[cfe-dev] RFC: First-class Matrix type

Chris Lattner via cfe-dev cfe-dev at lists.llvm.org
Wed Oct 24 11:08:00 PDT 2018



> On Oct 24, 2018, at 8:33 AM, Adam Nemet <anemet at apple.com> wrote:
> 
>>> 
>>> However, the argument seems to imply that a vector type like <16 x i32> can't do so. In the favor of option #1, I argue that the plain <16 x i32> enables the same optimization opportunities, as long as the uses are not on ABI boundaries.
>> 
>> Adam and I discussed this at the devmtg, and indeed his idea is to have a “codegen prepare” sort of pass that does some amount of pre-legalization of matrices (which should also be applicable to large vectors) with the goal of reducing register pressure etc.
>> 
>> Adam, can you please summarize the discussions you had and what you see as the next steps here?  Thanks!
> 
> I’d like to write up the main alternatives (flattened vector + shape/layout-aware intrinsics vs. N-dimensional vector) and contrast them with IR at the various stages.
> 
> I am busy with some internal stuff at the moment but hoping to get to this next week.
> 

Awesome, thanks.  Please don’t feel any pressure from me, I was just trying to be helpful and just didn’t want your work blocked on me being otherwise busy.

-Chris

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/cfe-dev/attachments/20181024/ae563086/attachment.html>


More information about the cfe-dev mailing list