diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-05-02 20:07:26 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-05-02 20:07:26 +0000 |
| commit | 2b957b5a6f228797a871426d48098fee479883ef (patch) | |
| tree | b4bf9a9ce48d543f320cbc6e212beb630a07f17c /llvm/tools/llvm-objdump/llvm-objdump.cpp | |
| parent | 5002a67ef2b0e05350220ba16a2b43f92001799c (diff) | |
| download | bcm5719-llvm-2b957b5a6f228797a871426d48098fee479883ef.tar.gz bcm5719-llvm-2b957b5a6f228797a871426d48098fee479883ef.zip | |
AMDGPU: Make i64 loads/stores promote to v2i32
Now that unaligned access expansion should not attempt
to produce i64 accesses, we can remove the hack in
PreprocessISelDAG where this is done.
This allows splitting i64 private accesses while
allowing the new add nodes indexing the vector components
can be folded with the base pointer arithmetic.
llvm-svn: 268293
Diffstat (limited to 'llvm/tools/llvm-objdump/llvm-objdump.cpp')
0 files changed, 0 insertions, 0 deletions
