Date: Sat, 2 May 2020 08:59:46 +0200 From: Arne Steinkamm <freebsd-questions@Steinkamm.COM> To: Per Hedeland <per@hedeland.org> Cc: freebsd-questions@freebsd.org, arne@steinkamm.com Subject: Re: FreeBSD-speedometer? Message-ID: <20200502065946.GA82984@trajan.stk.cx> In-Reply-To: <d7df3554-8575-99a1-ff59-03d6d517c6c0@hedeland.org> References: <FBFC422E-71A7-4AB4-9AD8-C4D3FB5E7CBE@kukulies.org> <20200501213912.GB83180@trajan.stk.cx> <d7df3554-8575-99a1-ff59-03d6d517c6c0@hedeland.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, May 02, 2020 at 08:52:38AM +0200, Per Hedeland wrote: > On 2020-05-01 23:39, Arne Steinkamm wrote: > > > > My command line tool to get a first idea of the integer(!) single-core(!) > > performance is this (attention: "time" is also in most shells a builtin) > > > > % echo '99999^99999' | time bc > /dev/null > > > > A few examples: > > > > CPU: Intel(R) Xeon(R) CPU E3-1225 v5 @ 3.30GHz (3312.16-MHz K8-class CPU) > > > > 1.83 real 1.83 user 0.00 sys > > Surely that can't be right - with 12.1-RELEASE on Intel(R) Core(TM) > i7-2600 CPU @ 3.40GHz, I get: > > 179.72 real 179.67 user 0.01 sys > > Perhaps you meant '99999^9999'? With that I get: > > 1.80 real 1.80 user 0.00 sys > You're right. It wanted to bring in the rpi and learned the hard way, that 99999^99999 is far too much. So I changed to 9999^99999 and forgot to change the text already written. .//. Arne -- Arne Steinkamm | Home: Mail: arne<at>steinkamm<dot>com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20200502065946.GA82984>