| Message ID | 20160521120618.11846-1-andrea.gelmini@gelma.net (mailing list archive) |
|---|---|
| State | Rejected |
| Headers | show |
On Sat, May 21, 2016 at 02:06:18PM +0200, Andrea Gelmini wrote: > Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net> > --- > arch/powerpc/lib/checksum_64.S | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > > diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S > index 8e6e510..f3b5b7d 100644 > --- a/arch/powerpc/lib/checksum_64.S > +++ b/arch/powerpc/lib/checksum_64.S > @@ -74,7 +74,7 @@ _GLOBAL(__csum_partial) > ld r11,24(r3) > > /* > - * On POWER6 and POWER7 back to back addes take 2 cycles because of > + * On POWER6 and POWER7 back to back adds take 2 cycles because of > * the XER dependency. This means the fastest this loop can go is > * 16 cycles per iteration. The scheduling of the loop below has > * been shown to hit this on both POWER6 and POWER7. > @@ -275,7 +275,7 @@ source; ld r10,16(r3) > source; ld r11,24(r3) > > /* > - * On POWER6 and POWER7 back to back addes take 2 cycles because of > + * On POWER6 and POWER7 back to back adds take 2 cycles because of > * the XER dependency. This means the fastest this loop can go is > * 16 cycles per iteration. The scheduling of the loop below has > * been shown to hit this on both POWER6 and POWER7. NAK - this is talking about the 'adde' instruction, not the 'add' instruction. Paul.
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 8e6e510..f3b5b7d 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -74,7 +74,7 @@ _GLOBAL(__csum_partial) ld r11,24(r3) /* - * On POWER6 and POWER7 back to back addes take 2 cycles because of + * On POWER6 and POWER7 back to back adds take 2 cycles because of * the XER dependency. This means the fastest this loop can go is * 16 cycles per iteration. The scheduling of the loop below has * been shown to hit this on both POWER6 and POWER7. @@ -275,7 +275,7 @@ source; ld r10,16(r3) source; ld r11,24(r3) /* - * On POWER6 and POWER7 back to back addes take 2 cycles because of + * On POWER6 and POWER7 back to back adds take 2 cycles because of * the XER dependency. This means the fastest this loop can go is * 16 cycles per iteration. The scheduling of the loop below has * been shown to hit this on both POWER6 and POWER7.
Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net> --- arch/powerpc/lib/checksum_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)