Symmetric Computing Teams with Penguin for Affordable Large-Memory HPC

Print Friendly, PDF & Email

Today Penguin Computing announced a partnership with Symmetric Computing to bring the power of large shared memory, high core-count HPC to the market at a reduced cost.

We have broken the price/performance barrier that previously existed for large shared memory/high core count. No longer do you need the budget of major government funded research facilities to afford supercomputers that because of their exceptionally large shared memory significantly reduce the time and effort required for research, simulation and modeling. These capabilities are now available at an affordable price.”

Initially available with 1.5TB or 3TB of shared memory and 192 cores, these machines cut the processing time for workloads that need access to large memory configurations. The Symmetric Computing Trio is usable for both shared memory and distributed memory applications.

Symmetric Computing’s patent-pending Distributed Symmetric Multi-Processing (DSMP) enables Distributed Shared Memory (DSM), or Distributed Global Address Space (DGAS), across an InfiniBand connected cluster of homogeneous Symmetric Multiprocessing (SMP) nodes. Homogeneous InfiniBand-connected clusters are converted into a DSM/DGAS supercomputer which can service very large data-sets or accommodate legacy MPI/MPICH applications with increased efficiency and throughput via application-utilities (gasket interface) that support MPI over shared-memory. DSMP can displace and, in some cases, obsolete message-passing as the protocol of choice for a wide range of memory intensive applications because of its ability to service economically a wider class of problems with greater efficiency. DSMP creates a large, shared-memory software architecture at the operating system level.

A cloud-based Penguin Computing on Demand (POD) HPC service offering is anticipated for those who need the performance of large shared memory HPC on a pay as you go basis.

Read the Full Story or check out the whitepaper on DSMP.