Commit Graph

4 Commits

Author SHA1 Message Date
Yaxun Liu 2a22c5deff [AMDGPU] Switch to the new addr space mapping by default
This requires corresponding clang change.

Differential Revision: https://reviews.llvm.org/D40955

llvm-svn: 324101
2018-02-02 16:07:16 +00:00
Matt Arsenault e0f9e984fd InferAddressSpaces: Search constant expressions for addrspacecasts
These are pretty common when using local memory, and the 64-bit generic
addressing is much more expensive to compute.

llvm-svn: 301711
2017-04-28 22:52:41 +00:00
Matt Arsenault a1e734050c InferAddressSpaces: Infer from just addrspacecasts
Eliminates some more cases where some subset of the addressing
computation remains flat. Some cases with addrspacecasts
in nested constant expressions are still left behind however.

llvm-svn: 301704
2017-04-28 22:18:08 +00:00
Matt Arsenault c07bda7b87 InferAddressSpaces: Infer for just GEPs
Fixes leaving intermediate flat addressing computations
where a GEP instruction's source is a constant expression.

Still leaves behind a trivial addrspacecast + gep pair that
instcombine is able to handle, which ideally could be folded
here directly.

llvm-svn: 301044
2017-04-21 21:35:04 +00:00