78 citations · 184 across the 24 of their papers we have counts for
26 papers
FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration
Geraldo F. Oliveira, Arash Tavakkol, Xiangyu Zhu +10
LLM inference is increasingly constrained by accelerator memory capacity rather than compute throughput. This constraint is especially acute in single-accelerator and small-node in…
At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference
Bowen Wang, Chi Zhang, Diyou Shen +3
Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models. In the…
RTLScout: Joint Agentic Code and Synthesis Optimization for Efficient Digital Circuits
Felix Arnold, Ryan Amaudruz, Dimitrios Tsaras +2
We present RTLScout, an autonomous system that combines LLM-driven agentic design with logic synthesis optimization and arithmetic architecture selection. An LLM agent iteratively…
FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Large Attention-Based Model Inference on Tile-Based Accelerators
Chi Zhang, Luca Colagrande, Renzo Andri +1
Attention accounts for an increasingly dominant fraction of total computation during inference for mixture-of-experts (MoE) models, making efficient acceleration critical. Emerging…
GenPairX: A Hardware-Algorithm Co-Designed Accelerator for Paired-End Read Mapping
Julien Eudine, Chu Li, Zhuo Cheng +11
Genome sequencing has become a central focus in computational biology. A genome study typically begins with sequencing, which produces millions to billions of short DNA fragments k…
Explicit Sign-Magnitude Encoders Enable Power-Efficient Multipliers
Felix Arnold, Maxence Bouvier, Ryan Amaudruz +2
This work presents a method to maximize power-efficiency of fixed point multiplier units by decomposing them into sub-components. First, an encoder block converts the operands from…
Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization
Giuseppe Ruggeri, Renzo Andri, Daniele Jahier Pagliari +1
Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck i…
GENIAL: Generative Design Space Exploration via Network Inversion for Low Power Algorithmic Logic Units
Maxence Bouvier, Ryan Amaudruz, Felix Arnold +2
As AI workloads proliferate, optimizing arithmetic units is becoming increasingly important for reducing the footprint of digital systems. Conventional design flows, which often re…
FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
Chi Zhang, Luca Colagrande, Renzo Andri +6
Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of…
The Art of Beating the Odds with Predictor-Guided Random Design Space Exploration
Felix Arnold, Maxence Bouvier, Ryan Amaudruz +2
This work introduces an innovative method for improving combinational digital circuits through random exploration in MIG-based synthesis. High-quality circuits are crucial for perf…
Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding
Konstantin Berestizshevsky, Renzo Andri, Lukas Cavigelli
We present Top-Theta (Top-) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be…
Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication
Jannis Schönleber, Lukas Cavigelli, Matteo Perotti +2
Artificial intelligence has surged in recent years, with advancements in machine learning rapidly impacting nearly every area of life. However, the growing complexity of these mode…
Ara2: Exploring Single- and Multi-Core Vector Processing with an Efficient RVV 1.0 Compliant Open-Source Processor
Matteo Perotti, Matheus Cavalcante, Renzo Andri +2
Vector processing is highly effective in boosting processor performance and efficiency for data-parallel workloads. In this paper, we present Ara2, the first fully open-source vect…
Flex-SFU: Accelerating DNN Activation Functions by Non-Uniform Piecewise Approximation
Enrico Reggiani, Renzo Andri, Lukas Cavigelli
Modern DNN workloads increasingly rely on activation functions consisting of computationally complex operations. This poses a challenge to current accelerators optimized for convol…
MemPool: A Scalable Manycore Architecture with a Low-Latency Shared L1 Memory
Samuel Riedel, Matheus Cavalcante, Renzo Andri +1
Shared L1 memory clusters are a common architectural pattern (e.g., in GPGPUs) for building efficient and flexible multi-processing-element (PE) engines. However, it is a common be…
Empowering Data Centers for Next Generation Trusted Computing
Aritra Dhar, Supraja Sridhara, Shweta Shinde +2
Modern data centers have grown beyond CPU nodes to provide domain-specific accelerators such as GPUs and FPGAs to their customers. From a security standpoint, cloud customers want…
A "New Ara" for Vector Computing: An Open Source Highly Efficient RISC-V V 1.0 Vector Processor Design
Matteo Perotti, Matheus Cavalcante, Nils Wistoff +3
Vector architectures are gaining traction for highly efficient processing of data-parallel workloads, driven by all major ISAs (RISC-V, Arm, Intel), and boosted by landmark chips,…
Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile
Renzo Andri, Beatrice Bussolino, Antonio Cipolletta +2
Most of today's computer vision pipelines are built around deep neural networks, where convolution operations require most of the generally high compute effort. The Winograd convol…
Identifying and Exploiting Sparse Branch Correlations for Optimizing Branch Prediction
Anastasios Zouzias, Kleovoulos Kalaitzidis, Konstantin Berestizshevsky +3
Branch prediction is arguably one of the most important speculative mechanisms within a high-performance processor architecture. A common approach to improve branch prediction accu…
Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
Gianmarco Cerutti, Lukas Cavigelli, Renzo Andri +3
Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or direct…
Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices
Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli +3
Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in te…
ChewBaccaNN: A Flexible 223 TOPS/W BNN Accelerator
Renzo Andri, Geethan Karunaratne, Lukas Cavigelli +1
Binary Neural Networks enable smart IoT devices, as they significantly reduce the required memory footprint and computational complexity while retaining a high network performance…
Extending the RISC-V ISA for Efficient RNN-based 5G Radio Resource Management
Renzo Andri, Tomas Henriksson, Luca Benini
Radio Resource Management (RRM) in 5G mobile communication is a challenging problem for which Recurrent Neural Networks (RNN) have shown promising results. Accelerating the compute…
Hyperdrive: A Multi-Chip Systolically Scalable Binary-Weight CNN Inference Engine
Renzo Andri, Lukas Cavigelli, Davide Rossi +1
Deep neural networks have achieved impressive results in computer vision and machine learning. Unfortunately, state-of-the-art networks are extremely compute and memory intensive w…