Unaligned SSE Memop Support Patch

Project Infrastructure LLVM Dev List Archives
1

This patch adds a feature to allow SSE memops to be unaligned
on supported architectures.

Mostly I want to see if the naming is reasonable.

Supporting unaligned memops requires a bit twiddle on 10h
processors. This patch makes the assumption that the OS
sets the bit correctly.

Comments?

                             -Dave

uamem.patch (3.5 KB)

2

Please mention "SIMD" or "vector" in the description string in
the SubtargetFeature definition, to avoid confusion. Also, it would be
good to mention "for example, the AMD 10h" in a comment somewhere.

Otherwise, looks good to me.

Dan