Just fixes comments (#1998)

* Just fixes comments

torch/csrc/jit/codegen/cuda/lower_alias_memory.cpp

@@ -24,15 +24,13 @@ IterDomain* exactConcreteId(IterDomain* id) {
       id, IdMappingMode::EXACT);
 }
 
-//! Checks that the current loop nest is not realizing a serial
-//!  broadcast so that each index of producer buffer will only
-//!  be visited once, which is the only case where aggressive
-//!  inner sharing is valid.
-//!
+//! Checks that the current loop nest is realizing a serial
+//!  broadcast so that each index of producer buffer can be visited
+//!  multiple times, in which case the aggressive is not valid.
 bool isSerialBroadcastResolution(TensorView* producer, TensorView* consumer) {
   //! Note: see issue #1785:
   //!  serial broadcast resolution doesn't only happen to
-  //! immediate producers of broadcast ops. We can also have
+  //! immediate outputs of broadcast ops. We can also have
   //! example:
   //!  T1[I,B] = broadcast(T0[I]])
   //!  T3[I,I] = T1[I,B] + T2[I,I]

torch/csrc/jit/codegen/cuda/scheduler/mma_utils.cpp

@@ -274,10 +274,10 @@ std::unordered_set<IterDomain*> getMmaDomainSet(
 //  optimizations.
 //
 // A concrete example:
-//  T0 [I0, I1, I2, I3, I4, I5] = mma(T1[I01, B11, B21, I31, I41, B51], T2[B02,
+//  T0 [I0, I1, I2, R3, I4, I5] = mma(T1[I01, B11, B21, I31, I41, B51], T2[B02,
 //  I12, B22, I32, I42, I52], {3};
 // In this case some example querries:
-//  K dimension of T0 = {I3}
+//  K dimension of T0 = {R3}
 //  M dimension of T1 = {I01}
 //  N dimension of T2 = {I52}
 //  etc.