A Survey of fault mitigation techniques for multi-core architectures

Shashikiran Venkatesha; Ranjani Parthasarathi

Home/Archive/arXiv

arXiv · 2112.14952

A Survey of fault mitigation techniques for multi-core architectures

Shashikiran Venkatesha·Ranjani Parthasarathi

View original source ↗Read source document ↗Export metadata ↓

Abstract

Fault tolerance in multi-core architecture has attracted attention of research community for the past 20 years. Rapid improvements in the CMOS technology resulted in exponential growth of transistor density. It resulted in increased challenges for designing resilient multi-core architecture at the same pace. The article presents a survey of fault tolerant methods like fault detection, recovery, re-configurability and repair techniques for multi-core architectures. Salvaging at micro-architectural and architectural level are also discussed. Gamut of fault tolerant approaches discussed in this article have tangible improvements on the reliability of the multi-core architectures. Every concept in the seminal articles is examined with respect to relevant metrics like performance cost, area overhead, fault coverage, level of protection, detection latency and Mean Time To Failure. The existing literature is critically examined. New research directions in the form of new fault tolerant design alternatives for both homogeneous and heterogeneous multi-core architectures are presented. Brief on an analytical approach for fault tolerating model is suggested for Intel and AMD based modern homogeneous multi-core architecture are presented to enhance the understanding of the readers about the architecture with respect to performance degradation, memory access time and execution time.

Explore related subjects

cs.AR

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Shashikiran Venkatesha, Ranjani Parthasarathi. 2021-12-30. A Survey of fault mitigation techniques for multi-core architectures. https://arxiv.org/abs/2112.14952

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Bi-SamplerZ: A Rejection-Aware Cooperative Gaussian Sampling Framework for Falcon Signature Hardware

We present Bi-SamplerZ, a rejection-aware cooperative sampling framework that converts this idle capacity into useful computation. After an asymmetric accept/reject outcome, Bi- SamplerZ latches the completed logical result and dynamically reassigns the released physical datapath to the unfinished target. The two paths then evaluate fresh independent candidates for the same remaining distribution. We show that this post-rejection cooperation increases the assisted-round completion probability without modifying the underlying candidate distribution or Bernoulli acceptance rule, and we state the randomness-allocation conditions required to preserve the joint output distribution of the original pair of logical sampler calls

cs.AR↗

arXiv2026

A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators

Mixture-of-Experts (MoE) decoding on scratchpad-based tensor accelerators (STA) is dominated by moving expert weights while the compute engines sit idle. This traffic is hard to hide, because the experts are known only after routing, and hard to shrink without losing quality or adding critical-path work. We present CARDAN, which represents each expert-weight matrix as a vector-quantized component plus a shared-basis low-rank component and co-designs this representation with a multi-engine decoding dataflow. The representation separates expert-common from expert-private work, so the dataflow overlaps DMA with computation on several engines. Across five MoE families on AWS Trainium3, CARDAN matches or improves BF16-teacher perplexity across all five models and speeds up batch-one decoding by 1.15-1.31x over AWS dense MoE megakernels, rising to 1.7x at batch size 16.

cs.AR↗

arXiv2026

Dissecting How Die Scaling Breaks GPU Fine-grained Scheduling

Modern GPUs are no longer physically symmetric. Die scaling leads to both manufacturing-driven floorsweeping and cache and memory partitioning. The former creates chip-specific compute topologies, while the latter causes non-uniform memory access. These asymmetries are substantial. Topology-oblivious compute unit allocation can lead to up to 1.33x performance variation, while remote accesses increase HBM latency by up to 67% and nearly double L2 latency. However, these asymmetries are hidden behind the GPU's logical resource abstractions and can vary across chips. We develop lightweight characterization methods to uncover per-chip compute topology and memory affinity. We then use the discovered information to make existing fine-grained scheduling asymmetry-aware, considering not only how many resources are allocated but also which physical resources are assigned. Across full-GPU kernel execution, intra-application multiplexing, and inter-application co-location, asymmetry-aware scheduling improves mainstream kernels by up to 1.22x, multiplexed LLM inference by up to 14.3%, and avoids up to 1.33x performance variation.

cs.AR↗