6aae379278
Network user buffer support for collectives * Leverage user buffer registration to achieve zero-copy inter-node communications for Ring, NVLS and Collnet Add RAS subsystem * Create a RAS thread keeping track of all NCCL communicators. * Add a ncclras tool contacting the RAS thread and getting a report. Add fp8 support * Add support for e5m2 and e4m3 8-bit floating point operations. * Use Tree/PAT algorithms when possible for better numerical stability. Add NIC fusion * Add a NET API to ask the network plugin to fuse a set of interfaces together. * Fuse multiple NICs under the same PCI switch as a single, larger NIC. Socket connection failure retry * Retry in case of socket connection failure (unreachable host) * Avoid "Software caused connection abort" errors on retries QP connection failure retry * Retry in case of IB QP connection failure during ibv_modify_qp. NET API improvements * Allow plugins to force a flush in case data and completion ordering is not guaranteed. * Indicate when completion is not needed (e.g. for the LL128 protocol), allowing plugins to skip generating a completion. * Allow for full offload of allgather operations when using one GPU per node. NCCL_ALGO/NCCL_PROTO strict enforcement * Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify ALGO/PROTO filters for each collective operation. * Strictly enforce the ALGO/PROTO filters, no longer fall back on the ring algorithm when the filtering leaves no option and error out instead. Enable CUMEM host allocations * Use cumem functions for host memory allocation by default. Improved profiler plugin API * Avoid dependencies with NCCL includes. * Add information on whether the buffer is registered or not Adjust PAT tuning * Improve transition between PAT and ring at scale. Fix hangs when running with different CPU architectures * Detect when we use a mix of GPU architectures * Ensure Algo/Proto decisions are made based on that unified state. Fix FD leak in UDS * Fix a leak when mapping buffers intra-node with cumem IPCs. Fix crash when mixing buffer registration and graph buffer registration. * Separate local and graph registration to avoid crashes when we free buffers. Fix user buffer registration with dmabuf * Make ncclSend/ncclRecv communication with buffer registration functional on network plugins relying on dmabuf for buffer registration. Fix crash in IB code caused by uninitialized fields. Fix non-blocking ncclSend/ncclRecv * Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking mode even though the operation was not enqueued onto the stream. * Issue #1495 Various compiler tweaks and fixes * PR #758 Fix typo in ncclTopoPrintGraph * Issue #1468
102 خطوط
3.3 KiB
C
102 خطوط
3.3 KiB
C
/*************************************************************************
|
|
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef NCCL_PROFILER_V1_H_
|
|
#define NCCL_PROFILER_V1_H_
|
|
|
|
#include <stdint.h>
|
|
|
|
typedef struct {
|
|
uint8_t type; // event type descriptor: ncclProfileColl, ...
|
|
void* parentObj; // pointer to the profiler parent object (for coll is the group)
|
|
int rank; // originating rank
|
|
union {
|
|
struct {
|
|
const char* name;
|
|
uint64_t commHash;
|
|
uint64_t seqNumber;
|
|
uint8_t func;
|
|
void const* sendBuff;
|
|
void* recvBuff;
|
|
size_t count;
|
|
int root;
|
|
uint8_t datatype;
|
|
uint32_t op;
|
|
size_t trafficBytes;
|
|
uint8_t nMaxChannels;
|
|
uint8_t nWarps;
|
|
uint8_t algo;
|
|
uint8_t proto;
|
|
int isCollnet;
|
|
int isNvls;
|
|
} coll;
|
|
|
|
struct {
|
|
const char* name;
|
|
uint64_t commHash;
|
|
uint8_t func;
|
|
void* buff;
|
|
uint8_t datatype;
|
|
size_t count;
|
|
int peer;
|
|
} p2p;
|
|
|
|
struct {
|
|
pid_t pid; // pid of the originating process
|
|
uint8_t channelId; // channel id for this proxy operation
|
|
int peer; // remote rank for send/recv
|
|
int nSteps; // number of steps for this proxy operation
|
|
int chunkSize; // amount of data transferred by this proxy operation
|
|
int isSend;
|
|
} proxyOp;
|
|
|
|
struct {
|
|
int step;
|
|
} proxyStep;
|
|
};
|
|
} ncclProfilerEventDescr_v1_t;
|
|
|
|
typedef ncclProfilerEventState_v2_t ncclProfilerEventState_v1_t;
|
|
typedef ncclProfilerEventStateArgs_v2_t ncclProfilerEventStateArgs_v1_t;
|
|
|
|
typedef struct {
|
|
const char* name;
|
|
|
|
// init - initialize the profiler plugin
|
|
// Input
|
|
// - context : opaque profiler context object for separating profiler behavior across comms
|
|
// Output
|
|
// - eActivationMask: bitmask of active events set by the plugin
|
|
ncclResult_t (*init)(void** context, int* eActivationMask);
|
|
|
|
// startEvent - initialize and start a new event for the supplied event descriptor inside the eventset
|
|
// Input
|
|
// - context: opaque profiler context object
|
|
// - eDescr : pointer to ncclProfilerEventDescr_t object
|
|
// Output
|
|
// - eHandle: return event handle for supplied event descriptor object
|
|
ncclResult_t (*startEvent)(void* context, void** eHandle, ncclProfilerEventDescr_v1_t* eDescr);
|
|
|
|
// stopEvent - stop/finalize an event inside and event set
|
|
// Input
|
|
// - eHandle: handle to event object
|
|
ncclResult_t (*stopEvent)(void* eHandle);
|
|
|
|
// recordEventState - record event state transitions and event attribute updates
|
|
// Input
|
|
// - eHandle : handle to event object created through startEvent
|
|
// - eStateArgs: optional argument used to capture event attribute updates associated with the state transition
|
|
// - eState : event state transition
|
|
ncclResult_t (*recordEventState)(void* eHandle, ncclProfilerEventState_v1_t eState, ncclProfilerEventStateArgs_v1_t* eStateArgs);
|
|
|
|
// finalize - finalize the profiler plugin
|
|
// Input
|
|
// - context: opaque profiler context object
|
|
ncclResult_t (*finalize)(void* context);
|
|
} ncclProfiler_v1_t;
|
|
|
|
#endif
|