Cherry pick llvm/llvm-project#165374

Author: pabloantoniom

external/llvm-project/mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td

@@ -558,6 +558,39 @@ 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.
+
+    Available on gfx1250+.
+  }];
+  let extraClassDefinition = [{
+    ::llvm::SmallVector<::mlir::Value> $cppClass::getAccessedOperands() {
+      return {getGlobalPtr(), getLdsPtr()};
+    }
+  }];
+}
+
+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">;
+
 //===---------------------------------------------------------------------===//
 // Operations on raw buffer resources (stride of 0, bounds checks either off or in
 // raw buffer mode).

external/llvm-project/mlir/test/Dialect/LLVMIR/rocdl.mlir

@@ -650,6 +650,19 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
   llvm.return
 }
 
+llvm.func @rocdl.global.load.async.to.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
+  // CHECK-LABEL @rocdl.global.load.async.to.lds
+  // CHECK: rocdl.global.load.async.to.lds.b8 %{{.*}}, %{{.*}}, 0, 0
+  // CHECK: rocdl.global.load.async.to.lds.b32 %{{.*}}, %{{.*}}, 0, 0
+  // CHECK: rocdl.global.load.async.to.lds.b64 %{{.*}}, %{{.*}}, 0, 0
+  // CHECK: rocdl.global.load.async.to.lds.b128 %{{.*}}, %{{.*}}, 0, 0
+  rocdl.global.load.async.to.lds.b8 %src, %dst, 0, 0 : <1>
+  rocdl.global.load.async.to.lds.b32 %src, %dst, 0, 0 : <1>
+  rocdl.global.load.async.to.lds.b64 %src, %dst, 0, 0 : <1>
+  rocdl.global.load.async.to.lds.b128 %src, %dst, 0, 0 : <1>
+  llvm.return
+}
+
 llvm.func @rocdl.make.buffer.rsrc(%ptr : !llvm.ptr,
                                   %stride : i16,
                                   %numRecords : i32,

external/llvm-project/mlir/test/Target/LLVMIR/rocdl.mlir

@@ -905,6 +905,30 @@ 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: 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
+}
+
 llvm.func @rocdl.make.buffer.rsrc(%ptr : !llvm.ptr,
                                   %stride : i16,
                                   %numRecords : i32,