On Wed, Sep 5, 2018 at 2:08 PM Guo Ren <ren_guo@xxxxxxxxx> wrote: > --- /dev/null > +++ b/arch/csky/abiv1/memset.c > @@ -0,0 +1,38 @@ > +// SPDX-License-Identifier: GPL-2.0 > +// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. > +#include <linux/types.h> > + > +void *memset(void *dest, int c, size_t l) > +{ > + char *d = dest; > + int ch = c; > + int tmp; > + > + if ((long)d & 0x3) > + while (l--) *d++ = ch; > + else { > + ch &= 0xff; > + tmp = (ch | ch << 8 | ch << 16 | ch << 24); > + > + while (l >= 16) { > + *(((long *)d)) = tmp; > + *(((long *)d)+1) = tmp; > + *(((long *)d)+2) = tmp; > + *(((long *)d)+3) = tmp; > + l -= 16; > + d += 16; > + } > + > + while (l > 3) { > + *(((long *)d)) = tmp; > + d = d + 4; > + l -= 4; > + } > + > + while (l) { > + *d++ = ch; > + l--; > + } > + } > + return dest; > +} I see that we have a trivial memset() implementation in lib/string.c, but yours seems to be better optimized. Where did you get it from? Is this a version that works particularly well on C-Sky, or is this a generic optimized memset that others could use as well? In the latter case, we could add it to lib/string.c and let architectures select it in place of the triivial version. Arnd