[PATCH] D54899: [LoopStrengthReduce] ComplexityLimit as an option

Wed Nov 28 23:53:00 PST 2018

samparker marked an inline comment as done.
samparker added a comment.

Hi Quentin

I've found that increasing this limit helps the performance of unrolled loops where too many registers can be used for address computation. I'm working towards enabling greater use of post increment addressing modes, and I believe getting LSR to produce pointer phis is the first step.

================
Comment at: test/Transforms/LoopStrengthReduce/lsr-comp-time.ll:2
 ; RUN: opt -loop-reduce -S < %s | FileCheck %s
+; RUN: opt -loop-reduce -lsr-complexity-limit=2147483647 -S < %s | FileCheck %s
+
----------------
gilr wrote:
> Won't this effectively limit LSR to search spaces it can process w/o pruning?
As I understand, this high limit will prevent pruning from happening in more cases which leads to the solver having to process more formulae. I would hope that this doesn't limit the transform.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D54899/new/

https://reviews.llvm.org/D54899