OpenAI Reportedly to Finalize In-House AI Chip Design Soon, Set for TSMC’s 3nm Production
Trendforce (February 12, 2025)
OpenAI, the maker of ChatGPT, is set to finalize its first in-house AI chip design in the coming months, taking a key step toward reducing its reliance on NVIDIA. According to Reuters, the company is expected to send the chips to TSMC for fabrication soon as it aims for mass production in 2026.
Notably, the report suggests that TSMC is producing OpenAI’s AI chip on its 3nm process, featuring a systolic array, HBM, and strong networking—similar to NVIDIA’s design.
To read the full article, click here
Related Semiconductor IP
- 1.6T Ultra Ethernet Controller
- Chiplet Die-to-Die Interconnect IP Solution
- High speed MACsec Engine 100G/200G/400G/800G/1.6T
- Temperature/Voltage sensors
- AMBA Bus Host to eSPI Controller/Target
Related News
- Unveiling the Availability of Industry's First Silicon-Proven 3nm, 24Gbps UCIe™ IP Subsystem with TSMC CoWoS® Technology
- Chips&Media Secures Access to TSMC 3nm Library
- GUC Announces Successful Launch of Industry's First 32G UCIe Silicon on TSMC 3nm and CoWoS Technology
- Analog Bits to Demonstrate IP Portfolio on TSMC 3nm and 2nm Processes at TSMC 2025 Technology Symposium
Latest News
- Alliance for Open Media Releases AV2 Codec, Advancing Next-Generation Open Video Coding
- VeriSilicon Drives Commercial Adoption of AV2 Across Next-Generation Video and Streaming Applications
- Cadence Announces Collaboration with Intel Foundry to Accelerate Intel 14A Process Optimization for HPC and Mobile Designs
- Menta and Presto Engineering Announce Strategic Collaboration to Accelerate Adaptive ASIC Architectures with Embedded FPGA Technology
- MIPI A-PHY To Power Industry’s First Four-Company Automotive SerDes Interoperability Demonstration at AutoSens USA