NeuReality Boosts AI Acelerator Utilization With NAPU
By Sally Ward-Foxton, EETimes (April 4, 2024)
Startup NeuReality wants to replace the host CPU in data center AI inference systems with dedicated silicon that can cut total cost of ownership and power consumption. The Israeli startup developed a class of chip it calls the network addressable processing unit (NAPU), which includes hardware implementations for typical CPU functions like the hypervisor. NeuReality’s aim is to increase AI accelerator utilization by removing bottlenecks caused by today’s host CPUs.
NeuReality CEO Moshe Tanach told EE Times its NAPU enables 100% utilization of AI accelerators.
To read the full article, click here
Related Semiconductor IP
- Verification IP for C-PHY
- Band-Gap Voltage Reference with dual 2µA Current Source - X-FAB XT018
- 250nA-88μA Current Reference - X-FAB XT018-0.18μm BCD-on-SOI CMOS
- UCIe D2D Adapter & PHY Integrated IP
- Low Dropout (LDO) Regulator
Related News
- Israeli AI Chip Startup Raises Seed Funding
- NeuReality unveils novel AI-centric platform to empower the growth of real-life AI applications
- IBM and NeuReality team up to build the next generation of AI inference platforms
- Samsung Ventures invests in Israeli AI systems and semiconductor company NeuReality
Latest News
- JEDEC Advances DDR5 MRDIMM Ecosystem with New Memory Interface Logic and Expanded MRDIMM Roadmap
- Altera Brings Determinism to Physical AI Systems with Latest Release of FPGA AI Suite
- Mosaic SoC raises $3.8M to bring real-time spatial intelligence to every consumer device
- UMC Reports First Quarter 2026 Results
- Rambus Appoints Sumeet Gagneja as Chief Financial Officer