PING^2 for vectorization and toplevel patches

[Paolo Bonzini]

> This is also OK for mainline, provided that you keep your
> promise (to Joseph Myers) to eventually add the documentation
> for UNITS_PER_SIMD_WORD.

I've included it now.

Since I was at it, I tweaked UNITS_PER_WORD (nearby) to mention 8 as a 
reasonable value (previously it only said 4!).

> For example, renaming the functions
> to begin with vect_

Done.

> new documentation describing the new
> transformations (in passes.texi?)

Like for UNITS_FOR_SIMD_WORD, there is absolutely no mention of a 
vectorizer in passes.texi except for if-conversion.  I don't think I'm 
most suited to write it so I'm CCing Dorit; I will take care of it if 
she asks me so, anyway.

> an perhaps changes to your new testcases

The agreement with Janis was to put the testcases in the tree-ssa 
directory, because they do not require a special driver.

Bootstrapped/regtested powerpc-apple-darwin7.8.0, ok for mainline?

Paolo
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: vect-generic-enable.patch
URL: <http://gcc.gnu.org/pipermail/gcc-patches/attachments/20050421/48fb9390/attachment.ksh>