ConvNext is a Winner!
On Chimera QC Ultra it runs 28x faster than DSP+NPU
ConvNext is one of today’s leading new ML networks. Frankly, it just doesn’t run on most NPUs. So if your AI/ML solution relies on an NPU plus DSP for fallback, you can bet ConvNext needs to run on that DSP as a fallback operation. Our tests of expected performance on a DSP + NPU is dismal – less than one inference per second trying to run the ConvNext backbone if the novel Operators – GeLu and LayerNorm – are not present in the hardwired NPU accelerator and instead those Ops ran on the largest and most powerful DSP core on the market today.
This poor performance makes most of today’s DSP + NPU silicon solutions obsolete. Because that NPU is hardwired, not programmable, new networks cannot efficiently be run.
To read the full article, click here
Related Semiconductor IP
- Over-Voltage Lockout (OVLO) IP
- Verification IP for Universal Chiplet Interconnect Express (UCIe) up to 3.0
- UCIe-S (Gen2) Compatible PHY for Standard Package (x16) in TSMC N3P, North/South Orientation
- DSP-Based 112G SerDes
- XTAL oscillator in TSMC-7nm
Latest Blogs
- M31 High-Speed and Long-Channel MIPI C/D-PHY Solution on TSMC N3P/N3C
- Understanding security certification and how analog IP can help
- Embedded Security explained: Secure boot for embedded systems
- World's First Standards-Compliant 112G PHY IP for Linear Optics: A Turning Point for AI Interconnects
- One Key for Every Door: How Aliro Extends the UWB Digital Key Beyond the Car