update with comment

Author: jhuber6

offload/DeviceRTL/CMakeLists.txt

@@ -119,6 +119,7 @@ function(compileDeviceRTLLibrary target_name target_triple)
     set(outfile "${outfile}-${target_name}.bc")
     set(depfile "${outfile}.d")
 
+    # Passing an empty CPU to -march= suppressed target specific metadata.
     add_custom_command(OUTPUT ${outfile}
       COMMAND ${CLANG_TOOL}
       ${bc_flags}

offload/DeviceRTL/src/Reduction.cpp

@@ -73,16 +73,16 @@ static int32_t nvptx_parallel_reduce_nowait(void *reduce_data,
   if (NumThreads == 1)
     return 1;
 
-  //
-  // This reduce function handles reduction within a team. It handles
-  // parallel regions in both L1 and L2 parallelism levels. It also
-  // supports Generic, SPMD, and NoOMP modes.
-  //
-  // 1. Reduce within a warp.
-  // 2. Warp master copies value to warp 0 via shared memory.
-  // 3. Warp 0 reduces to a single value.
-  // 4. The reduced value is available in the thread that returns 1.
-  //
+    //
+    // This reduce function handles reduction within a team. It handles
+    // parallel regions in both L1 and L2 parallelism levels. It also
+    // supports Generic, SPMD, and NoOMP modes.
+    //
+    // 1. Reduce within a warp.
+    // 2. Warp master copies value to warp 0 via shared memory.
+    // 3. Warp 0 reduces to a single value.
+    // 4. The reduced value is available in the thread that returns 1.
+    //
 
 #if __has_builtin(__nvvm_reflect)
   if (__nvvm_reflect("__CUDA_ARCH") >= 700) {