ARCv2: optimised string/mem lib routines
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
new file mode 100644
index 0000000..92d573c7
--- /dev/null
+++ b/arch/arc/lib/memset-archs.S
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#undef PREALLOC_NOT_AVAIL
+
+#ifdef PREALLOC_NOT_AVAIL
+#define PREWRITE(A,B) prefetchw [(A),(B)]
+#else
+#define PREWRITE(A,B) prealloc [(A),(B)]
+#endif
+
+ENTRY(memset)
+ prefetchw [r0] ; Prefetch the write location
+ mov.f 0, r2
+;;; if size is zero
+ jz.d [blink]
+ mov r3, r0 ; don't clobber ret val
+
+;;; if length < 8
+ brls.d.nt r2, 8, .Lsmallchunk
+ mov.f lp_count,r2
+
+ and.f r4, r0, 0x03
+ rsub lp_count, r4, 4
+ lpnz @.Laligndestination
+ ;; LOOP BEGIN
+ stb.ab r1, [r3,1]
+ sub r2, r2, 1
+.Laligndestination:
+
+;;; Destination is aligned
+ and r1, r1, 0xFF
+ asl r4, r1, 8
+ or r4, r4, r1
+ asl r5, r4, 16
+ or r5, r5, r4
+ mov r4, r5
+
+ sub3 lp_count, r2, 8
+ cmp r2, 64
+ bmsk.hi r2, r2, 5
+ mov.ls lp_count, 0
+ add3.hi r2, r2, 8
+
+;;; Convert len to Dwords, unfold x8
+ lsr.f lp_count, lp_count, 6
+ lpnz @.Lset64bytes
+ ;; LOOP START
+ PREWRITE(r3, 64) ;Prefetch the next write location
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+.Lset64bytes:
+
+ lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes
+ lpnz .Lset32bytes
+ ;; LOOP START
+ prefetchw [r3, 32] ;Prefetch the next write location
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+.Lset32bytes:
+
+ and.f lp_count, r2, 0x1F ;Last remaining 31 bytes
+.Lsmallchunk:
+ lpnz .Lcopy3bytes
+ ;; LOOP START
+ stb.ab r1, [r3, 1]
+.Lcopy3bytes:
+
+ j [blink]
+
+END(memset)
+
+ENTRY(memzero)
+ ; adjust bzero args to memset args
+ mov r2, r1
+ b.d memset ;tail call so need to tinker with blink
+ mov r1, 0
+END(memzero)
