RE: Proposal for path splitting for reduction in register pressure for Loops.

[Ajit Kumar Agarwal <ajit dot kumar dot agarwal at xilinx dot com>]

-----Original Message-----
From: Jeff Law [mailto:law@redhat.com] 
Sent: Monday, March 09, 2015 11:01 PM
To: Richard Biener
Cc: Ajit Kumar Agarwal; vmakarov@redhat.com; gcc@gcc.gnu.org; Vinod Kathail; Shail Aditya Gupta; Vidhumouli Hunsigida; Nagaraju Mekala
Subject: Re: Proposal for path splitting for reduction in register pressure for Loops.

On 03/09/15 05:40, Richard Biener wrote:
> On Sun, Mar 8, 2015 at 8:49 PM, Jeff Law <law@redhat.com> wrote:
>> On 03/08/15 12:13, Richard Biener wrote:
>>>
>>>
>>> I see.  This basically creates two loop latches and thus will make 
>>> our loop detection code turn the loop into a fake loop nest.  Not 
>>> sure if that is a good idea.
>>
>> I'd have to sit down and ponder this for a while -- what would be the 
>> register pressure implications of duplicating the contents of the 
>> join block into its predecessors, leaving an empty joiner so that we 
>> still have a single latch?
>
> Good question.  Now another question is why we don't choose this way 
> to disambiguate loops with multiple latches?  (create a forwarder as 
> new single latch block)

>>Dunno.  The RTL jump optimizer ought to eliminate the unnecessary jumping late in the optimization pipeline and creating the forwarder allows us to put the loop into a "more canonical" >>form for the loop optimizers.  Seems like it'd be worth some experimentation.

I agree with Jeff on this. The above approach of path splitting will keep the loop into more canonical form for the Loop optimizers.

>>I'm having trouble seeing how Ajit's proposal helps reduce register pressure in any significant way except perhaps by exposing partially dead code.  And if that's the primary benefit, we >>may better off actually building a proper framework for PDCE.

Jeff: The above approach of path splitting is very similar to superblock formation as we are duplicating  the join nodes into all its predecessors. By doing so,
The predecessors blocks duplicated from the join nodes will achieve more granularity with the scope of the scheduling and the register allocation. Due to
The bigger granularity of the predecessors blocks, the advantages will have similar to having superblock with more granularity. This gives more scheduling
Opportunities of basic blocks scheduling the independent operations. Due to the above path splitting approach, the LRA will have a more significant impact with
 the respect to register allocation. Because of more granular predecessors blocks the  scope of LRA will increase, and the LRA can reuse the registers thus impacting the 
Live range and the register pressure and  we can use better heuristics with respect to spill code in LRA.

>>I've often pondered if PDCE is really worth it.  There's some good PLDI papers from many years ago.  One is closely related to our RTL GCSE implementation (Knoop). But RTL seems the >>wrong place to be doing this.

>>Click's GCM/GVN can achieve similar results by the nature of code motion algorithm IIRC, but as much as I like Click's algorithm, I wasn't ever able to get it to do anything significantly >>better than existing bits in GCC.

Thanks Jeff.

Thanks & Regards
Ajit

Jeff