Address ravil comments, note that I changed the foreach slightly

Author: pabloantoniom

mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td

@@ -696,34 +696,33 @@ def ROCDL_GlobalLoadLDSOp :
 // Async load to LDS intrinsic (available in GFX1250)
 //===---------------------------------------------------------------------===//
 
-class ROCDL_GlobalLoadAsyncToLDSOp<string mnemonic> :
-  ROCDL_IntrOp<mnemonic, [], [], [], 0, 0, 1, 0, [2, 3], ["offset", "aux"]> {
-  dag args = (ins Arg<ROCDLGlobalBuffer, "", [MemRead]>:$globalPtr,
-                 Arg<ROCDLBufferLDS, "", [MemWrite]>:$ldsPtr,
-                 I32Attr:$offset,
-                 I32Attr:$aux);
-  let arguments = !con(args, baseArgs);
-  let assemblyFormat = [{
-    $globalPtr `,`  $ldsPtr `,` $offset `,` $aux
-    attr-dict `:` type($globalPtr)
-  }];
-  let description = [{
-    Loads data asynchronously from a global memory pointer to a local data
-    store (LDS) pointer.
+foreach bitsVal = [8, 32, 64, 128] in {
+  defvar bitsStr = "b" # !cast<string>(bitsVal);
+  def ROCDL_GlobalLoadAsyncToLDS # !toupper(bitsStr) # Op :
+    ROCDL_IntrOp<"global.load.async.to.lds." # bitsStr, [], [], [], 0, 0, 1, 0, [2, 3], ["offset", "aux"]> {
+    dag args = (ins Arg<ROCDLGlobalBuffer, "", [MemRead]>:$globalPtr,
+                   Arg<ROCDLBufferLDS, "", [MemWrite]>:$ldsPtr,
+                   I32Attr:$offset,
+                   I32Attr:$aux);
+    let arguments = !con(args, baseArgs);
+    let assemblyFormat = [{
+      $globalPtr `,`  $ldsPtr `,` $offset `,` $aux
+      attr-dict `:` type($globalPtr)
+    }];
+    let description = [{
+      Asynchronously loads }] # !cast<string>(bitsVal) # [{ bits of data from a global memory pointer
+      to a Local Data Share (LDS) pointer.
 
-    Available on gfx1250+.
-  }];
-  let extraClassDefinition = [{
-    ::llvm::SmallVector<::mlir::Value> $cppClass::getAccessedOperands() {
-      return {getGlobalPtr(), getLdsPtr()};
-    }
-  }];
-}
+      Available on gfx1250+.
+    }];
 
-def ROCDL_GlobalLoadAsyncToLDSB8Op : ROCDL_GlobalLoadAsyncToLDSOp<"global.load.async.to.lds.b8">;
-def ROCDL_GlobalLoadAsyncToLDSB32Op : ROCDL_GlobalLoadAsyncToLDSOp<"global.load.async.to.lds.b32">;
-def ROCDL_GlobalLoadAsyncToLDSB64Op : ROCDL_GlobalLoadAsyncToLDSOp<"global.load.async.to.lds.b64">;
-def ROCDL_GlobalLoadAsyncToLDSB128Op : ROCDL_GlobalLoadAsyncToLDSOp<"global.load.async.to.lds.b128">;
+    let extraClassDefinition = [{
+      ::llvm::SmallVector<::mlir::Value> $cppClass::getAccessedOperands() {
+        return {getGlobalPtr(), getLdsPtr()};
+      }
+    }];
+  }
+}
 
 //===---------------------------------------------------------------------===//
 // Tensor load/store intrinsics (available in GFX1250)

mlir/test/Target/LLVMIR/rocdl.mlir

@@ -1040,25 +1040,14 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   llvm.return
 }
 
-llvm.func @rocdl.global.load.async.lds.b8(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
+// CHECK-LABEL: rocdl.global.load.async.to.lds
+llvm.func @rocdl.global.load.async.to.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   // CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b8
   rocdl.global.load.async.to.lds.b8 %src, %dst, 0, 0 : !llvm.ptr<1>
-  llvm.return
-}
-
-llvm.func @rocdl.global.load.async.lds.b32(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   // CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b32
   rocdl.global.load.async.to.lds.b32 %src, %dst, 0, 0 : !llvm.ptr<1>
-  llvm.return
-}
-
-llvm.func @rocdl.global.load.async.lds.b64(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   // CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b64
   rocdl.global.load.async.to.lds.b64 %src, %dst, 0, 0 : !llvm.ptr<1>
-  llvm.return
-}
-
-llvm.func @rocdl.global.load.async.lds.b128(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   // CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b128
   rocdl.global.load.async.to.lds.b128 %src, %dst, 0, 0 : !llvm.ptr<1>
   llvm.return