llvm/mlir
Aart Bik ff6c84b803 [mlir][sparse] generalize sparse storage format to many more types
Rationale:
Narrower types for overhead storage yield a smaller memory footprint for
sparse tensors and thus needs to be supported. Also, more value types
need to be supported to deal with all kinds of kernels. Since the
"one-size-fits-all" sparse storage scheme implementation is used
instead of actual codegen, the library needs to be able to support
all combinations of desired types. With some crafty templating and
overloading, the actual code for this is kept reasonably sized though.

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D96819
2021-02-17 18:20:23 -08:00
..
cmake/modules [MLIR] [CMake] Support building MLIR standalone 2021-02-02 13:10:21 -06:00
docs Enable Pass::initialize() to fail by returning a LogicalResult 2021-02-11 01:51:53 +00:00
examples [mlir] Simplify ModuleTranslation for LLVM IR 2021-02-16 18:42:52 +01:00
include [MLIR][TOSA] Expand Tosa int types to I8 and I16 2021-02-17 14:18:38 -08:00
integration_test [mlir][sparse] generalize sparse storage format to many more types 2021-02-17 18:20:23 -08:00
lib [mlir][sparse] generalize sparse storage format to many more types 2021-02-17 18:20:23 -08:00
test [mlir][sparse] generalize sparse storage format to many more types 2021-02-17 18:20:23 -08:00
tools [mlir] Simplify ModuleTranslation for LLVM IR 2021-02-16 18:42:52 +01:00
unittests [mlir] Add clone method to ShapedType 2021-02-15 11:04:16 -08:00
utils [mlir][spirv] Fix script for availability autogen and refresh ops 2021-01-22 13:07:36 -05:00
.clang-format
.clang-tidy
CMakeLists.txt Fix CMake configuration for MLIR unittests 2021-02-11 01:17:49 +00:00
LICENSE.TXT
README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.