Received-SPF: pass (google.com: domain of linux-kernel+bounces-2771-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: David Laight <David.Laight@ACULAB.COM>
To: 'Ivan Orlov' <ivan.orlov0322@gmail.com>, "paul.walmsley@sifive.com"
	<paul.walmsley@sifive.com>, "palmer@dabbelt.com" <palmer@dabbelt.com>,
	"aou@eecs.berkeley.edu" <aou@eecs.berkeley.edu>
CC: "conor.dooley@microchip.com" <conor.dooley@microchip.com>,
	"ajones@ventanamicro.com" <ajones@ventanamicro.com>, "samuel@sholland.org"
	<samuel@sholland.org>, "alexghiti@rivosinc.com" <alexghiti@rivosinc.com>,
	"linux-riscv@lists.infradead.org" <linux-riscv@lists.infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"skhan@linuxfoundation.org" <skhan@linuxfoundation.org>
Subject: RE: [PATCH] riscv: lib: Optimize 'strlen' function
Thread-Topic: [PATCH] riscv: lib: Optimize 'strlen' function
Thread-Index: AQHaLduBo9lhsHug1EOTPi9OJpSM+LCtyBWA
Date: Sun, 17 Dec 2023 18:10:54 +0000
Message-ID: <a210197c479e48778672aa13287eef88@AcuMS.aculab.com>
References: <20231213154530.1970216-1-ivan.orlov0322@gmail.com>
In-Reply-To: <20231213154530.1970216-1-ivan.orlov0322@gmail.com>
Accept-Language: en-GB, en-US
Precedence: bulk
MIME-Version: 1.0
Content-Language: en-US
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

From: Ivan Orlov
> Sent: 13 December 2023 15:46

Looking at the old code...

>  1:
> -=09lbu=09t0, 0(t1)
> -=09beqz=09t0, 2f
> -=09addi=09t1, t1, 1
> -=09j=091b

I suspect there is (at least) a two clock stall between
the 'ldu' and 'beqz'.
Allowing for one clock for the 'predicted taken' branch
that is 7 clocks/byte.

Try this one - especially on 32bit:

=09mov=09t0, a0
=09and=09t1, t0, 1
=09sub=09t0, t0, t1
=09bnez=09t1, 2f
1:
=09ldb=09t1, 0(t0)
2:=09ldb=09t2, 1(t0)
=09add=09t0, t0, 2
=09beqz=09t1, 3f
=09bnez=09t2, 1b
=09add=09t0, t0, 1
3:=09sub=09t0, t0, 2
=09sub=09a0, t0, a0
=09ret

Might be 6 clocks for 2 bytes.
The much smaller cache footprint will also help.

=09David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1=
PT, UK
Registration No: 1397386 (Wales)