Re: [PATCH] Use get_nonzero_bits to improve vectorization

2013-10-30 Thread Richard Biener
On Tue, 29 Oct 2013, Jakub Jelinek wrote: > On Tue, Oct 29, 2013 at 01:11:53PM +0100, Richard Biener wrote: > > > +/* Return number of known trailing zero bits in EXPR, or, if the value of > > > + EXPR is known to be zero, the precision of it's type. */ > > > + > > > +int > > > > unsigned int?

Re: [PATCH] Use get_nonzero_bits to improve vectorization

2013-10-29 Thread Jakub Jelinek
On Tue, Oct 29, 2013 at 01:11:53PM +0100, Richard Biener wrote: > > +/* Return number of known trailing zero bits in EXPR, or, if the value of > > + EXPR is known to be zero, the precision of it's type. */ > > + > > +int > > unsigned int? Ok. > > +case PLUS_EXPR: > > +case MINUS_EXPR:

Re: [PATCH] Use get_nonzero_bits to improve vectorization

2013-10-29 Thread Richard Biener
On Fri, 25 Oct 2013, Jakub Jelinek wrote: > Hi! > > The following patch makes use of the computed nonzero_bits preserved > in the SSA_NAME_RANGE_INFO. > I chose to write a new routine instead of improving current > highest_pow2_factor, because that routine didn't care about overflows etc. > and b

[PATCH] Use get_nonzero_bits to improve vectorization

2013-10-25 Thread Jakub Jelinek
Hi! The following patch makes use of the computed nonzero_bits preserved in the SSA_NAME_RANGE_INFO. I chose to write a new routine instead of improving current highest_pow2_factor, because that routine didn't care about overflows etc. and by working on ctz numbers instead of powers of two in UHWI