On caches and parallelism
Nate and Dan,
I REALLY appreciate each of you taking the time to provide descriptions and speculations on the architecture and applications considerations of caches and parallelism. By quirks of history, I teach my department's Hennessy and Patterson Computer Architecture course. Although it is beyond my expertise, I do the best I can.
May I use each of your messages in my course when we get to the memory hierarchy chapter?
Most of my students go on to develop business applications, and it am always trying to help them see when they might actually need to know this Hennessy and Patterson stuff. Your messages might help.
Thank you.
Dr. George F. Corliss
Electrical and Computer Engineering
Marquette University
P.O. Box 1881
1515 W. Wisconsin Ave
Milwaukee WI 53201-1881 USA
414-288-6599; GasDay: 288-4400; Fax 288-5579
George.Corliss@xxxxxxxxxxxxx
www.eng.mu.edu/corlissg
Begin forwarded message:
> From: Nate Hayes <nh@xxxxxxxxxxxxxxxxx>
> Date: July 4, 2011 12:01:56 AM CDT
> To: Ralph Baker Kearfott <rbk@xxxxxxxxxxxx>, John Pryce <j.d.pryce@xxxxxxxxxxxx>
> Cc: stds-1788 <stds-1788@xxxxxxxxxxxxxxxxx>
> Subject: Re: Decorated intervals ARE intervals...
> Reply-To: Nate Hayes <nh@xxxxxxxxxxxxxxxxx>
>
> Baker,
>
> In response to your question, here is some of my understanding and personal
> experience on the issue:
Begin forwarded message:
> From: Dan Zuras Intervals <intervals08@xxxxxxxxxxxxxx>
> Date: July 4, 2011 2:48:38 AM CDT
> To: <rbk@xxxxxxxxxxxx>
> Cc: <stds-1788@xxxxxxxxxxxxxxxxx>, Dan Zuras Intervals <intervals08@xxxxxxxxxxxxxx>
> Subject: (long) 'severe' problems, was Re: Decorated intervals ARE intervals...
> Reply-To: Dan Zuras Intervals <intervals08@xxxxxxxxxxxxxx>
>
>> Date: Sun, 03 Jul 2011 15:20:35 -0500
>> From: Ralph Baker Kearfott <rbk@xxxxxxxxxxxx>
>> To: John Pryce <j.d.pryce@xxxxxxxxxxxx>
>> CC: stds-1788 <stds-1788@xxxxxxxxxxxxxxxxx>
>> Subject: Re: Decorated intervals ARE intervals...
>
> Ralph et al,
>
> This note is verbose & I buried the lead down near the
> bottom. Suffice it to say that I don't think our choice
> is as stark as failing to assure computing versus slow
> 17-byte objects. I think we can have 16 & 17-byte objects
> that are both fast & correct but you have to read the long
> note to see why I think so.