home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!caen!batcomputer!tasha.cheme.cornell.edu!elan
- From: elan@tasha.cheme.cornell.edu (Elan Feingold)
- Subject: Optimizing Old Code for i586
- Message-ID: <1992Nov6.194508.9171@tc.cornell.edu>
- Lines: 31
- Sender: news@tc.cornell.edu
- Nntp-Posting-Host: tasha.cheme.cornell.edu
- Reply-To: elan@tasha.cheme.cornell.edu (Elan Feingold)
- Organization: Cornell University
- Date: Fri, 6 Nov 1992 19:45:08 GMT
-
-
- OK, I don't read this group, so I don't know if this has been talked about
- much already, but I woke up last night at about 4AM in a cold sweat
- and with this wierd idea:
-
- Write a program that takes a .exe file and performs the following analysis
- on it:
-
- a) Break up the code into windows, bounded by branches.
- b) Rearrange the code within the windows following the i586
- idea of being able to execute two instructions in a cycle if
- there are no dependancies. The idea is that since the 586 only
- "looks ahead" one instruction, one helps the process by spending
- time reorganizing the code in the .exe to maximize the chance that
- the i586 will be able to execute two consecutive instructions concurrently.
-
- Is this a really stupid idea?
- Would the performance increase be anywhere noticiable?
- Will compilers for the i586 probably perform this optimization?
-
- Thanks,
-
- Elan
-
- --
- ---------------------------------------------------------------------------
- | Elan Feingold | .sig currently undergoing renovation... |
- | CS/EE Depts. | |
- | Cornell University | |
- | Ithaca NY 14850 | |
- ---------------------------------------------------------------------------
-