arXiv subjects

Niansong Zhang

Publications and source records attributed to Niansong Zhang.

9 recordsLinked to original sources

arXiv2026

From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level Synthesis

The rise of large language models has sparked interest in AI-driven hardware design, raising the question: does high-level synthesis (HLS) still matter in the agentic era? We argue that HLS remains essential. While we expect mature agentic hardware systems to leverage both HLS and RTL, this paper focuses on HLS and its role in enabling agentic optimization. HLS offers faster iteration cycles, portability, and design permutability that make it a natural layer for agentic optimization. This position paper makes three contributions. First, we explain why HLS serves as a practical abstraction layer and a golden reference for agentic hardware design. Second, we identify key limitations of current HLS tools, namely inadequate performance feedback, rigid interfaces, and limited debuggability that agents are uniquely positioned to address. Third, we propose a taxonomy for the symbiotic evolution of agentic HLS, clarifying how responsibility shifts from human designers to AI agents as systems advance from copilots to autonomous design partners.

cs.CL↗

arXiv2025

From Loop Nests to Silicon: Mapping AI Workloads onto AMD NPUs with MLIR-AIR

General-purpose compilers abstract away parallelism, locality, and synchronization, limiting their effectiveness on modern spatial architectures. As modern computing architectures increasingly rely on fine-grained control over data movement, execution order, and compute placement for performance, compiler infrastructure must provide explicit mechanisms for orchestrating compute and data to fully exploit such architectures. We introduce MLIR-AIR, a novel, open-source compiler stack built on MLIR that bridges the semantic gap between high-level workloads and fine-grained spatial architectures such as AMD's NPUs. MLIR-AIR defines the AIR dialect, which provides structured representations for asynchronous and hierarchical operations across compute and memory resources. AIR primitives allow the compiler to orchestrate spatial scheduling, distribute computation across hardware regions, and overlap communication with computation without relying on ad hoc runtime coordination or manual scheduling. We demonstrate MLIR-AIR's capabilities through two case studies: matrix multiplication and the multi-head attention block from the LLaMA 2 model. For matrix multiplication, MLIR-AIR achieves up to 78.7% compute efficiency and generates implementations with performance almost identical to state-of-the-art, hand-optimized matrix multiplication written using the lower-level, close-to-metal MLIR-AIE framework. For multi-head attention, we demonstrate that the AIR interface supports fused implementations using approximately 150 lines of code, enabling tractable expression of complex workloads with efficient mapping to spatial hardware. MLIR-AIR transforms high-level structured control flow into spatial programs that efficiently utilize the compute fabric and memory hierarchy of an NPU, leveraging asynchronous execution, tiling, and communication overlap through compiler-managed scheduling.

cs.CL↗

arXiv2025

Dato: A Task-Based Programming Model for Dataflow Accelerators

Recent deep learning workloads increasingly push computational demand beyond what current memory systems can sustain, with many kernels stalling on data movement rather than computation. While modern dataflow accelerators incorporate on-chip streaming to mitigate off-chip bandwidth limitations, existing programming models struggle to harness these capabilities effectively. Low-level interfaces provide fine-grained control but impose significant development overhead, whereas high-level tile-based languages abstract away communication details, restricting optimization and forcing compilers to reconstruct the intended dataflow. We present Dato, a Python-embedded, task-based programming model for dataflow accelerators that elevates data communication and sharding to first-class type constructs. Developers write programs as a graph of tasks connected via explicit stream types, with sharded inputs specified using layout types. These tasks are first mapped virtually onto the accelerator's spatial fabric, and the compiler then generates a physical mapping that respects hardware constraints. Experimental results on both AMD Ryzen AI NPU and Alveo FPGA devices demonstrate that Dato achieves high performance while significantly reducing the burden of writing optimized code. On the NPU, Dato attains up to 84% hardware utilization for GEMM and delivers a 2.81x speedup on attention kernels compared to a state-of-the-art commercial framework. On the FPGA, Dato surpasses leading frameworks in performance when generating custom systolic arrays, achieving 98% of the theoretical peak performance.

cs.PL↗

arXiv2025

Characterizing and Optimizing Realistic Workloads on a Commercial Compute-in-SRAM Device

Compute-in-SRAM architectures offer a promising approach to achieving higher performance and energy efficiency across a range of data-intensive applications. However, prior evaluations have largely relied on simulators or small prototypes, limiting the understanding of their real-world potential. In this work, we present a comprehensive performance and energy characterization of a commercial compute-in-SRAM device, the GSI APU, under realistic workloads. We compare the GSI APU against established architectures, including CPUs and GPUs, to quantify its energy efficiency and performance potential. We introduce an analytical framework for general-purpose compute-in-SRAM devices that reveals fundamental optimization principles by modeling performance trade-offs, thereby guiding program optimizations. Exploiting the fine-grained parallelism of tightly integrated memory-compute architectures requires careful data management. We address this by proposing three optimizations: communication-aware reduction mapping, coalesced DMA, and broadcast-friendly data layouts. When applied to retrieval-augmented generation (RAG) over large corpora (10GB--200GB), these optimizations enable our compute-in-SRAM system to accelerate retrieval by 4.8$\times$--6.6$\times$ over an optimized CPU baseline, improving end-to-end RAG latency by 1.1$\times$--1.8$\times$. The shared off-chip memory bandwidth is modeled using a simulated HBM, while all other components are measured on the real compute-in-SRAM device. Critically, this system matches the performance of an NVIDIA A6000 GPU for RAG while being significantly more energy-efficient (54.4$\times$-117.9$\times$ reduction). These findings validate the viability of compute-in-SRAM for complex, real-world applications and provide guidance for advancing the technology.

cs.AR↗

arXiv2024

Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that reuse hardware units for different network layers and operators. However, these methods often encounter challenges in achieving low latency due to considerable memory access overhead. This paper investigates the feasibility and potential of model-specific spatial acceleration for LLM inference on FPGAs. Our approach involves the specialization of distinct hardware units for specific operators or layers, facilitating direct communication between them through a dataflow architecture while minimizing off-chip memory accesses. We introduce a comprehensive analytical model for estimating the performance of a spatial LLM accelerator, taking into account the on-chip compute and memory resources available on an FPGA. Through our analysis, we can determine the scenarios in which FPGA-based spatial acceleration can outperform its GPU-based counterpart. To enable more productive implementations of an LLM model on FPGAs, we further provide a library of high-level synthesis (HLS) kernels that are composable and reusable. This library will be made available as open-source. To validate the effectiveness of both our analytical model and HLS library, we have implemented BERT and GPT2 on an AMD Alveo U280 FPGA device. Experimental results demonstrate our approach can achieve up to 13.4x speedup when compared to previous FPGA-based accelerators for the BERT model. For GPT generative inference, we attain a 2.2x speedup compared to DFX, an FPGA overlay, in the prefill stage, while achieving a 1.9x speedup and a 5.7x improvement in energy efficiency compared to the NVIDIA A100 GPU in the decode stage.

cs.LG↗

arXiv2024

Allo: A Programming Model for Composable Accelerator Design

Special-purpose hardware accelerators are increasingly pivotal for sustaining performance improvements in emerging applications, especially as the benefits of technology scaling continue to diminish. However, designers currently lack effective tools and methodologies to construct complex, high-performance accelerator architectures in a productive manner. Existing high-level synthesis (HLS) tools often require intrusive source-level changes to attain satisfactory quality of results. Despite the introduction of several new accelerator design languages (ADLs) aiming to enhance or replace HLS, their advantages are more evident in relatively simple applications with a single kernel. Existing ADLs prove less effective for realistic hierarchical designs with multiple kernels, even if the design hierarchy is flattened. In this paper, we introduce Allo, a composable programming model for efficient spatial accelerator design. Allo decouples hardware customizations, including compute, memory, communication, and data type from algorithm specification, and encapsulates them as a set of customization primitives. Allo preserves the hierarchical structure of an input program by combining customizations from different functions in a bottom-up, type-safe manner. This approach facilitates holistic optimizations that span across function boundaries. We conduct comprehensive experiments on commonly-used HLS benchmarks and several realistic deep learning models. Our evaluation shows that Allo can outperform state-of-the-art HLS tools and ADLs on all test cases in the PolyBench. For the GPT2 model, the inference latency of the Allo generated accelerator is 1.7x faster than the NVIDIA A100 GPU with 5.4x higher energy efficiency, demonstrating the capability of Allo to handle large-scale designs.

cs.PL↗

arXiv2022

CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance

Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training techniques. When applying to 3D tasks, the irregular data structure and limited data scale add to the difficulty of transformer's application. We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers. On the one hand, we propose the codebook-based attention that projects an attention space into its subspace represented by the combination of "prototypes" in a learnable codebook. It regularizes attention learning and improves generalization. On the other hand, we propose geometry-aware self-attention that utilizes geometric information (geometric pattern, density) to guide attention learning. CodedVTR could be embedded into existing sparse convolution-based methods, and bring consistent performance improvements for indoor and outdoor 3D semantic segmentation tasks

cs.CV↗

arXiv2020

aw_nas: A Modularized and Extensible NAS framework

Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner. aw_nas is an open-source Python framework implementing various NAS algorithms in a modularized manner. Currently, aw_nas can be used to reproduce the results of mainstream NAS algorithms of various types. Also, due to the modularized design, one can simply experiment with different NAS algorithms for various applications with awnas (e.g., classification, detection, text modeling, fault tolerance, adversarial robustness, hardware efficiency, and etc.). Codes and documentation are available at https://github.com/walkerning/aw_nas.

cs.NE↗

arXiv2020

RapidLayout: Fast Hard Block Placement of FPGA-optimized Systolic Arrays using Evolutionary Algorithms

Evolutionary algorithms can outperform conventional placement algorithms such as simulated annealing, analytical placement as well as manual placement on metrics such as runtime, wirelength, pipelining cost, and clock frequency when mapping FPGA hard block intensive designs such as systolic arrays on Xilinx UltraScale+ FPGAs. For certain hard-block intensive, systolic array accelerator designs, the commercial-grade Xilinx Vivado CAD tool is unable to provide a legal routing solution without tedious manual placement constraints. Instead, we formulate an automatic FPGA placement algorithm for these hard blocks as a multi-objective optimization problem that targets wirelength squared and maximum bounding box size metrics. We build an end-to-end placement and routing flow called RapidLayout using the Xilinx RapidWright framework. RapidLayout runs 5-6$\times$ faster than Vivado with manual constraints and eliminates the weeks-long effort to generate placement constraints manually for the hard blocks. We also perform automated post-placement pipelining of the long wires inside each convolution block to target 650MHz URAM-limited operation. RapidLayout outperforms (1) the simulated annealer in VPR by 33% in runtime, 1.9-2.4$\times$ in wirelength, and 3-4$\times$ in bounding box size, while also (2) beating the analytical placer UTPlaceF by 9.3$\times$ in runtime, 1.8-2.2$\times$ in wirelength, and 2-2.7$\times$ in bounding box size. We employ transfer learning from a base FPGA device to speed-up placement optimization for similar FPGA devices in the UltraScale+ family by 11-14$\times$ than learning the placements from scratch.

cs.AR↗