Part 6: Validate Slurm#

  1. Login to SLOGIN-01 and run sinfo to verify that all the nodes are up and ready.

    # At the OS/shell level on the slogin node, run
    
    root@slogin-01:~# module load slurm
    root@slogin-01:~# sinfo
    
    PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
    defq*        up   infinite      4   idle dgx-[01-04]
    
  2. Basic slurm job/GPU test using the DGX node running the RHEL image.

    # At the OS/shell level on the slogin node, run
    
    root@slogin-01:~# srun -w dgx-01 --gres=gpu:8 -n1 nvidia-smi
    
    Wed May 27 15:16:18 2026
    +-----------------------------------------------------------------------------------------+
    | NVIDIA-SMI 580.95.05              Driver Version: 580.95.05      CUDA Version: 13.0     |
    +-----------------------------------------+------------------------+----------------------+
    | GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
    | Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
    |                                         |                        |               MIG M. |
    |=========================================+========================+======================|
    |   0  NVIDIA B200                    On  |   00000000:1B:00.0 Off |                    0 |
    | N/A   32C    P0            220W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   1  NVIDIA B200                    On  |   00000000:43:00.0 Off |                    0 |
    | N/A   33C    P0            219W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   2  NVIDIA B200                    On  |   00000000:52:00.0 Off |                    0 |
    | N/A   37C    P0            220W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   3  NVIDIA B200                    On  |   00000000:61:00.0 Off |                    0 |
    | N/A   38C    P0            221W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   4  NVIDIA B200                    On  |   00000000:9D:00.0 Off |                    0 |
    | N/A   35C    P0            221W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   5  NVIDIA B200                    On  |   00000000:C3:00.0 Off |                    0 |
    | N/A   34C    P0            218W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   6  NVIDIA B200                    On  |   00000000:D1:00.0 Off |                    0 |
    | N/A   38C    P0            219W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    |   7  NVIDIA B200                    On  |   00000000:DF:00.0 Off |                    0 |
    | N/A   41C    P0            226W / 1000W |       0MiB / 183359MiB |      0%      Default |
    |                                         |                        |             Disabled |
    +-----------------------------------------+------------------------+----------------------+
    
    +-----------------------------------------------------------------------------------------+
    | Processes:                                                                              |
    |  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
    |        ID   ID                                                               Usage      |
    |=========================================================================================|
    |  No running processes found                                                             |
    +-----------------------------------------------------------------------------------------+
    

Host and Container Validation Test#

# At the OS/shell level on the slogin node, run

# Container Validation test
root@slogin-01:~# srun -w dgx-02 --container-image=redhat/ubi9  grep PRETTY /etc/os-release

pyxis: importing docker image: redhat/ubi9
pyxis: imported docker image: redhat/ubi9
PRETTY_NAME="Red Hat Enterprise Linux 9.8 (Plow)"

  # Host Validation test
root@slogin-01:~# srun -w dgx-02 grep PRETTY /etc/os-release

PRETTY_NAME="Red Hat Enterprise Linux 9.6 (Plow)"

Single-Node NCCL Test#

The following test uses the public image nvcr.io/nvidia/pytorch:26.04-py3. Enroot pulls it automatically via Pyxis at job runtime. All DGX nodes used are running the RHEL software image.

# At the OS/shell level on the slogin node, run

root@slogin-01:~# srun -w dgx-02 --export="NCCL_SOCKET_IFNAME=bond0" -N1 --exclusive --gpus-per-node=8 --mpi=pmix --container-name=nccl-test --container-image="nvcr.io/nvidia/pytorch:26.04-py3" all_reduce_perf_mpi -b 1G -e 16G -f 2 -g 8

[dgx-02:549474] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
# nThread 1 nGpus 8 minBytes 1073741824 maxBytes 17179869184 step: 2(factor) warmup iters: 5 iters: 20 agg iters: 1 validation: 1 graph: 0
#
# Using devices
#  Rank  0 Group  0 Pid 549474 on     dgx-02 device  0 [0x1b] NVIDIA B200
#  Rank  1 Group  0 Pid 549474 on     dgx-02 device  1 [0x43] NVIDIA B200
#  Rank  2 Group  0 Pid 549474 on     dgx-02 device  2 [0x52] NVIDIA B200
#  Rank  3 Group  0 Pid 549474 on     dgx-02 device  3 [0x61] NVIDIA B200
#  Rank  4 Group  0 Pid 549474 on     dgx-02 device  4 [0x9d] NVIDIA B200
#  Rank  5 Group  0 Pid 549474 on     dgx-02 device  5 [0xc3] NVIDIA B200
#  Rank  6 Group  0 Pid 549474 on     dgx-02 device  6 [0xd1] NVIDIA B200
#  Rank  7 Group  0 Pid 549474 on     dgx-02 device  7 [0xdf] NVIDIA B200
#
#                                                              out-of-place                       in-place
#       size         count      type   redop    root     time   algbw   busbw #wrong     time   algbw   busbw #wrong
#        (B)    (elements)                               (us)  (GB/s)  (GB/s)            (us)  (GB/s)  (GB/s)
1073741824     268435456     float     sum      -1   2544.6  421.96  738.43      0   2543.3  422.18  738.81      0
2147483648     536870912     float     sum      -1   4566.7  470.25  822.93      0   4568.2  470.09  822.66      0
4294967296    1073741824     float     sum      -1   9021.2  476.10  833.17      0   9019.6  476.18  833.32      0
8589934592    2147483648     float     sum      -1    17861  480.93  841.64      0    17854  481.12  841.95      0
17179869184    4294967296     float     sum      -1    36674  468.45  819.78      0    39547  434.41  760.22      0
# Out of bounds values : 0 OK
# Avg bus bandwidth    : 805.292

Multi-Node NCCL Test — Two and Three Nodes#

# At the OS/shell level on the slogin node, run

root@slogin-01:~# srun -w dgx-02,dgx-03 --export="UCX_NET_DEVICES=bond0,OMPI_MCA_pml=ucx,HCOLL_ENABLE_MCAST_ALL=0,OMPI_MCA_coll=^hcoll,NCCL_SOCKET_IFNAME=bond0,UCX_TLS=tcp,UCX_NET_DEVICES=bond0,MELLANOX_VISIBLE_DEVICES=all,OMPI_MCA_coll_hcoll_enable=0,OMPI_MCA_coll_ucc_enable=0" -N2 --exclusive --gpus-per-node=8 --mpi=pmix --container-name=nccl-test --container-image="nvcr.io/nvidia/pytorch:26.04-py3" all_reduce_perf_mpi -b 1G -e 16G -f 2 -g 8

[dgx-02:572898] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
[dgx-03:468807] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
# nThread 1 nGpus 8 minBytes 1073741824 maxBytes 17179869184 step: 2(factor) warmup iters: 5 iters: 20 agg iters: 1 validation: 1 graph: 0
#
# Using devices
#  Rank  0 Group  0 Pid 572898 on     dgx-02 device  0 [0x1b] NVIDIA B200
#  Rank  1 Group  0 Pid 572898 on     dgx-02 device  1 [0x43] NVIDIA B200
#  Rank  2 Group  0 Pid 572898 on     dgx-02 device  2 [0x52] NVIDIA B200
#  Rank  3 Group  0 Pid 572898 on     dgx-02 device  3 [0x61] NVIDIA B200
#  Rank  4 Group  0 Pid 572898 on     dgx-02 device  4 [0x9d] NVIDIA B200
#  Rank  5 Group  0 Pid 572898 on     dgx-02 device  5 [0xc3] NVIDIA B200
#  Rank  6 Group  0 Pid 572898 on     dgx-02 device  6 [0xd1] NVIDIA B200
#  Rank  7 Group  0 Pid 572898 on     dgx-02 device  7 [0xdf] NVIDIA B200
#  Rank  8 Group  0 Pid 468807 on     dgx-03 device  0 [0x1b] NVIDIA B200
#  Rank  9 Group  0 Pid 468807 on     dgx-03 device  1 [0x43] NVIDIA B200
#  Rank 10 Group  0 Pid 468807 on     dgx-03 device  2 [0x52] NVIDIA B200
#  Rank 11 Group  0 Pid 468807 on     dgx-03 device  3 [0x61] NVIDIA B200
#  Rank 12 Group  0 Pid 468807 on     dgx-03 device  4 [0x9d] NVIDIA B200
#  Rank 13 Group  0 Pid 468807 on     dgx-03 device  5 [0xc3] NVIDIA B200
#  Rank 14 Group  0 Pid 468807 on     dgx-03 device  6 [0xd1] NVIDIA B200
#  Rank 15 Group  0 Pid 468807 on     dgx-03 device  7 [0xdf] NVIDIA B200
#
#                                                              out-of-place                       in-place
#       size         count      type   redop    root     time   algbw   busbw #wrong     time   algbw   busbw #wrong
#        (B)    (elements)                               (us)  (GB/s)  (GB/s)            (us)  (GB/s)  (GB/s)
1073741824     268435456     float     sum      -1   3343.0  321.19  602.23      0   3352.4  320.29  600.54      0
2147483648     536870912     float     sum      -1   6499.0  330.43  619.56      0   6524.4  329.14  617.15      0
4294967296    1073741824     float     sum      -1    12773  336.27  630.50      0    12757  336.68  631.27      0
8589934592    2147483648     float     sum      -1    25240  340.33  638.12      0    25279  339.81  637.14      0
17179869184    4294967296     float     sum      -1    50350  341.21  639.76      0    50134  342.68  642.52      0
# Out of bounds values : 0 OK
# Avg bus bandwidth    : 625.878
#






## ---- 3 node NCCL test ----##
# At the OS/shell level on the slogin node, run

root@slogin-01:~# srun -w dgx-01,dgx-02,dgx-03 --export="UCX_NET_DEVICES=bond0,OMPI_MCA_pml=ucx,HCOLL_ENABLE_MCAST_ALL=0,OMPI_MCA_coll=^hcoll,NCCL_SOCKET_IFNAME=bond0,UCX_TLS=tcp,UCX_NET_DEVICES=bond0,MELLANOX_VISIBLE_DEVICES=all,OMPI_MCA_coll_hcoll_enable=0,OMPI_MCA_coll_ucc_enable=0" -N3 --exclusive --gpus-per-node=8 --mpi=pmix --container-name=nccl-test --container-image="nvcr.io/nvidia/pytorch:26.04-py3" all_reduce_perf_mpi -b 1G -e 16G -f 2 -g 8

pyxis: imported docker image: nvcr.io/nvidia/pytorch:26.04-py3
pyxis: imported docker image: nvcr.io/nvidia/pytorch:26.04-py3
pyxis: imported docker image: nvcr.io/nvidia/pytorch:26.04-py3
[dgx-03:1553761] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
[dgx-02:256136] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
[dgx-01:2922180] PMIX ERROR: ERROR in file gds_ds12_lock_pthread.c at line 168
# nccl-tests version 2.18.2 nccl-headers=22907 nccl-library=22907
# Collective test starting: all_reduce_perf_mpi
# nThread 1 nGpus 8 minBytes 1073741824 maxBytes 17179869184 step: 2(factor) warmup iters: 1 iters: 20 agg iters: 1 validation: 1 graph: 0 unalign: 0
#
# Using devices
#  Rank  0 Group  0 Pid 2922180 on     dgx-01 device  0 [0000:1b:00] NVIDIA B200
#  Rank  1 Group  0 Pid 2922180 on     dgx-01 device  1 [0000:43:00] NVIDIA B200
#  Rank  2 Group  0 Pid 2922180 on     dgx-01 device  2 [0000:52:00] NVIDIA B200
#  Rank  3 Group  0 Pid 2922180 on     dgx-01 device  3 [0000:61:00] NVIDIA B200
#  Rank  4 Group  0 Pid 2922180 on     dgx-01 device  4 [0000:9d:00] NVIDIA B200
#  Rank  5 Group  0 Pid 2922180 on     dgx-01 device  5 [0000:c3:00] NVIDIA B200
#  Rank  6 Group  0 Pid 2922180 on     dgx-01 device  6 [0000:d1:00] NVIDIA B200
#  Rank  7 Group  0 Pid 2922180 on     dgx-01 device  7 [0000:df:00] NVIDIA B200
#  Rank  8 Group  0 Pid 256136 on     dgx-02 device  0 [0000:1b:00] NVIDIA B200
#  Rank  9 Group  0 Pid 256136 on     dgx-02 device  1 [0000:43:00] NVIDIA B200
#  Rank 10 Group  0 Pid 256136 on     dgx-02 device  2 [0000:52:00] NVIDIA B200
#  Rank 11 Group  0 Pid 256136 on     dgx-02 device  3 [0000:61:00] NVIDIA B200
#  Rank 12 Group  0 Pid 256136 on     dgx-02 device  4 [0000:9d:00] NVIDIA B200
#  Rank 13 Group  0 Pid 256136 on     dgx-02 device  5 [0000:c3:00] NVIDIA B200
#  Rank 14 Group  0 Pid 256136 on     dgx-02 device  6 [0000:d1:00] NVIDIA B200
#  Rank 15 Group  0 Pid 256136 on     dgx-02 device  7 [0000:df:00] NVIDIA B200
#  Rank 16 Group  0 Pid 1553761 on     dgx-03 device  0 [0000:1b:00] NVIDIA B200
#  Rank 17 Group  0 Pid 1553761 on     dgx-03 device  1 [0000:43:00] NVIDIA B200
#  Rank 18 Group  0 Pid 1553761 on     dgx-03 device  2 [0000:52:00] NVIDIA B200
#  Rank 19 Group  0 Pid 1553761 on     dgx-03 device  3 [0000:61:00] NVIDIA B200
#  Rank 20 Group  0 Pid 1553761 on     dgx-03 device  4 [0000:9d:00] NVIDIA B200
#  Rank 21 Group  0 Pid 1553761 on     dgx-03 device  5 [0000:c3:00] NVIDIA B200
#  Rank 22 Group  0 Pid 1553761 on     dgx-03 device  6 [0000:d1:00] NVIDIA B200
#  Rank 23 Group  0 Pid 1553761 on     dgx-03 device  7 [0000:df:00] NVIDIA B200
#
#                                                              out-of-place                       in-place
#       size         count      type   redop    root     time   algbw   busbw  #wrong     time   algbw   busbw  #wrong
#        (B)    (elements)                               (us)  (GB/s)  (GB/s)             (us)  (GB/s)  (GB/s)
1073741824     268435456     float     sum      -1  6040.20  177.77  340.72       0  6039.51  177.79  340.76       0
2147483648     536870912     float     sum      -1  12018.7  178.68  342.47       0  12020.4  178.65  342.42       0
4294967296    1073741824     float     sum      -1  24153.0  177.82  340.83       0  24155.2  177.81  340.80       0
8589934592    2147483648     float     sum      -1  47763.0  179.84  344.70       0  47762.5  179.85  344.71       0
17179869184    4294967296     float     sum      -1  95263.0  180.34  345.65       0  95248.2  180.37  345.71       0
# Out of bounds values : 0 OK
# Avg bus bandwidth    : 342.876
#
# Collective test concluded: all_reduce_perf_mpi
#