Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-07-02 Thread Jeff Law
On 07/02/2015 05:40 AM, Alan Lawrence wrote: Jeff Law wrote: On 06/24/2015 01:59 AM, Richard Biener wrote: And then there is the possibility of making passes generate less needs to perform cleanups after them - like in the present case with the redundant IVs make them more appearant redundant b

Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-07-02 Thread Richard Biener
On Thu, 2 Jul 2015, Alan Lawrence wrote: > Jeff Law wrote: > > On 06/24/2015 01:59 AM, Richard Biener wrote: > > > And then there is the possibility of making passes generate less > > > needs to perform cleanups after them - like in the present case > > > with the redundant IVs make them more appe

Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-07-02 Thread Alan Lawrence
Jeff Law wrote: On 06/24/2015 01:59 AM, Richard Biener wrote: And then there is the possibility of making passes generate less needs to perform cleanups after them - like in the present case with the redundant IVs make them more appearant redundant by CSEing the initial value and step during vec

Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-06-24 Thread Jeff Law
On 06/24/2015 01:59 AM, Richard Biener wrote: Redundant, basically two IVs with the same initial value and same step. IVOPTs can deal with this if the initial values and the step are already same "enough" - the vectorizer can end up generating redundant huge expressions for both. Ah, so yes, this

Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-06-24 Thread Richard Biener
On Tue, 23 Jun 2015, Jeff Law wrote: > On 06/10/2015 08:02 AM, Richard Biener wrote: > > > > The following patch adds FRE after vectorization which is needed > > for IVOPTs to remove redundant PHI nodes (well, I'm testing a > > patch for FRE that will do it already there). > Redundant or degenera

Re: [PATCH][RFC] Add FRE in pass_vectorize

2015-06-23 Thread Jeff Law
On 06/10/2015 08:02 AM, Richard Biener wrote: The following patch adds FRE after vectorization which is needed for IVOPTs to remove redundant PHI nodes (well, I'm testing a patch for FRE that will do it already there). Redundant or degenerates which should be propagated? I believe Alan Lawrenc

[PATCH][RFC] Add FRE in pass_vectorize

2015-06-10 Thread Richard Biener
The following patch adds FRE after vectorization which is needed for IVOPTs to remove redundant PHI nodes (well, I'm testing a patch for FRE that will do it already there). The patch also makes FRE preserve loop-closed SSA form and thus make it suitable for use in the loop pipeline. With the pla