[PATCH] D24745: TLI: Add option to generate dependent stores in scalarization.

[Hal Finkel via llvm-commits]

hfinkel added a comment.

In https://reviews.llvm.org/D24745#552833, @jvesely wrote:

> In https://reviews.llvm.org/D24745#552401, @hfinkel wrote:
>
> > I don't understand why you need this (even if you end up lowing the individual stores using a RMW sequence). Can you please explain?
>
>
> the problem is if we use RMW sequence for two different elements of the same word. for example storing bytes at address A and A +1. let's assume that A is 4byte aligned. the generated code will look like this
>  1: r1 = LOAD A
>  2: r2 = {r1[8:31], x} //This is a sequence of AND/OR instructions that masks of the old bits and ORs the new ones
>  3: STORE A, r2
>  4: r3 = LOAD A
>  5: r4 ={r3[0:8],y,r3[15:31]} //This is a sequence of AND/OR instructions that masks of the old bits and ORs the new ones
>  6: STORE A, r4
>
> The original code does not have dependency between 3 and 4.


Why not? I understand why the truncated stores and extending loads might be independent, but if you have code that widens those without looking at potential aliased peers and adjusting the chain, I think the problem lies there.


Repository:
  rL LLVM

https://reviews.llvm.org/D24745