Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -3995,8 +3995,13 @@
       Args.hasArg(options::OPT_dA))
     CmdArgs.push_back("-masm-verbose");
 
-  if (!TC.useIntegratedAs())
+  if (!TC.useIntegratedAs()) {
     CmdArgs.push_back("-no-integrated-as");
+    // .cgprofile can only be parsed by llvm MC assembler, do not run
+    // CGProfilePass if integrated-as is not used.
+    CmdArgs.push_back("-mllvm");
+    CmdArgs.push_back("-enable-npm-call-graph-profile=false");
+  }
 
   if (Args.hasArg(options::OPT_fdebug_pass_structure)) {
     CmdArgs.push_back("-mdebug-pass");
Index: llvm/lib/Passes/PassBuilder.cpp
===================================================================
--- llvm/lib/Passes/PassBuilder.cpp
+++ llvm/lib/Passes/PassBuilder.cpp
@@ -212,6 +212,10 @@
     EnableCHR("enable-chr-npm", cl::init(true), cl::Hidden,
               cl::desc("Enable control height reduction optimization (CHR)"));
 
+static cl::opt<bool> EnableCallGraphProfile(
+    "enable-npm-call-graph-profile", cl::init(true), cl::Hidden,
+    cl::desc("Enable call graph profile pass for the new PM (default = on)"));
+
 extern cl::opt<bool> EnableHotColdSplit;
 extern cl::opt<bool> EnableOrderFileInstrumentation;
 
@@ -939,7 +943,8 @@
   // Add the core optimizing pipeline.
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(OptimizePM)));
 
-  MPM.addPass(CGProfilePass());
+  if (EnableCallGraphProfile)
+    MPM.addPass(CGProfilePass());
 
   // Now we need to do some global optimization transforms.
   // FIXME: It would seem like these should come first in the optimization