[Mlir-commits] [mlir] [mlir][gpu] Introduce `gpu.dynamic_shared_memory` Op (PR #71546)

[Oleksandr Alex Zinenko]

================
@@ -640,3 +640,52 @@ module {
   // expected-error @+1 {{'gpu.binary' op attribute 'offloadingHandler' failed to satisfy constraint: any attribute with the `OffloadingTranslationAttrTrait` trait.}}
   gpu.binary @binary <1> [#gpu.object<#nvvm.target, "">]
 }
+
+// -----
+
+func.func @main() {
+  %shmemSize = arith.constant 10000 : i32
+  %c1 = arith.constant 1 : index
+  gpu.launch blocks(%bx, %by, %bz) in (%sbx = %c1, %sby = %c1, %sbz = %c1)
+             threads(%tx, %ty, %tz) in (%stx = %c1, %sty = %c1, %stz = %c1) 
+             dynamic_shared_memory_size %shmemSize
+  {
+    // expected-error @+1 {{op Address space must be address_space<workgroup> or 3}}
----------------
ftynse wrote:

```suggestion
    // expected-error @below {{op Address space must be address_space<workgroup> or 3}}
```

https://github.com/llvm/llvm-project/pull/71546