RISC-V-based AI IP development for enhanced training and inference
Flex Logix Boosts AI Accelerator Performance and Long-Term Efficiency
Embedded FPGA (eFPGA) can reduced memory bandwidth requirements by more than 10x and allows efficient execution of future operators and activation functions
MOUNTAIN VIEW, Calif. – July 2, 2024 – Flex Logix® Technologies, Inc., the leading supplier of embedded FPGA (eFPGA) IP and reconfigurable DSP/SDR/AI solutions, today announced additional applications for embedded FPGA to improve the value proposition for AI Accelerators.
First, memory bandwidth – the scarcest resource in AI Accelerators, especially in the cloud, where model weights/parameters exceed 100 billion and HBM memory is expensive and scarce. Techniques for saving memory bandwidth are evolving faster than hardware.
“Embedded FPGA (eFPGA) can enable innovations in sub-INT4 data and weight representations (e.g. ternary, 2 bit, 3 bit, mixed or mat-mul free) to be converted on the fly by eFPGA into existing TPUs,” said Cheng Wang, Flex Logix CTO & SVP Software + Architecture. “This can also be mixed with innovations in sparsity that can further reduce the memory bandwidth requirements. Aggregate memory bandwidth reduction can be up to 16x.”
Second, higher performance. AI models are rapidly evolving. With most TPUs, new operators and activation functions must be handled by a much slower processor. eFPGA can be used to run the new operators and activation functions at much higher performance.
Flex Logix is already using these concepts in its own InferX AI optimized for edge vision AI models and DSP.
Get more information on EFLX eFPGA and a block diagram of weight memory reduction at www.flex-logix.com.
About Flex Logix
Flex Logix is a reconfigurable computing company providing leading edge eFPGA, DSP/SDR and AI Inference solutions for semiconductor and systems companies. Flex Logix eFPGA enables volume FPGA users to integrate the FPGA into their companion SoC, resulting in a 5-10x reduction in the cost and power of the FPGA and increasing compute density which is critical for communications, networking, data centers, microcontrollers and others. Its scalable DSP/SDR/AI is the most efficient, providing much higher inference throughput per square millimeter and per watt. Flex Logix supports process nodes from 180nm to 7nm, with 5nm, 3nm and 18A in development. Flex Logix is headquartered in Mountain View, California and has an office in Austin, Texas. For more information, visit https://flex-logix.com.
|
Flex Logix Technologies, Inc. Hot IP
Related News
- Flex Logix Pairs its InferX X1 AI Inference Accelerator with the High-Bandwidth Winbond 4Gb LPDDR4X Chip to Set a New Benchmark in Edge AI Performance
- Flex Logix Improves Deep Learning Performance By 10X With New EFLX4K AI eFPGA Core
- Flex Logix's EFLX Embedded FPGA Accelerates Processor Performance By 40-100X
- Fundamental Inventions Enable the Best PPA and Most Portable eFPGA/DSP/SDR/AI IP for Adaptable SoCs
- Flex Logix Announces InferX™ High Performance IP for DSP and AI Inference
Breaking News
- September foundry sales: a tale of differing fortunes
- Exclusive Interview: Antti Rauhala Discusses CoreHW's CHW3021 Radio Front-End IC
- SEMIFIVE Extends Partnership with Arm to Advance AI and HPC SoC Platforms
- DisplayPort Rx PHY and Controller IP Cores in multiple Leading Technology Nodes for Next-Generation Video SoCs
- SEMIFIVE Concluded Mass Production Contract for AI Chip with HyperAccel
Most Popular
- Intel, TSMC to detail 2nm processes at IEDM
- Crypto Quantique teams up with Attopsemi to simplify the implementation of PUF technology in MCUs and SoCs
- Efabless Unveils New Custom Chip Platform Designed for Edge ML Products
- Faraday and Kiwimoore Succeed in 2.5D Packaging Project for Mass Production
- SensiML Expands Platform Support to Include the RISC-V Architecture
E-mail This Article | Printer-Friendly Page |