Sylvain Jeaugey
db3bfd118f
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
[ROCm/rccl commit: 6aae379278]
70 γραμμές
1.7 KiB
C
70 γραμμές
1.7 KiB
C
#ifndef NCCL_REGISTER_H_
|
|
#define NCCL_REGISTER_H_
|
|
|
|
#include "device.h"
|
|
|
|
#include <cuda.h>
|
|
#include <stdint.h>
|
|
|
|
int64_t ncclParamLocalRegister();
|
|
int64_t ncclParamGraphRegister();
|
|
|
|
enum {
|
|
NET_REG_COMPLETE = 0x01,
|
|
NVLS_REG_COMPLETE = 0x02,
|
|
NVLS_REG_POSSIBLE = 0x04,
|
|
NVLS_REG_NO_SUPPORT = 0x08,
|
|
COLLNET_REG_COMPLETE = 0x10,
|
|
IPC_REG_COMPLETE = 0x20
|
|
};
|
|
|
|
struct ncclPeerRegIpcAddr {
|
|
uintptr_t* devPeerRmtAddrs;
|
|
uintptr_t* hostPeerRmtAddrs;
|
|
};
|
|
|
|
struct ncclRegNetHandles {
|
|
void* handle;
|
|
struct ncclProxyConnector* proxyConn;
|
|
struct ncclRegNetHandles* next;
|
|
};
|
|
|
|
struct ncclReg {
|
|
// common attributes
|
|
size_t pages;
|
|
int localRefs;
|
|
int graphRefs;
|
|
uintptr_t addr;
|
|
uint32_t state;
|
|
// net reg
|
|
struct ncclRegNetHandles* netHandleHead;
|
|
// nvls reg
|
|
uintptr_t baseAddr;
|
|
size_t baseSize;
|
|
CUdeviceptr regAddr;
|
|
size_t regSize;
|
|
int dev;
|
|
CUmemGenericAllocationHandle mcHandle;
|
|
uintptr_t caddrs[NCCL_MAX_LOCAL_RANKS]; /* use to check if NVLS buffers match among intra-node ranks */
|
|
// collnet reg
|
|
void* collnetHandle;
|
|
struct ncclProxyConnector* collnetProxyconn;
|
|
// general ipc reg
|
|
struct ncclPeerRegIpcAddr regIpcAddrs;
|
|
struct ncclIpcRegInfo* ipcInfos[NCCL_MAX_LOCAL_RANKS];
|
|
};
|
|
|
|
struct ncclRegCache {
|
|
struct ncclReg **slots;
|
|
int capacity, population;
|
|
uintptr_t pageSize;
|
|
};
|
|
|
|
ncclResult_t ncclRegCleanup(struct ncclComm* comm);
|
|
ncclResult_t ncclRegFind(struct ncclComm* comm, const void* data, size_t size, struct ncclReg** reg);
|
|
ncclResult_t ncclCommGraphRegister(const ncclComm_t comm, void* buff, size_t size, void** handle);
|
|
ncclResult_t ncclCommGraphDeregister(const ncclComm_t comm, struct ncclReg *handle);
|
|
ncclResult_t ncclRegLocalIsValid(struct ncclReg *reg, bool *isValid);
|
|
|
|
#endif
|