AI/rocm-systems
2
0
Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Actions Packages Projekty Wydania Wiki Aktywność

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

Przeglądaj źródła
This commit is contained in:
BertanDogancay
2025-06-20 07:53:59 -05:00
rodzic 12315c259a 8171af656b
commit aaf023976a
136 zmienionych plików z 8510 dodań i 5421 usunięć
Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files
src/include/graph.h
+19 -10
Wyświetl plik
@@ -37,17 +37,24 @@ ncclResult_t ncclTopoComputeCommCPU(struct ncclComm* comm);
ncclResult_t ncclTopoGetNetDev(struct ncclComm* comm, int rank, struct ncclTopoGraph* graph, int channelId, int peerRank, int64_t* id, int* dev, int* proxyRank);
ncclResult_t ncclTopoCheckP2p(struct ncclComm* comm, struct ncclTopoSystem* system, int rank1, int rank2, int* p2p, int *read, int* intermediateRank);
ncclResult_t ncclTopoCheckMNNVL(struct ncclTopoSystem* system, struct ncclPeerInfo* info1, struct ncclPeerInfo* info2, int* ret);
ncclResult_t ncclTopoCheckGdr(struct ncclTopoSystem* topo, int rank, int64_t netId, int read, int* useGdr);
#define MAX_XGMI_INTER_GPUS 4
ncclResult_t ncclTopoGetIntraNetDev(struct ncclTopoSystem* system, int rank, struct ncclTopoGraph* graph, int channelId, int type, int64_t* id, int* dev);
ncclResult_t ncclTopoGetLinkType(struct ncclTopoSystem* system, int cudaDev1, int cudaDev2, bool* isXGMI, int maxInter=MAX_XGMI_INTER_GPUS, int nInter=0, int *inter=nullptr);
ncclResult_t ncclTopoNeedFlush(struct ncclComm* comm, int netDev, int rank, int* flush);
enum ncclTopoGdrMode {
ncclTopoGdrModeDisable = 0,
ncclTopoGdrModeDefault = 1,
ncclTopoGdrModePci = 2,
ncclTopoGdrModeNum = 3
};
ncclResult_t ncclTopoCheckGdr(struct ncclTopoSystem* topo, int rank, int64_t netId, int read, enum ncclTopoGdrMode* gdrMode);
ncclResult_t ncclTopoNeedFlush(struct ncclComm* comm, int64_t netId, int netDev, int rank, int* flush);
ncclResult_t ncclTopoIsGdrAvail(struct ncclTopoSystem* system, int rank, bool *avail);
ncclResult_t ncclTopoCheckNet(struct ncclTopoSystem* system, int rank1, int rank2, int* net);
int ncclPxnDisable(struct ncclComm* comm);
ncclResult_t ncclTopoGetPxnRanks(struct ncclComm* comm, int** intermediateRanks, int* nranks);
ncclResult_t ncclGetLocalCpu(struct ncclTopoSystem* system, int gpu, int* retCpu);
#define MAX_XGMI_INTER_GPUS 4
ncclResult_t ncclTopoGetIntraNetDev(struct ncclTopoSystem* system, int rank, struct ncclTopoGraph* graph, int channelId, int type, int64_t* id, int* dev);
ncclResult_t ncclTopoGetLinkType(struct ncclTopoSystem* system, int cudaDev1, int cudaDev2, bool* isXGMI, int maxInter=MAX_XGMI_INTER_GPUS, int nInter=0, int *inter=nullptr);
// Find CPU affinity
ncclResult_t ncclTopoGetCpuAffinity(struct ncclTopoSystem* system, int rank, cpu_set_t* affinity);
@@ -59,11 +66,13 @@ ncclResult_t ncclTopoGetCpuAffinity(struct ncclTopoSystem* system, int rank, cpu
#define NCCL_TOPO_CPU_VENDOR_AMD 2
#define NCCL_TOPO_CPU_VENDOR_ZHAOXIN 3
#define NCCL_TOPO_CPU_VENDOR_MIXED 4
#define NCCL_TOPO_CPU_TYPE_BDW 1
#define NCCL_TOPO_CPU_TYPE_SKL 2
#define NCCL_TOPO_CPU_TYPE_ZEN 3
#define NCCL_TOPO_CPU_TYPE_ROME 4
#define NCCL_TOPO_CPU_TYPE_YONGFENG 1
#define NCCL_TOPO_CPU_MODEL_INTEL_BDW 1
#define NCCL_TOPO_CPU_MODEL_INTEL_SKL 2
#define NCCL_TOPO_CPU_MODEL_INTEL_SRP 3
#define NCCL_TOPO_CPU_MODEL_INTEL_ERP 4
#define NCCL_TOPO_CPU_MODEL_AMD_ZEN 5
#define NCCL_TOPO_CPU_MODEL_AMD_ROME 6
#define NCCL_TOPO_CPU_MODEL_YONGFENG 1
ncclResult_t ncclTopoCpuType(struct ncclTopoSystem* system, int* arch, int* vendor, int* model);
ncclResult_t ncclTopoGetGpuCount(struct ncclTopoSystem* system, int* count);
ncclResult_t ncclTopoGetNetCount(struct ncclTopoSystem* system, int* count);