Startup AI Chip Passes Road Test
X86 vet revamps ISA for machine learning
Rick Merritt, EETimes
8/13/2018 01:01 AM EDT
SAN JOSE, Calif. — A startup will sample before June a 13W machine-learning accelerator for cars, robots and drones said to handily beat Nvidia GPUs in recognizing images. Visteon is considering using the chip in future automotive systems based on test results on an FPGA version of the device.
AlphaICs designed an instruction set architecture (ISA) optimized for deep learning, reinforcement learning and other machine learning tasks. The startup aims to produce a family of chips with 16-256 cores, roughly spanning 2W to 200W.
E-mail This Article | Printer-Friendly Page |
Related News
- PCIe Eyes Road Ahead with AI, Automotive
- SEMIFIVE announces commercialization of its 5nm HPC SoC Platform with lead partner Rebellions, AI Chipmaker startup based in Korea
- Networking Chip Startup Enfabrica Emerges from Stealth Mode to Solve Scalability and Price-Performance Challenges for AI Growth in Cloud
- Spectral Design & Test Announces AI/ML Based Breakthrough Technology to Do Fast and Accurate Characterization & Validate Memory Compilers
- Startup AiM Future Set to Commercialize LG's AI IP
Breaking News
- AiM Future Brings GenAI Applications to Mainstream Consumer Devices
- Axiomise Names Two Executives to Newly Formed Technical Advisory Board
- GDDR7 Adds Headroom to Meet AI Pressures
- Esperanto Technologies and Rapidus Partner to Enable More Energy-Efficient Designs for the Coming "Post GPU Era"
- Actions Technology's smart watch SoC adopted VeriSilicon's 2.5D GPU IP
Most Popular
- GDDR7 Adds Headroom to Meet AI Pressures
- Actions Technology's smart watch SoC adopted VeriSilicon's 2.5D GPU IP
- Digital Core Design in cooperation with DCD-SEMI Unveils DCAN-XL: Revolutionary CAN XL IP Core Bridging the Gap Between CAN FD and Ethernet
- New Automotive Grade Linux Platform Release Adds Cloud-Native Functionality, RISC-V Architecture and Flutter-Based Applications
- Kevin O'Buckley to Lead Foundry Services at Intel