[LLVMdev] mem2reg optimization

[Chris Lattner]

On Aug 11, 2008, at 7:58 AM, Nicolas Capens wrote:

> Hi all,
>
> While profiling LLVM I noticed that a significant amount of time is  
> spent in the RewriteSingleStoreAlloca function. Especially for  
> fairly long basic blocks, linearly searching for uses before a store  
> isn’t fast. So I was wondering if there isn’t a faster way to locate  
> these uses?

This should be easy to fix, particularly if there are many "single  
store allocas" being accessed in the same block.  The check is  
verifying that the store happens before any loads in the same block.   
Can you provide a .bc testcase please?

>
> Are there any other known opportunities for optimization? I noticed  
> that register allocation takes a big bite out of JIT compilation  
> performance, and there’s a big reliance on STL containers (which are  
> often not as fast as specialized custom containers).

There are many possibilities and many people are working on reducing  
compile time.  If you're hitting some very slow case, it is best to  
file a bugzilla with a testcase.

-Chris
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20080811/d57ff6fe/attachment.html>