diff --git a/mlir/include/mlir/Conversion/Passes.td b/mlir/include/mlir/Conversion/Passes.td
--- a/mlir/include/mlir/Conversion/Passes.td
+++ b/mlir/include/mlir/Conversion/Passes.td
@@ -422,6 +422,10 @@
            "Bitwidth of the index type, 0 to use size of machine word">,
     Option<"hasRedux", "has-redux", "bool", /*default=*/"false",
            "Target gpu supports redux">,
+    Option<"useBarePtrCallConv", "use-bare-ptr-memref-call-conv", "bool",
+           /*default=*/"false",
+           "Replace memref arguments in GPU functions with bare pointers. "
+           "All memrefs must have static shape.">,
     Option<"useOpaquePointers", "use-opaque-pointers", "bool",
                    /*default=*/"true", "Generate LLVM IR using opaque pointers "
                    "instead of typed pointers">,
diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
--- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -231,6 +231,7 @@
     if (indexBitwidth != kDeriveIndexBitwidthFromDataLayout)
       options.overrideIndexBitwidth(indexBitwidth);
     options.useOpaquePointers = useOpaquePointers;
+    options.useBarePtrCallConv = useBarePtrCallConv;
 
     // Apply in-dialect lowering. In-dialect lowering will replace
     // ops which need to be lowered further, which is not supported by a