[Mlir-commits] [mlir] [mlir][py] Add NVGPU's `TensorMapDescriptorType` in py bindings (PR #88855)

[llvmlistbot at llvm.org]

github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {darker}-->


:warning: Python code formatter, darker found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
darker --check --diff -r d06ba376833553f38b5cbc606e479ed7936e5f5b...d0d37b7675b14547be615b47f7a5203b8ac3a035 mlir/python/mlir/dialects/nvgpu.py mlir/test/python/dialects/nvgpu.py
``````````

</details>

<details>
<summary>
View the diff from darker here.
</summary>

``````````diff
--- test/python/dialects/nvgpu.py	2024-04-16 08:26:49.000000 +0000
+++ test/python/dialects/nvgpu.py	2024-04-16 08:31:57.545089 +0000
@@ -12,21 +12,25 @@
         with InsertionPoint(module.body):
             f()
         print(module)
     return f
 
+
 # CHECK-LABEL: testTypes
 @constructAndPrintInModule
 def testTypes():
-    tensorType = MemRefType.get((128,64), F16Type.get(), memory_space=Attribute.parse("3"))
+    tensorType = MemRefType.get(
+        (128, 64), F16Type.get(), memory_space=Attribute.parse("3")
+    )
     # CHECK: !nvgpu.tensormap.descriptor<tensor = memref<128x64xf16, 3>, swizzle = swizzle_128b, l2promo = l2promo_256b, oob = nan, interleave = none>
     tma_desc = nvgpu.TensorMapDescriptorType.get(
-                tensorType,
-                nvgpu.TensorMapSwizzleKind.SWIZZLE_128B,
-                nvgpu.TensorMapL2PromoKind.L2PROMO_256B,
-                nvgpu.TensorMapOOBKind.OOB_NAN,
-                nvgpu.TensorMapInterleaveKind.INTERLEAVE_NONE)
+        tensorType,
+        nvgpu.TensorMapSwizzleKind.SWIZZLE_128B,
+        nvgpu.TensorMapL2PromoKind.L2PROMO_256B,
+        nvgpu.TensorMapOOBKind.OOB_NAN,
+        nvgpu.TensorMapInterleaveKind.INTERLEAVE_NONE,
+    )
     print(tma_desc)
 
 
 # CHECK-LABEL: testSmoke
 @constructAndPrintInModule

``````````

</details>


https://github.com/llvm/llvm-project/pull/88855