Modify All-To-All doc (#896)

* Modify All-To-All doc

* Update nccl.h.in

* update unit-tests

---------

Co-authored-by: gilbertlee-amd <44450918+gilbertlee-amd@users.noreply.github.com>

[ROCm/rccl commit: c1f57a7041]

projects/rccl/src/nccl.h.in

@@ -639,7 +639,8 @@ ncclResult_t pncclScatter(const void* sendbuff, void* recvbuff,
     @details    Device (i) send (j)th block of data to device (j) and be placed as (i)th
                 block. Each block for sending/receiving has *count* elements, which means
                 that *recvbuff* and *sendbuff* should have a size of nranks*count elements.
-                In-place operation will happen if sendbuff == recvbuff.
+                In-place operation is NOT supported. It is the user's responsibility
+                to ensure that sendbuff and recvbuff are distinct.
     @return     Result code. See @ref rccl_result_code for more details.
 
     @param[in]  sendbuff      Data array to send (contains blocks for each other rank)

projects/rccl/test/AllToAllTests.cpp

@@ -3,6 +3,9 @@
  *
  * See LICENSE.txt for license information
  ************************************************************************/
+
+ // Note: InPlace is not supported for All-To-All
+
 #include "TestBed.hpp"
 
 namespace RcclUnitTesting

projects/rccl/test/AllToAllVTests.cpp

@@ -3,6 +3,9 @@
  *
  * See LICENSE.txt for license information
  ************************************************************************/
+
+ // Note: InPlace is not supported for All-To-Allv
+ 
 #include "TestBed.hpp"
 
 namespace RcclUnitTesting