Meet us at TPC25 in San Jose, CA July 28-31, 2025

The Trillion Parameter Consortium’s 2025 all-hands conference and exhibition

Learn more and register

Existing HPC, AI, and graph analytics compute solutions are no longer “good enough”.  

They are expensive, hard to program, power hungry, and only work for limited applications.

The Third Wave of Accelerated Computing is Here

Thunderbird for HPC, AI, Graph Analytics

First wave of accelerated computing, math coprocessor
Second wave of accelerated computing, NVIDIA, AMD, GPU, proprietary
Third wave of accelerated computing, InspireSemi Thunderbird, Open, RISC-V

Accelerating the datacenter HPC-AI market

Providing the “ground truth” for AI in science & engineering

InspireSemi Thunderbird value proposition., Four pillars are: All CPU architecture/all 64-bit native, very high core count, low latency/high bandwidth mesh network, and best in class energy efficiency

  • Versatile all-CPU architecture applicable to all HPC-AI software, much of which does not benefit from GPUs

  • High precision, high performance, low power 64-bit native processors to solve “big math” problems required by most HPC software

Workflow - Thunderbird runs the highly accurate physics-based HPC simulations needed to train AI surrogate models for science and engineering.<br /> GPUs run fast AI surrogate models to approximate long-running physics-based HPC simulations

  • Thunderbird runs the highly accurate physics-based HPC simulations needed to train AI surrogate models for science and engineering

  • GPUs run fast AI surrogate models to approximate long-running physics-based HPC simulations

GAME CHANGING TECHNOLOGY

Addressing the need to accelerate All HPC-AI software

What customers always wanted…not “yet another GPU”

Addressing the Need to Accelerate All HPC & AI Software. Thousands of CPUs instead of GPUs or FPGAs

Thunderbird Datacenter Impact

Significant datacenter TCO savings and carbon footprint reduction

One Thunderbird board has more CPU cores than an entire rack of standard Intel or AMD severs!

  • Lower cost: less real estate, servers, networking, power, cooling
  • Less complexity, interconnects, points of failure
Supercomputer cluster of 8 racks of x86 servers, replaced by one server with 8 Thunderbird compute accelerator boards

Thunderbird has >20X CPU cores vs. Intel or AMD server chips

  • Intel and AMD CPUs: Up to 256 general purpose x86 cores per server board
  • Thunderbird: 6,144 high-performance / low-power RISC-V cores per add-in board (all 64-bit)
One server with 8 Thunderbird compute accelerator boards replacing supercomputer cluster of 8 racks of x86 servers
Learn more

MISSION

About Us

Setting New standards of performance, energy efficiency, versatility, and ease of programming

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 “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, and life sciences & drug discovery.  Based on the open standard RISC-V instruction set architecture, InspireSemi’s solutions leverage an established and thriving software ecosystem.

Download More Information

Solution Overview

InspireSemi one page solution overview handout

Executive Summary

Company Overview Presentation

Investor overview title page July2025

Innovate with InspireSemi

Contact us to learn more about partnership opportunities
CONTACT US