test_gpu_scripts/configs/bw1000_4node.yaml

87 lines
1.5 KiB
YAML

gpu_type: bw1000
runtime:
name: DTK
version: 25.04.2
benchmark:
memory:
size_mb: 4096
iterations: 10
nvbandwidth_buffer_mb: 512
nvbandwidth_samples: 3
compute:
dtypes: [fp32, tf32, fp16, bf16, fp8]
sweep_sizes: [4096, 6144, 8192, [2048, 2048, 13312]]
matrix_size: 8192
warmup: 10
iterations: 30
health:
temp_warning: 75
temp_critical: 85
power_limit: 800
nccl:
min_bandwidth_gbps: 10
test_allreduce: true
test_alltoall: true
test_broadcast: true
test_reduce_scatter: true
test_allgather: true
test_sendrecv: false
torch_backend: nccl
torchrun_size_mb: 64
torchrun_warmup: 5
torchrun_iterations: 20
stress:
duration_sec: 600
use_doubles: false
use_tensor_cores: true
memory_pct: 80
gpus: all
rdma:
min_bandwidth_gbps: 200
max_latency_us: 6
ib_iterations: 5000
msg_size: 1048576
ib_device: null
ib_port: 1
cross_node:
enabled: false
allow_roce: true
server: null
server_addr: null
ssh_user: root
devices: [mlx5_bond_0, mlx5_bond_1, mlx5_bond_2, mlx5_bond_3]
ib_port: 1
gid_index: 3
msg_size: 1048576
iters: 5000
duration_sec: 10
queue_pairs: 4
base_oob_port: 18515
server_warmup_sec: 2.0
min_bandwidth_gbps: 200
max_latency_us: 6
training:
model: synthetic
batch_size: 2
seq_length: 1024
num_steps: 20
dtype: bf16
hidden_size: 2048
num_layers: 4
num_heads: 16
vocab_size: 8192
report:
output_dir: ./reports
format: json
tools:
install_dir: /opt/gpu-test-tools