AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2.21.5-1

Browse Source 
Add support for IB SHARP 1PPN operation with user buffers.
Improve support for MNNVL, add NVLS support and multi-clique support.
 * Detect the NVLS clique through NVML
 * Exchange XML between peers in the same NVLS clique and fuse XMLs
   before creating the topology graph.
 * Rework bootstrap allgather algorithms to allow for large allgather
   operations intra-node (XML exchange).
Net/IB: add support for dynamic GID detection.
 * Automatically select RoCEv2/IPv4 interface by default. Allow to
   select IPv6 or even the network/mask.
Reduce NVLS memory usage.
 * Add stepSize as property of a connection to allow for different
   sizes on different peers; set it to 128K for NVLink SHARP.
Improve tuner loading
 * Look for more paths, be more consistent with the network device
   plugin.
 * Also search for tuner support inside the net plugin.
Improve tuner API
 * Add context to support multi-device per process.
Add magic number around comm object to detect comm corruption.
 * Add some basic check around communicators so that we can report a
   problem when a communicator gets corrupted or a wrong comm pointer
   is passed to NCCL.
Fix net/IB error path. Github PR #1164
Fix collnet rail mapping with split comm.
Fix packet reordering issue causing bootstrap mismatch
 * Use a different tag in ncclTransportP2pSetup for the connectInfo
   exchange and the following barrier.
Fix hang when crossNic is inconsistent between ranks.
Fix minCompCap/maxCompCap computation. Github issue #1184


[ROCm/rccl commit: ab2b89c4c3]
This commit is contained in:
Sylvain Jeaugey
2024-03-26 06:08:55 -07:00
parent b492ab6313
commit 792c33598f
52 changed files with 2124 additions and 944 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rccl/src/include/graph.h
+6 -6
View File
@@ -31,10 +31,10 @@ ncclResult_t ncclTopoGetNvbGpus(struct ncclTopoSystem* system, int rank, int* nr
int ncclTopoPathAllNVLink(struct ncclTopoSystem* system);
// Query topology
ncclResult_t ncclTopoGetNetDev(struct ncclComm* comm, int rank, struct ncclTopoGraph* graph, int channelId, int peerRank, int* net, int* proxyRank);
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 ncclTopoSystem* system, int64_t id1, int64_t id2, 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, int64_t busId, int netDev, int read, int* useGdr);
ncclResult_t ncclTopoCheckGdr(struct ncclTopoSystem* topo, int64_t busId, int64_t netId, int read, int* useGdr);
ncclResult_t ncclTopoNeedFlush(struct ncclTopoSystem* system, int64_t busId, int* flush);
ncclResult_t ncclTopoCheckNet(struct ncclTopoSystem* system, int64_t id1, int64_t id2, int* net);
int ncclPxnDisable(struct ncclComm* comm);
@@ -56,8 +56,8 @@ ncclResult_t ncclTopoCpuType(struct ncclTopoSystem* system, int* arch, int* vend
ncclResult_t ncclTopoGetGpuCount(struct ncclTopoSystem* system, int* count);
ncclResult_t ncclTopoGetNetCount(struct ncclTopoSystem* system, int* count);
ncclResult_t ncclTopoGetNvsCount(struct ncclTopoSystem* system, int* count);
ncclResult_t ncclTopoGetLocalNet(struct ncclTopoSystem* system, int rank, int channelId, int* id);
ncclResult_t ncclTopoGetLocalGpu(struct ncclTopoSystem* system, int net, int* gpuIndex);
ncclResult_t ncclTopoGetLocalNet(struct ncclTopoSystem* system, int rank, int channelId, int64_t* id, int* dev);
ncclResult_t ncclTopoGetLocalGpu(struct ncclTopoSystem* system, int64_t netId, int* gpuIndex);
ncclResult_t getLocalNetCountByBw(struct ncclTopoSystem* system, int gpu, int *count);
#define NCCL_TOPO_MAX_NODES 256
@@ -88,7 +88,7 @@ struct ncclTopoGraph {
int sameChannels;
int nHops;
int intra[MAXCHANNELS*NCCL_TOPO_MAX_NODES];
int inter[MAXCHANNELS*2];
int64_t inter[MAXCHANNELS*2];
};
ncclResult_t ncclTopoCompute(struct ncclTopoSystem* system, struct ncclTopoGraph* graph);
@@ -110,7 +110,7 @@ struct ncclTopoRanks {
ncclResult_t ncclTopoPreset(struct ncclComm* comm, struct ncclTopoGraph** graphs, struct ncclTopoRanks* topoRanks);
ncclResult_t ncclTopoPostset(struct ncclComm* comm, int* firstRanks, int* treePatterns,
struct ncclTopoRanks** allTopoRanks, int* rings, struct ncclTopoGraph** graphs);
struct ncclTopoRanks** allTopoRanks, int* rings, struct ncclTopoGraph** graphs, struct ncclComm* parent);
ncclResult_t ncclTopoTuneModel(struct ncclComm* comm, int minCompCap, int maxCompCap, struct ncclTopoGraph** graphs);
#include "info.h"