diff options
| author | Aart Bik <ajcbik@google.com> | 2021-08-25 21:01:12 -0700 |
|---|---|---|
| committer | Aart Bik <ajcbik@google.com> | 2021-08-25 21:50:39 -0700 |
| commit | 6b26857dbfc1f8675382f5510f9ca02dad62729a (patch) | |
| tree | f02c62b3c53301a2d94396e0eb1ed62a95df10e8 /llvm/lib/CodeGen/MachineScheduler.cpp | |
| parent | a45d72e0247d080eb9437736bb6cadfc27e4c065 (diff) | |
| download | llvm-6b26857dbfc1f8675382f5510f9ca02dad62729a.zip llvm-6b26857dbfc1f8675382f5510f9ca02dad62729a.tar.gz llvm-6b26857dbfc1f8675382f5510f9ca02dad62729a.tar.bz2 | |
[mlir][sparse] add asCOO() functionality to sparse tensor object
This prepares general sparse to sparse conversions. The code that
needs to be generated using this new feature is now simply:
(1) coo = sparse_tensor_1->asCOO(); // source format1
(2) sparse_tensor_2 = newSparseTensor(coo); // destination format2
By using COO as an intermediate, we can do *all* conversions without
having to implement the full O(N^2) conversion matrix. Note that we
can always improve particular conversions individually if a faster
solution is required.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D108681
Diffstat (limited to 'llvm/lib/CodeGen/MachineScheduler.cpp')
0 files changed, 0 insertions, 0 deletions