[PATCH] D25966: [AArch64] Lower multiplication by a constant int to shl+add+shl

Haicheng Wu via llvm-commits llvm-commits at lists.llvm.org
Sat Oct 29 08:59:54 PDT 2016


haicheng added a comment.

Thank you, Renato.  I rewrote my change and added more tests, please let me know if I did what you recommended.

In https://reviews.llvm.org/D25966#579090, @rengolin wrote:

> I have some comments inline, but my only additional question is: What is the motivation behind this? Benchmark numbers? Can you share them?


The biggest motivation is that GCC can do this, but LLVM cannot.  My patch is conservative and it does not make big change to the performance.  I have not observed any noticeable regression, but the gain is small.  spec2006/h264ref and spec2006/povray have around 1% improvement.  One internal benchmark which is integer multiplication centric has much larger improvement.


Repository:
  rL LLVM

https://reviews.llvm.org/D25966





More information about the llvm-commits mailing list