> Improved MAC swap performance for ARM platform. > The improvement was achieved by using neon intrinsics to save CPU cycles and > doing swap for four packets at a time. > The optimization had 15% - 20% throughput boost in testpmd MAC swap mode. > > Signed-off-by: Ruifeng Wang <ruifeng.w...@arm.com> > Reviewed-by: Gavin Hu <gavin...@arm.com> > Reviewed-by: Phil Yang <phil.y...@arm.com> > --- > app/test-pmd/macswap.c | 4 +- > app/test-pmd/macswap_neon.h | 93 > +++++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 96 insertions(+), 1 deletion(-) create mode 100644 > app/test- > pmd/macswap_neon.h > > diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c index > cbb41b7..71af916 100644 > --- a/app/test-pmd/macswap.c > +++ b/app/test-pmd/macswap.c > @@ -66,8 +66,10 @@ > #include <rte_flow.h> > > #include "testpmd.h" > -#ifdef RTE_ARCH_X86 > +#if defined(RTE_ARCH_X86) > #include "macswap_sse.h" > +#elif defined(RTE_MACHINE_CPUFLAG_NEON) #include "macswap_neon.h" > #else > #include "macswap.h" > #endif > diff --git a/app/test-pmd/macswap_neon.h b/app/test-pmd/macswap_neon.h > new file mode 100644 index 0000000..bad1b9b > --- /dev/null > +++ b/app/test-pmd/macswap_neon.h > @@ -0,0 +1,93 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2019 Arm Limited This change is derived from Intel's work in macswap_sse.h. Can you please add a header similar to lib/librte_lpm/rte_lpm_neon.h?
> + */ > + > +#ifndef _MACSWAP_NEON_H_ > +#define _MACSWAP_NEON_H_ > + <snip>
