diff --git a/mlir/include/mlir/Dialect/GPU/TransformOps/GPUTransformOps.h b/mlir/include/mlir/Dialect/GPU/TransformOps/GPUTransformOps.h
--- a/mlir/include/mlir/Dialect/GPU/TransformOps/GPUTransformOps.h
+++ b/mlir/include/mlir/Dialect/GPU/TransformOps/GPUTransformOps.h
@@ -41,17 +41,17 @@
 /// predication. Dynamic, `scf.foreach_thread` trip counts are currently not
 /// supported. Dynamic block dim sizes are currently not supported.
 DiagnosedSilenceableFailure
-mapNestedForeachToThreadsImp(RewriterBase &rewriter, Operation *target,
-                             const SmallVectorImpl<int64_t> &blockDim,
-                             bool syncAfterDistribute,
-                             llvm::Optional<TransformOpInterface> transformOp);
+mapNestedForeachToThreadsImpl(RewriterBase &rewriter, Operation *target,
+                              const SmallVectorImpl<int64_t> &blockDim,
+                              bool syncAfterDistribute,
+                              llvm::Optional<TransformOpInterface> transformOp);
 
 /// Maps the top level `scf.foreach_thread` op to GPU Thread Blocks. Mapping is
 /// one-to-one and the induction variables of `scf.foreach_thread` are rewritten
 /// to gpu.block_id according to the thread_dim_apping attribute. Dynamic,
 /// `scf.foreach_thread` trip counts are currently not supported. Dynamic block
 /// dim sizes are currently not supported.
-DiagnosedSilenceableFailure mapForeachToBlocksImp(
+DiagnosedSilenceableFailure mapForeachToBlocksImpl(
     RewriterBase &rewriter, scf::ForeachThreadOp foreachThreadOp,
     function_ref<void(RewriterBase &, scf::ForeachThreadOp,
                       SmallVectorImpl<Value> &)>
diff --git a/mlir/lib/Dialect/GPU/TransformOps/GPUTransformOps.cpp b/mlir/lib/Dialect/GPU/TransformOps/GPUTransformOps.cpp
--- a/mlir/lib/Dialect/GPU/TransformOps/GPUTransformOps.cpp
+++ b/mlir/lib/Dialect/GPU/TransformOps/GPUTransformOps.cpp
@@ -151,7 +151,7 @@
 // MapForeachToBlocks
 //===----------------------------------------------------------------------===//
 
-DiagnosedSilenceableFailure mlir::transform::gpu::mapForeachToBlocksImp(
+DiagnosedSilenceableFailure mlir::transform::gpu::mapForeachToBlocksImpl(
     RewriterBase &rewriter, scf::ForeachThreadOp foreachThreadOp,
     function_ref<void(RewriterBase &, scf::ForeachThreadOp,
                       SmallVectorImpl<Value> &)>
@@ -291,7 +291,7 @@
   }
 
   SmallVector<int64_t> gridDim = extractFromI64ArrayAttr(getGridDim());
-  diag = mlir::transform::gpu::mapForeachToBlocksImp(
+  diag = mlir::transform::gpu::mapForeachToBlocksImpl(
       rewriter, topLevelForeachThreadOp, generateGpuBlockIds, gridDim,
       transformOp);
   if (diag.succeeded()) {
@@ -422,7 +422,7 @@
   return DiagnosedSilenceableFailure::success();
 }
 
-DiagnosedSilenceableFailure mlir::transform::gpu::mapNestedForeachToThreadsImp(
+DiagnosedSilenceableFailure mlir::transform::gpu::mapNestedForeachToThreadsImpl(
     RewriterBase &rewriter, Operation *target,
     const SmallVectorImpl<int64_t> &blockDim, bool syncAfterDistribute,
     llvm::Optional<TransformOpInterface> transformOp) {
@@ -463,7 +463,7 @@
   SimpleRewriter rewriter(getContext());
   rewriter.setInsertionPoint(target);
 
-  diag = mlir::transform::gpu::mapNestedForeachToThreadsImp(
+  diag = mlir::transform::gpu::mapNestedForeachToThreadsImpl(
       rewriter, target, blockDim, getSyncAfterDistribute(), llvm::None);
   if (diag.succeeded()) {
     diag =