diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
--- a/llvm/lib/Transforms/Utils/Local.cpp
+++ b/llvm/lib/Transforms/Utils/Local.cpp
@@ -1404,6 +1404,13 @@
 static bool valueCoversEntireFragment(Type *ValTy, DbgVariableIntrinsic *DII) {
   const DataLayout &DL = DII->getModule()->getDataLayout();
   TypeSize ValueSize = DL.getTypeAllocSizeInBits(ValTy);
+
+  // If we are replacing a double indirection with a single-indirection, the
+  // fragment size could be (happens with reference params) that of the object
+  // but the pointer will only be 32/64 bits.
+  if (ValTy->isPointerTy())
+    return true;
+
   if (Optional<uint64_t> FragmentSize = DII->getFragmentSizeInBits()) {
     assert(!ValueSize.isScalable() &&
            "Fragments don't work on scalable types.");
diff --git a/llvm/test/Transforms/Util/nvptx-int128-ref-debuginfo.ll b/llvm/test/Transforms/Util/nvptx-int128-ref-debuginfo.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/Util/nvptx-int128-ref-debuginfo.ll
@@ -0,0 +1,63 @@
+; RUN: opt -mem2reg -S < %s | FileCheck %s
+
+source_filename = "moduleOutput"
+target datalayout = "e-p:64:64:64-p3:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-i128:128:128-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; CHECK-LABEL: @_Z3sumRnn
+define i128 @_Z3sumRnn(i128* %foo, i128 %bar) !dbg !7 {
+  %retval = alloca i128, align 16
+  %foo.addr = alloca i128*, align 8
+  %bar.addr = alloca i128, align 16
+  store i128* %foo, i128** %foo.addr, align 8
+; CHECK: call void @llvm.dbg.value(metadata i128* %foo, metadata !11, metadata !DIExpression()), !dbg !12
+  call void @llvm.dbg.declare(metadata i128** %foo.addr, metadata !11, metadata !DIExpression()), !dbg !12
+  %1 = bitcast i128* %bar.addr to <2 x i64>*
+  %2 = bitcast i128 %bar to <2 x i64>
+  store <2 x i64> %2, <2 x i64>* %1, align 16
+; CHECK: call void @llvm.dbg.declare(metadata i128* %bar.addr, metadata !13, metadata !DIExpression()), !dbg !14
+  call void @llvm.dbg.declare(metadata i128* %bar.addr, metadata !13, metadata !DIExpression()), !dbg !14
+  %tmp = load i128*, i128** %foo.addr, align 8, !dbg !15
+  %3 = bitcast i128* %tmp to <2 x i64>*, !dbg !15
+  %4 = load <2 x i64>, <2 x i64>* %3, align 16, !dbg !15
+  %5 = bitcast <2 x i64> %4 to i128, !dbg !15
+  %tmp1 = load i128, i128* %tmp, align 16, !dbg !15
+  %6 = bitcast i128* %bar.addr to <2 x i64>*, !dbg !15
+  %7 = load <2 x i64>, <2 x i64>* %6, align 16, !dbg !15
+  %8 = bitcast <2 x i64> %7 to i128, !dbg !15
+  %tmp2 = load i128, i128* %bar.addr, align 16, !dbg !15
+  %add = add nsw i128 %5, %8, !dbg !15
+  %9 = bitcast i128* %retval to <2 x i64>*, !dbg !15
+  %10 = bitcast i128 %add to <2 x i64>, !dbg !15
+  store <2 x i64> %10, <2 x i64>* %9, align 16, !dbg !15
+  %11 = bitcast i128* %retval to <2 x i64>*, !dbg !15
+  %12 = load <2 x i64>, <2 x i64>* %11, align 16, !dbg !15
+  %13 = bitcast <2 x i64> %12 to i128, !dbg !15
+  %14 = load i128, i128* %retval, align 16, !dbg !15
+  ret i128 %13, !dbg !15
+}
+
+declare void @llvm.dbg.declare(metadata, metadata, metadata) #0
+
+attributes #0 = { nofree nosync nounwind readnone speculatable willreturn }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "foo", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, retainedTypes: !3)
+!1 = !DIFile(filename: "test.cu", directory: "/foo/bar")
+!2 = !{}
+!3 = !{!4}
+!4 = !DIDerivedType(tag: DW_TAG_typedef, name: "__int128_t", scope: !1, file: !1, baseType: !5)
+!5 = !DIBasicType(name: "__int128", size: 128, encoding: DW_ATE_signed)
+!6 = !{i32 1, !"Debug Info Version", i32 3}
+!7 = distinct !DISubprogram(name: "sum", linkageName: "_Z3sumRnn", scope: !1, file: !1, line: 5, type: !8, scopeLine: 5, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !2)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!4, !10, !4}
+!10 = !DIDerivedType(tag: DW_TAG_reference_type, baseType: !4)
+!11 = !DILocalVariable(name: "foo", arg: 1, scope: !7, file: !1, line: 5, type: !10)
+!12 = !DILocation(line: 5, column: 52, scope: !7)
+!13 = !DILocalVariable(name: "bar", arg: 2, scope: !7, file: !1, line: 5, type: !4)
+!14 = !DILocation(line: 5, column: 68, scope: !7)
+!15 = !DILocation(line: 7, column: 11, scope: !16)
+!16 = distinct !DILexicalBlock(scope: !7, file: !1, line: 6, column: 1)