diff options
author | Matthias Braun <matze@braunis.de> | 2024-04-17 12:48:02 -0700 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-04-17 12:48:02 -0700 |
commit | 652bcf685c72447f3cc46d93d6c9c1948e8499f3 (patch) | |
tree | bcada6c64aee0c2ce4c93da6bf044857125df281 /llvm/lib/CodeGen/MachineBasicBlock.cpp | |
parent | db2f64ee1f743153f242ca92bf627458ba7f8000 (diff) | |
download | llvm-652bcf685c72447f3cc46d93d6c9c1948e8499f3.zip llvm-652bcf685c72447f3cc46d93d6c9c1948e8499f3.tar.gz llvm-652bcf685c72447f3cc46d93d6c9c1948e8499f3.tar.bz2 |
CodeGenPrepare: Add support for llvm.threadlocal.address address-mode sinking (#87844)
Depending on the TLSMode many thread-local accesses on x86 can be
expressed by adding a %fs: segment register to an addressing mode. Even
if there are mutliple users of a `llvm.threadlocal.address` intrinsic it
is generally not worth sharing the value in a register but instead fold
the %fs access into multiple addressing modes.
Hence this changes CodeGenPrepare to duplicate the
`llvm.threadlocal.address` intrinsic as necessary.
Introduces a new `TargetLowering::addressingModeSupportsTLS` callback
that allows targets to indicate whether TLS accesses can be part of an
addressing mode.
This is fixing a performance problem, as this folding of TLS-accesses
into multiple addressing modes happened naturally before the
introduction of the `llvm.threadlocal.address` intrinsic, but regressed
due to `SelectionDAG` keeping things in registers when accessed across
basic blocks, so CodeGenPrepare needs to duplicate to mitigate this. We
see a ~0.5% recovery in a codebase with heavy TLS usage (HHVM).
This fixes most of #87437
Diffstat (limited to 'llvm/lib/CodeGen/MachineBasicBlock.cpp')
0 files changed, 0 insertions, 0 deletions