. */
+    shll8   r2
+    or      r2,r0       /* ..combine with the 3 bytes of second long.. */
+    mov.l   r0,@-r4     /* ..and store as long */
+    shlr8   r1          /* get middle 2 bytes */
+    mov.w   r1,@-r4     /* store as word */
+    shlr16  r1          /* get upper byte */
+    mov.b   r1,@-r4     /* and store */
+    bt      .loop_do1
+    add     #4,r3       /* readjust end address */
+.last_do13:
+    cmp/hi  r5,r3       /* one long left? */
+    bf      .start_b2   /* no, jump to trailing byte loop */
+    mov.l   @r5+,r0     /* load last long & increment source addr */
+    add     #12,r4      /* increment dest addr */
+    mov.b   r0,@-r4     /* store low byte */
+    shlr8   r0          /* get middle 2 bytes */
+    mov.w   r0,@-r4     /* store as word */
+    shlr16  r0          /* get upper byte */
+    mov.b   r0,@-r4     /* and store */
+    bra     .start_b2   /* jump to trailing byte loop */
+    add     #-4,r4      /* readjust destination */
+    /* byte aligned destination (long + 3) */
+    .align  2
+.loop_do3:
+    mov.l   @r5+,r1     /* load first long & increment source addr */
+    add     #16,r4      /* increment dest addr */
+    mov.l   @r5+,r0     /* load second long & increment source addr */
+    mov     r1,r2       /* copy first long */
+    mov.b   r0,@-r4     /* store low byte of second long */
+    shlr8   r0          /* get middle 2 bytes */
+    mov.w   r0,@-r4     /* store as word */
+    shlr16  r0          /* get upper byte */
+    shll8   r2          /* move lower 3 bytes of first long one up.. */
+    or      r2,r0       /* ..combine with the 1 byte of second long.. */
+    mov.l   r0,@-r4     /* ..and store as long */
+    shlr16  r1          /* get upper byte of first long.. */
+    shlr8   r1
+    cmp/hi  r5,r3       /* runs r5 up to last or second last long bound */
+    mov.b   r1,@-r4     /* ..and store */
+    bt      .loop_do3
+    bra     .last_do13  /* handle last longword: reuse routine for (long + 1) */
+    add     #4,r3       /* readjust end address */
+    /* trailing byte loop: copies 0..3 bytes (or all for < 11 in total) */
+    .align  2
+.loop_b2:
+    mov.b   @r5+,r0     /* load byte & increment source addr */
+    add     #1,r4       /* increment dest addr */
+    mov.b   r0,@(7,r4)  /* store byte */
+.start_b2:
+    cmp/hi  r5,r6       /* runs r5 up to end address */
+    bt      .loop_b2
+    rts
+    mov     r7,r0       /* return dest start address */
+.end:
+    .size   _memcpy,.end-_memcpy

diff --git a/firmware/target/sh/memcpy-sh.S b/firmware/target/sh/memcpy-sh.S new file mode 100755 index 0000000000..0b5e086be9 --- /dev/null +++ b/firmware/target/sh/memcpy-sh.S
@@ -0,0 +1,217 @@
	1	/***************************************************************************
	2	* __________ __ ___.
	3	* Open \______ \ ____ ____ \| \| _\_ \|__ _______ ___
	4	* Source \| _// _ \_/ ___\\| \|/ /\| __ \ / _ \ \/ /
	5	* Jukebox \| \| ( <_> ) \___\| < \| \_\ ( <_> > < <
	6	* Firmware \|____\|_ /\____/ \___ >__\|_ \\|___ /\____/__/\_ \
	7	* \/ \/ \/ \/ \/
	8	* $Id$
	9	*
	10	* Copyright (C) 2004-2005 by Jens Arnold
	11	*
	12	* All files in this archive are subject to the GNU General Public License.
	13	* See the file COPYING in the source tree root for full license agreement.
	14	*
	15	* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
	16	* KIND, either express or implied.
	17	*
	18	****************************************************************************/
	19	#include "config.h"
	20
	21	.section .icode,"ax",@progbits
	22
	23	.align 2
	24	.global _memcpy
	25	.global ___memcpy_fwd_entry
	26	.type _memcpy,@function
	27
	28	/* Copies <length> bytes of data in memory from <source> to <dest>
	29	* This version is optimized for speed
	30	*
	31	* arguments:
	32	* r4 - destination address
	33	* r5 - source address
	34	* r6 - length
	35	*
	36	* return value:
	37	* r0 - destination address (like ANSI version)
	38	*
	39	* register usage:
	40	* r0 - data / scratch
	41	* r1 - 2nd data / scratch
	42	* r2 - scratch
	43	* r3 - first long bound / adjusted end address (only if >= 11 bytes)
	44	* r4 - current dest address
	45	* r5 - current source address
	46	* r6 - source end address
	47	* r7 - stored dest start address
	48	*
	49	* The instruction order is devised in a way to utilize the pipelining
	50	* of the SH1 to the max. The routine also tries to utilize fast page mode.
	51	*/
	52
	53	_memcpy:
	54	mov r4,r7 /* store dest for returning */
	55	___memcpy_fwd_entry:
	56	add #-8,r4 /* offset for early increment (max. 2 longs) */
	57	mov #11,r0
	58	cmp/hs r0,r6 /* at least 11 bytes to copy? (ensures 2 aligned longs) */
	59	add r5,r6 /* r6 = source_end */
	60	bf .start_b2 /* no: jump directly to byte loop */
	61
	62	mov #3,r0
	63	neg r5,r3
	64	and r0,r3 /* r3 = (4 - align_offset) % 4 */
	65	tst r3,r3 /* already aligned? */
	66	bt .end_b1 /* yes: skip leading byte loop */
	67
	68	add r5,r3 /* r3 = first source long bound */
	69
	70	/* leading byte loop: copies 0..3 bytes */
	71	.loop_b1:
	72	mov.b @r5+,r0 /* load byte & increment source addr */
	73	add #1,r4 /* increment dest addr */
	74	mov.b r0,@(7,r4) /* store byte */
	75	cmp/hi r5,r3 /* runs r5 up to first long bound */
	76	bt .loop_b1
	77	/* now r5 is always at a long boundary */
	78	/* -> memory reading is done in longs for all dest alignments */
	79
	80	/* selector for main copy loop */
	81	.end_b1:
	82	mov #3,r1
	83	and r4,r1 /* r1 = dest alignment offset */
	84	mova .jmptab,r0
	85	mov.b @(r0,r1),r1 /* select appropriate main loop */
	86	add r0,r1
	87	mov r6,r3 /* move end address to r3 */
	88	jmp @r1 /* and jump to it */
	89	add #-7,r3 /* adjust end addr for main loops doing 2 longs/pass */
	90
	91	/ main loops, copying 2 longs per pass to profit from fast page mode /
	92
	93	/* long aligned destination (fastest) */
	94	.align 2
	95	.loop_do0:
	96	mov.l @r5+,r1 /* load first long & increment source addr */
	97	add #16,r4 /* increment dest addr & account for decrementing stores */
	98	mov.l @r5+,r0 /* load second long & increment source addr */
	99	cmp/hi r5,r3 /* runs r5 up to last or second last long bound */
	100	mov.l r0,@-r4 /* store second long */
	101	mov.l r1,@-r4 /* store first long; NOT ALIGNED - no speed loss here! */
	102	bt .loop_do0
	103
	104	add #4,r3 /* readjust end address */
	105	cmp/hi r5,r3 /* one long left? */
	106	bf .start_b2 /* no, jump to trailing byte loop */
	107
	108	mov.l @r5+,r0 /* load last long & increment source addr */
	109	add #4,r4 /* increment dest addr */
	110	bra .start_b2 /* jump to trailing byte loop */
	111	mov.l r0,@(4,r4) /* store last long */
	112
	113	/* word aligned destination (long + 2) */
	114	.align 2
	115	.loop_do2:
	116	mov.l @r5+,r1 /* load first long & increment source addr */
	117	add #16,r4 /* increment dest addr */
	118	mov.l @r5+,r0 /* load second long & increment source addr */
	119	cmp/hi r5,r3 /* runs r5 up to last or second last long bound */
	120	mov.w r0,@-r4 /* store low word of second long */
	121	xtrct r1,r0 /* extract low word of first long & high word of second long */
	122	mov.l r0,@-r4 /* and store as long */
	123	swap.w r1,r0 /* get high word of first long */
	124	mov.w r0,@-r4 /* and store it */
	125	bt .loop_do2
	126
	127	add #4,r3 /* readjust end address */
	128	cmp/hi r5,r3 /* one long left? */
	129	bf .start_b2 /* no, jump to trailing byte loop */
	130
	131	mov.l @r5+,r0 /* load last long & increment source addr */
	132	add #4,r4 /* increment dest addr */
	133	mov.w r0,@(6,r4) /* store low word */
	134	shlr16 r0 /* get high word */
	135	bra .start_b2 /* jump to trailing byte loop */
	136	mov.w r0,@(4,r4) /* and store it */
	137
	138	/* jumptable for loop selector */
	139	.align 2
	140	.jmptab:
	141	.byte .loop_do0 - .jmptab /* placed in the middle because the SH1 */
	142	.byte .loop_do1 - .jmptab /* loads bytes sign-extended. Otherwise */
	143	.byte .loop_do2 - .jmptab /* the last loop would be out of reach */
	144	.byte .loop_do3 - .jmptab /* of the offset range. */
	145
	146	/* byte aligned destination (long + 1) */
	147	.align 2
	148	.loop_do1:
	149	mov.l @r5+,r1 /* load first long & increment source addr */
	150	add #16,r4 /* increment dest addr */
	151	mov.l @r5+,r0 /* load second long & increment source addr */
	152	cmp/hi r5,r3 /* runs r5 up to last or second last long bound */
	153	mov.b r0,@-r4 /* store low byte of second long */
	154	shlr8 r0 /* get upper 3 bytes */
	155	mov r1,r2 /* copy first long */
	156	shll16 r2 /* move low byte of first long all the way up, .. */
	157	shll8 r2
	158	or r2,r0 /* ..combine with the 3 bytes of second long.. */
	159	mov.l r0,@-r4 /* ..and store as long */
	160	shlr8 r1 /* get middle 2 bytes */
	161	mov.w r1,@-r4 /* store as word */
	162	shlr16 r1 /* get upper byte */
	163	mov.b r1,@-r4 /* and store */
	164	bt .loop_do1
	165
	166	add #4,r3 /* readjust end address */
	167	.last_do13:
	168	cmp/hi r5,r3 /* one long left? */
	169	bf .start_b2 /* no, jump to trailing byte loop */
	170
	171	mov.l @r5+,r0 /* load last long & increment source addr */
	172	add #12,r4 /* increment dest addr */
	173	mov.b r0,@-r4 /* store low byte */
	174	shlr8 r0 /* get middle 2 bytes */
	175	mov.w r0,@-r4 /* store as word */
	176	shlr16 r0 /* get upper byte */
	177	mov.b r0,@-r4 /* and store */
	178	bra .start_b2 /* jump to trailing byte loop */
	179	add #-4,r4 /* readjust destination */
	180
	181	/* byte aligned destination (long + 3) */
	182	.align 2
	183	.loop_do3:
	184	mov.l @r5+,r1 /* load first long & increment source addr */
	185	add #16,r4 /* increment dest addr */
	186	mov.l @r5+,r0 /* load second long & increment source addr */
	187	mov r1,r2 /* copy first long */
	188	mov.b r0,@-r4 /* store low byte of second long */
	189	shlr8 r0 /* get middle 2 bytes */
	190	mov.w r0,@-r4 /* store as word */
	191	shlr16 r0 /* get upper byte */
	192	shll8 r2 /* move lower 3 bytes of first long one up.. */
	193	or r2,r0 /* ..combine with the 1 byte of second long.. */
	194	mov.l r0,@-r4 /* ..and store as long */
	195	shlr16 r1 /* get upper byte of first long.. */
	196	shlr8 r1
	197	cmp/hi r5,r3 /* runs r5 up to last or second last long bound */
	198	mov.b r1,@-r4 /* ..and store */
	199	bt .loop_do3
	200
	201	bra .last_do13 /* handle last longword: reuse routine for (long + 1) */
	202	add #4,r3 /* readjust end address */
	203
	204	/* trailing byte loop: copies 0..3 bytes (or all for < 11 in total) */
	205	.align 2
	206	.loop_b2:
	207	mov.b @r5+,r0 /* load byte & increment source addr */
	208	add #1,r4 /* increment dest addr */
	209	mov.b r0,@(7,r4) /* store byte */
	210	.start_b2:
	211	cmp/hi r5,r6 /* runs r5 up to end address */
	212	bt .loop_b2
	213
	214	rts
	215	mov r7,r0 /* return dest start address */
	216	.end:
	217	.size _memcpy,.end-_memcpy