Thread View: de.comp.sys.next
2 messages
2 total messages
Started by Matthias Zepf
Sat, 12 Sep 1992 15:16
Byte UNIX Benchmarks 3.11
Author: Matthias Zepf
Date: Sat, 12 Sep 1992 15:16
Date: Sat, 12 Sep 1992 15:16
60 lines
4182 bytes
4182 bytes
And here are the results of the Byte jury:
*******************************************************************************
BYTE UNIX Benchmarks (Version 3.11)
System -- amylnd [NeXTstation; MC 68040; 25 MHz; NeXTstep 2.1; Mach; SCSI]
Start Benchmark Run: Sat Sep 12 14:14:42 MET DST 1992
0 interactive users.
Dhrystone 2 without register variables 25974.3 lps (10 secs, 6 samples)
Dhrystone 2 using register variables 25971.6 lps (10 secs, 6 samples)
Arithmetic Test (type = arithoh) 47347.5 lps (10 secs, 6 samples)
Arithmetic Test (type = register) 3088.3 lps (10 secs, 6 samples)
Arithmetic Test (type = short) 3460.3 lps (10 secs, 6 samples)
Arithmetic Test (type = int) 3113.3 lps (10 secs, 6 samples)
Arithmetic Test (type = long) 3113.5 lps (10 secs, 6 samples)
Arithmetic Test (type = float) 2846.3 lps (10 secs, 6 samples)
Arithmetic Test (type = double) 2810.5 lps (10 secs, 6 samples)
System Call Overhead Test 8463.4 lps (10 secs, 6 samples)
Pipe Throughput Test 2949.6 lps (10 secs, 6 samples)
Pipe-based Context Switching Test 1192.8 lps (10 secs, 6 samples)
Process Creation Test 40.6 lps (10 secs, 6 samples)
Execl Throughput Test 26.3 lps (9 secs, 6 samples)
File Read (10 seconds) 19281.0 KBps (10 secs, 6 samples)
File Write (10 seconds) 600.0 KBps (10 secs, 6 samples)
File Copy (10 seconds) 466.0 KBps (10 secs, 6 samples)
File Read (30 seconds) 20060.0 KBps (30 secs, 6 samples)
File Write (30 seconds) 466.0 KBps (30 secs, 6 samples)
File Copy (30 seconds) 474.0 KBps (30 secs, 6 samples)
C Compiler Test 36.9 lpm (62 secs, 3 samples)
Shell scripts (1 concurrent) 26.8 lpm (62 secs, 3 samples)
Shell scripts (2 concurrent) 16.6 lpm (62 secs, 3 samples)
Shell scripts (4 concurrent) 8.6 lpm (62 secs, 3 samples)
Shell scripts (8 concurrent) 4.8 lpm (62 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places 1043.5 lpm (62 secs, 6 samples)
Recursion Test--Tower of Hanoi 340.1 lps (10 secs, 6 samples)
INDEX VALUES
TEST BASELINE RESULT INDEX
Arithmetic Test (type = double) 2541.7 2810.5 1.1
Dhrystone 2 without register variables 22366.3 25974.4 1.2
Execl Throughput Test 16.5 26.3 1.6
File Copy (30 seconds) 179.0 474.0 2.6
Pipe-based Context Switching Test 1318.5 1192.8 0.9
Shell scripts (8 concurrent) 4.0 4.8 1.2
=========
SUM of 6 items 8.6
AVERAGE 1.4
*******************************************************************************
Ich weiss nun leider nicht (ich habe naemlich die Doku nicht gelesen),
von welchem System die Referenzwerte sind, aber man sieht vor allem
sehr deutlich die langsame und unbrauchbare SCSI-Implementierung im
NeXT.
Gruss, Matthias
--
** Matthias Zepf, Riegelaeckerstrasse 27, 7250 Leonberg, Germany **
** +49 7152 41917 Email: agnus@amylnd.stgt.sub.org (NeXTmail) **
Re: Byte UNIX Benchmarks 3.11
Author: Oliver Eichler
Date: Mon, 14 Sep 1992 19:00
Date: Mon, 14 Sep 1992 19:00
39 lines
2342 bytes
2342 bytes
In article <1992Sep12.151639.874@amylnd.stgt.sub.org>
agnus@amylnd.stgt.sub.org (Matthias Zepf) writes:
> Ich weiss nun leider nicht (ich habe naemlich die Doku nicht gelesen),
> von welchem System die Referenzwerte sind, aber man sieht vor allem
> sehr deutlich die langsame und unbrauchbare SCSI-Implementierung im
> NeXT.
Also zunaechst weiss ich nicht, wie Du an Hand dieser Zahlen auf eine
'unbrauchbare SCSI-Implementierung' kommst, ergibt sich doch gerade hier
ein Indexwert von 2.6 ! (179 KB/sec zu 474 KB/sec auf dem NeXT)
Laut Byte July 1991 stammen die Baseline-Werte von einer SUN IPC, 25 MHZ,
LSI-Chipset mit 24MB Hauptspeicher. Ich kann jedoch nicht garantieren,
dass wir die korrekten Base-Werte zur Indexbildung haben.
Hier nen paar Zahlen zum Vergleich: (Aus Byte 7/91 u.12/91)
SUN Sparcstation Solbourne CompuAdd Opus
IPX ELC S4000 SS-1 PM 5000 NeXT
Shell Scripts: 1.8 1.5 1.0 0.8 1.0 1.2
Context Switching: 1.8 1.4 0.8 1.0 1.2 0.9
File Copy: 1.5 1.4 4.7 1.2 1.5 2.6
Execl: 1.7 1.4 1.1 0.8 1.1 1.6
Dhrystone 2: 1.6 1.3 1.1 0.8 1.0 1.2
Anicuche ninerauc<1upupun.2ucs 1.inesirdrpt.1 .1 .nusnusn±n wdunorn(A)
e Re Regro0 Bytstgt.sUNíPXPXPhcz@RefeRefeR(HÄT
®µ 124M nes.8 .8 .
atiatiadrsysr)
a4 <19> .1 .iberu1.1d wirrg>lnd gan on: A3 çsub.newzunnesnesn¾¾¾ati1800:nes. neNaNaN
eindil
deudeud14@aT Gm
#
#
(men weip1ncikeikei
ub.orub.ub.u,
zum zum plaben°diediedReReRnbhcz@Ro on: 91 helsysrr zr zrpu.8 v!ps KB2.6 !s: 4en)ca!eloB B B5ts
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads