RSA-ECC Public Key Accelerator Engine, 2K ops/sec, DPA Resistant
aiMotive ships first aiWare4 NPU production RTL
Budapest, Hungary -- June 2, 2022 – aiMotive, one of the world's leading modular automated driving technology suppliers, announced today that it has shipped final production-validated RTL of the latest generation of its ultra-high efficiency NPU aiWare4 to lead customers. The latest aiWare4 RTL shipped delivers up to 5x the performance of the previous generation aiWare3 NPUs, while using less than 2x the silicon area. This demonstrates the exceptional scalability, PPA and performance per mm2 of aiWare4, while extending the feature set and operational “sweet spot” for high-efficiency CNN acceleration.
“Our aiWare team has relentlessly refined our production validation processes to enable us to deliver customer configurations at record speed to full automotive quality for aiWare4,” says Márton Fehér, SVP hardware engineering at aiMotive. “Thanks to our sophisticated wavefront processing making full use of our new WFRAM technology, plus many other architectural advances from aiWare3, we have been able to achieve exceptional PPA for our lead customers without compromising our leadership in high-efficiency execution up to 95% of the most demanding automotive inference CNN workloads”.
Ad |
4-/8-bit mixed-precision NPU IP Deep Neural Network Programmable Accelerator AI accelerator (NPU) IP - 32 to 128 TOPS |
To achieve extremely demanding PPA constraints from customers, aiMotive was able to fine-tune the exact feature set of the aiWare4 production RTL to best meet customers’ requirements. Making full use of the physical tile-based layout and dataflow methodologies, the aiWare team demonstrated clock speeds for the production RTL of up to 1.3GHz over the full automotive AEC-Q100 Grade 2 temperature range on a 14nm process. The aiWare4 hardware IP has been assessed externally as suitable for certification to ASIL-B or higher as an SEooC.
The aiWare4 NPU scales from 1 to 256 TOPS and is supported by an exceptionally comprehensive SDK featuring highly accurate offline performance estimation, enabling customers to accurately estimate and fine-tune their CNN workloads to within 5% of final silicon performance prior to first silicon.
aiWare4 hardware IP is available now for licensing.
|
AImotive Hot IP
Related News
- aiMotive achieves an industry first milestone with ISO26262 ASIL B certification for aiWare4 NPU IP
- Latest aiWare4+ automotive NPU brings enhanced programmability, flexibility and scalability while retaining highest efficiency
- AImotive launches aiWare4, featuring advanced wavefront processing, upgraded safety and low-power features
- Nextchip licenses aiMotive's aiWare4 for their Apache6 automotive domain processor
- AImotive's latest aiWare3P delivers superior NN acceleration for production L2-L3 automotive AI
Breaking News
- Is Graphcore Deal Finally About to Close?
- Frontgrade Gaisler Leads the Way in RISC-V Processor Development for Space Applications
- NEO Semiconductor Reveals a Performance Boosting Floating Body Cell Mechanism for 3D X-DRAM during IEEE IMW 2024
- TSMC April 2024 Revenue Report
- lowRISC Deploys Real Intent Ascent Lint, Meridian CDC, & Meridian RDC for OpenTitan Project
Most Popular
- Arm revenues up 47%; shares fall
- X-Silicon Announces a NEW Low-Power Open-Standard Vulkan-Enabled C-GPU™ - a RISC-V Vector CPU Infused with GPU ISA and AI/ML acceleration in a Single Processor Core
- Softbank reported to be in talks to buy Graphcore
- Siemens delivers end-to-end silicon quality assurance for next-generation IC designs with new Solido IP Validation Suite
- Ceva, Inc. Announces First Quarter 2024 Financial Results
E-mail This Article | Printer-Friendly Page |