Software Engineer

InspireSemi and E4 Computer Engineering collaboration and exhibiting at RISC-V Europe Summit 2026. VANCOUVER, British Columbia, AUSTIN, Texas and SCANDIANO, Italy, June 03, 2026 (GLOBE NEWSWIRE) - Inspire Semiconductor Holdings Inc. ("InspireSemi" or the "Company") a chip design company that provides revolutionary high-performance, energy-efficient accelerated computing solutions for High Performance Computing (HPC), AI, graph analytics, and other compute-intensive workloads, will be exhibiting at the annual RISC-V Europe Summit in Bologna Italy from June 8-12, 2026. In conjunction with strategic partner E4 Computer Engineering, they will share more details on their upcoming Thunderbird(TM)"supercomputer cluster-on-a-chip" accelerated computing platform. InspireSemi and E4 Computer Engineering have been collaborating to bring leading-edge HPC-AI technologies based on the open standard RISC-V instruction set architecture (ISA) to the European market. The combined focus has been on optimizing workload performance while delivering best-in-class energy efficiency and the lowest Total Cost of Ownership (TCO). InspireSemi and E4 have worked side-by-side for the last four years to refine the specs of the all-CPU Thunderbird compute accelerator. Each Thunderbird chip has a remarkable 1,536 64-bit CPU cores, all supporting the double precision math that most HPC applications require (i.e.- native FP64). These are InspireSemi-designed high performance, low power, superscalar RISC-V CPU cores, all interconnected by an innovative, patent-pending, low latency on-chip network fabric. Thunderbird was designed from the beginning to support an open software stack, including the ability to run Linux, Zephyr RTOS, and support the OpenMP offload model. Initial deployments planned for Q4 2026 will be Thunderbird PCIe server-class add-in cards with 4 devices, delivering a remarkable 6,144 CPU cores each. That is the equivalent of an entire rack of x86 servers, greatly reducing cost, power, cooling, complexity, and points of failure. E4 has been preparing for Thunderbird PCIe server-class add-in cards at the system-level targeting their innovative servers designed to scale to the needs of compute-demanding HPC & AI customers. E4 is planning to integrate Thunderbird in its product line and deliver Thunderbird-powered servers and is a strategic InspireSemi go to market partner. In addition to delivering on this, the companies will continue to collaborate on their mutual roadmaps to continue to deliver on the best HPC-AI solution, including future mixed-precision workloads. About InspireSemi InspireSemi provides revolutionary high-performance, energy-efficient accelerated computing solutions for High-Performance Computing (HPC), AI, graph analytics, and other compute-intensive workloads. The Thunderbird I 'supercomputer-cluster-on-a-chip' is a disruptive, next-generation datacenter accelerator designed to address multiple underserved and diversified industries, including financial services, computer-aided engineering, energy, climate modeling, cybersecurity, and life sciences & drug discovery. Based on the open standard RISC-V instruction set architecture, InspireSemi's solutions set new standards of performance, energy efficiency, and ease of programming. InspireSemi is headquartered in Austin, TX. About E4 Computer Engineering E4 Computer Engineering is a strategic partner in the development of HPC, AI, Big Data and Quantum Computing solutions for both the academic sector and innovation-driven businesses. With over 20 years' experience, a robust ecosystem of partnerships and multidisciplinary R&D, the company designs, integrates and supports end-to-end solutions. Based in Emilia's Data Valley but with a strong focus on international markets, E4 collaborates with leading European centres and participates in EU projects centred on next-generation technologies. Cautionary Statement on Forward-Looking Information This press release contains certain statements that constitute forward-looking information within the meaning of applicable securities laws ("forward-looking statements"). Statements concerning InspireSemi's objectives, goals, strategies, priorities, intentions, plans, beliefs, expectations and estimates, and the business, operations, financial performance and condition of InspireSemi are forward-looking statements. Often, but not always, forward-looking information can be identified by the use of words such as "plans", "expects", "is expected", "budget", "scheduled", "estimates", "forecasts", "intends", "anticipates", or "believes" or variations (including negative variations) of such words and phrases, or statements formed in the future tense or indicating that certain actions, events or results "may", "could", "would", "might" or "will" (or other variations of the forgoing) be taken, occur, be achieved, or come to pass. Forward-looking information includes, but is not limited to, information regarding the Delisting and any future listing. Forward-looking information is based on currently available competitive, financial and economic data and operating plans, strategies or beliefs as of the date of this presentation, but involve known and unknown risks, uncertainties, assumptions and other factors that may cause the actual results, performance or achievements of InspireSemi, to be materially different from any future results, performance or achievements expressed or implied by the forward-looking information. Such factors may be based on information currently available to the Company including information obtained from third-party industry analysts and other third-party sources and are based on management's current expectations or beliefs. Any and all forward-looking information contained in this news release is expressly qualified by this cautionary statement. Investors are cautioned that forward-looking information is not based on historical facts but instead reflect management's expectations, estimates or projections concerning future results or events based on the opinions, assumptions and estimates of management considered reasonable at the date the statements are made. Forward-looking information reflects management's current beliefs and is based on information currently available to them and on assumptions they believe to be not unreasonable in light of all of the circumstances. There can be no assurance that forward-looking information will prove to be accurate, as actual results and future events could differ materially from those anticipated in such statements. Accordingly, readers should not place undue reliance on forward-looking information. Should assumptions underlying the forward-looking information prove incorrect, actual results may vary materially from those described herein as intended, planned, anticipated, believed, estimated or expected. Although the Company has attempted to identify important risks, uncertainties and factors which could cause actual results to differ materially, there may be others that cause results not to be as anticipated, estimated or intended. The Company does not intend, and does not assume any obligation, to update this forward-looking information except as otherwise required by applicable law. Legal Disclaimer: EIN Presswire provides this news content "as is" without warranty of any kind. Military Industry Today do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.

Thunder Compute, a cloud-GPU platform for AI and machine learning workloads, has raised $4.5 million in seed funding led by Matrix Partners. Y Combinator, Avesta Fund, Preston-Werner Ventures, CyberAgent Capital, Transpose Platform and Amino Capital also participated. The startup offers access to GPU instances for AI training, fine-tuning and inference, positioning itself as a software-driven alternative to traditional hardware providers. Thunder Compute claims to offer the cheapest on-demand A100 and H100 GPUs on the market, with instances scalable up to eight GPUs, 144 vCPUs and 720GB of RAM. The platform integrates with VS Code and Cursor, provides pre-configured PyCharm environments and offers CLI tools and API endpoints for workflow automation. The funding will support platform expansion and broader customer access.

Community Engagement Platform. Founded in 2021 by Bhavesh Khandelwal and Rahul Khanna, Thunderpod has 12 employees based in Mumbai, Maharashtra, India.