When it comes to compute-intensive research areas, like high-energy particle physics, or industrial design projects that require computer-aided engineering (CAE) and other commercial applications, simulation, and modeling workloads need to run on high-performance computing (HPC) clusters. To support those applications at scale, modern HPC systems require multi-core processors, high-bandwidth fabrics, and fast storage and other broad input/output (I/O) capabilities. Because of the complexity and variety of technologies available on the market, designing and assembling an HPC system for specific workloads can be time-consuming, requiring specific expertise. Integration and configuration of selected components can impact the performance of the solution with the reality of properly configuring the combined solution intimidating technologists. Boston, Ltd. (www.boston.co.uk) not only designs, builds, and delivers large computing clusters, it offers extensive consultancy services and expertise with early access to systems to help ensure workloads will run optimally on their systems. Boston, Ltd. – Expertise, Experience, and Service Worldwide Boston, Ltd. is a worldwide, leading integrator of HPC clusters used for simulation and modeling. With over 25 years of experience and vast expertise in various scientific and commercial domains, Boston services customers with design, build, integration, and installation of supercomputers, plus benchmarking and application testing, tuning, and optimization, setting them apart from other integrators. Based on Supermicro ® servers and Intel ® technologies, Boston builds custom HPC solutions that appear in universities and businesses in Europe, the United States, Asia, India, Russia, and Australia. Their engineers work closely with leading organizations within Formula 1, manufacturing, engineering, and genomics. Boston offers both potential and existing customers pre- and post-sales access to their systems and labs to help ensure that their workloads run optimally on their systems. High-Performance Enabling Ingredients COMPUTE Boston offers high-performance dual-processor Supermicro servers based on Intel® Xeon® Scalable processors. Intel® Xeon® Scalable processors, such as the Intel® Xeon® Gold 6148 processor, feature significant enhancements that benefit HPC applications, including improvements in I/O, memory, fabric integration, and Intel® Advanced Vector Instructions 512 (Intel® AVX-512). Optionally, Intel® Xeon® Platinum processors—with up to 28 cores—can be used to meet the most challenging compute demands, depending on the requirements of the workload and other customer needs. FABRIC Intel® Omni-Path Architecture (Intel® OPA) provides 100 gigabits per second (Gbps) bandwidth and a lowlatency, next-generation fabric for HPC clusters. Its 48-port switch chip delivers a 33 percent increase in density over the traditional 36-port switch ASIC historically used for InfiniBand* networking. The denser radix chip reduces the number of required switches, cutting costs and enhancing reliability. Intel OPA also reduces cabling-related costs, power consumption, space requirements, and ongoing system maintenance requirements. These advancements can lower fabric costs by up to 61 percent. INTEL SOLID STATE DRIVE - DATA CENTER FAMILY Intel ® Solid State Drive Data Center Family (Intel ® SSD DC) and Intel ® Optane™ SSD DC products offer responsive performance and high capacities for local scratch storage, burst buffers, and augmented parallel files systems. Intel ® Optane ™ SSD DC storage is the world’s most responsive data center SSD with Intel ® Optane™ technology. Intel ® S SD DC storage includes PCIe interface with NVMe protocol options. TECHNOLOGY SELECTIONS In addition to the Intel ® Xeon ® processor-based hardware foundation and Intel ® OPA, other technologies from Intel and Boston provide further performance gains: Intel ® AVX-512: Boosts performance for the most demanding computational workloads, with up to double the number of floating point operations per second (FLOPS) per clock cycle, compared to previous-generation Intel ® processors. Intel ® Cluster Checker: Inspects more than 100 characteristics related to cluster health. Intel ® Cluster Checker examines the system at both the node and cluster level, making sure all components work together to deliver optimal performance. It assesses firmware, kernel, storage, and network settings. It also conducts high-level tests of node and network performance using the Intel ® MPI Library benchmarks, STREAM,* the High-Performance LINPACK* (HPL*) benchmark, the High Performance Conjugate Gradients* (HPCG*) benchmark, and other benchmarks. Intel ® Cluster Checker can be extended with custom tests, and its functionality can be embedded into other software. Intel ® Parallel Studio: This comprehensive suite of development tools makes it simpler to build and modernize code with the latest techniques in vectorization, multithreading, multinode parallelization, and memory optimization. It enables C, C++, Fortran, and Python* software developers to: ■ Increase performance: Boost application performance that scales on current and future Intel ® platforms. ■ Build code faster: Simplify the process of creating parallel code. ■ Get Priority Support: Connect directly to Intel ® engineers for confidential answers to technical questions. Intel ® Cluster Runtimes: Supplies key software runtime elements that are required on each cluster to ensure optimal performance paths for applications. Intel ® runtime performance libraries, including Intel ® Math Kernel Library (Intel ® MKL) and Intel MPI Library, deliver excellent performance optimized for clusters based on Intel ® architecture.