46 lines
2.2 KiB
Plaintext
46 lines
2.2 KiB
Plaintext
|
# NCCL Tuner Configuration File (CSV Format)
|
||
|
|
# Format: collective_type,min_bytes,max_bytes,algorithm,protocol,channels,nNodes,nRanks,numPipeOps,regBuff
|
||
|
|
#
|
||
|
|
# Collective types: broadcast, reduce, allgather, reducescatter, allreduce
|
||
|
|
# Algorithms: tree, ring, collnet_direct, collnet_chain, nvls, nvls_tree, pat
|
||
|
|
# Protocols: ll, ll128, simple
|
||
|
|
# Channels: number of channels to use, or -1 to keep default
|
||
|
|
# nNodes: number of nodes to match, or -1 for any number of nodes
|
||
|
|
# nRanks: number of ranks to match, or -1 for any number of ranks
|
||
|
|
# numPipeOps: number of pipeline operations to match, or -1 for any number (optional)
|
||
|
|
# regBuff: whether user buffer can be registered (0=no, 1=yes, -1=any) (optional)
|
||
|
|
#
|
||
|
|
# Note: numPipeOps and regBuff parameters are optional - configurations without them will match any value
|
||
|
|
#
|
||
|
|
# Examples:
|
||
|
|
|
||
|
|
# For single-node configurations with registered buffers
|
||
|
|
# Small allreduce operations on single node - use tree algorithm, registered buffers
|
||
|
|
allreduce,0,65536,tree,simple,2,1,-1,-1,1
|
||
|
|
|
||
|
|
# For multi-node configurations with 4 nodes, 32 total ranks, single pipeline op, non-registered buffers
|
||
|
|
# Medium allreduce operations - use ring algorithm
|
||
|
|
allreduce,65537,1048576,ring,simple,4,4,32,1,0
|
||
|
|
|
||
|
|
# For any topology - large allreduce operations with LL128 protocol, multiple pipeline ops, any buffer type
|
||
|
|
allreduce,1048577,4294967295,ring,ll128,-1,-1,-1,4,-1
|
||
|
|
|
||
|
|
# Broadcast operations - different configs for different topologies, pipeline complexity, and buffer types
|
||
|
|
# Single node broadcast - prefer tree, any pipeOps, registered buffers only
|
||
|
|
broadcast,0,32768,tree,simple,-1,1,-1,-1,1
|
||
|
|
|
||
|
|
# Multi-node broadcast with single pipeline operation, non-registered buffers - use ring
|
||
|
|
broadcast,32769,4294967295,ring,simple,2,-1,-1,1,0
|
||
|
|
|
||
|
|
# AllGather operations - optimized for 2-node configurations, any pipeOps, any buffer type
|
||
|
|
allgather,0,4294967295,ring,simple,4,2,-1
|
||
|
|
|
||
|
|
# ReduceScatter operations
|
||
|
|
# Small messages on single node, single pipeline op, registered buffers
|
||
|
|
reducescatter,0,131072,tree,simple,2,1,-1,1,1
|
||
|
|
# Large messages on any topology, multiple pipeline ops, non-registered buffers
|
||
|
|
reducescatter,131073,4294967295,ring,simple,-1,-1,-1,2,0
|
||
|
|
|
||
|
|
# Reduce operations - any topology, keep default channels, any pipeOps, any buffer type
|
||
|
|
reduce,0,4294967295,tree,simple,-1,-1,-1
|