[T106][ZXW-22]7520V3SCV2.01.01.02P42U09_VEC_V0.8_AP_VEC origin source commit
Change-Id: Ic6e05d89ecd62fc34f82b23dcf306c93764aec4b
diff --git a/ap/build/uClibc/libc/string/avr32/memmove.S b/ap/build/uClibc/libc/string/avr32/memmove.S
new file mode 100644
index 0000000..535f4a2
--- /dev/null
+++ b/ap/build/uClibc/libc/string/avr32/memmove.S
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2004-2007 Atmel Corporation
+ *
+ * This file is subject to the terms and conditions of the GNU Lesser General
+ * Public License. See the file "COPYING.LIB" in the main directory of this
+ * archive for more details.
+ */
+
+#define dst r12
+#define src r11
+#define len r10
+
+ .text
+ .global memmove
+ .type memmove, @function
+memmove:
+ cp.w src, dst
+ brge HIDDEN_JUMPTARGET(memcpy)
+
+ add dst, len
+ add src, len
+ pref src[-1]
+
+ /*
+ * The rest is basically the same as in memcpy.S except that
+ * the direction is reversed.
+ */
+ cp.w len, 32
+ brge .Lmore_than_31
+
+ sub len, 1
+ retlt r12
+1: ld.ub r8, --src
+ st.b --dst, r8
+ sub len, 1
+ brge 1b
+ retal r12
+
+.Lmore_than_31:
+ pushm r0-r7, lr
+
+ /* Check alignment */
+ mov r8, src
+ andl r8, 31, COH
+ brne .Lunaligned_src
+ mov r8, r12
+ andl r8, 3, COH
+ brne .Lunaligned_dst
+
+.Laligned_copy:
+ sub len, 32
+ brlt .Lless_than_32
+
+1: /* Copy 32 bytes at a time */
+ sub src, 32
+ ldm src, r0-r7
+ sub dst, 32
+ sub len, 32
+ stm dst, r0-r7
+ brge 1b
+
+.Lless_than_32:
+ /* Copy 16 more bytes if possible */
+ sub len, -16
+ brlt .Lless_than_16
+ sub src, 16
+ ldm src, r0-r3
+ sub dst, 16
+ sub len, 16
+ stm dst, r0-r3
+
+.Lless_than_16:
+ /* Do the remaining as byte copies */
+ sub len, -16
+ breq 2f
+1: ld.ub r0, --src
+ st.b --dst, r0
+ sub len, 1
+ brne 1b
+
+2: popm r0-r7, pc
+
+.Lunaligned_src:
+ /* Make src cacheline-aligned. r8 = (src & 31) */
+ sub len, r8
+1: ld.ub r0, --src
+ st.b --dst, r0
+ sub r8, 1
+ brne 1b
+
+ /* If dst is word-aligned, we're ready to go */
+ pref src[-4]
+ mov r8, 3
+ tst dst, r8
+ breq .Laligned_copy
+
+.Lunaligned_dst:
+ /* src is aligned, but dst is not. Expect bad performance */
+ sub len, 4
+ brlt 2f
+1: ld.w r0, --src
+ st.w --dst, r0
+ sub len, 4
+ brge 1b
+
+2: neg len
+ add pc, pc, len << 2
+ .rept 3
+ ld.ub r0, --src
+ st.b --dst, r0
+ .endr
+
+ popm r0-r7, pc
+ .size memmove, . - memmove
+
+libc_hidden_def(memmove)