Add support for CUDA 12.0, drop Kepler (sm_35).
Support for H100 features.
Make socket code more robust and protected. Solves #555.
Improve performance on large CUDA graphs, reducing dependencies.
Reduce inter-socket bandwidth on AMD CPUs to favor better paths.
Various fixes to ncclCommAbort.
Make service thread polling resistant to EINTR.
Compile with profiling API by default.
Extend NVTX instrumentation with call arguments.
Этот коммит содержится в:
Sylvain Jeaugey
2022-11-29 04:27:46 -08:00
родитель 614b49f0de
Коммит 28189e2df8
46 изменённых файлов: 3325 добавлений и 1037 удалений
+9 -3
Просмотреть файл
@@ -10,10 +10,16 @@
#include "nccl.h"
#include "comm.h"
struct ncclBootstrapHandle {
uint64_t magic;
union ncclSocketAddress addr;
};
static_assert(sizeof(struct ncclBootstrapHandle) <= sizeof(ncclUniqueId), "Bootstrap handle is too large to fit inside NCCL unique ID");
ncclResult_t bootstrapNetInit();
ncclResult_t bootstrapCreateRoot(ncclUniqueId* commId, bool idFromEnv);
ncclResult_t bootstrapGetUniqueId(ncclUniqueId* out);
ncclResult_t bootstrapInit(ncclUniqueId* id, struct ncclComm* comm);
ncclResult_t bootstrapCreateRoot(struct ncclBootstrapHandle* handle, bool idFromEnv);
ncclResult_t bootstrapGetUniqueId(struct ncclBootstrapHandle* handle);
ncclResult_t bootstrapInit(struct ncclBootstrapHandle* handle, struct ncclComm* comm);
ncclResult_t bootstrapAllGather(void* commState, void* allData, int size);
ncclResult_t bootstrapSend(void* commState, int peer, int tag, void* data, int size);
ncclResult_t bootstrapRecv(void* commState, int peer, int tag, void* data, int size);