diff --git a/mlir/lib/Conversion/GPUToROCDL/CMakeLists.txt b/mlir/lib/Conversion/GPUToROCDL/CMakeLists.txt
--- a/mlir/lib/Conversion/GPUToROCDL/CMakeLists.txt
+++ b/mlir/lib/Conversion/GPUToROCDL/CMakeLists.txt
@@ -11,6 +11,7 @@
 
   LINK_LIBS PUBLIC
   MLIRArithmeticToLLVM
+  MLIRAMDGPUToROCDL
   MLIRFuncToLLVM
   MLIRGPUOps
   MLIRGPUToGPURuntimeTransforms
diff --git a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
--- a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
+++ b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -14,6 +14,7 @@
 #include "mlir/Conversion/ControlFlowToLLVM/ControlFlowToLLVM.h"
 #include "mlir/Conversion/GPUToROCDL/GPUToROCDLPass.h"
 
+#include "mlir/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.h"
 #include "mlir/Conversion/ArithmeticToLLVM/ArithmeticToLLVM.h"
 #include "mlir/Conversion/FuncToLLVM/ConvertFuncToLLVM.h"
 #include "mlir/Conversion/LLVMCommon/ConversionTarget.h"
@@ -79,6 +80,7 @@
 
     mlir::arith::populateArithmeticToLLVMConversionPatterns(converter,
                                                             llvmPatterns);
+    populateAMDGPUToROCDLConversionPatterns(converter, llvmPatterns);
     populateVectorToLLVMConversionPatterns(converter, llvmPatterns);
     populateVectorToROCDLConversionPatterns(converter, llvmPatterns);
     cf::populateControlFlowToLLVMConversionPatterns(converter, llvmPatterns);
diff --git a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
--- a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
+++ b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
@@ -3798,6 +3798,7 @@
     includes = ["include"],
     deps = [
         ":ArithmeticToLLVM",
+        ":AMDGPUToROCDL",
         ":ControlFlowToLLVM",
         ":ConversionPassIncGen",
         ":FuncDialect",