Resources | crc.pitt.edu | University of Pittsburgh

Pitt CRC Hardware Resources

Pitt Center for Research Computing provides different types of hardware for different advanced computing needs

MPI: distributed computing across nodes using the Message Passing Interface. MPI nodes are for tightly-coupled codes that are parallelized using the Message Passing Interface (MPI) and benefit from the low-latency Omni-Path (OP) or Infiniband (IB) interconnect fabrics.
SMP: shared memory processing on a single node. SMP nodes are appropriate for programs that are parallelized using the shared memory framework. They are also appropriate for those who want to move up to supercomputers while keeping the programming style of their laptops, such as running MATLAB. These nodes have up to 512GB of shared memory.
GPU: accelerated computing using Graphic Processing Units, GPU nodes are targeted for applications specifically written to take advantage of the inherent parallelism in general purpose graphics processing unit architectures.
VIZ: graphic user interface (GUI) interface, especially for visualization projects.
HTC: HTC nodes are designed for High Throughput Computing workflows such as gene sequence analysis and data-intensive analytics.

Investing in Hardware

Pitt CRC encourages researchers to allocate grant dollars or startup funds to enable CRC to purchase hardware that becomes part of computing resources for the broader Pitt community, rather than buying and managing their own hardware or maintaining inefficient old hardware that becomes a maintenance burden. Faculty who do so are called investors.

MPI (Omni-path Network)

dual 14-core Broadwell CPU (Intel Xeon E5-2690 2.60 GHz)

96 nodes
64 GB RAM
256 GB SSD
Omni-path

dual 14-core Skylake CPU (Intel Xeon Gold 6132 2.60 GHz)

36 nodes
192 GB RAM
256 GB SSD & 500 GB SSD
Omni-path

MPI (Infiniband Network)

dual 10-core Haswell CPU (Intel Xeon E5-2660 v3 2.6 GHz)

32 nodes
128 GB RAM
256 GB SSD
FDR Infiniband

SMP

dual 16-core Rome CPU (AMD EPYC 7302 3.0 GHz); 10GigE (will be deployed in mid-Jan 2020)

58 nodes
256 GB RAM
256 GB SSD & 1TB SSD

dual 12-core Skylake CPU (Intel Xeon Gold 6126 2.60 GHz); 10GigE

132 nodes
192 GB RAM
256 GB SSD & 500 GB SSD

dual 6-core Broadwell CPU (Intel Xeon E5-2643 v4 3.40 GHz); 10GigE

24 nodes
- 256 GB RAM
- 256 GB SSD & 1 TB SSD
2 Nodes
- 256 GB RAM
- 256 GB SSD & 3 TB SSD
2 Nodes
- 512 GB RAM
- 256 GB SSD & 3 TB SSD
1 Node
- 256 GBRAM
- 256 GB SSD & 6 TB NVMe

dual 16-core Naples CPU (AMD 2.40 GHz); 10GigE

1 nodes
1024 GB RAM
256 GB SSD & 1TB NVMe

GPU

7 nodes with 4 NVIDIA Titan X GPUs/node. Each GPU has 12GB of memory. The host node has 128GB RAM and dual CPUs with 6 cores/CPU
8 nodes with 4 NVIDIA GTX1080 GPUs/node. Each GPU has 8GB of memory. The host node has 128GB RAM and dual CPUs with 6 cores/CPU
10 nodes with 4 NVIDIA GTX1080 Ti GPUs/node. Each GPU has 11GB of memory. The host node has 96GB RAM and dual CPUs with 4 cores/CPU
1 node with 2 NVIDIA K40 GPUs/node. Each GPU has 12GB of memory. The host node has 128GB RAM and dual CPUs with 10 cores/CPU
1 nodes with 4 NVIDIA V100 32GB GPUs/node. Each GPU has 32GB of memory. The host node has 192GB RAM and dual CPUs with 12 cores/CPU

VIZ (GUI Interface)

Review documentations for VIZ

dual 14-core Broadwell CPU (Intel Xeon E5-2680 v4 2.4 GHz)

1 node
256 GB RAM
1.6 TB SSD (/scratch)
2 NVIDIA GTX1080 Graphic Cards

HTC

The HTC cluster is designed to run high throughput computing jobs to support bioinformatics and health science research.

Review documentation for HTC

dual 8-core Haswel-EP CPU (Intel Xeon E5-2630 v3 2.4GHz)

20 nodes
256 GB RAM
256 GB SSD
FDR Infiniband

dual 12-core Skylake CPU (Intel Xeon Gold 6126 2.60 GHz)

4 nodes
384 GB RAM
256 GB SSD & 500 GB SSD
FDR Infiniband

dual 24-core Cascade Lake CPU (Intel Xeon Gold 6248R 3.0 GHz)

6 nodes
768 GB RAM
480 GB SSD & 960 GB SSD
100 Gb/s HDR InfiniBand