Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis

High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called ``kernel'') and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To stably train the hierarchical MoE, we further propose a two-stage training method. Extensive experiments verify the effectiveness of the hierarchical MoE.

Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference

Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a promising solution, leveraging a smaller auxiliary model to draft future tokens, which are then validated simultaneously by the larger model, achieving a speed-up of 1-2x. Although speculative decoding matches the same distribution as multinomial sampling, multinomial sampling itself is prone to suboptimal outputs, whereas beam sampling is widely recognized for producing higher-quality results by maintaining multiple candidate sequences at each step. This paper explores the novel integration of speculative decoding with beam sampling. However, there are four key challenges: (1) how to generate multiple sequences from the larger model's distribution given drafts sequences from the small model; (2) how to dynamically optimize the number of beams to balance efficiency and accuracy; (3) how to efficiently verify the multiple drafts in parallel; and (4) how to address the extra memory costs inherent in beam sampling. To address these challenges, we propose dynamic-width speculative beam decoding (DSBD). Specifically, we first introduce a novel draft and verification scheme that generates multiple sequences following the large model's distribution based on beam sampling trajectories from the small model. Then, we introduce an adaptive mechanism to dynamically tune the number of beams based on the context, optimizing efficiency and effectiveness. Besides, we extend tree-based parallel verification to handle multiple trees simultaneously, accelerating the verification process. Finally, we illustrate a simple modification to our algorithm to mitigate the memory overhead of beam sampling...

Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review

Large Language Model (LLM) pretraining traditionally relies on autoregressive language modeling on randomly sampled data blocks from web-scale datasets. We take inspiration from human learning techniques like spaced repetition to hypothesize that random data sampling for LLMs leads to high training cost and low quality models which tend to forget data. In order to effectively commit web-scale information to long-term memory, we propose the LFR (Learn, Focus, and Review) pedagogy, a new dynamic training paradigm which focuses and repeatedly reviews complex data blocks at systematic intervals based on the model's learning pace and progress. LFR records the model perplexities for different data blocks and frequently revisits blocks with higher perplexity which are more likely to be forgotten. We pretrain the GPT-2 models (124M - 1.5B) from scratch on the OpenWebText dataset using LFR. We test on downstream tasks from the language modeling, question answering, translation, and problem solving domains to achieve consistently lower perplexity and higher accuracy than the baseline OpenAI models, while obtaining a 20x pretraining speed-up.

Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference

Transformer-based Large language models (LLMs) have demonstrated their power in various tasks, but their inference incurs significant time and energy costs. To accelerate LLM inference, speculative decoding uses a smaller model to propose one sequence of tokens, which are subsequently validated in batch by the target large model. Compared with autoregressive decoding, speculative decoding generates the same number of tokens with fewer runs of the large model, hence accelerating the overall inference by $1$-$2\times$. However, greedy decoding is not the optimal decoding algorithm in terms of output perplexity, which is a direct measurement of the effectiveness of a decoding algorithm. An algorithm that has better output perplexity and even better efficiency than speculative decoding can be more useful in practice. To achieve this seemingly contradictory goal, we first introduce multi-token joint greedy decoding (MJGD), which greedily generates multiple tokens at each step based on their joint perplexity. We show that it leads to better perplexity for the whole output. But the computation cost of MJGD is infeasible in practice. So we further propose multi-token joint speculative decoding (MJSD), which approximates and accelerates the MJGD from two aspects: it approximates the joint distribution of the large model with that of a small model, and uses a verification step to guarantee the accuracy of approximation; then it uses beam decoding to accelerate the sequence generation from the joint distribution. Compared with vanilla speculative decoding, MJSD has two advantages: (1) it is an approximation of MJGD, thus achieving better output perplexity; (2) verification with joint likelihood allows it to accept the longest prefix sub-sequence of the draft tokens with valid perplexity, leading to better efficiency...

Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis

In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers use high-level synthesis (HLS) to compile a high-level description written in C/C++ into a design with low-level hardware description languages that eventually synthesize DSAs on circuits. However, creating a high-quality HLS design still demands significant domain knowledge, particularly in microarchitecture decisions expressed as \textit{pragmas}. Thus, it is desirable to automate such decisions with the help of machine learning for predicting the quality of HLS designs, requiring a deeper understanding of the program that consists of original code and pragmas. Naturally, these programs can be considered as sequence data. In addition, these programs can be compiled and converted into a control data flow graph (CDFG). But existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results show that ProgSG reduces the RMSE of design performance predictions by up to $22\%$, and identifies designs with an average of $1.10\times$ and $1.26\times$ (up to $8.17\times$ and $13.31\times$) performance improvement in design space exploration (DSE) task compared to HARP and AutoDSE, respectively.

HMT: Hierarchical Memory Transformer for Long Context Language Processing

Transformer-based large language models (LLM) have been widely used in language processing applications. However, most of them restrict the context window that permits the model to attend to every token in the inputs. Previous works in recurrent models can memorize past tokens to enable unlimited context and maintain effectiveness. However, they have "flat" memory architectures, which have limitations in selecting and filtering information. Since humans are good at learning and self-adjustment, we speculate that imitating brain memory hierarchy is beneficial for model memorization. We propose the Hierarchical Memory Transformer (HMT), a novel framework that enables and improves models' long-context processing ability by imitating human memorization behavior. Leveraging memory-augmented segment-level recurrence, we organize the memory hierarchy by preserving tokens from early input token segments, passing memory embeddings along the sequence, and recalling relevant information from history. Evaluating general language modeling (Wikitext-103, PG-19) and question-answering tasks (PubMedQA), we show that HMT steadily improves the long-context processing ability of context-constrained and long-context models. With an additional 0.5% - 2% of parameters, HMT can easily plug in and augment future LLMs to handle long context effectively. Our code is open-sourced on Github: https://github.com/OswaldHe/HMT-pytorch.

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware

Graph neural networks (GNNs) are emerging for machine learning research on graph-structured data. GNNs achieve state-of-the-art performance on many tasks, but they face scalability challenges when it comes to real-world applications that have numerous data and strict latency requirements. Many studies have been conducted on how to accelerate GNNs in an effort to address these challenges. These acceleration techniques touch on various aspects of the GNN pipeline, from smart training and inference algorithms to efficient systems and customized hardware. As the amount of research on GNN acceleration has grown rapidly, there lacks a systematic treatment to provide a unified view and address the complexity of relevant works. In this survey, we provide a taxonomy of GNN acceleration, review the existing approaches, and suggest future research directions. Our taxonomic treatment of GNN acceleration connects the existing works and sets the stage for further development in this area.

ProgSG: Cross-Modality Representation Learning for Programs in Electronic Design Automation

Recent years have witnessed the growing popularity of domain-specific accelerators (DSAs), such as Google's TPUs, for accelerating various applications such as deep learning, search, autonomous driving, etc. To facilitate DSA designs, high-level synthesis (HLS) is used, which allows a developer to compile a high-level description in the form of software code in C and C++ into a design in low-level hardware description languages (such as VHDL or Verilog) and eventually synthesized into a DSA on an ASIC (application-specific integrated circuit) or FPGA (field-programmable gate arrays). However, existing HLS tools still require microarchitecture decisions, expressed in terms of pragmas (such as directives for parallelization and pipelining). To enable more people to design DSAs, it is desirable to automate such decisions with the help of deep learning for predicting the quality of HLS designs. This requires us a deeper understanding of the program, which is a combination of original code and pragmas. Naturally, these programs can be considered as sequence data, for which large language models (LLM) can help. In addition, these programs can be compiled and converted into a control data flow graph (CDFG), and the compiler also provides fine-grained alignment between the code tokens and the CDFG nodes. However, existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG allowing the source code sequence modality and the graph modalities to interact with each other in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results on two benchmark datasets show the superiority of ProgSG over baseline methods that either only consider one modality or combine the two without utilizing the alignment information.

FPGA-Based In-Vivo Calcium Image Decoding for Closed-Loop Feedback Applications

The miniaturized calcium imaging is an emerging neural recording technique that can monitor neural activity at large scale at a specific brain region of a rat or mice. It has been widely used in the study of brain functions in experimental neuroscientific research. Most calcium-image analysis pipelines operate offline, which incurs long processing latency thus are hard to be used for closed-loop feedback stimulation targeting certain neural circuits. In this paper, we propose our FPGA-based design that enables real-time calcium image processing and position decoding for closed-loop feedback applications. Our design can perform real-time calcium image motion correction, enhancement, and fast trace extraction based on predefined cell contours and tiles. With that, we evaluated a variety of machine learning methods to decode positions from the extracted traces. Our proposed design and implementation can achieve position decoding with less than 1 ms latency under 300 MHz on FPGA for a variety of mainstream 1-photon miniscope sensors. We benchmarked the position decoding accuracy on open-sourced datasets collected from six different rats, and we show that by taking advantage of the ordinal encoding in the decoding task, we can consistently improve decoding accuracy without any overhead on hardware implementation and runtime across the subjects.

Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks

High-level synthesis (HLS) has freed the computer architects from developing their designs in a very low-level language and needing to exactly specify how the data should be transferred in register-level. With the help of HLS, the hardware designers must describe only a high-level behavioral flow of the design. Despite this, it still can take weeks to develop a high-performance architecture mainly because there are many design choices at a higher level that requires more time to explore. It also takes several minutes to hours to get feedback from the HLS tool on the quality of each design candidate. In this paper, we propose to solve this problem by modeling the HLS tool with a graph neural network (GNN) that is trained to be used for a wide range of applications. The experimental results demonstrate that by employing the GNN-based model, we are able to estimate the quality of design in milliseconds with high accuracy which can help us search through the solution space very quickly.