diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index 1124154..231a20c 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -7912,8 +7912,11 @@
   const auto *ReqdWGS = M.getLangOpts().OpenCL ?
     FD->getAttr<ReqdWorkGroupSizeAttr>() : nullptr;
 
-  if (((M.getLangOpts().OpenCL && FD->hasAttr<OpenCLKernelAttr>()) ||
-      (M.getLangOpts().HIP && FD->hasAttr<CUDAGlobalAttr>())) &&
+
+  const bool IsOpenCLKernel = M.getLangOpts().OpenCL &&
+                              FD->hasAttr<OpenCLKernelAttr>();
+  if ((IsOpenCLKernel ||
+       (M.getLangOpts().HIP && FD->hasAttr<CUDAGlobalAttr>())) &&
       (M.getTriple().getOS() == llvm::Triple::AMDHSA))
     F->addFnAttr("amdgpu-implicitarg-num-bytes", "56");
 
@@ -7939,6 +7942,9 @@
       F->addFnAttr("amdgpu-flat-work-group-size", AttrVal);
     } else
       assert(Max == 0 && "Max must be zero");
+  } else if (IsOpenCLKernel) {
+    // By default, restrict the maximum size to 256.
+    F->addFnAttr("amdgpu-flat-work-group-size", "1,256");
   }
 
   if (const auto *Attr = FD->getAttr<AMDGPUWavesPerEUAttr>()) {