Paper
Research
SafeTI Traffic Injector Enhancement for Effective Interference Testing in Critical Real-Time Systems
Abstract
Safety-critical systems utilizing powerful multicores must rigorously validate mutual interference arising from shared hardware resources. This paper introduces significant enhancements to the SafeTI traffic injector, including internal pipelining for higher-rate injection and
Research
Envisioning a Safety Island to Enable HPC Devices in Safety-Critical Domains
Abstract
High Performance Computing (HPC) devices are increasingly required for autonomous systems, yet they often lack adequate, standardized support for safety-critical operations. This paper proposes a novel 'Safety Island' concept designed
Research
Towards a RISC-V Open Platform for Next-generation Automotive ECUs
Abstract
This paper presents a mixed-criticality, multi-OS architecture designed for next-generation automotive Electronic Control Units (ECUs) based on open hardware and open-source technologies. The heterogeneous platform utilizes a RISC-V processor running safety-critical AUTOSAR
Research
A 3 TOPS/W RISC-V Parallel Cluster for Inference of Fine-Grain Mixed-Precision Quantized Neural Networks
Abstract
This work introduces Flex-V, a novel RISC-V parallel cluster designed for highly energy-efficient inference of fine-grain mixed-precision Quantized Neural Networks (QNNs) in demanding IoT environments. The architecture integrates custom fused Mac&
Research
A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms
Abstract
This comprehensive survey categorizes the recent evolution of Deep Learning (DL) hardware accelerators essential for fulfilling the demanding performance requirements of High-Performance Computing (HPC) applications. It thoroughly reviews established platforms, including GPUs,
Research
Pushing the Limits of Machine Design: Automated CPU Design with AI
Abstract
This paper presents a novel AI approach that autonomously designs an industrial-scale Central Processing Unit (CPU) solely from external input-output observations, navigating an unprecedented search space of $10^{10^{540}}$. Using a