Products:Ada Midframe Trio Workstation
Ada is a hybrid supercomputer consistng of a large memory head node and 2 to 10 compute nodes with 4 GPUs each. It includes a 4TB global NVMe filesystem and a Python based distributed computing environment. Ada is perfect for Artificial Intelligence, Machine Learing, Bioinformatics, and scientific and technical applications requiring support for large datasets. It is optimized for running Pytorch. Designed for computationally intensive high-performance computing, the maximum 11 node Ada configuration has 2112 CPU cores, 40 GPUs, and 2PB of disk array storage.
Features
Maximum Combined GPU Floating Point Performance:
A new generation mainframe class computer with large shared memory and many cores that is departmental sized with the ability to replace traditional mainframes in many applications. It is perfect for In-memory Databases, Big Data and Artificial Intelligence, and for traditional enterprise computing applications with large in-memory needs. The Midframe includes a 4TB global NVMe filesystem and a Python based distributed computing environment. With the maximum 11 node configuration, it supports 2112 cores (4224 threads), 3TB memory (head node), 768GB/1.5TB memory (worker node) and up to 2PB mixed flash/HDD storage.
Features
The Trio and Duet large memory servers provide up to 3TB per node. The 6U Trio provides 576 cores (1152 threads) and 36 NMVe/SATA drive bays. The 4U Duet provides 384 cores (768 threads) and 24 drive bays. These servers include a 4TB global NVMe filesystem and a Python based distributed computing environment. The Trio and Duet Linux systems are ideal for hosting large in-memory databases, and Big Data and enterprise applications. With the distributed symmetric multiprocessing (DSMP) option, a global shared memory with Pthreads is supported across all nodes. These systems also have the option of adding up to two MI210 GPUs per node tranforming them into powerful computational engines for machine learning, advanced statistics and heavy duty floating point processing.
Features
The AI/ML Graphics Workstation is designed to allow users to execute high performance computing activities at their deskside. It is built around the AMD Threadripper Pro 7900 series processor and the W7900DS GPUs. The workstation hosts up to 4 GPUs along with a single Threadripper Pro CPU with the option of 24, 32, 64 or 96 cores. A 512GB or 1TB memory configuration is supported. The workstation includes a 4TB global NVMe filesystem and a Python based distributed computing environment which allows two or more workstations to network and operate on the same job. The Workstation is ideal for artificial intelligence and machine learning, advanced statistics and heavy duty floating point processing, as well as high definition graphics.
