diff --git a/llvm/include/llvm/CodeGen/AsmPrinter.h b/llvm/include/llvm/CodeGen/AsmPrinter.h
--- a/llvm/include/llvm/CodeGen/AsmPrinter.h
+++ b/llvm/include/llvm/CodeGen/AsmPrinter.h
@@ -236,6 +236,10 @@
   /// split stack prologue.
   bool HasNoSplitStack = false;
 
+  /// Raw FDOstream for outputting machine basic block frequncies if the
+  /// --mbb-profile-dump flag is set for downstream cost modelling applications
+  std::unique_ptr<raw_fd_ostream> MBBProfileDumpFileOutput;
+
 protected:
   explicit AsmPrinter(TargetMachine &TM, std::unique_ptr<MCStreamer> Streamer);
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -39,6 +39,7 @@
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/CodeGen/GCMetadata.h"
 #include "llvm/CodeGen/GCMetadataPrinter.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineDominators.h"
@@ -128,6 +129,13 @@
 
 #define DEBUG_TYPE "asm-printer"
 
+static cl::opt<std::string> BasicBlockProfileDump(
+    "mbb-profile-dump", cl::Hidden,
+    cl::desc("Basic block profile dump for external cost modelling. If "
+             "matching up BBs with afterwards, the compilation must be "
+             "performed with -fbasic-block-sections=labels. Enabling this "
+             "flag during in-process ThinLTO is not supported."));
+
 const char DWARFGroupName[] = "dwarf";
 const char DWARFGroupDescription[] = "DWARF Emission";
 const char DbgTimerName[] = "emit";
@@ -352,11 +360,23 @@
   VerboseAsm = OutStreamer->isVerboseAsm();
   DwarfUsesRelocationsAcrossSections =
       MAI->doesDwarfUseRelocationsAcrossSections();
+  if (!BasicBlockProfileDump.empty()) {
+    std::error_code PossibleFileError;
+    MBBProfileDumpFileOutput = std::make_unique<raw_fd_ostream>(
+        BasicBlockProfileDump, PossibleFileError);
+    if (PossibleFileError) {
+      errs() << "Failed to open file for MBB Profile Dump:"
+             << PossibleFileError.message() << "\n";
+    }
+  }
 }
 
 AsmPrinter::~AsmPrinter() {
   assert(!DD && Handlers.size() == NumUserHandlers &&
          "Debug/EH info didn't get finalized");
+  if(MBBProfileDumpFileOutput) {
+    MBBProfileDumpFileOutput->close();
+  }
 }
 
 bool AsmPrinter::isPositionIndependent() const {
@@ -414,6 +434,7 @@
   MachineFunctionPass::getAnalysisUsage(AU);
   AU.addRequired<MachineOptimizationRemarkEmitterPass>();
   AU.addRequired<GCModuleInfo>();
+  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
 }
 
 bool AsmPrinter::doInitialization(Module &M) {
@@ -1862,6 +1883,18 @@
     OutStreamer->getCommentOS() << "-- End function\n";
 
   OutStreamer->addBlankLine();
+
+  // Output MBB numbers, function names, and frequencies if the flag to dump
+  // MBB profile information has been set
+  if (!BasicBlockProfileDump.empty()) {
+    MachineBlockFrequencyInfo &MBFI =
+        getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI();
+    for (const auto &MBB : *MF) {
+      *MBBProfileDumpFileOutput.get()
+          << MF->getName() << "," << MBB.getNumber() << ","
+          << MBFI.getBlockFreqRelativeToEntryBlock(&MBB) << "\n";
+    }
+  }
 }
 
 /// Compute the number of Global Variables that uses a Constant.
diff --git a/llvm/test/CodeGen/MLRegalloc/bb-profile-dump.ll b/llvm/test/CodeGen/MLRegalloc/bb-profile-dump.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/MLRegalloc/bb-profile-dump.ll
@@ -0,0 +1,21 @@
+; REQUIRES: have_tflite
+; REQUIRES: default_triple
+;
+; Check that the basic block profile dump outputs data and in the correct
+; format.
+;
+; RUN: llc -o /dev/null -mbb-profile-dump=%t %s
+; RUN: FileCheck --input-file %t %s
+
+define i64 @f2(i64 %a, i64 %b) {
+    %sum = add i64 %a, %b
+    ret i64 %sum
+}
+
+define i64 @f1() {
+    %sum = call i64 @f2(i64 2, i64 2)
+    ret i64 %sum
+}
+
+; CHECK: f2,0,1.000000e+00
+; CHECK-NEXT: f1,0,1.000000e+00