<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="/rss.xsl.xml"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
    <title>Changes in sparse_kernels.mlir</title>
    <description></description>
    <language>en</language>
    <copyright>Copyright 2015</copyright>
    <generator>Java</generator><item>
        <title>c66303c2 - [mlir][sparse] Switch to One-Shot Bufferize</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#c66303c2</link>
        <description>[mlir][sparse] Switch to One-Shot BufferizeThis change removes the partial bufferization passes from the sparse compilation pipeline and replaces them with One-Shot Bufferize. One-Shot Analysis (and TensorCopyInsertion) is used to resolve all out-of-place bufferizations, dense and sparse. Dense ops are then bufferized with BufferizableOpInterface. Sparse ops are still bufferized in the Sparsification pass.Details:* Dense allocations are automatically deallocated, unless they are yielded from a block. (In that case the alloc would leak.) All test cases are modified accordingly. E.g., some funcs now have an &quot;out&quot; tensor argument that is returned from the function. (That way, the allocation happens at the call site.)* Sparse allocations are *not* automatically deallocated. They must be &quot;released&quot; manually. (No change, this will be addressed in a future change.)* Sparse tensor copies are not supported yet. (Future change)* Sparsification no longer has to consider inplacability. If necessary, allocations and/or copies are inserted during TensorCopyInsertion. All tensors are inplaceable by the time Sparsification is running. Instead of marking a tensor as &quot;not inplaceable&quot;, it can be marked as &quot;not writable&quot;, which will trigger an allocation and/or copy during TensorCopyInsertion.Differential Revision: https://reviews.llvm.org/D129356

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Thu, 14 Jul 2022 07:47:37 +0000</pubDate>
        <dc:creator>Matthias Springer &lt;springerm@google.com&gt;</dc:creator>
    </item>
<item>
        <title>6232a8f3 - [mlir][sparse][NFC] Switch InitOp to bufferization::AllocTensorOp</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#6232a8f3</link>
        <description>[mlir][sparse][NFC] Switch InitOp to bufferization::AllocTensorOpNow that we have an AllocTensorOp (previously InitTensorOp) in the bufferization dialect, the InitOp in the sparse dialect is no longer needed.Differential Revision: https://reviews.llvm.org/D126180

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Wed, 01 Jun 2022 21:59:58 +0000</pubDate>
        <dc:creator>Matthias Springer &lt;springerm@google.com&gt;</dc:creator>
    </item>
<item>
        <title>fb35cd3b - [mlir][NFC] Update textual references of `func` to `func.func` in SparseTensor tests</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#fb35cd3b</link>
        <description>[mlir][NFC] Update textual references of `func` to `func.func` in SparseTensor testsThe special case parsing of `func` operations is being removed.

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Wed, 20 Apr 2022 23:18:14 +0000</pubDate>
        <dc:creator>River Riddle &lt;riddleriver@gmail.com&gt;</dc:creator>
    </item>
<item>
        <title>52fb4f53 - [mlir][sparse] added linalg.dot to sparse kernel collection</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#52fb4f53</link>
        <description>[mlir][sparse] added linalg.dot to sparse kernel collectionReviewed By: bixiaDifferential Revision: https://reviews.llvm.org/D121315

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Wed, 09 Mar 2022 19:04:00 +0000</pubDate>
        <dc:creator>Aart Bik &lt;ajcbik@google.com&gt;</dc:creator>
    </item>
<item>
        <title>34381a76 - [mlir][sparse] avoid some codeup in sparsification transformation</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#34381a76</link>
        <description>[mlir][sparse] avoid some codeup in sparsification transformationA very small refactoring, but a big impact on tests that expect an exact order.This revision fixes the tests, but also makes them less brittle for similarminor changes in the future!Reviewed By: bixiaDifferential Revision: https://reviews.llvm.org/D119992

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Thu, 17 Feb 2022 00:30:46 +0000</pubDate>
        <dc:creator>Aart Bik &lt;ajcbik@google.com&gt;</dc:creator>
    </item>
<item>
        <title>dec8af70 - [mlir] Move SelectOp from Standard to Arithmetic</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#dec8af70</link>
        <description>[mlir] Move SelectOp from Standard to ArithmeticThis is part of splitting up the standard dialect. See https://llvm.discourse.group/t/standard-dialect-the-final-chapter/ for discussion.Differential Revision: https://reviews.llvm.org/D118648

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Mon, 31 Jan 2022 20:44:35 +0000</pubDate>
        <dc:creator>River Riddle &lt;riddleriver@gmail.com&gt;</dc:creator>
    </item>
<item>
        <title>e1b9d805 - [mlir][sparse] add a few more sparse output tests (for generated IR)</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#e1b9d805</link>
        <description>[mlir][sparse] add a few more sparse output tests (for generated IR)also fixes two typos in IR docReviewed By: bixiaDifferential Revision: https://reviews.llvm.org/D115288

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Tue, 07 Dec 2021 22:33:39 +0000</pubDate>
        <dc:creator>Aart Bik &lt;ajcbik@google.com&gt;</dc:creator>
    </item>
<item>
        <title>57470abc - [mlir] Move memref.[tensor_load|buffer_cast|clone] to &quot;bufferization&quot; dialect.</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#57470abc</link>
        <description>[mlir] Move memref.[tensor_load|buffer_cast|clone] to &quot;bufferization&quot; dialect.https://llvm.discourse.group/t/rfc-dialect-for-bufferization-related-ops/4712Differential Revision: https://reviews.llvm.org/D114552

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Thu, 25 Nov 2021 10:42:16 +0000</pubDate>
        <dc:creator>Alexander Belyaev &lt;pifon@google.com&gt;</dc:creator>
    </item>
<item>
        <title>a54f4eae - [MLIR] Replace std ops with arith dialect ops</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#a54f4eae</link>
        <description>[MLIR] Replace std ops with arith dialect opsPrecursor: https://reviews.llvm.org/D110200Removed redundant ops from the standard dialect that were moved to the`arith` or `math` dialects.Renamed all instances of operations in the codebase and in tests.Reviewed By: rriddle, jpienaarDifferential Revision: https://reviews.llvm.org/D110797

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Tue, 12 Oct 2021 23:14:57 +0000</pubDate>
        <dc:creator>Mogball &lt;jeffniu22@gmail.com&gt;</dc:creator>
    </item>
<item>
        <title>a924fcc7 - [mlir][sparse] add sparse kernels test to sparse compiler test suite</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir#a924fcc7</link>
        <description>[mlir][sparse] add sparse kernels test to sparse compiler test suiteThis test makes sure kernels map to efficient sparse code, i.e. allcompressed for-loops, no co-iterating while loops.  In addition, thisrevision removes the special constant folding inside the sparsecompiler in favor of Mahesh&apos; new generic linalg folding. Thanks!NOTE: relies on Mahesh fix, which needs to be rebased firstReviewed By: bixiaDifferential Revision: https://reviews.llvm.org/D110001

            List of files:
            /llvm-project-15.0.7/mlir/test/Dialect/SparseTensor/sparse_kernels.mlir</description>
        <pubDate>Mon, 20 Sep 2021 18:15:13 +0000</pubDate>
        <dc:creator>Aart Bik &lt;ajcbik@google.com&gt;</dc:creator>
    </item>
</channel>
</rss>
