diff --git a/flang/include/flang/Optimizer/Builder/IntrinsicCall.h b/flang/include/flang/Optimizer/Builder/IntrinsicCall.h
index b15dd29d68f65..01801dbdaffca 100644
--- a/flang/include/flang/Optimizer/Builder/IntrinsicCall.h
+++ b/flang/include/flang/Optimizer/Builder/IntrinsicCall.h
@@ -241,7 +241,6 @@ struct IntrinsicLibrary {
   void genCFProcPointer(llvm::ArrayRef<fir::ExtendedValue>);
   fir::ExtendedValue genCFunLoc(mlir::Type, llvm::ArrayRef<fir::ExtendedValue>);
   fir::ExtendedValue genCLoc(mlir::Type, llvm::ArrayRef<fir::ExtendedValue>);
-  mlir::Value genClock64(mlir::Type, llvm::ArrayRef<mlir::Value>);
   template <mlir::arith::CmpIPredicate pred>
   fir::ExtendedValue genCPtrCompare(mlir::Type,
                                     llvm::ArrayRef<fir::ExtendedValue>);
diff --git a/flang/lib/Optimizer/Builder/IntrinsicCall.cpp b/flang/lib/Optimizer/Builder/IntrinsicCall.cpp
index bfbc26e5e6c19..7aa5602d2bc84 100644
--- a/flang/lib/Optimizer/Builder/IntrinsicCall.cpp
+++ b/flang/lib/Optimizer/Builder/IntrinsicCall.cpp
@@ -386,7 +386,10 @@ static constexpr IntrinsicHandler handlers[]{
      {{{"name", asAddr}, {"status", asAddr, handleDynamicOptional}}},
      /*isElemental=*/false},
     {"clock", &I::genNVVMTime<mlir::NVVM::ClockOp>, {}, /*isElemental=*/false},
-    {"clock64", &I::genClock64, {}, /*isElemental=*/false},
+    {"clock64",
+     &I::genNVVMTime<mlir::NVVM::Clock64Op>,
+     {},
+     /*isElemental=*/false},
     {"cmplx",
      &I::genCmplx,
      {{{"x", asValue}, {"y", asValue, handleDynamicOptional}}}},
@@ -3565,16 +3568,6 @@ IntrinsicLibrary::genChdir(std::optional<mlir::Type> resultType,
   return {};
 }
 
-// CLOCK64
-mlir::Value IntrinsicLibrary::genClock64(mlir::Type resultType,
-                                         llvm::ArrayRef<mlir::Value> args) {
-  constexpr llvm::StringLiteral funcName = "llvm.nvvm.read.ptx.sreg.clock64";
-  mlir::MLIRContext *context = builder.getContext();
-  mlir::FunctionType ftype = mlir::FunctionType::get(context, {}, {resultType});
-  auto funcOp = builder.createFunction(loc, funcName, ftype);
-  return builder.create<fir::CallOp>(loc, funcOp, args).getResult(0);
-}
-
 // CMPLX
 mlir::Value IntrinsicLibrary::genCmplx(mlir::Type resultType,
                                        llvm::ArrayRef<mlir::Value> args) {
@@ -7204,7 +7197,7 @@ IntrinsicLibrary::genNull(mlir::Type, llvm::ArrayRef<fir::ExtendedValue> args) {
   return fir::MutableBoxValue(boxStorage, mold->nonDeferredLenParams(), {});
 }
 
-// CLOCK, GLOBALTIMER
+// CLOCK, CLOCK64, GLOBALTIMER
 template <typename OpTy>
 mlir::Value IntrinsicLibrary::genNVVMTime(mlir::Type resultType,
                                           llvm::ArrayRef<mlir::Value> args) {
diff --git a/flang/test/Lower/CUDA/cuda-device-proc.cuf b/flang/test/Lower/CUDA/cuda-device-proc.cuf
index 2d6f734670740..d5e614a83b354 100644
--- a/flang/test/Lower/CUDA/cuda-device-proc.cuf
+++ b/flang/test/Lower/CUDA/cuda-device-proc.cuf
@@ -48,7 +48,6 @@ attributes(global) subroutine devsub()
 
   smalltime = clock()
   time = clock64()
-
   time = globalTimer()
 end
 
@@ -87,7 +86,7 @@ end
 ! CHECK: %{{.*}} = llvm.atomicrmw udec_wrap  %{{.*}}, %{{.*}} seq_cst : !llvm.ptr, i32
 
 ! CHECK: %{{.*}} = nvvm.read.ptx.sreg.clock : i32
-! CHECK: fir.call @llvm.nvvm.read.ptx.sreg.clock64()
+! CHECK: %{{.*}} = nvvm.read.ptx.sreg.clock64 : i64
 ! CHECK: %{{.*}} = nvvm.read.ptx.sreg.globaltimer : i64
 
 subroutine host1()