Milad Hashemi

Alexander Shypula, Aman Madaan, Yimeng Zeng et al. · cmu

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the semantics of code. Simultaneously, pretrained large language models (LLMs) have demonstrated strong capabilities at solving a wide range of programming tasks. To that end, we introduce a framework for adapting LLMs to high-level program optimization. First, we curate a dataset of performance-improving edits made by human programmers of over 77,000 competitive C++ programming submission pairs, accompanied by extensive unit tests. A major challenge is the significant variability of measuring performance on commodity hardware, which can lead to spurious "improvements." To isolate and reliably evaluate the impact of program optimizations, we design an environment based on the gem5 full system simulator, the de facto simulator used in academia and industry. Next, we propose a broad range of adaptation strategies for code optimization; for prompting, these include retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play. A combination of these techniques achieves a mean speedup of 6.86 with eight generations, higher than average optimizations from individual programmers (3.66). Using our model's fastest generations, we set a new upper limit on the fastest speedup possible for our dataset at 9.64 compared to using the fastest human submissions available (9.56).

Sadegh Mahdavi, Kevin Swersky, Thomas Kipf et al.

In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks. First, we argue that OOD generalization in this setting is significantly different than common OOD settings. For example, some phenomena in OOD generalization of image classifications such as \emph{accuracy on the line} are not observed here, and techniques such as data augmentation methods do not help as assumptions underlying many augmentation techniques are often violated. Second, we analyze the main challenges (e.g., input distribution shift, non-representative data generation, and uninformative validation metrics) of the current leading benchmark, i.e., CLRS \citep{deepmind2021clrs}, which contains 30 algorithmic reasoning tasks. We propose several solutions, including a simple-yet-effective fix to the input distribution shift and improved data generation. Finally, we propose an attention-based 2WL-graph neural network (GNN) processor which complements message-passing GNNs so their combination outperforms the state-of-the-art model by a 3% margin averaged over all algorithms. Our code is available at: \url{https://github.com/smahdavi4/clrs}.

Cristina Vasconcelos, Cengiz Oztireli, Mark Matthews et al. · deepmind

Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolution architectures. When upsampling images of size 256x256 we show that our architecture is 2x-10x more efficient than competing arbitrary-scale super-resolution architectures, and more efficient than sub-pixel convolutions when instantiated to a single-scale model. In the general setting, these gains grow polynomially with the square of the target scale. We validate our method on standard benchmarks showing such efficiency gains can be achieved without sacrifices in super-resolution performance.

Binghong Chen, Daniel Tarlow, Kevin Swersky et al.

Improvements in the performance of computing systems, driven by Moore's Law, have transformed society. As such hardware-driven gains slow down, it becomes even more important for software developers to focus on performance and efficiency during development. While several studies have demonstrated the potential from such improved code efficiency (e.g., 2x better generational improvements compared to hardware), unlocking these gains in practice has been challenging. Reasoning about algorithmic complexity and the interaction of coding patterns on hardware can be challenging for the average programmer, especially when combined with pragmatic constraints around development velocity and multi-person development. This paper seeks to address this problem. We analyze a large competitive programming dataset from the Google Code Jam competition and find that efficient code is indeed rare, with a 2x runtime difference between the median and the 90th percentile of solutions. We propose using machine learning to automatically provide prescriptive feedback in the form of hints, to guide programmers towards writing high-performance code. To automatically learn these hints from the dataset, we propose a novel discrete variational auto-encoder, where each discrete latent variable represents a different learned category of code-edit that increases performance. We show that this method represents the multi-modal space of code efficiency edits better than a sequence-to-sequence baseline and generates a distribution of more efficient solutions.

Jeffrey Jian Ma, Milad Hashemi, Amir Yazdanbakhsh et al.

Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather than how to fix code. We introduce SWE-fficiency, a benchmark for evaluating repository-level performance optimization on real workloads. Our suite contains 498 tasks across nine widely used data-science, machine-learning, and HPC repositories (e.g., numpy, pandas, scipy): given a complete codebase and a slow workload, an agent must investigate code semantics, localize bottlenecks and relevant tests, and produce a patch that matches or exceeds expert speedup while passing the same unit tests. To enable this how-to-fix evaluation, our automated pipeline scrapes GitHub pull requests for performance-improving edits, combining keyword filtering, static analysis, coverage tooling, and execution validation to both confirm expert speedup baselines and identify relevant repository unit tests. Empirical evaluation of state-of-the-art agents reveals significant underperformance. On average, agents achieve less than 0.15x the expert speedup: agents struggle in localizing optimization opportunities, reasoning about execution across functions, and maintaining correctness in proposed edits. We release the benchmark and accompanying data pipeline to facilitate research on automated performance engineering and long-horizon software reasoning.

Aditya Kini, Satish Chandra, Milad Hashemi et al.

Enterprise software development is a continuous evolutionary process, characterized by incremental additions, architectural revisions, production deployments and rigorous maintenance. These activities generate valuable data that modern LLMs could be finetuned on, to unlock additional tool possibilities for enterprise software engineering. While frontier LLMs are already very capable, this form of customization offers a compelling path for enterprise-specific optimization. We introduce Gemini for Google (GfG)}, an adaptation of Gemini specialized for Google's internal software engineering ecosystem. This paper details the model's end-to-end development, from curating a trillion-token proprietary dataset to implementing a mid-training strategy that mitigates catastrophic forgetting. In a large-scale blind A/B study across 29,000 developers, Gemini for Google significantly outperformed baselines: reducing the mean number of iterations per turn by 23\%, and increasing code survival rates by about 17%. Beyond metrics, we provide a comprehensive blueprint for enterprise model adaptation, covering: (1)The extraction of high-value signals from software engineering data, (2)Data preparation strategies, (3)Full-stack model tuning (continued pre-training and post-training), and (4)The deployment of downstream applications. We believe this methodology offers a replicable path for other organizations to unlock the full potential of their internal engineering data.

Leon Sixt, Evan Zheran Liu, Marie Pellat et al.

Machine Learning has been successfully applied in systems applications such as memory prefetching and caching, where learned models have been shown to outperform heuristics. However, the lack of understanding the inner workings of these models -- interpretability -- remains a major obstacle for adoption in real-world deployments. Understanding a model's behavior can help system administrators and developers gain confidence in the model, understand risks, and debug unexpected behavior in production. Interpretability for models used in computer systems poses a particular challenge: Unlike ML models trained on images or text, the input domain (e.g., memory access patterns, program counters) is not immediately interpretable. A major challenge is therefore to explain the model in terms of concepts that are approachable to a human practitioner. By analyzing a state-of-the-art caching model, we provide evidence that the model has learned concepts beyond simple statistics that can be leveraged for explanations. Our work provides a first step towards explanability of system ML models and highlights both promises and challenges of this emerging research area.

Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi et al.

Industry has gradually moved towards application-specific hardware accelerators in order to attain higher efficiency. While such a paradigm shift is already starting to show promising results, designers need to spend considerable manual effort and perform a large number of time-consuming simulations to find accelerators that can accelerate multiple target applications while obeying design constraints. Moreover, such a "simulation-driven" approach must be re-run from scratch every time the set of target applications or design constraints change. An alternative paradigm is to use a "data-driven", offline approach that utilizes logged simulation data, to architect hardware accelerators, without needing any form of simulations. Such an approach not only alleviates the need to run time-consuming simulation, but also enables data reuse and applies even when set of target applications changes. In this paper, we develop such a data-driven offline optimization method for designing hardware accelerators, dubbed PRIME, that enjoys all of these properties. Our approach learns a conservative, robust estimate of the desired cost function, utilizes infeasible points, and optimizes the design against this estimate without any additional simulator queries during optimization. PRIME architects accelerators -- tailored towards both single and multiple applications -- improving performance upon state-of-the-art simulation-driven methods by about 1.54x and 1.20x, while considerably reducing the required total simulation time by 93% and 99%, respectively. In addition, PRIME also architects effective accelerators for unseen applications in a zero-shot setting, outperforming simulation-based methods by 1.26x.

Yujun Yan, Milad Hashemi, Kevin Swersky et al.

In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data. However, it is known that the performance of GCNs degrades with increasing number of layers (oversmoothing problem) and recent studies have also shown that GCNs may perform worse in heterophilous graphs, where neighboring nodes tend to belong to different classes (heterophily problem). These two problems are usually viewed as unrelated, and thus are studied independently, often at the graph filter level from a spectral perspective. We are the first to take a unified perspective to jointly explain the oversmoothing and heterophily problems at the node level. Specifically, we profile the nodes via two quantitative metrics: the relative degree of a node (compared to its neighbors) and the node-level heterophily. Our theory shows that the interplay of these two profiling metrics defines three cases of node behaviors, which explain the oversmoothing and heterophily problems jointly and can predict the performance of GCNs. Based on insights from our theory, we show theoretically and empirically the effectiveness of two strategies: structure-based edge correction, which learns corrected edge weights from structural properties (i.e., degrees), and feature-based edge correction, which learns signed edge weights from node features. Compared to other approaches, which tend to handle well either heterophily or oversmoothing, we show that {our model, GGCN}, which incorporates the two strategies performs well in both problems.

Will Grathwohl, Kevin Swersky, Milad Hashemi et al.

We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a Metropolis-Hastings sampler. We show empirically that this approach outperforms generic samplers in a number of difficult settings including Ising models, Potts models, restricted Boltzmann machines, and factorial hidden Markov models. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data. This approach outperforms variational auto-encoders and existing energy-based models. Finally, we give bounds showing that our approach is near-optimal in the class of samplers which propose local updates.

Amir Yazdanbakhsh, Christof Angermueller, Berkin Akin et al.

The looming end of Moore's Law and ascending use of deep learning drives the design of custom accelerators that are optimized for specific neural architectures. Architecture exploration for such accelerators forms a challenging constrained optimization problem over a complex, high-dimensional, and structured input space with a costly to evaluate objective function. Existing approaches for accelerator design are sample-inefficient and do not transfer knowledge between related optimizations tasks with different design constraints, such as area and/or latency budget, or neural architecture configurations. In this work, we propose a transferable architecture exploration framework, dubbed Apollo, that leverages recent advances in black-box function optimization for sample-efficient accelerator design. We use this framework to optimize accelerator configurations of a diverse set of neural architectures with alternative design constraints. We show that our framework finds high reward design configurations (up to 24.6% speedup) more sample-efficiently than a baseline black-box optimization approach. We further show that by transferring knowledge between target architectures with different design constraints, Apollo is able to find optimal configurations faster and often with better objective value (up to 25% improvements). This encouraging outcome portrays a promising path forward to facilitate generating higher quality accelerators.

Will Grathwohl, Jacob Kelly, Milad Hashemi et al.

Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty. Despite recent advances, training EBMs on high-dimensional data remains a challenging problem as the state-of-the-art approaches are costly, unstable, and require considerable tuning and domain expertise to apply successfully. In this work, we present a simple method for training EBMs at scale which uses an entropy-regularized generator to amortize the MCMC sampling typically used in EBM training. We improve upon prior MCMC-based entropy regularization methods with a fast variational approximation. We demonstrate the effectiveness of our approach by using it to train tractable likelihood models. Next, we apply our estimator to the recently proposed Joint Energy Model (JEM), where we match the original performance with faster and stable training. This allows us to extend JEM models to semi-supervised classification on tabular data from a variety of continuous domains.

Zhan Shi, Chirag Sakhuja, Milad Hashemi et al.

The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep learning software stacks and hardware accelerators is diverse and vast, prior work considers software optimizations separately from hardware architectures, effectively reducing the search space. Unfortunately, this bifurcated approach means that many profitable design points are never explored. This paper instead casts the problem as hardware/software co-design, with the goal of automatically identifying desirable points in the joint design space. The key to our solution is a new constrained Bayesian optimization framework that avoids invalid solutions by exploiting the highly constrained features of this design space, which are semi-continuous/semi-discrete. We evaluate our optimization framework by applying it to a variety of neural models, improving the energy-delay product by 18% (ResNet) and 40% (DQN) over hand-tuned state-of-the-art systems, as well as demonstrating strong results on other neural network architectures, such as MLPs and Transformers.

Evan Zheran Liu, Milad Hashemi, Kevin Swersky et al.

Program execution speed critically depends on increasing cache hits, as cache hits are orders of magnitude faster than misses. To increase cache hits, we focus on the problem of cache replacement: choosing which cache line to evict upon inserting a new line. This is challenging because it requires planning far ahead and currently there is no known practical solution. As a result, current replacement policies typically resort to heuristics designed for specific common access patterns, which fail on more diverse and complex access patterns. In contrast, we propose an imitation learning approach to automatically learn cache access patterns by leveraging Belady's, an oracle policy that computes the optimal eviction decision given the future cache accesses. While directly applying Belady's is infeasible since the future is unknown, we train a policy conditioned only on past accesses that accurately approximates Belady's even on diverse and complex access patterns, and call this approach Parrot. When evaluated on 13 of the most memory-intensive SPEC applications, Parrot increases cache miss rates by 20% over the current state of the art. In addition, on a large-scale web search benchmark, Parrot increases cache hit rates by 61% over a conventional LRU policy. We release a Gym environment to facilitate research in this area, as data is plentiful, and further advancements can have significant real-world impact.

Yujun Yan, Kevin Swersky, Danai Koutra et al.

A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This is evidenced by their inability to generalize to data distributions that are outside of their restricted training sets, namely larger inputs and unseen data. We study these generalization issues at the level of numerical subroutines that comprise common algorithms like sorting, shortest paths, and minimum spanning trees. First, we observe that transformer-based sequence-to-sequence models can learn subroutines like sorting a list of numbers, but their performance rapidly degrades as the length of lists grows beyond those found in the training set. We demonstrate that this is due to attention weights that lose fidelity with longer sequences, particularly when the input numbers are numerically similar. To address the issue, we propose a learned conditional masking mechanism, which enables the model to strongly generalize far outside of its training range with near-perfect accuracy on a variety of algorithms. Second, to generalize to unseen data, we show that encoding numbers with a binary representation leads to embeddings with rich structure once trained on downstream tasks like addition or multiplication. This allows the embedding to handle missing data by faithfully interpolating numbers not seen during training.

Zhan Shi, Kevin Swersky, Daniel Tarlow et al.

As the performance of computer systems stagnates due to the end of Moore's Law, there is a need for new models that can understand and optimize the execution of general purpose code. While there is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of source code, these representations do not understand how code dynamically executes. In this work, we propose a new approach to use GNNs to learn fused representations of general source code and its execution. Our approach defines a multi-task GNN over low-level representations of source code and program state (i.e., assembly code and dynamic memory states), converting complex source code constructs and complex data structures into a simpler, more uniform format. We show that this leads to improved performance over similar methods that do not use execution and it opens the door to applying GNN models to new tasks that would not be feasible from static code alone. As an illustration of this, we apply the new model to challenging dynamic tasks (branch prediction and prefetching) from the SPEC CPU benchmark suite, outperforming the state-of-the-art by 26% and 45% respectively. Moreover, we use the learned fused graph embeddings to demonstrate transfer learning with high performance on an indirectly related task (algorithm classification).

Milad Hashemi, Kevin Swersky, Jamie A. Smith et al.

The explosion in workload complexity and the recent slow-down in Moore's law scaling call for new approaches towards efficient computing. Researchers are now beginning to use recent advances in machine learning in software optimizations, augmenting or replacing traditional heuristics and data structures. However, the space of machine learning for computer hardware architecture is only lightly explored. In this paper, we demonstrate the potential of deep learning to address the von Neumann bottleneck of memory performance. We focus on the critical problem of learning memory access patterns, with the goal of constructing accurate and efficient memory prefetchers. We relate contemporary prefetching strategies to n-gram models in natural language processing, and show how recurrent neural networks can serve as a drop-in replacement. On a suite of challenging benchmark datasets, we find that neural networks consistently demonstrate superior performance in terms of precision and recall. This work represents the first step towards practical neural-network based prefetching, and opens a wide range of exciting directions for machine learning in computer architecture research.