arXiv subjects

Mehdi Saligane

Publications and source records attributed to Mehdi Saligane.

9 recordsLinked to original sources

arXiv2026

CircuitsDNA: Discovering Unconventional Multi-Accuracy Arithmetic Circuits via Evolutionary Synthesis

Emerging edge AI workloads increasingly require arithmetic units that can trade computational accuracy for efficiency on demand. However, existing approximate arithmetic circuits are typically fixed-accuracy or rely on predefined structures for runtime configurability. This work introduces CircuitsDNA, an evolutionary framework that automatically evolves accuracy-configurable arithmetic circuits supporting multiple accuracy modes within a single circuit. It integrates three key features: 1) multi-threshold verifiability miter to enforce mode-specific accuracy requirements, 2) resource-limited verifiability-driven search to reduce verification overhead without sacrificing correctness, enabling efficient exploration of large circuit design, and 3) feedback-driven adaptive mutation to prioritize effective structural modifications and accelerate search convergence. Experimental results show that the 8-bit multiplier variants synthesized in 28-nm CMOS reduce the area-power product by up to 56% on INT8 DNN workload and 93% under exhaustive activity, compared with an exact 8-bit multiplier. Across CNNs and DeiTs, the accuracy loss relative to FP32 remains below 2% after fine-tuning under worst-case error (WCE) budgets of at most 1%. CircuitsDNA eliminates all search stalls observed in conventional methods across 8/12/16-bit multipliers, while adaptive mutation provides up to 1.33 times faster convergence than its non-adaptive counterpart.

cs.NE↗

arXiv2026

SILK: Closing the Time-of-Check-to-Time-of-Use Gap in RoT-Protected AI Systems

Root-of-trust (RoT) authentication verifies a DNN model at load time, but weights may subsequently traverse DRAM, DMA, interconnect, and prefetch paths before reaching the compute engine. Post-verification tampering along this path can therefore alter the weights actually consumed while leaving the authenticated model image unchanged, creating a time-of-check-to-time-of-use (TOCTOU) integrity gap. We present SILK (Streaming Inline Lightweight Keying), an in-place integrity mechanism that verifies the weight stream at the final pre-compute boundary. SILK repurposes quantized-weight LSBs as secret-keyed integrity bits and chains dependencies across weight bytes, so a local modification perturbs multiple integrity checks. A lightweight streaming checker recomputes these checks without separate authentication tags and uses commit gating to prevent unverified weights from reaching computation. Under a secure pseudorandom function (PRF), the forgery probability decreases exponentially with the number of affected checks, and measured miss rates closely track the analytical bound. SILK detects every stream-modifying instance in our functional attack suite. For INT8, it limits quality loss to at most 0.76 pp across evaluated CNNs and 0.17 perplexity across eight LLMs, while INT4 and MXFP4 provide a configurable security-quality tradeoff through check sparsity. On a Xilinx ZCU102, the synthesized reference pipelined implementation sustains 756 MB/s at only 1.00% of the equivalent area cost of a Caliptra 2.x RoT, while a configuration with a conservative per-attempt forgery bound of 2^-128 still sustains 678 MB/s at 6.15% of the RoT cost.

cs.CR↗

arXiv2026

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference

Microscaling (MX) is now the standard for low-bit large language model (LLM) inference. Its 4-bit form MXFP4 still loses substantial accuracy, because existing MX formats fix either the element format or the precision-recovery scheme across blocks, and thus capture only limited quantization heterogeneity. Quantization heterogeneity appears at two levels: 1) across blocks, the preferred element format and precision-recovery scheme vary; 2) across operands, weights and activations require different encoding. We introduce AdaMX (Adaptive Microscaling), a heterogeneity-aware format and accelerator. It selects the precision-recovery scheme per block and the representation per operand, at no increase in equivalent bit width (EBW). One design covers two block sizes, giving a higher-accuracy operating point and a lower-EBW operating point that saves storage. We implement a 22nm FD-SOI AI accelerator prototype with the proposed decoder, computing unit, and quantization logic. Against an otherwise identical MXFP4 accelerator with FP4-only multipliers, AdaMX adds about 1% system energy. At the lower-EBW point, AdaMX stays more accurate than the baseline while lowering both memory footprint and energy. Across LLMs from 3B to 70B, AdaMX removes 83% of the MXFP4 accuracy loss on commonsense and 82% on MMLU, and 43% and 27% of the NVFP4 loss. AdaMX also generalizes to multimodal models. On Gemma-4 12B, it leads MXFP4 on all four vision-language benchmarks and keeps up to 96% of FP16 accuracy.

cs.AR↗

arXiv2026

CryoZip: An Efficient Cryogenic Compressor for Quantum Error Correction Syndromes

Scaling fault tolerant quantum computing is increasingly constrained by the limited bandwidth and power budget across the 4 K to room temperature (RT) interface. We present CryoZip, a cross stack cryogenic compression framework that cooperates with a lightweight cryogenic quantum error correction (QEC) predecoder to reduce 4 K to RT syndrome transmission under realistic, circuit level noise. CryoZip targets sparse syndrome vectors with a sliding window compression architecture sized under strict decoding latency constraints to maximize energy efficiency. We implement and evaluate the design in 22 nm FDSOI characterized at 4 K, using vector based power, performance, and area analysis to obtain realistic hardware data. CryoZip achieves up to 48x compression, 1.8x higher than state of the art compressors, across various QEC codes while delivering 4 to 26x energy savings. When paired with a QEC predecoder, it yields over 14,238x bandwidth reduction, while energy savings rise to 42x when accounting for realistic QEC interface overheads.

quant-ph↗

arXiv2026

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal budgets that make architectural choice and accelerator-specific cost central to efficient inference. We present LLMForge, a hardware-aware neural architecture search (NAS) framework whose three composable contributions together make edge-LM architecture search hardware-conditioned, since different substrates impose different hardware cost bottlenecks. Infinite-Head Attention (IHA) decouples the number of query heads, KV groups, and per-head query/key and value dimensions, expanding the feasible per-layer attention configuration space by approximately 400x over grouped-query attention within our search-space ranges. Forge-Former, an encoder-based surrogate for ranking architectural candidates, outperforms MLP and random-forest baselines. Forge-DSE, an NSGA-II-based design-space-exploration engine, pairs Forge-Former with a multi-backend hardware cost model spanning GPUs, systolic accelerators, and ring-dataflow edge accelerators. Across four different hardware substrates, the searches converge to visibly different architectures whose shapes track each substrate's cost bottleneck. On the multi-chip ring substrate, our co-search returns three 300M-scale deployment-aware variants on the Pareto front. Each is re-trained on FineWeb-Edu-10BT under matched recipe against SmolLM2-360M and Qwen-0.5B architecture baselines. The accurate variant has the lowest validation loss 2.798 and competitive benchmark performance with fewer parameters, the energy-optimized variant lowers energy per token by 40%, and the latency-optimized variant lowers TTFT and TPOT by 43%.

cs.LG↗

arXiv2026

Mitigating Classical Resource Costs in Quantum Error Correction via Generalized qLDPC Predecoding

Large-scale fault-tolerant quantum computing (FTQC) will require quantum-classical interfaces (QCIs) that orchestrate real-time decoding over thousands to millions of logical qubits simultaneously. To scale FTQC systems, complex decoding resources must be shared between logical qubits, creating resource contention bottlenecks in the QCI. Mitigating this contention via optimal resource allocation remains an open problem. Lightweight predecoding techniques can reduce decoder utilization and average latency, both of which ease contention for shared decoding resources. To date, both decoder allocation and predecoding work is limited to the surface code. As focus shifts towards general qLDPC codes, slower decoding exacerbates resource contention, while code complexity precludes manual predecoder design. To address this gap, we introduce an automated framework designed to generate predecoders for arbitrary qLDPC codes. By independently handling up to 99.98% of the decoding workload, these predecoders reduce decoder utilization up to 4,090$\times$, including up to 81.19% decrease in expensive OSD post-processing and 59.96% decrease in extra RelayBP legs. An efficient, pipelined hardware architecture enables simultaneous decoding of ~1,800 BB code logical qubits on a single FPGA, while cryogenic ASIC implementation supports ~50,000-500,000 BB code logical qubits within a 1.5 W power budget at 4 K.

quant-ph↗

arXiv2025

Pinball: A Cryogenic Predecoder for Surface Code Decoding Under Circuit-Level Noise

Scaling fault tolerant quantum computers, especially cryogenic systems based on the surface code, to millions of qubits is challenging due to poorly-scaling data processing and power consumption overheads. One key hurdle is the design of real-time quantum error correction (QEC) decoders, which demands high data rates for error processing; this is particularly apparent in systems with cryogenic qubits and room temperature (RT) decoders. In response, cryogenic predecoding using lightweight logic has been proposed to handle sparse errors in the cryogenic domain. However, prior work only accounts for a subset of error sources in real-world quantum systems with limited accuracy, often degrading performance below useful levels in practical scenarios. Moreover, prior reliance on SFQ logic precludes detailed architecture-technology co-optimization. To address these limitations, this paper introduces Pinball, a comprehensive design in cryogenic CMOS of a QEC predecoder for the surface code tailored to realistic, circuit-level noise. By accounting for error generation and propagation through QEC circuits, our design achieves higher predecoding accuracy, outperforming logical error rates (LER) of the current state-of-the-art (SOTA) cryogenic predecoder by nearly six orders of magnitude. Remarkably, despite operating under much stricter power and area constraints, Pinball also reduces LER by 32.58x and 5x, respectively, compared to SOTA RT predecoder and RT ensemble configurations. By increasing cryogenic coverage, we also reduce syndrome bandwidth up to 3780.72x. Through co-design with 4 K-characterized 22nm FDSOI technology, we achieve peak power consumption under 0.56 mW. Voltage/frequency scaling and body biasing enable 22.2x lower typical power consumption, yielding up to 67.4x total energy savings. Assuming a 1.5 W 4 K power budget, our predecoder supports up to 2,668 logical qubits at d=21.

quant-ph↗

arXiv2024

ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters

The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains challenging due to the extensive use of Softmax in self-attention. In addition to the non-linearity, the low arithmetic intensity significantly limits processing parallelism, especially when working with longer contexts. To address this challenge, we propose Constant Softmax (ConSmax), a software-hardware co-design that serves as an efficient alternative to Softmax. ConSmax utilizes differentiable normalization parameters to eliminate the need for maximum searching and denominator summation in Softmax. This approach enables extensive parallelization while still executing the essential functions of Softmax. Moreover, a scalable ConSmax hardware design with a bitwidth-split look-up table (LUT) can achieve lossless non-linear operations and support mixed-precision computing. Experimental results show that ConSmax achieves a minuscule power consumption of 0.2mW and an area of 0.0008mm^2 at 1250MHz working frequency in 16nm FinFET technology. For open-source contribution, we further implement our design with the OpenROAD toolchain under SkyWater's 130nm CMOS technology. The corresponding power is 2.69mW and the area is 0.007mm^2. ConSmax achieves 3.35x power savings and 2.75x area savings in 16nm technology, and 3.15x power savings and 4.14x area savings with the open-source EDA toolchain. In the meantime, it also maintains comparable accuracy on the GPT-2 model and the WikiText103 dataset. The project is available at https://github.com/ReaLLMASIC/ConSmax

cs.AR↗

arXiv2024

Quantum Circuit Simulation with Fast Tensor Decision Diagram

Quantum circuit simulation is a challenging computational problem crucial for quantum computing research and development. The predominant approaches in this area center on tensor networks, prized for their better concurrency and less computation than methods using full quantum vectors and matrices. However, even with the advantages, array-based tensors can have significant redundancy. We present a novel open-source framework that harnesses tensor decision diagrams to eliminate overheads and achieve significant speedups over prior approaches. On average, it delivers a speedup of 37$\times$ over Google's TensorNetwork library on redundancy-rich circuits, and 25$\times$ and 144$\times$ over quantum multi-valued decision diagram and prior tensor decision diagram implementation, respectively, on Google random quantum circuits. To achieve this, we introduce a new linear-complexity rank simplification algorithm, Tetris, and edge-centric data structures for recursive tensor decision diagram operations. Additionally, we explore the efficacy of tensor network contraction ordering and optimizations from binary decision diagrams.

quant-ph↗