Midway, a professionally-managed high performance computing cluster, forms the core of RCC’s advanced computational infrastructure. Midway is comprised of two clusters: Midway1 was deployed in 2012 and had some extensions over the years. Midway2 was deployed in 2016. Midway1 and Midway2 collectively include a large pool of servers, software, and storage that researchers can utilize to increase the efficiency and scale of their computational science. RCC provides resources for distributed cluster computing, and shared memory computing, as well as emerging technologies including GPU computing, Intel Xeon Phi devices, and Hadoop.
RCC resources are free to use for University of Chicago researchers. For more information, see the Getting Started page. To learn how you can extend RCC resources with more storage and computation, see Cluster Partnership Program.
Cluster Computing Resources
RCC maintains three pools of servers for distributed high-performance computing. Ideal for tightly coupled parallel calculations, our tightly-coupled nodes on Midway1 are linked by a fully non-blocking FDR-10 Infiniband interconnect. Tightly coupled nodes on Midway2, on the other hand, have a faster fully non-blocking FDR and EDR Infiniband interconnect. Loosely-coupled nodes are similar to the tightly-coupled nodes, but are connected with GigE rather than Infiniband and are best suited for high-throughput jobs. Finally, our shared memory nodes contain much larger main memories (up to 1 TB) and are ideal for memory-bound computations.
The types of CPU architectures RCC maintains are are:
- Intel Sandybridge—16 cores @ 2.6 GHz with 32 GB memory per node
- Intel Ivybridge—20 cores @ 2.8 GHz with 64 GB memory per node
- Intel Haswell—24 cores @ 2.5 GHz with 64 GB memory per node
- Intel Broadwell—28 cores @ 2.4 GHz with 64 GB memory per node
- AMD Opteron 6386SE—64 cores @ 2.8 GHz with 256 GB memory per node
RCC also maintains a number of specialty nodes:
- Large shared memory nodes—up to 1 TB of memory per node with either 16, 28, or 32 Intel CPU cores.
Midway is always expanding, but at time of writing Midway1 contains a total of 13,500 cores across 792 nodes, and 1.5 PB of storage. Midway2 adds 10,696 cores across 382 nodes, and 2.2 PB of storage.
Just as the University of Chicago is at the forefront of science, RCC’s emerging technology resources allow researchers to be on the cutting edge of scientific computing.
- Hadoop: Originally developed at Google, Hadoop is a framework for large-scale data processing. Researchers can experiment with our Hadoop infrastructure to become familiar with big data techniques.
- GPU Computing: Scientific computing on graphics cards can unlock even greater amounts of parallelism from code. Our GPU nodes on Midway1 each includes two Nvidia Tesla-class accelerator cards and are integrated in the Infiniband network. The GPU devices on Midway1 are Fermi-generation M2090, and Kepler-generation K20 and K40. GPU nodes on Midway2 each has 4 Nvidia K80 accelerator cards and are integrated in the Infiniband network.
- Xeon Phi: The Many Integrated-Core architecture (MIC) is Intel’s newest approach to manycore computing. Researchers can experiment with these accelerators by using our MIC nodes, each of which has two Xeon Phi Knights Corner cards, and are integrated into the Infiniband network.