Re: [PATCH v5 1/3] riscv: optimized memcpy

From: Matteo Croce <mcroce@linux.microsoft.com>
To: Pavel Machek <pavel@ucw.cz>
Cc: linux-riscv <linux-riscv@lists.infradead.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linux-arch <linux-arch@vger.kernel.org>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Atish Patra <atish.patra@wdc.com>,
	Emil Renner Berthing <kernel@esmil.dk>,
	Akira Tsukamoto <akira.tsukamoto@gmail.com>,
	Drew Fustini <drew@beagleboard.org>,
	Bin Meng <bmeng.cn@gmail.com>,
	David Laight <David.Laight@aculab.com>,
	Guo Ren <guoren@kernel.org>, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH v5 1/3] riscv: optimized memcpy
Date: Sat, 2 Oct 2021 19:20:24 +0200	[thread overview]
Message-ID: <CAFnufp3uD7Wx=TnHYFaHBCy3mQu08zvv2NO=dws=tOMkKTpKCA@mail.gmail.com> (raw)
In-Reply-To: <20211001112354.GA10720@duo.ucw.cz>

On Fri, Oct 1, 2021 at 1:23 PM Pavel Machek <pavel@ucw.cz> wrote:
>
> Hi!
>
> > From: Matteo Croce <mcroce@microsoft.com>
> >
> > Write a C version of memcpy() which uses the biggest data size allowed,
> > without generating unaligned accesses.
> >
> > The procedure is made of three steps:
> > First copy data one byte at time until the destination buffer is aligned
> > to a long boundary.
> > Then copy the data one long at time shifting the current and the next u8
> > to compose a long at every cycle.
> > Finally, copy the remainder one byte at time.
> >
> > On a BeagleV, the TCP RX throughput increased by 45%:
> >
> > before:
> >
> > $ iperf3 -c beaglev
> > Connecting to host beaglev, port 5201
> > [  5] local 192.168.85.6 port 44840 connected to 192.168.85.48 port 5201
> > [ ID] Interval           Transfer     Bitrate         Retr  Cwnd
> > [  5]   0.00-1.00   sec  76.4 MBytes   641 Mbits/sec   27    624 KBytes
> > [  5]   1.00-2.00   sec  72.5 MBytes   608 Mbits/sec    0    708 KBytes
> >
> > after:
> >
> > $ iperf3 -c beaglev
> > Connecting to host beaglev, port 5201
> > [  5] local 192.168.85.6 port 44864 connected to 192.168.85.48 port 5201
> > [ ID] Interval           Transfer     Bitrate         Retr  Cwnd
> > [  5]   0.00-1.00   sec   109 MBytes   912 Mbits/sec   48    559 KBytes
> > [  5]   1.00-2.00   sec   108 MBytes   902 Mbits/sec    0    690
> > KBytes
>
> That's really quite cool. Could you see if it is your "optimized
> unaligned" copy doing the difference?>
>
> +/* convenience union to avoid cast between different pointer types */
> > +union types {
> > +     u8 *as_u8;
> > +     unsigned long *as_ulong;
> > +     uintptr_t as_uptr;
> > +};
> > +
> > +union const_types {
> > +     const u8 *as_u8;
> > +     unsigned long *as_ulong;
> > +     uintptr_t as_uptr;
> > +};
>
> Missing consts here?
>
> Plus... this is really "interesting" coding style. I'd just use casts
> in kernel.
>

Yes, the one for as_ulong is missing.

By using casts I had to use too many of them, making repeated
assignments in every function.
This is basically the same, with less code :)

Cheers,
-- 
per aspera ad upstream