2.17.1-1

Add new NVLS algorithm for allreduce using NVLink SHARP (intra-node only).
Add new config options: cgaClusterSize, minCTAs, maxCTAs, netName.
Enable LL128 when we use PXN to close rings.
NVTX3 includes update.
Fix crash when one CollNet (SHARP) rail fails to initialize.

src/Makefile

@@ -12,7 +12,8 @@ INCEXPORTS  := nccl.h nccl_net.h
 LIBSRCFILES := init.cc init_nvtx.cc channel.cc bootstrap.cc transport.cc enqueue.cc group.cc debug.cc proxy.cc net.cc \
 		misc/cudawrap.cc misc/nvmlwrap.cc misc/ibvwrap.cc misc/gdrwrap.cc \
 		misc/utils.cc misc/argcheck.cc misc/socket.cc misc/shmutils.cc misc/profiler.cc misc/param.cc misc/strongstream.cc \
-		transport/p2p.cc transport/shm.cc transport/net.cc transport/net_socket.cc transport/net_ib.cc transport/coll_net.cc \
+		misc/ipcsocket.cc \
+		transport/p2p.cc transport/shm.cc transport/net.cc transport/net_socket.cc transport/net_ib.cc transport/coll_net.cc transport/nvls.cc \
                 collectives/sendrecv.cc collectives/all_reduce.cc collectives/all_gather.cc collectives/broadcast.cc collectives/reduce.cc collectives/reduce_scatter.cc \
                 graph/topo.cc graph/paths.cc graph/search.cc graph/connect.cc graph/rings.cc graph/trees.cc graph/tuning.cc graph/xml.cc
 
@@ -62,7 +63,7 @@ ALWAYS_REBUILD:
 -include $(DEPFILES)
 $(LIBDIR)/$(LIBTARGET) $(LIBDIR)/$(STATICLIBTARGET) : $(LIBOBJ)
 
-$(INCDIR)/nccl.h : nccl.h.in
+$(INCDIR)/nccl.h : nccl.h.in ../makefiles/version.mk
 # NCCL_VERSION(X,Y,Z) ((X) * 10000 + (Y) * 100 + (Z))
 	@$(eval NCCL_VERSION := $(shell printf "%d%02d%02d" $(NCCL_MAJOR) $(NCCL_MINOR) $(NCCL_PATCH)))
 	mkdir -p $(INCDIR)