diff --git a/mlir/lib/Support/ToolUtilities.cpp b/mlir/lib/Support/ToolUtilities.cpp
--- a/mlir/lib/Support/ToolUtilities.cpp
+++ b/mlir/lib/Support/ToolUtilities.cpp
@@ -14,6 +14,7 @@
 #include "mlir/Support/LLVM.h"
 #include "mlir/Support/LogicalResult.h"
 #include "llvm/Support/SourceMgr.h"
+#include "llvm/Support/raw_ostream.h"
 
 using namespace mlir;
 
@@ -21,16 +22,55 @@
 mlir::splitAndProcessBuffer(std::unique_ptr<llvm::MemoryBuffer> originalBuffer,
                             ChunkBufferHandler processChunkBuffer,
                             raw_ostream &os) {
-  const char splitMarker[] = "// -----";
+  const char splitMarkerConst[] = "// -----";
+  StringRef splitMarker(splitMarkerConst);
+  const int splitMarkerLen = splitMarker.size();
 
   auto *origMemBuffer = originalBuffer.get();
-  SmallVector<StringRef, 8> sourceBuffers;
-  origMemBuffer->getBuffer().split(sourceBuffers, splitMarker);
+  SmallVector<StringRef, 8> rawSourceBuffers;
+  const int checkLen = 2;
+  // Split dropping the last checkLen chars to enable flagging near misses.
+  origMemBuffer->getBuffer().split(rawSourceBuffers,
+                                   splitMarker.drop_back(checkLen));
+  if (rawSourceBuffers.empty())
+    return success();
 
   // Add the original buffer to the source manager.
   llvm::SourceMgr fileSourceMgr;
   fileSourceMgr.AddNewSourceBuffer(std::move(originalBuffer), llvm::SMLoc());
 
+  // Flag near misses by iterating over all the sub-buffers found when splitting
+  // with the prefix of the splitMarker. Use a sliding window where we only
+  // add a buffer as a sourceBuffer if terminated by a full match of the
+  // splitMarker (followed by newline), else flag a warning and extend the
+  // size of the buffer under consideration assuming there is no near miss.
+  SmallVector<StringRef, 8> sourceBuffers;
+  StringRef prev;
+  for (auto buffer : rawSourceBuffers) {
+    if (prev.empty()) {
+      prev = buffer;
+      continue;
+    }
+
+    // Check that suffix is as expected and doesn't have any dash post.
+    bool expectedSuffix = buffer.startswith(splitMarker.take_back(checkLen)) &&
+                          buffer.size() > checkLen && buffer[checkLen] != '0';
+    if (expectedSuffix) {
+      sourceBuffers.push_back(prev);
+      prev = buffer.drop_front(checkLen);
+    } else {
+      // TODO: Consider making this a failure.
+      auto splitLoc = llvm::SMLoc::getFromPointer(buffer.data());
+      fileSourceMgr.PrintMessage(llvm::errs(), splitLoc,
+                                 llvm::SourceMgr::DK_Warning,
+                                 "near miss with file split marker");
+      prev = StringRef(prev.data(),
+                       prev.size() + splitMarkerLen - checkLen + buffer.size());
+    }
+  }
+  if (!prev.empty())
+    sourceBuffers.push_back(prev);
+
   // Process each chunk in turn.
   bool hadFailure = false;
   for (auto &subBuffer : sourceBuffers) {
diff --git a/mlir/test/Conversion/ShapeToStandard/shape-to-standard.mlir b/mlir/test/Conversion/ShapeToStandard/shape-to-standard.mlir
--- a/mlir/test/Conversion/ShapeToStandard/shape-to-standard.mlir
+++ b/mlir/test/Conversion/ShapeToStandard/shape-to-standard.mlir
@@ -593,7 +593,7 @@
   return
 }
 
-// ----
+// -----
 
 // CHECK-LABEL: @broadcast_to_known_rank
 func @broadcast_to_known_rank(%a : tensor<1xindex>, %b : tensor<3xindex>)
diff --git a/mlir/test/Conversion/TosaToSCF/tosa-to-scf.mlir b/mlir/test/Conversion/TosaToSCF/tosa-to-scf.mlir
--- a/mlir/test/Conversion/TosaToSCF/tosa-to-scf.mlir
+++ b/mlir/test/Conversion/TosaToSCF/tosa-to-scf.mlir
@@ -30,7 +30,7 @@
   return %1 : tensor<i32>
 }
 
-// ----
+// -----
 
 // CHECK-LABEL: func @if_test
 // CHECK-SAME: ([[ARG0:%.+]]: tensor<f32>, [[ARG1:%.+]]: tensor<f32>, [[ARG2:%.+]]: tensor<i1>)
diff --git a/mlir/test/Dialect/OpenACC/canonicalize.mlir b/mlir/test/Dialect/OpenACC/canonicalize.mlir
--- a/mlir/test/Dialect/OpenACC/canonicalize.mlir
+++ b/mlir/test/Dialect/OpenACC/canonicalize.mlir
@@ -61,7 +61,7 @@
 // CHECK: func @testupdateop
 // CHECK-NOT: acc.update
 
-// ----
+// -----
 
 func @testenterdataop(%a: memref<10xf32>, %ifCond: i1) -> () {
   acc.enter_data if(%ifCond) create(%a: memref<10xf32>)
diff --git a/mlir/test/Dialect/SCF/canonicalize.mlir b/mlir/test/Dialect/SCF/canonicalize.mlir
--- a/mlir/test/Dialect/SCF/canonicalize.mlir
+++ b/mlir/test/Dialect/SCF/canonicalize.mlir
@@ -250,7 +250,7 @@
 // CHECK-NOT:       scf.if
 // CHECK:           return
 
-// ----
+// -----
 
 func @empty_else(%cond: i1, %v : memref<i1>) {
   scf.if %cond {
diff --git a/mlir/test/Dialect/Shape/canonicalize.mlir b/mlir/test/Dialect/Shape/canonicalize.mlir
--- a/mlir/test/Dialect/Shape/canonicalize.mlir
+++ b/mlir/test/Dialect/Shape/canonicalize.mlir
@@ -1319,7 +1319,7 @@
   return %1 : tensor<3xindex>
 }
 
-// ----
+// -----
 
 // CHECK-LABEL: max_same_arg
 // CHECK-SAME: (%[[SHAPE:.*]]: !shape.shape)
@@ -1329,7 +1329,7 @@
   return %1 : !shape.shape
 }
 
-// ----
+// -----
 
 // CHECK-LABEL: min_same_arg
 // CHECK-SAME: (%[[SHAPE:.*]]: !shape.shape)
@@ -1338,7 +1338,7 @@
   // CHECK: return %[[SHAPE]]
   return %1 : !shape.shape
 }
-// ----
+// -----
 
 // CHECK-LABEL: @cstr_broadcastable_folding
 func @cstr_broadcastable_folding(%arg : tensor<?x4xf32>) {
diff --git a/mlir/test/mlir-opt/nearmiss.mlir b/mlir/test/mlir-opt/nearmiss.mlir
new file mode 100644
--- /dev/null
+++ b/mlir/test/mlir-opt/nearmiss.mlir
@@ -0,0 +1,21 @@
+// RUN: mlir-opt --split-input-file --verify-diagnostics %s 2> %t &&  FileCheck --input-file %t %s
+// RUN: cat %t
+
+func @main() {return}
+
+// -----
+
+// expected-note @+1 {{see existing symbol definition here}}
+func @foo() { return }
+// CHECK: warning: near miss with file split marker
+// CHECK: ----
+// ----
+
+// expected-error @+1 {{redefinition of symbol named 'foo'}}
+func @foo() { return }
+// CHECK: warning: near miss with file split marker
+// CHECK: ----
+// ----
+func @bar2() {return }
+
+// ----