Aaron Zhao

Haoran Wu, Can Xiao, Jiayi Nie et al.

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused inference. They often involve much longer context lengths to capture complex and prolonged inputs, such as an entire webpage DOM or complicated tool-call trajectories. This, in turn, generates significant off-chip memory traffic during inference and causes workloads to be constrained by two memory walls, namely the bandwidth wall and the capacity wall, preventing compute units from achieving high utilization. In this paper, we introduce PLENA, a hardware-software co-designed system built around three core optimization pathways. PLENA features a novel flattened systolic-array architecture (Pathway 1) and efficient compute and memory units that support an asymmetric quantization scheme (Pathway 2). It also provides native support for FlashAttention (Pathway 3). In addition, PLENA includes a complete software-hardware stack, consisting of a custom ISA, a compiler, a transaction-level simulator, and an automated design-space exploration flow. Experimental results show that PLENA delivers up to 2.23x and 4.70x higher throughput than the A100 GPU and TPU v6e, respectively, under identical multiplier counts and memory configurations during LLaMA agentic inference. PLENA also achieves up to 4.04x higher energy efficiency than the A100 GPU. The full PLENA system, including its simulator, compiler, ISA, and RTL implementation, will be open-sourced to the research community.

Haoran Wu, Zeyu Cao, Yao Lai et al. · cambridge, tsinghua

Emerging agentic LLM workloads are driving rapidly growing demand on both memory capacity and bandwidth, with different phases of inference (e.g., prefill and decode) imposing distinct requirements. Industry is responding by composing heterogeneous accelerators into single interconnected systems, as exemplified by NVIDIA's Vera Rubin platform, where each device brings its own memory architecture. This heterogeneity is further compounded by a widening landscape of available memory technologies: high-density on-chip SRAM, HBM, LPDDR, GDDR, and emerging options such as high-bandwidth flash (HBF), each offering different capacity, bandwidth, and power trade-offs. Identifying the right memory architecture for next-generation inference accelerators requires navigating a vast and rapidly evolving design space, in which the interplay between workload characteristics, NPU design dimensions, and memory system design remains largely underexplored. To address this challenge, we present MemExplorer, a new memory system synthesizer for heterogeneous NPU systems. MemExplorer provides a unified abstraction for modeling diverse memory technologies across different hierarchy levels (e.g., on-chip and off-chip) and automatically determines an efficient heterogeneous memory system together with NPU design choices (e.g., matrix engine size) to balance throughput and power between prefilling and decoding devices in a multi-device NPU system. Experimental results show that, under the same power budget for agentic workloads, MemExplorer achieves up to 2.3x higher energy efficiency than the baseline NPU and 3.23x higher than H100 in the prefill-only setting. Under equivalent performance targets in the decode setting, it further delivers up to 1.93x and 2.72x higher power efficiency over the baseline NPU and H100, respectively.

Binglei Lou, Haoran Wu, Yao Lai et al.

Diffusion Large Language Models (dLLMs) introduce iterative denoising to enable parallel token generation, but their sampling phase displays fundamentally different characteristics compared to GEMM-centric transformer layers. Profiling on modern GPUs reveals that sampling can account for up to 70% of total model inference latency-primarily due to substantial memory loads and writes from vocabulary-wide logits, reduction-based token selection, and iterative masked updates. These processes demand large on-chip SRAM and involve irregular memory accesses that conventional NPUs struggle to handle efficiently. To address this, we identify a set of critical instructions that an NPU architecture must specifically optimize for dLLM sampling. Our design employs lightweight non-GEMM vector primitives, in-place memory reuse strategies, and a decoupled mixed-precision memory hierarchy. Together, these optimizations deliver up to a 2.53x speedup over the NVIDIA RTX A6000 GPU under an equivalent nm technology node. We also open-source our cycle-accurate simulation and post-synthesis RTL verification code, confirming functional equivalence with current dLLM PyTorch implementations.

Xiaoke Wang, Batuhan Altundas, Zhaoxin Li et al.

Mixed Integer Linear Programs (MILPs) are essential tools for solving planning and scheduling problems across critical industries such as construction, manufacturing, and logistics. However, their widespread adoption is limited by long computational times, especially in large-scale, real-time scenarios. To address this, we present a learning-based framework that leverages Behavior Cloning (BC) and Reinforcement Learning (RL) to train Graph Neural Networks (GNNs), producing high-quality initial solutions for warm-starting MILP solvers in Multi-Agent Task Allocation and Scheduling Problems. Experimental results demonstrate that our method reduces optimization time and variance compared to traditional techniques while maintaining solution quality and feasibility.