home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!cis.ohio-state.edu!ucbvax!UDEL.EDU!Mills
- From: Mills@UDEL.EDU
- Newsgroups: comp.protocols.time.ntp
- Subject: Encryption follies, take 2
- Message-ID: <9208212303.aa28160@huey.udel.edu>
- Date: 22 Aug 92 03:03:01 GMT
- Sender: daemon@ucbvax.BERKELEY.EDU
- Distribution: inet
- Organization: The Internet
- Lines: 31
-
- Folks,
-
- A bunch of conspirators have sent me data for the authspeed
- program on several hotshot workstations. The results follow below.
- Perhaps I should have leveled the playing field by asking all
- players to use the native system compiler and default optimization.
- Anyway, the data are sorted by DES speed just because I didn't
- think of anything more clever. The performance differences of
- DES relative to MD5 on some machines is interesting. I'm sure this
- will interest the architects among us.
-
- Authentication delays (us) DES MD5
- HP9000/730 hpux8.07 (+O1) 18 87
- SGI Indigo R4000 19 48
- HP9000/720 hpux8.07 21 66
- SGI 4/35 38 110
- DECstation 5000/240 cowbird 39 81
- Sun4c/75 SS2 43 96
- Sun4c/50 IPX malarky 47 94
- DECstation 5000/33 sundeck 49 106
- SGI Indigo 54 115
- DECstation 5000/125 herald 63 136
- Sun4c/65 SS1+ pogo 72 159
- Sun4c/40 IPC grundoon 73 163
- Sun4c/60 SS1 albert 95 199
- Sun4c/20 SLC 95 203
- DECstation 3100 sheol 98 214
- DECstation 2100 circus 126 278
-
-
- Dave
-