build based on ce69c0d

JuliaLLVM · Apr 12, 2024 · 410a4a8 · 410a4a8
1 parent 732df95
commit 410a4a8
Show file tree

Hide file tree

Showing 56 changed files with 482 additions and 482 deletions.
diff --git a/dev/IR/affineexpr/index.html b/dev/IR/affineexpr/index.html
diff --git a/dev/IR/affinemap/index.html b/dev/IR/affinemap/index.html
diff --git a/dev/IR/attribute/index.html b/dev/IR/attribute/index.html
diff --git a/dev/IR/block/index.html b/dev/IR/block/index.html
diff --git a/dev/IR/context/index.html b/dev/IR/context/index.html
diff --git a/dev/IR/dialect/index.html b/dev/IR/dialect/index.html
diff --git a/dev/IR/identifier/index.html b/dev/IR/identifier/index.html
diff --git a/dev/IR/integerset/index.html b/dev/IR/integerset/index.html
diff --git a/dev/IR/iterators/index.html b/dev/IR/iterators/index.html
diff --git a/dev/IR/location/index.html b/dev/IR/location/index.html
diff --git a/dev/IR/logicalresult/index.html b/dev/IR/logicalresult/index.html
diff --git a/dev/IR/module/index.html b/dev/IR/module/index.html
diff --git a/dev/IR/operation/index.html b/dev/IR/operation/index.html
diff --git a/dev/IR/pass/index.html b/dev/IR/pass/index.html
diff --git a/dev/IR/region/index.html b/dev/IR/region/index.html
diff --git a/dev/IR/symboltable/index.html b/dev/IR/symboltable/index.html
diff --git a/dev/IR/type/index.html b/dev/IR/type/index.html
diff --git a/dev/IR/typeid/index.html b/dev/IR/typeid/index.html
diff --git a/dev/IR/value/index.html b/dev/IR/value/index.html
diff --git a/dev/api/index.html b/dev/api/index.html
diff --git a/dev/dialects/affine/index.html b/dev/dialects/affine/index.html
diff --git a/dev/dialects/amdgpu/index.html b/dev/dialects/amdgpu/index.html
diff --git a/dev/dialects/amx/index.html b/dev/dialects/amx/index.html
diff --git a/dev/dialects/arith/index.html b/dev/dialects/arith/index.html
diff --git a/dev/dialects/arm_neon/index.html b/dev/dialects/arm_neon/index.html
diff --git a/dev/dialects/arm_sve/index.html b/dev/dialects/arm_sve/index.html
diff --git a/dev/dialects/async/index.html b/dev/dialects/async/index.html
diff --git a/dev/dialects/bufferization/index.html b/dev/dialects/bufferization/index.html
@@ -3,6 +3,6 @@
 %0 = linalg.matmul
   ins(%a, %b: tensor&lt;?x?xf32, #SparseMatrix&gt;, tensor&lt;?x?xf32, #SparseMatrix&gt;)
   outs(%c: tensor&lt;?x?xf32, #SparseMatrix&gt;) -&gt; tensor&lt;?x?xf32, #SparseMatrix&gt;
-return %0 : tensor&lt;?x?xf32, #SparseMatrix&gt;</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/e6a5ef204941ce0ed17d32e110601c3ddc5898c6/src/Dialects/15/Bufferization.jl#L8-L48">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.clone-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.clone-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.clone</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>clone</code></p><p>Clones the data in the input view into an implicitly defined output view.</p><p>Usage:</p><pre><code class="language-mlir hljs">%arg1 = bufferization.clone %arg0 : memref&lt;?xf32&gt; to memref&lt;?xf32&gt;</code></pre><p>Valid implementations of this operation may alias the input and output views or create an actual copy. Mutating the source or result of the clone operation after the clone operation thus leads to undefined behavior.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/e6a5ef204941ce0ed17d32e110601c3ddc5898c6/src/Dialects/15/Bufferization.jl#L67-L82">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.dealloc_tensor-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.dealloc_tensor-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.dealloc_tensor</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>dealloc_tensor</code></p><p><code>bufferization.dealloc_tensor</code> is a buffer deallocation in tensor land. This op can be used for manual buffer deallocation. Some bufferizations (such as One-Shot Bufferize) take care of buffer deallocation, in which case this op is usually not needed. Details can be found in the documentation of the respective bufferization passes.</p><p>In case of a dense tensor, this op lowers to a <code>memref.dealloc</code> op during bufferization.</p><p>In case of a sparse tensor, this op releases the underlying sparse storage format for a tensor that materialized earlier through a <code>new</code> operation, a <code>convert</code> operation with annotated destination tensor type (unless the convert is folded away), or a <code>bufferization.alloc_tensor</code> operation. The release operation should only be called once for any materialized tensor. After this operation, any subsequent <code>memref</code> querying operation on the tensor returns undefined results.</p><p><strong>Example</strong></p><pre><code class="language-mlir hljs">bufferization.dealloc_tensor %tensor : tensor&lt;1024x1024xf64, #CSR&gt;</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/e6a5ef204941ce0ed17d32e110601c3ddc5898c6/src/Dialects/15/Bufferization.jl#L98-L123">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.to_memref-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.to_memref-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.to_memref</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>to_memref</code></p><p>Casts a tensor to a memref.</p><pre><code class="language-mlir hljs">// Result type is memref&lt;4x?xf32, #map0, 42&gt;
-%12 = bufferization.to_memref %10 : memref&lt;4x?xf32, #map0, 42&gt;</code></pre><p>Note, that mutating the result of the <code>to_memref</code> operation leads to undefined behavior.</p><p>This operation is a specialized variant of the built-in <code>unrealized_conversion_cast</code> and is intended for use in the context of gradual bufferization.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/e6a5ef204941ce0ed17d32e110601c3ddc5898c6/src/Dialects/15/Bufferization.jl#L139-L155">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.to_tensor-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.to_tensor-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.to_tensor</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>to_tensor</code></p><p>Create a tensor from a <code>memref</code>, making an independent copy of the element data. The result value is a tensor whose shape and element type match the memref operand.</p><p>The opposite of this op is <code>to_memref</code>. Together, these two ops are useful for source/target materializations when doing type conversions involving tensors and memrefs.</p><p><strong>Example</strong></p><pre><code class="language-mlir hljs">// Produces a value of tensor&lt;4x?xf32&gt; type.
-%12 = bufferization.to_tensor %10 : memref&lt;4x?xf32, #layout, memspace0&gt;</code></pre><p>If tensor load is used in the bufferization steps, mutating the source buffer after loading leads to undefined behavior.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/e6a5ef204941ce0ed17d32e110601c3ddc5898c6/src/Dialects/15/Bufferization.jl#L171-L191">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../async/">« <code>async</code></a><a class="docs-footer-nextpage" href="../builtin/"><code>builtin</code> »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 0.27.25 on <span class="colophon-date" title="Friday 12 April 2024 17:43">Friday 12 April 2024</span>. Using Julia version 1.10.2.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+return %0 : tensor&lt;?x?xf32, #SparseMatrix&gt;</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/ce69c0df26b332aa2e03c73e7b15c5764befa4b6/src/Dialects/15/Bufferization.jl#L8-L48">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.clone-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.clone-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.clone</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>clone</code></p><p>Clones the data in the input view into an implicitly defined output view.</p><p>Usage:</p><pre><code class="language-mlir hljs">%arg1 = bufferization.clone %arg0 : memref&lt;?xf32&gt; to memref&lt;?xf32&gt;</code></pre><p>Valid implementations of this operation may alias the input and output views or create an actual copy. Mutating the source or result of the clone operation after the clone operation thus leads to undefined behavior.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/ce69c0df26b332aa2e03c73e7b15c5764befa4b6/src/Dialects/15/Bufferization.jl#L67-L82">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.dealloc_tensor-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.dealloc_tensor-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.dealloc_tensor</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>dealloc_tensor</code></p><p><code>bufferization.dealloc_tensor</code> is a buffer deallocation in tensor land. This op can be used for manual buffer deallocation. Some bufferizations (such as One-Shot Bufferize) take care of buffer deallocation, in which case this op is usually not needed. Details can be found in the documentation of the respective bufferization passes.</p><p>In case of a dense tensor, this op lowers to a <code>memref.dealloc</code> op during bufferization.</p><p>In case of a sparse tensor, this op releases the underlying sparse storage format for a tensor that materialized earlier through a <code>new</code> operation, a <code>convert</code> operation with annotated destination tensor type (unless the convert is folded away), or a <code>bufferization.alloc_tensor</code> operation. The release operation should only be called once for any materialized tensor. After this operation, any subsequent <code>memref</code> querying operation on the tensor returns undefined results.</p><p><strong>Example</strong></p><pre><code class="language-mlir hljs">bufferization.dealloc_tensor %tensor : tensor&lt;1024x1024xf64, #CSR&gt;</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/ce69c0df26b332aa2e03c73e7b15c5764befa4b6/src/Dialects/15/Bufferization.jl#L98-L123">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.to_memref-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.to_memref-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.to_memref</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>to_memref</code></p><p>Casts a tensor to a memref.</p><pre><code class="language-mlir hljs">// Result type is memref&lt;4x?xf32, #map0, 42&gt;
+%12 = bufferization.to_memref %10 : memref&lt;4x?xf32, #map0, 42&gt;</code></pre><p>Note, that mutating the result of the <code>to_memref</code> operation leads to undefined behavior.</p><p>This operation is a specialized variant of the built-in <code>unrealized_conversion_cast</code> and is intended for use in the context of gradual bufferization.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/ce69c0df26b332aa2e03c73e7b15c5764befa4b6/src/Dialects/15/Bufferization.jl#L139-L155">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="MLIR.Dialects.bufferization.to_tensor-Tuple{MLIR.IR.Value}" href="#MLIR.Dialects.bufferization.to_tensor-Tuple{MLIR.IR.Value}"><code>MLIR.Dialects.bufferization.to_tensor</code></a> — <span class="docstring-category">Method</span></header><section><div><p><code>to_tensor</code></p><p>Create a tensor from a <code>memref</code>, making an independent copy of the element data. The result value is a tensor whose shape and element type match the memref operand.</p><p>The opposite of this op is <code>to_memref</code>. Together, these two ops are useful for source/target materializations when doing type conversions involving tensors and memrefs.</p><p><strong>Example</strong></p><pre><code class="language-mlir hljs">// Produces a value of tensor&lt;4x?xf32&gt; type.
+%12 = bufferization.to_tensor %10 : memref&lt;4x?xf32, #layout, memspace0&gt;</code></pre><p>If tensor load is used in the bufferization steps, mutating the source buffer after loading leads to undefined behavior.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaLabs/MLIR.jl/blob/ce69c0df26b332aa2e03c73e7b15c5764befa4b6/src/Dialects/15/Bufferization.jl#L171-L191">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../async/">« <code>async</code></a><a class="docs-footer-nextpage" href="../builtin/"><code>builtin</code> »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 0.27.25 on <span class="colophon-date" title="Friday 12 April 2024 17:55">Friday 12 April 2024</span>. Using Julia version 1.10.2.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>