[PATCH] D130258: [AMDGPU] Remove IR SpeculativeExecution pass from codegen pipeline

[Nicolai Hähnle via Phabricator via llvm-commits]

nhaehnle added a comment.

The test diff looks surprisingly small. Intuitively speaking, the most interesting instructions for speculative execution are loads. You wouldn't necessarily see a change in the instruction frequency there...


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130258/new/

https://reviews.llvm.org/D130258