[clang] [llvm] [mlir] [AMDGPU] Add a new amdgcn.load.to.lds intrinsic (PR #137425)

[Alan Li via cfe-commits]

================
@@ -444,17 +444,40 @@ def ROCDL_ds_read_tr6_b96 : ROCDL_LDS_Read_Tr_IntrOp<"ds.read.tr6.b96">;
 def ROCDL_ds_read_tr16_b64 : ROCDL_LDS_Read_Tr_IntrOp<"ds.read.tr16.b64">;
 
 //===---------------------------------------------------------------------===//
-// Global load to LDS intrinsic (available in GFX950)
+// Load to LDS intrinsic (available in GFX9 and GFX10)
+//===---------------------------------------------------------------------===//
+
+def ROCDL_LoadToLDSOp :
+  ROCDL_IntrOp<"load.to.lds", [], [0], [], 0, 0, 1, [2, 3, 4], ["size", "offset", "aux"]> {
+  dag args = (ins Arg<LLVM_AnyPointer, "", [MemRead]>:$globalPtr,
+                 Arg<ROCDLBufferLDS, "", [MemWrite]>:$ldsPtr,
+                 I32Attr:$size,
+                 I32Attr:$offset,
+                 I32Attr:$aux);
+  let arguments = !con(args, aliasAttrs);
+  let assemblyFormat = [{
+    $globalPtr `,`  $ldsPtr `,` $size `,` $offset `,` $aux
+    attr-dict `:` type($globalPtr)
+  }];
+  let extraClassDefinition = [{
+    ::llvm::SmallVector<::mlir::Value> $cppClass::getAccessedOperands() {
+      return {getGlobalPtr(), getLdsPtr()};
+    }
+  }];
+}
 
 def ROCDL_GlobalLoadLDSOp :
-  ROCDL_IntrOp<"global.load.lds", [], [], [], 0, 0, 1> {
+  ROCDL_IntrOp<"global.load.lds", [], [], [], 0, 0, 1, [2, 3, 4], ["size", "offset", "aux"]> {
----------------
lialan wrote:

@krzysz00 should we simply remove this op?

https://github.com/llvm/llvm-project/pull/137425