Documentation updates for NCCL 2.7.0 (#219)

* Making hip-clang the default compiler; documentation update

* Adding back --hip-clang to install.sh as a silent option for CI

* Documentation updates for NCCL 2.7

* Restoring deleted line in install script

src/nccl.h.in

@@ -238,11 +238,9 @@ ncclResult_t  ncclAllGather(const void* sendbuff, void* recvbuff, size_t sendcou
 ncclResult_t pncclAllGather(const void* sendbuff, void* recvbuff, size_t sendcount,
     ncclDataType_t datatype, ncclComm_t comm, hipStream_t stream);
 
-/*
- * Send
- *
- * Send data from sendbuff to rank peer.
+/*! @brief Send
  *
+ * @details Send data from sendbuff to rank peer.
  * Rank peer needs to call ncclRecv with the same datatype and the same count from this
  * rank.
  *
@@ -255,11 +253,9 @@ ncclResult_t  ncclSend(const void* sendbuff, size_t count, ncclDataType_t dataty
 ncclResult_t pncclSend(const void* sendbuff, size_t count, ncclDataType_t datatype, int peer,
     ncclComm_t comm, hipStream_t stream);
 
-/*
- * Receive
- *
- * Receive data from rank peer into recvbuff.
+/*! @brief Receive
  *
+ * @details Receive data from rank peer into recvbuff.
  * Rank peer needs to call ncclSend with the same datatype and the same count to this
  * rank.
  *
@@ -272,11 +268,11 @@ ncclResult_t pncclRecv(void* recvbuff, size_t count, ncclDataType_t datatype, in
 ncclResult_t  ncclRecv(void* recvbuff, size_t count, ncclDataType_t datatype, int peer,
     ncclComm_t comm, hipStream_t stream);
 
-/*
- * Gather
+/*! @brief Gather
  *
- * Root device gathers sendcount values from other GPUs into recvbuff,
+ * @details Root device gathers sendcount values from other GPUs into recvbuff,
  * receiving data from rank i at offset i*sendcount.
+ *
  * Assumes recvcount is equal to nranks*sendcount, which means that recvbuff
  * should have a size of at least nranks*sendcount elements.
  *
@@ -287,11 +283,11 @@ ncclResult_t  ncclGather(const void* sendbuff, void* recvbuff, size_t sendcount,
 ncclResult_t pncclGather(const void* sendbuff, void* recvbuff, size_t sendcount,
     ncclDataType_t datatype, int root, ncclComm_t comm, hipStream_t stream);
 
-/*
- * Scatter
+/*! @brief Scatter
  *
- * Scattered over the devices so that recvbuff on rank i will contain the i-th
+ * @details Scattered over the devices so that recvbuff on rank i will contain the i-th
  * block of the data on root.
+ *
  * Assumes sendcount is equal to nranks*recvcount, which means that sendbuff
  * should have a size of at least nranks*recvcount elements.
  *
@@ -304,10 +300,9 @@ ncclResult_t pncclScatter(const void* sendbuff, void* recvbuff,
     size_t recvcount, ncclDataType_t datatype, int root, ncclComm_t comm,
     hipStream_t stream);
 
-/*
- * All-To-All
+/*! @brief All-To-All
  *
- * Device (i) send (j)th block of data to device (j) and be placed as (i)th
+ * @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.
  *