Laptop Structure analysis has an extended historical past of creating simulators and instruments to guage and form the design of pc techniques. For instance, the SimpleScalar simulator was launched within the late Nineteen Nineties and allowed researchers to discover numerous microarchitectural concepts. Laptop structure simulators and instruments, equivalent to gem5, DRAMSys, and lots of extra have performed a big function in advancing pc structure analysis. Since then, these shared assets and infrastructure have benefited business and academia and have enabled researchers to systematically construct on one another’s work, resulting in important advances within the area.

Nonetheless, pc structure analysis is evolving, with business and academia turning in the direction of machine studying (ML) optimization to fulfill stringent domain-specific necessities, equivalent to ML for pc structure, ML for TinyML acceleration, DNN accelerator datapath optimization, reminiscence controllers, energy consumption, safety, and privateness. Though prior work has demonstrated the advantages of ML in design optimization, the dearth of robust, reproducible baselines hinders honest and goal comparability throughout totally different strategies and poses a number of challenges to their deployment. To make sure regular progress, it’s crucial to know and deal with these challenges collectively.

To alleviate these challenges, in “ArchGym: An Open-Supply Gymnasium for Machine Studying Assisted Structure Design”, accepted at ISCA 2023, we launched ArchGym, which incorporates quite a lot of pc structure simulators and ML algorithms. Enabled by ArchGym, our outcomes point out that with a sufficiently giant variety of samples, any of a various assortment of ML algorithms are able to find the optimum set of structure design parameters for every goal downside; nobody resolution is essentially higher than one other. These outcomes additional point out that choosing the optimum hyperparameters for a given ML algorithm is important for locating the optimum structure design, however selecting them is non-trivial. We launch the code and dataset throughout a number of pc structure simulations and ML algorithms.

Challenges in ML-assisted structure analysis

ML-assisted structure analysis poses a number of challenges, together with:

1. For a selected ML-assisted pc structure downside (e.g., discovering an optimum resolution for a DRAM controller) there is no such thing as a systematic method to establish optimum ML algorithms or hyperparameters (e.g., studying charge, warm-up steps, and so on.). There’s a wider vary of ML and heuristic strategies, from random stroll to reinforcement studying (RL), that may be employed for design house exploration (DSE). Whereas these strategies have proven noticeable efficiency enchancment over their alternative of baselines, it’s not evident whether or not the enhancements are due to the selection of optimization algorithms or hyperparameters.
   Thus, to make sure reproducibility and facilitate widespread adoption of ML-aided structure DSE, it’s needed to stipulate a scientific benchmarking methodology.
2. Whereas pc structure simulators have been the spine of architectural improvements, there may be an rising want to handle the trade-offs between accuracy, velocity, and price in structure exploration. The accuracy and velocity of efficiency estimation extensively varies from one simulator to a different, relying on the underlying modeling particulars (e.g., cycle–correct vs. ML–primarily based proxy fashions). Whereas analytical or ML-based proxy fashions are nimble by advantage of discarding low-level particulars, they often undergo from excessive prediction error. Additionally, because of business licensing, there could be strict limits on the variety of runs collected from a simulator. Total, these constraints exhibit distinct efficiency vs. pattern effectivity trade-offs, affecting the selection of optimization algorithm for structure exploration.
   It’s difficult to delineate how you can systematically examine the effectiveness of varied ML algorithms beneath these constraints.
3. Lastly, the panorama of ML algorithms is quickly evolving and a few ML algorithms want information to be helpful. Moreover, rendering the result of DSE into significant artifacts equivalent to datasets is essential for drawing insights in regards to the design house.
   On this quickly evolving ecosystem, it’s consequential to make sure how you can amortize the overhead of search algorithms for structure exploration. It’s not obvious, nor systematically studied how you can leverage exploration information whereas being agnostic to the underlying search algorithm.

ArchGym design

ArchGym addresses these challenges by offering a unified framework for evaluating totally different ML-based search algorithms pretty. It contains two primary parts: 1) the ArchGym setting and a pair of) the ArchGym agent. The setting is an encapsulation of the structure value mannequin — which incorporates latency, throughput, space, power, and so on., to find out the computational value of operating the workload, given a set of architectural parameters — paired with the goal workload(s). The agent is an encapsulation of the ML algorithm used for the search and consists of hyperparameters and a guiding coverage. The hyperparameters are intrinsic to the algorithm for which the mannequin is to be optimized and may considerably affect efficiency. The coverage, then again, determines how the agent selects a parameter iteratively to optimize the goal goal.

Notably, ArchGym additionally features a standardized interface that connects these two parts, whereas additionally saving the exploration information because the ArchGym Dataset. At its core, the interface entails three primary alerts: {hardware} state, {hardware} parameters, and metrics. These alerts are the naked minimal to ascertain a significant communication channel between the setting and the agent. Utilizing these alerts, the agent observes the state of the {hardware} and suggests a set of {hardware} parameters to iteratively optimize a (user-defined) reward. The reward is a perform of {hardware} efficiency metrics, equivalent to efficiency, power consumption, and so on. 

ArchGym contains two primary parts: the ArchGym setting and the ArchGym agent. The ArchGym setting encapsulates the price mannequin and the agent is an abstraction of a coverage and hyperparameters. With a standardized interface that connects these two parts, ArchGym supplies a unified framework for evaluating totally different ML-based search algorithms pretty whereas additionally saving the exploration information because the ArchGym Dataset.

ML algorithms may very well be equally favorable to fulfill user-defined goal specs

Utilizing ArchGym, we empirically reveal that throughout totally different optimization aims and DSE issues, not less than one set of hyperparameters exists that ends in the identical {hardware} efficiency as different ML algorithms. A poorly chosen (random choice) hyperparameter for the ML algorithm or its baseline can result in a deceptive conclusion {that a} specific household of ML algorithms is best than one other. We present that with enough hyperparameter tuning, totally different search algorithms, even random stroll (RW), are capable of establish the absolute best reward. Nonetheless, word that discovering the correct set of hyperparameters could require exhaustive search and even luck to make it aggressive.

With a enough variety of samples, there exists not less than one set of hyperparameters that ends in the identical efficiency throughout a variety of search algorithms. Right here the dashed line represents the utmost normalized reward. Cloud-1, cloud-2, stream, and random point out 4 totally different reminiscence traces for DRAMSys (DRAM subsystem design house exploration framework).

Dataset development and high-fidelity proxy mannequin coaching

Making a unified interface utilizing ArchGym additionally allows the creation of datasets that can be utilized to design higher data-driven ML-based proxy structure value fashions to enhance the velocity of structure simulation. To guage the advantages of datasets in constructing an ML mannequin to approximate structure value, we leverage ArchGym’s capacity to log the info from every run from DRAMSys to create 4 dataset variants, every with a distinct variety of information factors. For every variant, we create two classes: (a) Various Dataset, which represents the info collected from totally different brokers (ACO, GA, RW, and BO), and (b) ACO solely, which reveals the info collected solely from the ACO agent, each of that are launched together with ArchGym. We practice a proxy mannequin on every dataset utilizing random forest regression with the target to foretell the latency of designs for a DRAM simulator. Our outcomes present that:

1. As we improve the dataset dimension, the typical normalized root imply squared error (RMSE) barely decreases.
2. Nonetheless, as we introduce variety within the dataset (e.g., gathering information from totally different brokers), we observe 9× to 42× decrease RMSE throughout totally different dataset sizes.

Various dataset assortment throughout totally different brokers utilizing ArchGym interface.

The influence of a various dataset and dataset dimension on the normalized RMSE.

The necessity for a community-driven ecosystem for ML-assisted structure analysis

Whereas, ArchGym is an preliminary effort in the direction of creating an open-source ecosystem that (1) connects a broad vary of search algorithms to pc structure simulators in an unified and easy-to-extend method, (2) facilitates analysis in ML-assisted pc structure, and (3) types the scaffold to develop reproducible baselines, there are lots of open challenges that want community-wide help. Under we define among the open challenges in ML-assisted structure design. Addressing these challenges requires a properly coordinated effort and a group pushed ecosystem.

Key challenges in ML-assisted structure design.

We name this ecosystem Structure 2.0. We define the important thing challenges and a imaginative and prescient for constructing an inclusive ecosystem of interdisciplinary researchers to deal with the long-standing open issues in making use of ML for pc structure analysis. In case you are fascinated with serving to form this ecosystem, please fill out the curiosity survey.

Conclusion

ArchGym is an open supply gymnasium for ML structure DSE and allows an standardized interface that may be readily prolonged to go well with totally different use circumstances. Moreover, ArchGym allows honest and reproducible comparability between totally different ML algorithms and helps to ascertain stronger baselines for pc structure analysis issues.

We invite the pc structure group in addition to the ML group to actively take part within the improvement of ArchGym. We consider that the creation of a gymnasium-type setting for pc structure analysis can be a big step ahead within the area and supply a platform for researchers to make use of ML to speed up analysis and result in new and modern designs.

Acknowledgements

This blogpost is predicated on joint work with a number of co-authors at Google and Harvard College. We want to acknowledge and spotlight Srivatsan Krishnan (Harvard) who contributed a number of concepts to this mission in collaboration with Shvetank Prakash (Harvard), Jason Jabbour (Harvard), Ikechukwu Uchendu (Harvard), Susobhan Ghosh (Harvard), Behzad Boroujerdian (Harvard), Daniel Richins (Harvard), Devashree Tripathy (Harvard), and Thierry Thambe (Harvard).  As well as, we might additionally prefer to thank James Laudon, Douglas Eck, Cliff Younger, and Aleksandra Faust for his or her help, suggestions, and motivation for this work. We might additionally prefer to thank John Guilyard for the animated determine used on this put up. Amir Yazdanbakhsh is now a Analysis Scientist at Google DeepMind and Vijay Janapa Reddi is an Affiliate Professor at Harvard.