<feed xmlns='http://www.w3.org/2005/Atom'>
<title>llvm-project.git/mlir/lib/ExecutionEngine/SparseTensor/File.cpp, branch main</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/'/>
<entry>
<title>[mlir][sparse] remove very thin header file from sparse runtime support (#82820)</title>
<updated>2024-02-23T20:37:36+00:00</updated>
<author>
<name>Aart Bik</name>
<email>39774503+aartbik@users.noreply.github.com</email>
</author>
<published>2024-02-23T20:37:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=1c2456d6593cea317a00627889b5c35766a732e0'/>
<id>1c2456d6593cea317a00627889b5c35766a732e0</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] minor edits in runtime lib Cpp files (#68165)</title>
<updated>2023-10-03T23:28:54+00:00</updated>
<author>
<name>Aart Bik</name>
<email>39774503+aartbik@users.noreply.github.com</email>
</author>
<published>2023-10-03T23:28:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=427f120f60becd23d6e037ccd14104adde8a3af9'/>
<id>427f120f60becd23d6e037ccd14104adde8a3af9</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Extend readCOOIndices to support overhead types beyond index_type.</title>
<updated>2023-02-13T22:51:59+00:00</updated>
<author>
<name>bixia1</name>
<email>bixia@google.com</email>
</author>
<published>2023-02-13T20:43:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=e800c664f0e925f6acb30dfa054906e3059ce125'/>
<id>e800c664f0e925f6acb30dfa054906e3059ce125</id>
<content type='text'>
This is to prepare for implementing the C API for reading a COO tensor to the
given buffers for indices and values.

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D143861
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is to prepare for implementing the C API for reading a COO tensor to the
given buffers for indices and values.

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D143861
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Breaking up openSparseTensor to better support non-permutations</title>
<updated>2022-12-02T19:10:57+00:00</updated>
<author>
<name>wren romano</name>
<email>2998727+wrengr@users.noreply.github.com</email>
</author>
<published>2022-12-02T02:18:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=2af2e4dbb790daafd3cbbf6189a7a27145cf4c12'/>
<id>2af2e4dbb790daafd3cbbf6189a7a27145cf4c12</id>
<content type='text'>
This commit updates how the `SparseTensorConversion` pass handles `NewOp`.  It breaks up the underlying `openSparseTensor` function into two parts (`SparseTensorReader::create` and `SparseTensorReader::readSparseTensor`) so that the pass can inject code for constructing `lvlSizes` between those two parts.  Migrating the construction of `lvlSizes` out of the runtime and into the pass is a necessary first step toward fully supporting non-permutations.  (The alternative would be for the pass to generate a `FuncOp` for performing the construction and then passing that to the runtime; which doesn't seem to have any benefits over the design of this commit.)  And since the pass now generates the code to call these two functions, this change also removes the `Action::kFromFile` value from the enum used by `_mlir_ciface_newSparseTensor`.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D138363
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This commit updates how the `SparseTensorConversion` pass handles `NewOp`.  It breaks up the underlying `openSparseTensor` function into two parts (`SparseTensorReader::create` and `SparseTensorReader::readSparseTensor`) so that the pass can inject code for constructing `lvlSizes` between those two parts.  Migrating the construction of `lvlSizes` out of the runtime and into the pass is a necessary first step toward fully supporting non-permutations.  (The alternative would be for the pass to generate a `FuncOp` for performing the construction and then passing that to the runtime; which doesn't seem to have any benefits over the design of this commit.)  And since the pass now generates the code to call these two functions, this change also removes the `Action::kFromFile` value from the enum used by `_mlir_ciface_newSparseTensor`.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D138363
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Making way for SparseTensorRuntime to support non-permutations</title>
<updated>2022-11-14T21:48:41+00:00</updated>
<author>
<name>wren romano</name>
<email>2998727+wrengr@users.noreply.github.com</email>
</author>
<published>2022-11-09T21:33:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=c518745bbadcfb5b0cc7be8615172ecbb3573efb'/>
<id>c518745bbadcfb5b0cc7be8615172ecbb3573efb</id>
<content type='text'>
Systematically updates the SparseTensorRuntime to properly distinguish tensor-dimensions from storage-levels (and their associated ranks, shapes, sizes, indices, etc).  With a few exceptions which are noted in the code, this ensures the runtime has all the **semantic** changes necessary to support non-permutations.

(Whereas **operationally**, since we're still using `std::vector&lt;uing64_t&gt;` to represent the mappings, there's no way to pass in any interesting non-permutations.  Changing the representation to `std::function` will be done in a separate differential.)

Depends On D137680

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D137681
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Systematically updates the SparseTensorRuntime to properly distinguish tensor-dimensions from storage-levels (and their associated ranks, shapes, sizes, indices, etc).  With a few exceptions which are noted in the code, this ensures the runtime has all the **semantic** changes necessary to support non-permutations.

(Whereas **operationally**, since we're still using `std::vector&lt;uing64_t&gt;` to represent the mappings, there's no way to pass in any interesting non-permutations.  Changing the representation to `std::function` will be done in a separate differential.)

Depends On D137680

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D137681
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Rename SparseTensorFile to SparseTensorReader.</title>
<updated>2022-10-10T15:24:37+00:00</updated>
<author>
<name>bixia1</name>
<email>bixia@google.com</email>
</author>
<published>2022-10-07T19:01:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=461c461a7cbf36c094dbd9663bd36cf0e7c2bd9a'/>
<id>461c461a7cbf36c094dbd9663bd36cf0e7c2bd9a</id>
<content type='text'>
This is to prepare for adding SparseTensorWriter.

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D135477
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is to prepare for adding SparseTensorWriter.

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D135477
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Case coverage fix no errorhandling</title>
<updated>2022-10-05T22:35:00+00:00</updated>
<author>
<name>Nathaniel McVicar</name>
<email>namcvica@microsoft.com</email>
</author>
<published>2022-10-05T21:51:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=ff7a2b60555a28754b9513b78c5a6b4678b6656f'/>
<id>ff7a2b60555a28754b9513b78c5a6b4678b6656f</id>
<content type='text'>
Restores the fix from D134925 for MSVC without breaking cpu runner.

Differential Revision: https://reviews.llvm.org/D135304
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Restores the fix from D134925 for MSVC without breaking cpu runner.

Differential Revision: https://reviews.llvm.org/D135304
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "[mlir][sparse] Restore case coverage warning fix"</title>
<updated>2022-10-05T16:53:58+00:00</updated>
<author>
<name>Vitaly Buka</name>
<email>vitalybuka@google.com</email>
</author>
<published>2022-10-05T16:47:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=0df37528ebe495c2974e755be464722d0a8bfda1'/>
<id>0df37528ebe495c2974e755be464722d0a8bfda1</id>
<content type='text'>
Breaks https://lab.llvm.org/buildbot/#/builders/168/builds/9288

This reverts commit 83839700c32996c58ddebc0c74e3dc4970e005bc.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Breaks https://lab.llvm.org/buildbot/#/builders/168/builds/9288

This reverts commit 83839700c32996c58ddebc0c74e3dc4970e005bc.
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir][sparse] Restore case coverage warning fix</title>
<updated>2022-10-04T16:59:20+00:00</updated>
<author>
<name>Nathaniel McVicar</name>
<email>namcvica@microsoft.com</email>
</author>
<published>2022-10-04T16:42:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=83839700c32996c58ddebc0c74e3dc4970e005bc'/>
<id>83839700c32996c58ddebc0c74e3dc4970e005bc</id>
<content type='text'>
This restores the fix from D134925 to make MSVC and clang happy.

Reviewed By: stella.stamenova

Differential Revision: https://reviews.llvm.org/D135126
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This restores the fix from D134925 to make MSVC and clang happy.

Reviewed By: stella.stamenova

Differential Revision: https://reviews.llvm.org/D135126
</pre>
</div>
</content>
</entry>
<entry>
<title>[mlir] Fix warnings</title>
<updated>2022-09-30T22:00:56+00:00</updated>
<author>
<name>Kazu Hirata</name>
<email>kazu@google.com</email>
</author>
<published>2022-09-30T22:00:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=e898be2f6edbb886af2f6b23e2f5db5210535620'/>
<id>e898be2f6edbb886af2f6b23e2f5db5210535620</id>
<content type='text'>
This patch fixes:

  mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp:1348:31: error: comparison
  of integers of different signs: 'size_t' (aka 'unsigned long') and
  'int64_t' (aka 'long') [-Werror,-Wsign-compare]

  mlir/lib/ExecutionEngine/SparseTensor/File.cpp:110:3: error: default
  label in switch which covers all enumeration values
  [-Werror,-Wcovered-switch-default]
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This patch fixes:

  mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp:1348:31: error: comparison
  of integers of different signs: 'size_t' (aka 'unsigned long') and
  'int64_t' (aka 'long') [-Werror,-Wsign-compare]

  mlir/lib/ExecutionEngine/SparseTensor/File.cpp:110:3: error: default
  label in switch which covers all enumeration values
  [-Werror,-Wcovered-switch-default]
</pre>
</div>
</content>
</entry>
</feed>
