CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
60 lines
2.9 KiB
C
60 lines
2.9 KiB
C
/*
|
|
* Copyright (c) 2017-2026, NVIDIA CORPORATION. All rights reserved.
|
|
*/
|
|
|
|
#ifndef GIN_V11_H_
|
|
#define GIN_V11_H_
|
|
|
|
#include <stdbool.h>
|
|
|
|
typedef struct {
|
|
// Name of the GIN support (mainly for logs)
|
|
const char* name;
|
|
// Initialize the GIN support.
|
|
ncclResult_t (*init)(void** ctx, uint64_t commId, ncclDebugLogger_t logFunction);
|
|
// Return the number of adapters capable of doing GIN operations.
|
|
// If ndev returns 0, all other functions might be set to NULL.
|
|
ncclResult_t (*devices)(int* ndev);
|
|
// Get various device properties.
|
|
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v11_t* props);
|
|
// Create a receiving object and provide a handle to connect to it. The
|
|
// handle can be up to NCCL_NET_HANDLE_MAXSIZE bytes and will be exchanged
|
|
// between ranks to create connections.
|
|
ncclResult_t (*listen)(void* ctx, int dev, void* handle, void** listenComm);
|
|
// Create a group for GIN operations. handles have been created
|
|
// using listen() above. rank indicates caller's rank in the collective network.
|
|
ncclResult_t (*connect)(void* ctx, void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
|
// Create device-side GIN context. devHandle will be passed to device code.
|
|
// This function is not used in GIN_PROXY mode.
|
|
ncclResult_t (*createContext)(void* collComm, int nSignals, int nCounters, void** ginCtx, ncclNetDeviceHandle_v11_t** devHandle);
|
|
// Collective memory registration
|
|
ncclResult_t (*regMrSym)(void* collComm, void* data, size_t size, int type, uint64_t mrFlags, void** mhandle, void **ginHandle);
|
|
ncclResult_t (*regMrSymDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, uint64_t mrFlags, void** mhandle, void **ginHandle);
|
|
ncclResult_t (*deregMrSym)(void* collComm, void* mhandle);
|
|
// Close and free collective comm objects
|
|
ncclResult_t (*destroyContext)(void* ginCtx);
|
|
ncclResult_t (*closeColl)(void* collComm);
|
|
ncclResult_t (*closeListen)(void* listenComm);
|
|
|
|
// Put operations
|
|
ncclResult_t (*iput)(void* collComm, uint64_t srcOff, void* srcMhandle, size_t size,
|
|
uint64_t dstOff, void* dstMhandle, uint32_t rank, void** request);
|
|
ncclResult_t (*iputSignal)(void* collComm, uint64_t srcOff, void* srcMhandle,
|
|
size_t size, uint64_t dstOff, void* dstMhandle,
|
|
uint32_t rank, uint64_t signalOff, void *signalMhandle,
|
|
uint64_t signalValue, uint32_t signalOp, void** request);
|
|
|
|
// Test whether a request is complete.
|
|
ncclResult_t (*test)(void* collComm, void* request, int* done);
|
|
|
|
// Progress function. Will be called if non-NULL in GIN_PROXY mode, or if devHandle.needsProxyProgress=1.
|
|
ncclResult_t (*ginProgress)(void* collComm);
|
|
|
|
// Query the last error for the GIN support. Particularly important when ginProgress is not used, to report errors.
|
|
ncclResult_t (*queryLastError)(void* ginCtx, bool *hasError);
|
|
|
|
// Finalize the GIN support
|
|
ncclResult_t (*finalize)(void* ctx);
|
|
} ncclGin_v11_t;
|
|
#endif // end include guard
|