PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
December 10, 2025Electronics3 citationsOpen Access

Workload-Dependent Vulnerability of SDRAM Multi-Bit Upsets in a LEON3 Soft-Core Processor

View Full Paper
AKAfef KchaouSSSehmi SaadHGHatem Garrab

Key Points

  • Examine how workload characteristics influence vulnerability to multi-bit upsets in SDRAM within an embedded processor.
  • Conducted fault injection study using FPGA targeting SDRAM in LEON3 processor.
  • Injected over 300,000 dual-bit multi-bit upsets across three workloads: FFT, matrix multiplication, AES.
  • Analyzed effects of workload semantics on fault detectability and processor vulnerability.
  • Found that workload characteristics significantly influenced multi-bit upset manifestation.
  • Memory-intensive workloads showed high detectability of faults, while AES demonstrated intrinsic masking.
  • Processor vulnerability is affected by memory access patterns and control flow regularity.

Abstract

Multi-bit upsets (MBUs) are a growing reliability threat in high-density SDRAM, particularly in radiation-prone embedded systems. This paper presents a large-scale FPGA-based fault injection (FI) study targeting external SDRAM in a cache-enabled LEON3 SPARC V8 processor, with over 300,000 dual-bit MBUs injected across three diverse workloads: Fast Fourier transform (FFT), matrix multiplication (MulMatrix), and advanced encryption standard (AES). Our results reveal a profound dependence of MBU manifestation on application semantics: memory-intensive benchmarks (FFT, MulMatrix) exhibit high fault detectability through data store and access exceptions, while the AES workload demonstrates exceptional intrinsic masking, with the vast majority of MBUs producing no observable effect. These results demonstrate that processor vulnerability to MBUs is not uniform but fundamentally shaped by workload characteristics, including memory access patterns, control flow regularity, and algorithmic redundancy. The study provides a hardware-validated foundation for designing workload-aware fault tolerance strategies in space-grade and safety-critical embedded platforms.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Kchaou et al. (2025) studied this question.

synapsesocial.com/papers/69401b3d2d562116f28f827fhttps://doi.org/10.3390/electronics14244852
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Overview on Radiation Damage Effects and Protection Techniques in Microelectronic Devices2024 · 44 citations
  2. 2Data Center Silent Data Errors: Implications to Artificial Intelligence Workloads & Mitigations2024 · 17 citations
  3. 3Emulation-Based Analysis of Multiple Cell Upsets in LEON3 SDRAM: A Workload-Dependent Vulnerability Study2025 · 4 citations
  4. 4A Survey of Fault-Tolerance Techniques for Embedded Systems From the Perspective of Power, Energy, and Thermal Issues2022 · 69 citations
  5. 5Impact of Scaling on Neutron-Induced Soft Error in SRAMs From a 250 nm to a 22 nm Design Rule2010 · 504 citations