Best HPC Software in Japan

Simr (formerly UberCloud) is revolutionizing the world of simulation operations with our flagship solution, Simulation Operations Automation (SimOps). Designed to streamline and automate complex simulation workflows, Simr enhances productivity, collaboration, and efficiency for engineers and scientists across various industries, including automotive, aerospace, biomedical engineering, defense, and consumer electronics. Our cloud-based infrastructure provides scalable and cost-effective solutions, eliminating the need for significant upfront investments in hardware. This ensures that our clients have access to the computational power they need, exactly when they need it, leading to reduced costs and improved operational efficiency. Simr is trusted by some of the world's leading companies, including three of the seven most successful companies globally. One of our notable success stories is BorgWarner, a Tier 1 automotive supplier that leverages Simr to automate its simulation environments, significantly enhancing their efficiency and driving innovation.

Metariver Technology Co., Ltd. develops innovative and creative computer-aided engineering (CAE) analysis S/W based upon the most recent HPC technology and S/W technologies including CUDA technology. We are changing the paradigm in CAE technology by using particle-based CAE technology, high-speed computation technology with GPUs, and CAE analysis software. Here is an introduction to our products. 1. Samadii-DEM: works with discrete element method and solid particles. 2. Samadii-SCIV (Statistical Contact In Vacuum): working with high vacuum system gas-flow simulation. 3. Samadii-EM (Electromagnetics) : For full-field interpretation 4. Samadii-Plasma: For Analysis of ion and electron behavior in an electromagnetic field. 5. Vampire (Virtual Additive Manufacturing System): Specializes in transient heat transfer analysis.

Covalent's serverless HPC architecture makes it easy to scale jobs from your laptop to the HPC/Cloud. Covalent is a Pythonic workflow tool that computational scientists, AI/ML program engineers, and anyone who needs to perform experiments on limited or costly computing resources such as HPC clusters and GPU arrays, cloud services, and quantum computers. Covalent allows researchers to run computation tasks on advanced hardware platforms, such as a serverless HPC cluster or quantum computer, using just one line of code. Covalent's latest release includes three major enhancements and two new feature sets. Covalent's modular design allows users to create custom pre-and post-hooks for electrons. This allows them to facilitate a variety of use cases, including setting up remote environments (using DepsPip), and running custom functions.

Manage, optimize, and optimize HPC and large compute clusters at any scale. You can deploy full clusters and other resources including schedulers, compute VMs (storage, networking, and caching), and other resources such as cache, network, networking, and storage. Advanced policy and governance features allow you to customize and optimize clusters, including cost controls, Active Directory integration and monitoring. You can continue using your existing job scheduler and other applications. Administrators have complete control over who can run jobs and where they are located. You can take advantage of autoscaling and battle-tested references architectures for a wide variety of HPC workloads. CycleCloud supports every job scheduler and software stack, from proprietary in-house to open source, third-party, or commercial. Your cluster should adapt to your changing resource requirements. Scheduler-aware autoscaling allows you to match your resources to your workload.

The NVIDIA GPU Optimized AMI is a virtual image that accelerates your GPU-accelerated Machine Learning and Deep Learning workloads. This AMI allows you to spin up a GPU accelerated EC2 VM in minutes, with a preinstalled Ubuntu OS and GPU driver. Docker, NVIDIA container toolkit, and Docker are also included. This AMI provides access to NVIDIA’s NGC Catalog. It is a hub of GPU-optimized software for pulling and running performance-tuned docker containers that have been tested and certified by NVIDIA. The NGC Catalog provides free access to containerized AI and HPC applications. It also includes pre-trained AI models, AI SDKs, and other resources. This GPU-optimized AMI comes free, but you can purchase enterprise support through NVIDIA Enterprise. Scroll down to the 'Support information' section to find out how to get support for AMI.

TotalView debugging software gives you the specialized tools to quickly analyze, scale, and debug high-performance computing applications (HPC). This includes multicore, parallel, and highly dynamic applications that run on a variety of hardware, from desktops to supercomputers. TotalView's powerful tools allow for faster fault isolation, better memory optimization, and dynamic visualisation to improve HPC development efficiency and time-to market. You can simultaneously debug thousands upon thousands of threads and processes. TotalView is a tool that was specifically designed for parallel and multicore computing. It provides unprecedented control over thread execution and processes, as well as deep insight into program data and program states.

Intel®, DevCloud provides free access to a variety of Intel®, architectures. This allows you to get hands-on experience using Intel®, software, and execute your edge and AI, high-performance computing, (HPC) and rendering workloads. You have all the tools and libraries you need to accelerate your learning and project prototyping with preinstalled Intel®. optimized frameworks, tools and libraries. Freely learn, prototype, test, run and manage your workloads on a cluster with the latest Intel®, hardware and software. A new collection of curated experiences will help you learn, including market vertical samples and Jupyter Notebook tutorials. You can build your solution in JupyterLab, test it with bare metal, or create a containerized solution. You can quickly bring it to Intel DevCloud to be tested. Use the deep learning toolbench to optimize your solution for a specific target device edge. Take advantage of the new, stronger telemetry dashboard.

Accelerate compute jobs such as machine learning and HPC. There are many GPUs available to suit different price points and performance levels. Flexible pricing and machine customizations are available to optimize your workload. High-performance GPUs available on Google Cloud for machine intelligence, scientific computing, 3D visualization, and machine learning. NVIDIA K80 and P100 GPUs, T4, V100 and A100 GPUs offer a variety of compute options to meet your workload's cost and performance requirements. You can optimize the processor, memory and high-performance disk for your specific workload by using up to 8 GPUs per instance. All this with per-second billing so that you only pay for what you use. You can run GPU workloads on Google Cloud Platform, which offers industry-leading storage, networking and data analytics technologies. Compute Engine offers GPUs that can be added to virtual machine instances. Learn more about GPUs and the types of hardware available.

The Lustre file is an open-source parallel file system which supports many of the requirements of simulation environments for leadership class HPC. These pages are a great resource for anyone who is interested in the Lustre filesystem as a parallel system or a member of its diverse development community. The Lustre filesystem provides a POSIX compliant file system interface that can scale up to thousands of clients and petabytes in storage. It also supports hundreds of gigabytes/second of I/O bandwidth. The Lustre file system is composed of Metadata Servers, Metadata Targets, Object Storage Servers, Object Server Targets and Lustre Clients. Lustre was designed to provide a global, POSIX compliant namespace that is coherent and scalable for supercomputer platforms, as well as very large computer infrastructure. It can support hundreds or petabytes worth of data storage.

TrinityX, an open-source cluster management system created by ClusterVision to provide 24/7 oversight of High-Performance Computing and Artificial Intelligence environments. It provides a reliable, SLA-compliant system of support, allowing users the freedom to focus on their research, while still managing complex technologies like Linux, SLURM CUDA, InfiniBand Lustre and Open OnDemand. TrinityX simplifies cluster deployment with an intuitive interface that guides users step-bystep in configuring clusters for diverse purposes such as container orchestration, HPC and InfiniBand/RDMA. The BitTorrent protocol enables rapid deployment and setup of AI/HPC Nodes. The platform offers a dashboard that provides real-time insights on cluster metrics, resource usage, and workload distribution. This allows for the identification of bottlenecks, and optimizes resource allocation.

The ultimate full-stack clustering solution that allows you to manage and scale clusters with ease and control. Qlustar provides unmatched simplicity and robust capability to your HPC and AI environments. Qlustar offers a seamless cluster operation, from bare-metal installations with the Qlustar Installer to seamless cluster operations. Setup and manage your clusters in an unmatched manner. Designed to grow along with your needs and handle even the most complex workloads without any hassle. Designed for speed, reliability and resource efficiency. Upgrade your OS, manage security patches and avoid reinstallations. Regular updates protect your clusters from vulnerabilities. Qlustar optimizes computing power to deliver peak efficiency in high-performance computing environments. Our solution provides robust workload management, high availability built-in, and an intuitive user interface for streamlined operations.

Warewulf, a cluster management system and provisioning tool, has been a pioneer in stateless node-management for more than two decades. It allows provisioning containers directly on bare metal hardware, at scales ranging from 10s to 10,000s of compute systems, while maintaining simplicity and versatility. The platform is extensible and allows users to modify the default functionalities and images of nodes to suit different clustering use cases. Warewulf provides stateless provisioning using SELinux and per-node asset keys-based provisioning. It also offers access controls to ensure secure deployments. Its minimal requirements, ease of customization, integration, and optimization make it accessible to a wide range of industries. Warewulf is a highly successful HPC cluster platform that is used across many sectors. It's supported by OpenHPC, and has contributors from around the world. Easy to start, easy to customize and integrate, minimal system requirements.

Our unique, transient Lattice Boltzmann physics PowerFLOW CFD solution allows simulations to accurately predict real-world conditions by leveraging this unique technology. PowerFLOW suite allows engineers to evaluate product performance before any prototype is built. This is when budgets and design impact are most important. PowerFLOW imports complex model geometry and performs accurate and efficient aerodynamic, thermal management and aeroacoustic simulations. Automated domain modeling and turbulence modeling without the need to manually volume mesh or boundary layer mesh can be done with PowerFLOW. PowerFLOW simulations can be run confidently on a large number of compute cores running on common High Performance Computing platforms (HPC).

CIQ empowers people to do amazing things by providing innovative and stable software infrastructure solutions for all computing needs. From the base operating system, through containers, orchestration, provisioning, computing, and cloud applications, CIQ works with every part of the technology stack to drive solutions for customers and communities with stable, scalable, secure production environments. CIQ is the founding support and services partner of Rocky Linux, and the creator of the next generation federated computing stack.

The Ansys HPC software suite allows you to use today's multicore processors to run more simulations in a shorter time. These simulations can be larger, more complex, and more accurate than ever before thanks to high-performance computing (HPC). Ansys HPC licensing options allow you to scale to any computational level you require, including single-user or small-user groups options for entry-level parallel processing to virtually unlimited parallel capability. Ansys allows large groups to run parallel processing simulations that are highly scalable and can be used for even the most difficult projects. Ansys offers parallel computing solutions as well as parametric computing. This allows you to explore your design parameters (size and weight, shape, materials mechanical properties, etc.). Early in the product development process.

There is no need to modify your code or the way that you build it. Profiling of applications that run on multiple servers and multiple processes. Clear views of bottlenecks in I/O in computing, in a thread or in multi-process activity. Deep insight into the actual instruction types of processors that impact your performance. To see memory usage over time, you can find high watermarks or changes across the entire memory footprint. Arm MAP is a unique, scalable, low-overhead profiler that can be used standalone or as part the Arm Forge profile and debug suite. It allows server and HPC developers to speed up their software by revealing the root causes of slow performance. It can be used on multicore Linux workstations as well as supercomputers. With a typical runtime overhead of 5%, you can profile the test cases you care about most. The interactive user interface was designed for developers and computational scientists.

You can build reliable and optimized code to achieve the best results on multiple Server or HPC architectures. This includes the latest compilers and C++ standard, as well as Intel, 64-bit Arm and AMD, OpenPOWER and Nvidia GPU hardware. Arm Forge combines Arm DDT (the leading debugger for efficient, high-performance application debugging), Arm MAP (the trusted performance profiler that provides invaluable optimization advice across native, Python, and HPC codes), and Arm Performance Reports, which provide advanced reporting capabilities. Arm DDT/Arm MAP can also be purchased as standalone products. Arm experts provide full technical support for efficient application development on Linux Server and HPC. Arm DDT is the best debugger for C++, C, and Fortran parallel applications. Arm DDT's intuitive graphical interface makes it easy to detect memory bugs at all scales and divergent behavior. This makes it the most popular debugger in academia, industry, research, and academia.

High-performance computing is the heart of AI, machine learning and deep learning applications. The Intel® oneAPI HPC Toolkit is a toolkit that allows developers to create, analyze, optimize and scale HPC applications using the most recent techniques in vectorization and multithreading, multi-node paralelization, memory optimization, and multi-node parallelization. This toolkit is an extension to the Intel(r] oneAPI Base Toolkit. It is required for full functionality. Access to the Intel(r?) Distribution for Python*, Intel(r] oneAPI DPC++/C++ C compiler, powerful data-centric library and advanced analysis tools are all included. You get everything you need to optimize, test, and build your oneAPI projects. An Intel(r] Developer Cloud account gives you 120 days access to the latest Intel®, hardware, CPUs and GPUs as well as Intel oneAPI tools, frameworks and frameworks. No software downloads. No configuration steps and no installations

NVIDIA Modulus, a neural network framework, combines the power of Physics in the form of governing partial differential equations (PDEs), with data to create high-fidelity surrogate models with near real-time latency. NVIDIA Modulus is a tool that can help you solve complex, nonlinear, multiphysics problems using AI. This tool provides the foundation for building physics machine learning surrogate models that combine physics and data. This framework can be applied to many domains and uses, including engineering simulations and life sciences. It can also be used to solve forward and inverse/data assimilation issues. Parameterized system representation that solves multiple scenarios in near real-time, allowing you to train once offline and infer in real-time repeatedly.

Azure high-performance computing (HPC). Power breakthrough innovations, solve complicated problems, and optimize compute-intensive workloads. A full stack solution designed for HPC allows you to run and build your most demanding workloads on the cloud. Azure Virtual Machines deliver supercomputing, interoperability and near-infinite scaling for compute-intensive workloads. Azure AI and analytics are industry-leading services that empower decision-making and deliver the next-generation AI. Multilayered, built-in privacy and security features help you secure your data and applications while ensuring compliance.

Amazon EC2 instances P4d deliver high performance in cloud computing for machine learning applications and high-performance computing. They offer 400 Gbps networking and are powered by NVIDIA Tensor Core GPUs. P4d instances offer up to 60% less cost for training ML models. They also provide 2.5x better performance compared to the previous generation P3 and P3dn instance. P4d instances are deployed in Amazon EC2 UltraClusters which combine high-performance computing with networking and storage. Users can scale from a few NVIDIA GPUs to thousands, depending on their project requirements. Researchers, data scientists and developers can use P4d instances to build ML models to be used in a variety of applications, including natural language processing, object classification and detection, recommendation engines, and HPC applications.

Amazon S3 Express One Zone, a high-performance storage class with a single Availability Zone, is designed to deliver consistent data access in milliseconds for your most frequently used data and applications that are latency sensitive. It offers data access rates up to 10x faster and request costs up to 50 percent lower than S3 Standard. S3 Express One Zone allows you to select a specific AWS availability zone within an AWS Region for your data storage. This allows you to co-locate both your compute and storage resources in the same AWS Region, further optimizing performance and lowering compute costs. The data is stored in an S3 directory bucket that supports hundreds of thousands requests per second. S3 Express One Zone can be used with services like Amazon SageMaker, Amazon Athena and Amazon EMR to accelerate machine learning and analytics workloads.

AWS Parallel Computing Service is a managed service which simplifies the running and scaling of high-performance computing workloads, and building scientific and engineering model on AWS with Slurm. It allows users to create complete, elastic environments that integrate storage, networking, computing, and visualization tools. This allows them to focus on their research and innovation, without having to worry about infrastructure management. AWS PCS provides managed updates and integrated observability features to enhance cluster operations and maintenance. Users can deploy HPC clusters that are scalable, secure, and reliable using the AWS Management Console (AWS CLI), AWS SDK, or AWS Command Line Interface. The service supports a variety of use cases including tightly coupled workloads such as computer-aided design, high-throughput computations like genomics analysis, GPU-accelerated computing, and custom silicon, like AWS Trainium or AWS Inferentia.

Software technologies have improved tremendously over the past 20 years and HPC computing has grown by orders of magnitude. Our ability to understand simulation results has remained the exact same. Making movies and plots in the traditional way is not scalable when dealing with multi-billion cell networks or tens of thousands of time steps. Automated solution assessment can be accelerated when features or quantitative properties are directly produced via eigen analysis and machine learning. The powerful VisIt Prime backend is paired with the easy-to-use, industry-standard FieldView desktop.

NVIDIA GPU Cloud is a GPU-accelerated cloud platform that is optimized for scientific computing and deep learning. NGC is responsible for a catalogue of fully integrated and optimized deep-learning framework containers that take full benefit of NVIDIA GPUs in single and multi-GPU configurations.