AI Software Startup Moreh Partners with AI Semiconductor Company Tenstorrent to Challenge NVIDIA in AI Data Center Market
Joint R&D of AI data center solutions by integrating tenstorrent's semiconductors with Moreh's software; Targeting NVIDIA dominant datacenter market with top-notch performance solutions
November 15, 2024 -- Moreh, an AI software company led by CEO Gangwon Jo, has established a strategic partnership with Tenstorrent, an AI semiconductor company led by world's top processor semiconductor expert Jim Keller, to start developing AI solutions for data centers.
Over the past two years, the two companies have been engaged in various collaborative discussions and joint R&D efforts. To further formalize their partnership, CEO Gangwon Jo and CEO Jim Keller signed an MOU at Moreh’s Seoul headquarters on the 4th of this month.
This partnership outlines plans to integrate Moreh's software with Tenstorrent’s AI semiconductors (NPUs) to target the AI data center market, which has been rapidly expanding since the emergence of large language models (LLMs). Tenstorrent, led by Jim Keller—a renowned expert in processors for his work on CPUs and AI processors at AMD, Tesla, and Apple—focuses on developing innovative next-generation AI hardware and CPUs. Moreh, founded by researchers who spent over 10 years studying supercomputer software at Seoul National University's Computer Science department, possesses unique experience and capabilities in parallel processing SW, particularly in combining multiple GPUs and NPUs. The solution that combines Tenstorrent’s NPU and Moreh’s software will support a wide range of AI applications, not only simple inference but also large language models (LLMs) training. This solution is expected to be commercialized by the first half of 2025, and through this venture, the two companies are going to enter the global AI data center market, currently dominated by NVIDIA.
Moreh CEO Gangwon Jo stated, "To compete with NVIDIA, we need to innovate both AI semiconductors and software comprehensively. We are pleased to collaborate with Tenstorrent, which has an innovative architecture suitable for the LLM era. By combining our software with Tenstorrent's AI semiconductors, we aim to fundamentally transform the AI data center landscape."
“Moreh has a great software team that will bring new capabilities to the data center,” said Jim Keller, CEO of Tenstorrent. “Moreh challenged us to build better software and APIs, we look forward to working together on AI software.”
|
Related News
- Achronix Releases Groundbreaking Speedster AC7t800 Mid-Range FPGA, Driving Innovation in AI/ML, 5G/6G and Data Center Applications
- Avery Design Partners with S2C to Bring PCIe 6.0 and LPDDR5 and HBM3 Speed Adapters to FPGA prototyping solutions for Data Center and AI/ML SoC Validation
- Moving AI Processing to the Edge Will Shake Up the Semiconductor Industry
- Rambus Enhances Data Center and AI Protection with Next-Gen CryptoManager Security IP Solutions
- BOS and Tenstorrent Unveil Eagle-N, Industry's First Automotive AI Accelerator Chiplet SoC
Breaking News
- Silicon Proven AV1 Decoder IP with support for 12-bit pixel size and 4:4:4 Chroma Sub-Sampling Released by Allegro DVT
- Cadence Enables Next-Gen AI and HPC Systems with Industry's Fastest HBM4 12.8Gbps IP Memory System Solution
- S2C and Andes Technology Announce FPGA-Based Prototyping Partnership to Accelerate Advanced RISC-V SoC Development
- PQShield launches UltraPQ-Suite for deeply specialized implementations of post-quantum cryptography
- Andes Technology and Imagination Technologies Showcase Android 15 on High-Performance RISC-V Based Platform
Most Popular
- Certus Semiconductor Joins TSMC IP Alliance Program to Enhance Custom I/O and ESD Solutions
- Cadence to Acquire Arm Artisan Foundation IP Business
- Siemens to accelerate customer time to market with advanced silicon IP through new Alphawave Semi partnership
- New Breakthroughs in China's RISC-V Chip Industry
- Ceva Neural Processing Unit IP for Edge AI Selected by Nextchip for Next-Generation ADAS Solutions
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |