1994-04-20 - cryptophone ideas
Header Data
From: Eric Blossom <eb@sr.hp.com>
To: pgf@srl01.cacs.usl.edu
Message Hash: 8dcdda2cd8e5c1063824ed30153ebb6d0ef7b0d42c29121ab45ee4453b40a25e
Message ID: <9404202202.AA18655@srlr14.sr.hp.com>
Reply To: <199404192239.AA17456@srl03.cacs.usl.edu>
UTC Datetime: 1994-04-20 21:56:54 UTC
Raw Date: Wed, 20 Apr 94 14:56:54 PDT
Raw message
From: Eric Blossom <eb@sr.hp.com>
Date: Wed, 20 Apr 94 14:56:54 PDT
To: pgf@srl01.cacs.usl.edu
Subject: cryptophone ideas
In-Reply-To: <199404192239.AA17456@srl03.cacs.usl.edu>
Message-ID: <9404202202.AA18655@srlr14.sr.hp.com>
MIME-Version: 1.0
Content-Type: text/plain
> Anyway, why do you need a DSP? I have read in several places that
> DSP's are going to be "replaced" by the CPU as time goes on and the
> CPUs just get more and more powerful.
Yeah, eventually.
Analog Devices 2105's cost $12 in quantity 1.
They are capable of doing 2 data moves, a 16x16 multiply, a 40 bit
accumulate and a prefech of the next instruction all in 100ns.
10 Million Multiply-Accumulates per second. Ever tried that on a 386?
For more money, you can get ones with 60ns clocks (16.7 MACS).
Eric Blossom
Thread
Return to April 1994
- Return to “Eric Blossom <eb@sr.hp.com>”
- Return to ““Phil G. Fraering” <pgf@srl.cacs.usl.edu>”
- Return to “Phil Karn <karn@qualcomm.com>”
- Return to “sdw@meaddata.com (Stephen Williams)”
Return to “uri@watson.ibm.com”
- 1994-04-19 (Tue, 19 Apr 94 15:43:48 PDT) - Re: cryptophone ideas - “Phil G. Fraering” <pgf@srl.cacs.usl.edu>
- 1994-04-19 (Tue, 19 Apr 94 16:24:06 PDT) - Re: cryptophone ideas - sdw@meaddata.com (Stephen Williams)
- 1994-04-20 (Wed, 20 Apr 94 10:34:35 PDT) - Re: cryptophone ideas - uri@watson.ibm.com
- 1994-04-20 (Wed, 20 Apr 94 14:56:54 PDT) - cryptophone ideas - Eric Blossom <eb@sr.hp.com>
- 1994-04-21 (Thu, 21 Apr 94 16:07:24 PDT) - Re: cryptophone ideas - Phil Karn <karn@qualcomm.com>