Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 27 Mar 2005 08:57:53 +0930
From:      "Paul A. Hoadley" <paulh@logicsquad.net>
To:        freebsd-questions@freebsd.org
Subject:   Re: hyper threading.
Message-ID:  <20050326232753.GA64620@grover.logicsquad.net>
In-Reply-To: <49251524.20050326234521@wanadoo.fr>
References:  <c6ef380c050326061976f164b@mail.gmail.com> <1641928994.20050326192811@wanadoo.fr> <8C700529A2DFD74-A44-3A157@mblk-d34.sysops.aol.com> <439876144.20050326220638@wanadoo.fr> <8C7006AE7E80573-FAC-3B652@mblk-r28.sysops.aol.com> <49251524.20050326234521@wanadoo.fr>

next in thread | previous in thread | raw e-mail | index | archive | help

--KsGdsel6WgEHnImy
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Sat, Mar 26, 2005 at 11:45:21PM +0100, Anthony Atkielski wrote:

> Where can I see the measurements?

Here are some measurements.  A few weeks ago I ran Unixbench 4.1.0
(/usr/ports/benchmarks/unixbench) on a P4 2.8GHz with and without
hyperthreading enabled.  I note a slight difference in the 10 minute
load average in favour of the uniprocessor run (0.00 vs 0.10 in the
hyperthreading run), though I doubt this alone could account for a 15%
difference in total score.


Uniprocessor run:
-----------------
  BYTE UNIX Benchmarks (Version 4.1.0)
  System -- bigbird.logicsquad.net
  Start Benchmark Run: Sun Feb 20 08:23:08 CST 2005
   14 interactive users.
   8:23AM  up 3 days, 14:37, 14 users, load averages: 0.00, 0.00, 0.00
  -r-xr-xr-x  1 root  wheel  105624 Feb 12 00:09 /bin/sh
  /bin/sh: ELF 32-bit LSB executable, Intel 80386, version 1 (FreeBSD), for=
 FreeBSD 5.3-CURRENT (rev 1), dynamically linked (uses shared libs), stripp=
ed
  /dev/mirror/gm0s1f 164607432 5190146 146248692     3%    /usr
Dhrystone 2 using register variables     4438000.0 lps   (10.0 secs, 10 sam=
ples)
Double-Precision Whetstone                  786.2 MWIPS (10.4 secs, 10 samp=
les)
System Call Overhead                     387391.7 lps   (10.0 secs, 10 samp=
les)
Pipe Throughput                          595757.1 lps   (10.0 secs, 10 samp=
les)
Pipe-based Context Switching              94343.7 lps   (10.0 secs, 10 samp=
les)
Process Creation                           5143.3 lps   (30.0 secs, 3 sampl=
es)
Execl Throughput                           1127.4 lps   (29.9 secs, 3 sampl=
es)
File Read 1024 bufsize 2000 maxblocks    637932.0 KBps  (30.0 secs, 3 sampl=
es)
File Write 1024 bufsize 2000 maxblocks    86241.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 1024 bufsize 2000 maxblocks     84790.0 KBps  (30.0 secs, 3 sampl=
es)
File Read 256 bufsize 500 maxblocks      182188.0 KBps  (30.0 secs, 3 sampl=
es)
File Write 256 bufsize 500 maxblocks      83127.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 256 bufsize 500 maxblocks       53860.0 KBps  (30.0 secs, 3 sampl=
es)
File Read 4096 bufsize 8000 maxblocks    1662218.0 KBps  (30.0 secs, 3 samp=
les)
File Write 4096 bufsize 8000 maxblocks    47821.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 4096 bufsize 8000 maxblocks     47003.0 KBps  (30.0 secs, 3 sampl=
es)
Shell Scripts (1 concurrent)               2584.9 lpm   (60.0 secs, 3 sampl=
es)
Shell Scripts (8 concurrent)                353.3 lpm   (60.0 secs, 3 sampl=
es)
Shell Scripts (16 concurrent)               177.0 lpm   (60.0 secs, 3 sampl=
es)
Arithmetic Test (type =3D short)           687842.3 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D int)             697114.1 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D long)            697313.5 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D float)           658678.8 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D double)          658663.3 lps   (10.0 secs, 3 sam=
ples)
Arithoh                                  14359071.4 lps   (10.0 secs, 3 sam=
ples)
C Compiler Throughput                      1373.3 lpm   (60.0 secs, 3 sampl=
es)
Dc: sqrt(2) to 99 decimal places         161336.3 lpm   (30.0 secs, 3 sampl=
es)
Recursion Test--Tower of Hanoi            98086.8 lps   (20.0 secs, 3 sampl=
es)


                     INDEX VALUES           =20
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        116700.0  4438000.0      380.3
Double-Precision Whetstone                      55.0      786.2      142.9
Execl Throughput                                43.0     1127.4      262.2
File Copy 1024 bufsize 2000 maxblocks         3960.0    84790.0      214.1
File Copy 256 bufsize 500 maxblocks           1655.0    53860.0      325.4
File Copy 4096 bufsize 8000 maxblocks         5800.0    47003.0       81.0
Pipe Throughput                              12440.0   595757.1      478.9
Pipe-based Context Switching                  4000.0    94343.7      235.9
Process Creation                               126.0     5143.3      408.2
Shell Scripts (8 concurrent)                     6.0      353.3      588.8
System Call Overhead                         15000.0   387391.7      258.3
                                                                 =3D=3D=3D=
=3D=3D=3D=3D=3D=3D
     FINAL SCORE                                                     270.4


Hyperthreading run:
-------------------
  BYTE UNIX Benchmarks (Version 4.1.0)
  System -- bigbird.logicsquad.net
  Start Benchmark Run: Sun Feb 20 17:22:33 CST 2005
   2 interactive users.
   5:22PM  up 2 mins, 2 users, load averages: 0.31, 0.23, 0.10
  -r-xr-xr-x  1 root  wheel  105624 Feb 12 00:09 /bin/sh
  /bin/sh: ELF 32-bit LSB executable, Intel 80386, version 1 (FreeBSD), for=
 FreeBSD 5.3-CURRENT (rev 1), dynamically linked (uses shared libs), stripp=
ed
  /dev/mirror/gm0s1f 164607432 5264584 146174254     3%    /usr
Dhrystone 2 using register variables     4463262.0 lps   (10.0 secs, 10 sam=
ples)
Double-Precision Whetstone                  785.8 MWIPS (10.5 secs, 10 samp=
les)
System Call Overhead                     320010.4 lps   (10.0 secs, 10 samp=
les)
Pipe Throughput                          445274.8 lps   (10.0 secs, 10 samp=
les)
Pipe-based Context Switching              60275.3 lps   (10.0 secs, 10 samp=
les)
Process Creation                           3614.9 lps   (30.0 secs, 3 sampl=
es)
Execl Throughput                            970.2 lps   (30.0 secs, 3 sampl=
es)
File Read 1024 bufsize 2000 maxblocks    387635.0 KBps  (30.0 secs, 3 sampl=
es)
File Write 1024 bufsize 2000 maxblocks    85403.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 1024 bufsize 2000 maxblocks     81190.0 KBps  (30.0 secs, 3 sampl=
es)
File Read 256 bufsize 500 maxblocks      103384.0 KBps  (30.0 secs, 3 sampl=
es)
File Write 256 bufsize 500 maxblocks      59661.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 256 bufsize 500 maxblocks       37122.0 KBps  (30.0 secs, 3 sampl=
es)
File Read 4096 bufsize 8000 maxblocks    1204605.0 KBps  (30.0 secs, 3 samp=
les)
File Write 4096 bufsize 8000 maxblocks    47284.0 KBps  (30.0 secs, 3 sampl=
es)
File Copy 4096 bufsize 8000 maxblocks     46684.0 KBps  (30.0 secs, 3 sampl=
es)
Shell Scripts (1 concurrent)               2476.7 lpm   (60.0 secs, 3 sampl=
es)
Shell Scripts (8 concurrent)                360.7 lpm   (60.0 secs, 3 sampl=
es)
Shell Scripts (16 concurrent)               181.0 lpm   (60.0 secs, 3 sampl=
es)
Arithmetic Test (type =3D short)           692417.8 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D int)             701337.9 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D long)            701730.5 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D float)           663616.7 lps   (10.0 secs, 3 sam=
ples)
Arithmetic Test (type =3D double)          663693.8 lps   (10.0 secs, 3 sam=
ples)
Arithoh                                  14226118.2 lps   (10.0 secs, 3 sam=
ples)
C Compiler Throughput                      1357.7 lpm   (60.0 secs, 3 sampl=
es)
Dc: sqrt(2) to 99 decimal places         110706.6 lpm   (30.0 secs, 3 sampl=
es)
Recursion Test--Tower of Hanoi           100825.9 lps   (20.0 secs, 3 sampl=
es)


                     INDEX VALUES           =20
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        116700.0  4463262.0      382.5
Double-Precision Whetstone                      55.0      785.8      142.9
Execl Throughput                                43.0      970.2      225.6
File Copy 1024 bufsize 2000 maxblocks         3960.0    81190.0      205.0
File Copy 256 bufsize 500 maxblocks           1655.0    37122.0      224.3
File Copy 4096 bufsize 8000 maxblocks         5800.0    46684.0       80.5
Pipe Throughput                              12440.0   445274.8      357.9
Pipe-based Context Switching                  4000.0    60275.3      150.7
Process Creation                               126.0     3614.9      286.9
Shell Scripts (8 concurrent)                     6.0      360.7      601.2
System Call Overhead                         15000.0   320010.4      213.3
                                                                 =3D=3D=3D=
=3D=3D=3D=3D=3D=3D
     FINAL SCORE                                                     228.9


--=20
Paul.

w  http://logicsquad.net/
h  http://paul.hoadley.name/

--KsGdsel6WgEHnImy
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (FreeBSD)

iD8DBQFCRe/5730Z/jysbzIRArlrAJ4n6bAyFlmJKFjo0DilnWM6JyoF3ACePCm8
uMO7TFa3Y0cPmUfAVTRW0kI=
=Oqm8
-----END PGP SIGNATURE-----

--KsGdsel6WgEHnImy--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050326232753.GA64620>