TACC Stampede3

RP account needed

TACC Stampede3 is a general-purpose supercomputer designed for large-scale simulation, high-throughput computing, artificial intelligence, GPU-accelerated workloads, and large-memory applications. Stampede3 provides multiple node types to support a wide range of research needs, including Intel Sapphire Rapids high-bandwidth-memory nodes, Ice Lake CPU nodes, large-memory Ice Lake NVDIMM nodes, NVIDIA H100 GPU nodes, Intel Data Center GPU Max nodes, and Skylake CPU nodes.

Jobs

Stampede3 uses Slurm for Job Scheduling. Create a job script and use Slurm's sbatch command to submit a job. 

Stampede3's accounting system is based on node-hours: one unadjusted Service Unit (SU) represents a single compute node used for one hour (a node-hour). The queue charge rates are determined by the supply and demand for that particular queue or type of node used and are subject to change.

Stampede3 SUs billed = (# nodes) x max(job duration in wall clock hours,.25) x (charge rate per node-hour)

The Slurm scheduler tracks and charges for usage to a granularity of a few seconds of wall clock time. The system charges only for the resources you actually use, not those you request; however, there is a 15 minute minimum charge of queue time. 

To display a summary of your TACC project balances and disk quotas at any time, execute:
login1$ /usr/local/etc/taccinfo 

For more information on jobs, visit these links on:

Job Scripts, Running Jobs, Submitting Batch Jobs, Job Management, and Launching Applications

 

Queue specifications

Name Purpose Nodes CPU cores / node GPUs / node Node RAM Jobs
30 days
Wait Time
30-day trend
Wall Time
30-day trend
nvdimm Ultra-high memory jobs. 3 Intel Xeon Platinum 8380 ("Ice Lake") (80 cores) 4 TB
icx General CPU jobs in ICX nodes. 224 Intel Xeon Platinum 8380 ("Ice Lake") (80 cores) 256 GB
spr High-throughput, memory bandwidth intensive jobs. 560 Intel Xeon CPU MAX 9480 ("Sapphire Rapids HBM") (112 cores) 128 GB
skx General CPU jobs on SKX nodes. 1,060 Intel Xeon Platinum 8160 ("Skylake") (48 cores) 192 GB
skx-dev Development and testing on SKX. 1,060 Intel Xeon Platinum 8160 ("Skylake") (48 cores) 192 GB
h100 NVIDIA GPU workloads. 24 Intel Xeon Platinum 8468 ("Sapphire Rapids") (96 cores) 4 NVDIA H100 SXM5 (96 GB vRAM) 4 TB
pvc Intel GPU workloads. 20 Intel Xeon Platinum 8480 ("Sapphire Rapids") (96 cores) 4 Intel Data Center GPU Max 1550s ("Ponte Vecchio") (124 GB vRAM) 1 TB

Software

No software usage data is currently reported for TACC Stampede3 in XDMoD.


Storage

File System

Directory Path Quota Purge Backup Notes
$HOME $HOME 15 GB, 300,000 files After account deactivation Yes - backed up regularly VAST filesystem. Personal scripts, config files; not for high-intensity
$WORK $WORK 1 TB, 3,000,000 files Not on a schedule Not backed up Lustre filesystem. Quota is across all TACC systems. Not intended for parallel or high−intensity file operations.
$SCRATCH $SCRATCH Subject to purge if access time is more than 10 days old. Not backed up VAST filesystem. See Scratch File System Purge Policy. https://docs.tacc.utexas.edu/hpc/stampede3/#scratchpolicy

External Storage

RANCH (Long-term Archival Tape Storage)

RANCH (Long-term Archival Tape Storage) is an allocated resource that is only available to users who have an allocation on a TACC system such as Stampede3. The default allocation for RANCH is 2 TB, and it is provided at no additional cost, meaning it does not consume ACCESS credits. It is intended for final data that is unlikely to change and does not require frequent access. RANCH can be accessed through the Globus endpoint Ranch3, and files can also be transferred using SCP with a command such as scp myfile ${ARCHIVER}:${ARCHIVE}/myfilepath.

Corral (Online Project Storage)

Corral (Online Project Storage) is TACC’s online project storage system. It is designed for users and projects that need more storage than $HOME and $WORK provide. Corral can be accessed from Stampede3 through supported TACC data transfer methods, including Globus.

For more information on managing your files, see this page


File Transfer

Stampede3 supports two primary data transfer technologies: SSH-based tools (scp, sftp, rsync) and Globus.

For smaller transfers less than ~200GB, ssh tools are typically easier to work with. See https://docs.tacc.utexas.edu/datatransfer/ssh/ for more information.

For transfer larger than 200GB, Globus is the recommended transfer method. For more information on Globus on Stampede3, see https://docs.tacc.utexas.edu/datatransfer/globus/

For more information about Data Transfer at TACC, see this page.

Supported Methods Data Transfer Node URL
SCP stampede3.tacc.utexas.edu Using scp
GLOBUS stampede3.tacc.utexas.edu Globus Data Transfer Guide at TACC
SFTP stampede3.tacc.utexas.edu Using sftp
RSYNC stampede3.tacc.utexas.edu Using rsync