[llvm] [AMDGPU][MISched] Allow memory ops of different base pointers to be c… (PR #140674)

[via llvm-commits]

choikwa wrote:

The main motivation for doing this came from looking at MISched logs and observing degradation when two loads from different arrays of dot_product weren't put adjacent. I saw that shouldClusterMemOp was the main determinant for rejecting clustering two loads if base pointers were different and otherwise it was relying only on tie-breaking heuristics to decide if loads should be put together, which isn't deterministic.

Shader Programming Guide section 3.1.8 on "Soft" Memory Clause also notes that back-to-back requests are much more efficient for the cache.

https://github.com/llvm/llvm-project/pull/140674