diff options
| author | Aart Bik <ajcbik@google.com> | 2021-06-11 10:33:43 -0700 |
|---|---|---|
| committer | Aart Bik <ajcbik@google.com> | 2021-06-15 14:55:07 -0700 |
| commit | 727a63e0d9a79d8e650674c0aca8fb3629e06b2d (patch) | |
| tree | fba6214e9ea9e852b721fd8874f649578e6ad750 /flang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 434fed5aff5e62460e2e984c7cc2674c12779b1e (diff) | |
| download | llvm-727a63e0d9a79d8e650674c0aca8fb3629e06b2d.zip llvm-727a63e0d9a79d8e650674c0aca8fb3629e06b2d.tar.gz llvm-727a63e0d9a79d8e650674c0aca8fb3629e06b2d.tar.bz2 | |
[mlir][sparse] allow all-dense annotated "sparse" tensor output
This is a very careful start with alllowing sparse tensors at the
left-hand-side of tensor index expressions (viz. sparse output).
Note that there is a subtle difference between non-annotated tensors
(dense, remain n-dim, handled by classic bufferization) and all-dense
annotated "sparse" tensors (linearized to 1-dim without overhead
storage, bufferized by sparse compiler, backed by runtime support library).
This revision gently introduces some new IR to facilitate annotated outputs,
to be generalized to truly sparse tensors in the future.
Reviewed By: gussmith23, bixia
Differential Revision: https://reviews.llvm.org/D104074
Diffstat (limited to 'flang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions