2.5.6-1 (#255)

Add LL128 Protocol.

Rewrite the topology detection and tree/ring creation (#179). Improve
tree performance by sending/receiving from different GPUs. Add
model-based tuning to switch between the different algorithms and
protocols.

Rework P2P/SHM detection in containers (#155, #248).

Detect duplicated devices and return an error (#231).

Add tuning for GCP

[ROCm/rccl commit: 299c554dcc]

projects/rccl/src/include/utils.h

@@ -10,6 +10,14 @@
 #include "nccl.h"
 #include <stdint.h>
 
+int ncclCudaCompCap();
+
+// PCI Bus ID <-> int64 conversion functions
+ncclResult_t int64ToBusId(int64_t id, char* busId);
+ncclResult_t busIdToInt64(char* busId, int64_t* id);
+
+ncclResult_t getBusId(int cudaDev, int64_t *busId);
+
 ncclResult_t getHostName(char* hostname, int maxlen, const char delim);
 uint64_t getHash(const char* string, int n);
 uint64_t getHostHash();
@@ -23,4 +31,10 @@ struct netIf {
 int parseStringList(const char* string, struct netIf* ifList, int maxList);
 bool matchIfList(const char* string, int port, struct netIf* ifList, int listSize, bool matchExact);
 
+static long log2i(long n) {
+ long l = 0;
+ while (n>>=1) l++;
+ return l;
+}
+
 #endif