Added ERROR message class to handle fatal error messages. (#2002)

* Added ERROR message class to handle fatal error messages.

New ERROR message class will print the message in all debug level,
including none.

Change some of the fatal error message to be in ERROR instead of WARN.

Added new error handler function to print out more meaningful error
message in the future.

* Added CHANGELOG entry.

* Update CHANGELOG.md

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

* Change to no longer reuse NONE as ERROR. ERROR is now a separated class.

* Update CHANGELOG.md

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

---------

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

src/include/debug.h

@@ -25,6 +25,7 @@ void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *file
 extern thread_local int ncclDebugNoWarn;
 extern char ncclLastError[];
 
+#define ERROR(...) ncclDebugLog(NCCL_LOG_ERROR, NCCL_ALL, __FILE__, __LINE__, __VA_ARGS__)
 #define VERSION(...) ncclDebugLog(NCCL_LOG_VERSION, NCCL_ALL, __FILE__, __LINE__, __VA_ARGS__)
 #define WARN(...) ncclDebugLog(NCCL_LOG_WARN, NCCL_ALL, __FILE__, __LINE__, __VA_ARGS__)
 #define INFO(FLAGS, ...) ncclDebugLog(NCCL_LOG_INFO, (FLAGS), __func__, __LINE__, __VA_ARGS__)
@@ -40,4 +41,22 @@ void ncclSetThreadName(pthread_t thread, const char *fmt, ...);
 
 void ncclResetDebugInit();
 
+// RCCL custom error message handling.
+static inline ncclResult_t rcclCudaErrorHandler(cudaError_t err) {
+
+    // Print the cuda error
+    ERROR("HIP failure: '%s'", cudaGetErrorString(err));
+
+    // Special error message here:
+    switch (err) {
+    case cudaErrorStreamCaptureInvalidated:
+	    ERROR("Application is trying to use an invalidated stream to launch RCCL kernel. "
+	          "This operation is invalid. RCCL is exiting.");
+	    break;
+    default:
+	    break;
+    }
+    return ncclUnhandledCudaError;
+}
+
 #endif