Sponsored Content
Special Forums News, Links, Events and Announcements A seriously interesting article about fab times. Post 302998080 by cb88 on Wednesday 24th of May 2017 10:58:36 PM
Old 05-24-2017
That really is a great article, I think one of the ways Intel is going to work around this is multi process chips... so things that aren't as performance intensive are going to be made on older faster cheaper processes, or more optimized processes. So they can make IO optimized drivers for high speed ram interfaces, logic optimized areas for the CPU, and low cost peripheral areas. It is certainly interesting to see companies trying to cope with the limits they are running up against. As well as they can conentrate on making only one sub unit faster per generation... rather than thier tick - tock tock they have been doing. They could do some iteration on aspects of the design without having to worry about parts that won't change getting broken by moving to a new process etc.. .

I've seen some ideas about die stacking of CPU and GPU components instead of chips ram as is done with HBM. So, perhaps they would make tiny very high yeild dies, but stack a bunch of them and run them rather slowly for a higher aggregate speed so they don't fry themselves with heat.

As an aside I've actually seen Daifuku (Wynright is the specific branch I've worked with) equipment installed in several locations where I have been out on an on site setup trip for the equipment my employer makes... very cool cranes (I've seen them shuffling shoe boxes and potato chips) though apparently they shuffle computer chips around as well!

Last edited by cb88; 05-25-2017 at 12:03 AM..
 

4 More Discussions You Might Find Interesting

1. UNIX for Advanced & Expert Users

An interesting problem

hi!, here is an interesting problem ..... I ftp a file named " my first file.doc" from windows to my HP workstation. Ftp is succesful. The file appears with the same name in my home directory.. But now how do I open this file?? while using Vi or More or other editor, they take only the... (5 Replies)
Discussion started by: jyotipg
5 Replies

2. Shell Programming and Scripting

interesting problem

Hi, I am new in this forum and I am glad to be a part of it. I have a problem that has two parts: 1/ extract just the timestamp from a filename: for example, I have a file called 'sales20080226144525.txt' and I want to extract just the '20080226144525' part out of it. 2/ Now, take that... (5 Replies)
Discussion started by: ChicagoBlues
5 Replies

3. AIX

how would you know your server was rebooted 3 times or 5 times

Is there such location or command to know how many times did you reboot your server in that particular day?in AIX. (3 Replies)
Discussion started by: kenshinhimura
3 Replies

4. Programming

Problem with implementing the times() function in C (struct tms times return zero/negative values)

Hello, i'm trying to implement the times() function and i'm programming in C. I'm using the "struct tms" structure which consists of the fields: The tms_utime structure member is the CPU time charged for the execution of user instructions of the calling process. The tms_stime structure... (1 Reply)
Discussion started by: g_p
1 Replies
SM(1)							    InterNetNews Documentation							     SM(1)

NAME
sm - Command-line interface to the INN storage manager SYNOPSIS
sm [-cdHiqRrSs] [token ...] DESCRIPTION
The INN storage manager is the subsystem that stores and keeps track of all of the articles and what storage backend they're in. All stored articles are assigned a storage API token. sm is a command-line interface to that storage manager, primarily used to retrieve articles by those tokens but also to perform other operations on the storage subsystem. token is the token of an article (the same thing that's returned by grephistory or stored in the history file). It looks something like: @0502000005A4000000010000000000000000@ Any number of tokens can be given on the command-line for any function other than -s. If none are, sm normally reads tokens from standard input, one per line. The default operation is to retrieve and write to standard output the corresponding article for each token given. If -s is given, sm instead stores the article given on standard input (in native format, not wire format) using the standard rules of the storage subsystem. If the article is stored successfully, the token of the article is printed to standard output. Please note that this does not make any attempt to write a history entry or any overview data, and is therefore only useful under very specific circumstances. OPTIONS
-c Show a clear, decoded form of the storage API token. Each part of the token is explained, in a human-readable string. Amongst other elements, this command gives the path to where the corresponding article is supposed to be stored. -d, -r Rather than retrieving the specified article, remove the article. This will delete the article out of the news spool and it will not subsequently be retrievable by any part of INN. It's equivalent to "ctlinnd cancel" except it takes a storage API token instead of a message-ID. -H Retrieve only the headers of the article rather than the entire article. This option cannot be used with -d, -r, -i, or -S. -i Show the newsgroup name and article number associated with the token rather than the article itself. Note that for crossposted articles, only the first newsgroup and article number to which the article is associated will be returned. -q Suppress all error messages except usage errors. -R Display the raw article. This means that line endings won't be converted to native line endings and will be left as CRLF sequences; leading periods will still be escaped for sending over NNTP, and the article will end in a CRLF.CRLF sequence. -S Write the article to standard output in the format used by rnews spool files. Multiple articles can be written in this format, and the resulting output can be fed to rnews (on another system, for example) to inject those articles into INN. This option cannot be used with -d, -r, -H, -i, or -R. -s Store the article given on standard input using the normal storage rules for articles as configured in storage.conf(5). Print the new token for the message to standard output if it is stored successfully. If this option is given, no other options except possibly -q should be given. EXIT STATUS
If all operations were successful, sm exits with status 0. If an operation on any of the provided tokens fails, sm will exit with status 1, even if the operations on other tokens were successful. In other words, if twenty tokens are fed to "sm -r" on stdin, 19 articles were successfully removed, but the sixth article couldn't be found, sm will still exit with status 1. This means that if you need to be sure whether a particular operation succeeded, you should run sm on one token at a time. HISTORY
Written by Katsuhiro Kondou <kondou@nec.co.jp> for InterNetNews. Rewritten in POD by Russ Allbery <rra@stanford.edu>. $Id: sm.pod 8818 2009-11-17 18:58:24Z iulius $ SEE ALSO
ctlinnd(8), grephistory(1), history(5), rnews(1), storage.conf(5). INN 2.5.3 2010-02-08 SM(1)
All times are GMT -4. The time now is 11:25 PM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy