Superblock analysis?

Hi All:

I have some questions about superblocks:

1--Is it possible to have two independent branch instructions in a superbloc
k?

2--Do compilers perform post register-allocation instruction scheduling usin
g
superblocks ?

Regards
Abid

ammalik@cs.uwaterloo.ca wrote:
> I have some questions about superblocks:
>
> 1--Is it possible to have two independent branch instructions in a superbl
ock?
>
> 2--Do compilers perform post register-allocation instruction scheduling us
ing
> superblocks ?

Here's a recent paper on superblocks in the GNU Compiler Collection:

http://www.gccsummit.org/2006/view_...?content_key=38

>
> Regards
> Abid

ammalik@cs.uwaterloo.ca wrote:
> 1--Is it possible to have two independent branch instructions in a superblock?[/co
lor]

One definition of a superblock have it as "a linear sequence of basic
blocks that has a single entry point only.", thus yes, you can have as
many [independent] branches as you like in a superblock.

> 2--Do compilers perform post register-allocation instruction scheduling us
ing
> superblocks?

That seems like several questions in one.  First, you can do register
allocation before or after scheduling (in some approaches even
simultaneously).  There are pros and cons to either choice, but
generally, if you have enough registers, you'd do allocation last (to
maximize the scheduling freedom).

You can most definitely schedule using superblocks.  Using superblocks
may offer more scheduling opportunities at a lower complexity than
using basic blocks.

You could do a lot worse than reading the seminal dissertation
"Bulldog: a compiler for VLIW architectures" by John R. Ellis
(http://portal.acm.org/citation.cfm?...br />
=6184618)

Tommy