Merge remote-tracking branch 'nccl/master' into develop

src/include/enqueue.h

@@ -17,7 +17,7 @@
 #define NCCL_SIMPLE_ALIGNMENT (WARP_SIZE * 8LL * 16LL)
 #define NCCL_BYTES_ALIGNMENT 16
 
-ncclResult_t ncclInitKernelsForDevice(int cudaArch, size_t* maxStackSize);
+ncclResult_t ncclInitKernelsForDevice(int cudaArch, int maxSharedMem, size_t* maxStackSize);
 ncclResult_t ncclEnqueueCheck(struct ncclInfo* info);
 ncclResult_t ncclLaunchPrepare(struct ncclComm* comm);
 ncclResult_t ncclLaunchKernelBefore_NoUncapturedCuda(struct ncclComm* comm, struct ncclKernelPlan* plan);