From: Garth Brown (Skylight Software) <v-garthb@microsoft.com>
To: cypherpunks@toad.com
Message Hash: 45be53d171acaf2e370bbebd41b28191a72073a0b28c25b88968e051ff8a0dd3
Message ID: <9403292324.AA22631@netmail2.microsoft.com>
Reply To: N/A
UTC Datetime: 1994-03-29 23:23:07 UTC
Raw Date: Tue, 29 Mar 94 15:23:07 PST
From: Garth Brown (Skylight Software) <v-garthb@microsoft.com>
Date: Tue, 29 Mar 94 15:23:07 PST
To: cypherpunks@toad.com
Subject: FW: mail problem
Message-ID: <9403292324.AA22631@netmail2.microsoft.com>
MIME-Version: 1.0
Content-Type: text/plain
The author stated use of 8 processors and "aggressive vectorization",
or, IOW, Using the 8 processors in conjunction instead of as 8 separate
data paths, making their co-operative speed MUCH faster than
an 8X increase.
----------
| From: Adam Shostack <netmail!adam@bwh.harvard.edu>
|
| Could someone explain why jumping to 8 processors knocks the
| time down by a factor of 400, instead of a factor of 8? Is the 400
| billion years a load of crap, intended to sound more impressive than
| 8?
|
Return to March 1994
Return to “Garth Brown (Skylight Software) <v-garthb@microsoft.com>”
1994-03-29 (Tue, 29 Mar 94 15:23:07 PST) - FW: mail problem - Garth Brown (Skylight Software) <v-garthb@microsoft.com>