1. Traditional framework's computing and resource bottlenecks

Traditional blockchain technology, represented by Bitcoin, Ethereum, etc., has achieved significant accomplishments in decentralization, transparency, and security, promoting the development of cryptographic technologies and applications. However, due to the 'blockchain impossible triangle' dilemma (Figure 1-1), there are significant bottlenecks in computational performance and resource utilization, hindering technological innovation and application development, posing challenges for the cryptocurrency industry.

Figure 1-1. Blockchain impossible triangle

First, let’s analyze the three elements in the 'blockchain impossible triangle':

• Security: Security essentially reflects consensus needs, specifically manifested in ensuring the consistency, integrity, tamper-resistance, traceability, and verifiability of block data. Meeting these characteristics allows the blockchain to construct a 'trustless' strong trust security mechanism. Therefore, the security of consensus is the primary demand of blockchain and the cornerstone of its development.

• Decentralization: Decentralization means that there is no single control point in the system, and power and control are distributed among multiple nodes, which can enhance the system's fault tolerance, censorship resistance, and security, preventing single points of failure and malicious manipulation. While distributed systems are not necessarily decentralized (for example, a distributed system controlled by a single entity is not decentralized), decentralized systems are indeed distributed systems.

• Scalability: In the concept of the 'blockchain impossible triangle', scalability refers to the ability of distributed systems to expand computational performance. For digital systems, everything is computation, and different applications have different computational performance requirements. But broadly speaking, scalability refers to the ability of a system to handle an ever-growing amount of data, transaction volume, and number of users, which is reflected not only in TPS but also in storage capacity, network bandwidth, and number of nodes. High scalability is essential to support large-scale applications and user growth. The scalability of distributed systems directly affects the innovation and scaling of decentralized applications (DApps) built on them.

Among the three elements, blockchain emphasizes decentralization and strengthens validation and consensus security, while being relatively weak in computational performance. This leads to the blockchain impossible triangle dilemma: when the demands for decentralization and consensus security are met, the scalability of computation is restricted, as exemplified by Bitcoin. This means that within such a system framework, the distributed system of blockchain struggles to support application innovations with high computational performance or cannot meet the scalability needs of applications, such as AI big data models, graphic rendering, on-chain games, and large-scale social interactions.

The above mainly analyzes the computational performance expansion challenges brought by the blockchain impossible triangle. What is the root of this issue? Next, we will explore the interrelations among various elements within the block formation process.

In blockchain technology, a 'block' refers to a dataset formed by packaging a series of verified transaction data within a specific time interval. This concept includes the following key elements and their interrelations:

• Consensus (data): Verified transaction data with state consistency, i.e., the consensus data formed within the block.

• Block space: Refers to the storage space for transaction data. These transactions are encapsulated within blocks, and the number of transactions that can be stored is limited by the block size (set by the system or constrained by the total Gas fee of the block), meaning that the on-chain storage space is a limited resource, subsequently affecting the scalability of applications.

• Computational performance: The number of packaged transactions divided by the block time gives the number of transactions processed per second, i.e., TPS (transactions per second) = the number of transactions in the block / block time. Computational performance relates to the consensus process and storage space.

From the above analysis, it can be seen that the three elements of consensus, storage space, and computing performance in the block are interconnected, forming a constraint relationship. While blockchain pursues consistent consensus, it not only constrains the scalability of individual block storage space but also limits the scalability of computing performance. This is the root cause of the blockchain impossible triangle problem.

Further analysis indicates that during the block formation process, the blockchain system constructs three types of global, system-level resources: data (consensus) resources, storage resources, and computing resources. However, the impossible triangle problem limits the roles and scalability of these three resources, forming resource bottlenecks that hinder their full potential. If there were a way to break this constraint, would it create a new resource-driven development landscape for blockchain?

This is precisely the core question contemplated in this paper, aiming to find answers. Research indicates that from the SCP paradigm, the super-parallel computing model Actor, to the SSI distributed system architecture, a complete technical chain has formed in the engineering practice of AO + Arweave, breaking the impossible triangle dilemma of blockchain, fully releasing the resource potential of blockchain and distributed systems, and providing empowerment in practice, paving a new development path for value creation and large-scale application in Web3.

2. SCP: Breaking through the bottleneck of computational performance and resource expansion

2.1. Breaking the blockchain impossible triangle based on SCP

AO (super-parallel computing network) is built on Arweave, realizing the engineering application of the storage consensus paradigm (SCP). As shown in the following figure:

Figure 2-1. Modular system architecture of AO + Arweave based on SCP

Based on the core concept of SCP, the AO + Arweave system architecture achieves an effective separation of on-chain storage (consensus) and off-chain computation:

• Storage layer: The storage resources provided by Arweave are responsible for the permanent storage of data, while blockchain technology ensures the traceability and immutability of on-chain data, achieving consistency and high availability of data, embodying the concept of 'storage as consensus'.

• Computing layer: Computing tasks are migrated off-chain and decoupled from the storage (consensus) layer. This design allows computational performance to be unaffected by direct constraints of on-chain consensus, enabling infinite scalability by adding off-chain computing nodes, significantly enhancing processing efficiency and system flexibility.

• Comprehensive effect: Arweave's storage public chain maintains the decentralization of the system and the consensus security of the data, while AO ensures infinite scalability of computational performance off-chain. This structure ensures that the entire AO + Arweave system meets the demands for decentralization, consensus security, and computational performance scalability, effectively addressing the challenges of the blockchain impossible triangle.

2.2. Constructing three types of global system-level resources

The aforementioned characteristics realized based on SCP play important roles in the practical application of the system, making storage, computation, and data (consensus) both interconnected and independently functioning system elements, forming global, system-level resources, as shown in Figure 2-2:

Figure 2-2. Global system-level resources in the AO network

• Storage space resources: As a storage public chain, Arweave's storage space expansion is not limited by block size or total Gas fees, but is entirely determined by storage needs, achieving truly unlimited expansion. This not only satisfies the system's demand for flexible storage space but also enriches the diversity of on-chain data types, providing more possibilities for innovation of on-chain native applications.

• Computing resources: The AO computing network is composed of MU, SU, and CU. Here, we first discuss CU, while the roles and interrelations of various network units will be analyzed in detail later. CU is the unit responsible for computation and can scale horizontally to form CU clusters. These clusters compete for computing rights, supporting different processes to run in parallel across different CUs. This design of scalability and parallelism enables AO to provide infinite computing node resources, supporting high-performance parallel computing.

• Data (consensus) resources: On Arweave, any type and size of data can be permanently stored in the form of 'atomic assets', such as NFTs, documents, images, audio and video, web pages, games, legal contracts, program code, etc. This data forms a tamper-proof massive database, providing a foundation for data monetization and circulation. At the same time, AO does not reach consensus on the state of computation itself but focuses on ensuring that interaction logs are written to Arweave, ensuring the persistent availability and integrity of data, and ensuring the consistency and verifiability of computation output results. Any type of data can be referenced without permission or trust, realizing new value creation.

• Security resources: During the operation of AO, security resources supported by the protocol token $AO are also constructed, but this is not directly related to SCP; it involves the operation and security mechanisms of AO network communication units, which will be analyzed specifically in Section 3 'Customizable security and security resources'.

2.3. Trusted computing based on storage consensus

Utilizing the aforementioned system-level resources and distributed characteristics, AO is built on the Arweave storage public chain, forming a cloud computing network. Similar to traditional Web2 cloud computing, AO theoretically possesses unlimited computing and storage resource capabilities, able to support massive data resources. However, AO's uniqueness lies in its establishment of a decentralized, globally consistent trustworthy computing platform based on the storage consensus paradigm.

• Firstly, Arweave provides a permissionless, permanent storage service for global users, establishing a consensus data foundation that does not rely on trust.

• Secondly, AO stores the source code of various applications on the Arweave chain, which can be downloaded and run locally; the inputs come from trustworthy data on-chain, ensuring the consistency and predictability of output results under fixed inputs and execution logic.

• Finally, any client can perform consistency verification, because under the same input parameters and execution logic, its computational output results will inevitably be consistent, ensuring trustworthiness.

Therefore, it can be seen that, with deterministic source programs, inputs, and outputs, AO has constructed a trustworthy computing system based on storage consensus.

The storage consensus paradigm differs from traditional node consensus systems. In the storage consensus paradigm, computation, validation, and consensus are all conducted off-chain, with the final consensus data submitted for storage on-chain, forming the system's availability layer, consensus layer, and settlement layer. In other words, with the support of SCP, computational performance is no longer constrained by consensus and can scale infinitely off-chain. This mechanism provides feasibility for the AO network to create a high-performance computing architecture that supports high parallelism and distribution.

So, how has AO evolved into a decentralized world computer that is distributed and operates in high parallelism? This is primarily attributed to the Actor model, network communication units, and the distributed architecture realized based on SSI.

3. Super-parallel: Actor model and network communication units

3.1. Defining the basic framework for parallel computing using the Actor model

The name of the AO network comes from 'Actor Oriented', signifying that it is a super-parallel computing network. This designation derives from its core application of the Actor model, which establishes the basic structure of parallel computation within the system.

In the Actor model, an 'actor' is the basic unit of parallel computing, consisting of three main elements: state (State), behavior (Behavior), and mailbox (Mailbox). These three elements and their interactions constitute the core concept of the Actor model, as illustrated in Figure 3-1:

Figure 3-1. Actor model illustration (Image source: Reference material 5)

This model defines the core components and interaction rules of the system. An actor can be seen as an independent, concurrently active entity that can receive messages, process messages, send messages, and dynamically create new actors. The model has the following characteristics:

• Asynchronous communication: Multiple actors send uniformly formatted messages to each other in a peer-to-peer manner, with message sending and processing occurring asynchronously, making this communication method naturally suitable for interactions between nodes in a distributed system.

• Parallel operation: Each actor is independent, with no shared state, so there is no need to worry that the state of other actors will affect itself. Each actor can independently handle its tasks, achieving true parallel operation.

• Distributed deployment: Actors can be dispersedly deployed and scheduled to run on different CPUs, nodes, or even different time slices without affecting the final result.

• Scalability: Due to its distributed nature and loosely coupled design, the Actor model can flexibly achieve horizontal scalability by adding nodes and dynamic load balancing.

In summary, the Actor model optimizes parallel and concurrent issues with its elegant processing mechanism, making it particularly suitable for building distributed systems and high-concurrency applications. The AO network adopts the Actor model as the architectural foundation for parallel computing, thereby achieving efficient asynchronous communication, parallel operation, distributed deployment, and excellent scalability.

3.2. Efficient parallel computing implementation of communication network units

The Actor model provides a framework for parallel computing, while the communication network units of AO embody the concrete practice of this model. These network units include Message Units (MU), Scheduling Units (SU), and Computing Units (CU), each acting as an independent 'actor' that collaborates and synchronizes through messages in a unified format (ANS-104). Figure 3-2 demonstrates the basic functions of these network units and the message interaction process.

Figure 3-2. Working principle of AO network communication units (Image source: AO White Paper)

In the AO network, launching an application triggers the start of one or more processes, and the system allocates resources such as memory, virtual machines, and communication network units for each process. Inter-process interactions are all completed through messages. First, messages from users or other processes are sent to MU, which then forwards the messages to SU for sorting. The sorted messages and their results are permanently stored on Arweave, and state calculations are performed by a CU in a competing CU cluster, meaning processes can run on any computing node, showcasing typical decentralized parallel computing characteristics. After computation, CU returns the results to SU in the form of signed credentials to ensure the accuracy and verifiability of the computation results, which are ultimately uploaded to Arweave by SU. The complete data set formed by each process—including the initial state, processing steps, and final results—will be permanently stored on Arweave, becoming consensus data available for others to retrieve, verify, and use.

Figure 3-3. Communication process between units during TOken transfers (Image source: AO White Paper)

Figure 3-3 illustrates the specific application scenario of AO network handling token transfer requests, clearly depicting the composition and communication processes of modular network units, as well as the distributed storage mechanism formed through interaction with Arweave.

The AO system comprehensively utilizes computing resources (distributed CU clusters), storage resources (distributed Arweave nodes), and data resources (long-term available data stored in Arweave) to lay the foundation for AO to become a global computing platform. Based on the Actor model, the AO computing network not only possesses characteristics of asynchronous communication, parallel operation, and distributed deployment but also boasts excellent scalability, making it a truly decentralized, distributed, and parallel computing network.

3.3. Customizable security and security resources

In the previous section, we explored the composition and working principle of the AO network communication units. In this section, we will delve deeper into the security of this network, which is closely linked to the native token $AO of the AO protocol. This analysis will correspond to the content of 'Security resources' in Section 2.2, focusing on the customizable security and security resources within the AO network.

The network communication units composed of MU, SU, and CU are the core components of the AO computing network, creating the operational mechanism of a decentralized world computer, forming three types of system-level resources: computing, storage, and data. This forms the basis of the technical model and resource model in the AO network. Based on the technical model and resource model, the AO system creates a demand-driven customizable security mechanism. This is an economic model built on the protocol's native token $AO, where security guarantees arise from economic competition, thereby providing a security market within AO.

To facilitate understanding, the security mechanisms in AO are simplified from the user’s perspective into several core elements and their interrelations: customizable needs, security/economic resources, security mechanisms, and security competition markets.

Figure 3-4. The relationship between elements in the AO network security mechanism

Figure 3-4 describes the interrelationship of elements in the AO network security mechanism:

• Customizable needs: As a super-parallel computing platform, each node in AO independently runs various processes in parallel, handling different types of data. These different data transaction scenarios have varying demands for system latency, cost, and efficiency, which requires AO's security model to be flexible, capable of customizing security policies according to needs. Users can customize the specific security level required for each message, thereby promoting the customization and effective allocation of security resources.

• Security/economic resources: $AO is the native token of the protocol, serving as a circulating public value unit and economic resource, supporting all security mechanisms’ economic game mechanisms in the AO network.

• Security mechanisms: In the various processes of AO, including nodes like MU, SU, and CU, $AO must be staked to participate in security mechanisms. By staking economic value, the system manages funds and executes penalties according to rules to prevent malicious behavior. For example, if MU signs an invalid message or CU provides invalid signature proof, the system will reduce its staked assets.

• Security competition market: Since security is purchased per message, different messages correspond to different staking needs, creating a dynamic competition market. The price of security is determined by market supply and demand rather than fixed network rules. This market competition mechanism promotes the effective pricing and allocation of security resources, providing tailored security.

In summary, the decentralized peer-to-peer market structure of the AO network essentially allows nodes to independently set the fees for their messaging services, adapting to the different security level demands of various data transactions, and reflecting the system's efficiency in responding to specific security needs. This flexibility allows it to dynamically adapt to changes in market demand and supply, promoting competition and enhancing response efficiency, thereby achieving efficient market equilibrium.

$AO's liquidity serves as a tool for economic competition, establishing a comprehensive, real-time token valuation framework while building a security mechanism, providing a solid foundation for effective token valuation. A well-structured valuation framework and indicators for the $AO token economic model will undoubtedly further enhance the security of the AO network.

4. SSI: Unified experience of distributed system architecture

In previous discussions, we have elaborated on the basic framework provided by the Actor model for parallel computing in the AO network, and how the network communication units composed of MU, SU, and CU specifically realize this model. These communication units are deployed across different heterogeneous nodes in the distributed network, allowing process execution to be unrestricted by specific physical locations and enabling seamless user interaction through the network. All of this together forms a unified computing environment, realizing a single system image (SSI), which is the foundation for the AO network to support countless processes. This section will explore the definition of SSI and its specific role in AO.

Single System Image (SSI) is a core concept in distributed computing that integrates physically separated heterogeneous computing resources into a unified resource pool through virtualization technology. This integration not only raises the system's abstraction level but also greatly optimizes user experience. Under the influence of SSI, even though the system may consist of multiple servers, distributed databases, or various networks, the user perceives it as operating a single computer.

Typically, the SSI structure includes the user layer, unified interface, resource management layer, computing nodes, and storage layer, illustrated in the structure diagram of Figure 4-1.

Figure 4-1. Single System Image (SSI) structure diagram

Users interact with the SSI system through clients or web front-ends at the user layer. The unified interface is responsible for receiving user requests and distributing these requests to the resource management layer. The resource management layer schedules distributed computing nodes and storage resources to perform parallel computing tasks or carry out data read and write operations.

SSI provides a feasible solution to the current issue of multiple chains coexisting in public chains. For instance, the Ethereum ecosystem, due to rapid development, faces congestion, low efficiency, and high-cost issues, while Layer2, as the main solution to these scalability problems, introduces new challenges. Each Layer2 chain, while reconstructing infrastructure, also leads to liquidity dispersion and cross-chain asset risks, increasing the complexity and participation threshold for users switching between chains, severely impacting user experience and the large-scale development of applications.

Public chains such as Solana and Polkadot have already recognized these issues and adjusted based on their original architectures. However, AO adopted the distributed architecture of SSI from the very beginning, demonstrating foresight and vision.

Utilizing the Actor model, AO's network communication units are hosted on a heterogeneous node set in a distributed network, which may be spread across various regions worldwide and include servers of various types and functions. The AO computing network based on the Actor model is a decentralized distributed network that requires a unified architecture for integration to provide consistent availability and user experience.

When a user initiates an AO process through the front end, the system configures the necessary different resources to handle tasks such as message passing, transaction sorting, and state computation. For users, the underlying complex distributed architecture is abstracted, so even a massive node cluster operates like a single computer. This is because the AO system uses SSI to integrate the complex components of distributed systems, achieving a unified computing environment through modularization. In other words, through the SSI architecture, AO integrates multiple distributed computing nodes into a unified resource, providing users with a transparent, efficient, scalable, and unified computing platform.

5. Resource-driven value creation and application innovation

In summary, through the combination of SCP, Actor, and SSI, AO has constructed an innovative architecture that builds three scalable system-level resources for computation, storage, and data (consensus), as well as a security resource supported by $AO. Resources, as core production factors, play a key role in promoting technological progress, stimulating application innovation, and improving economic efficiency. By clarifying the resource elements in the AO + Arweave system, we can optimize resource planning and management, leveraging resources to drive technological and application innovation, accelerate value creation in Web3, and promote growth in the cryptocurrency economy.

Here, we provide a summary:

1. Infrastructure-type value creation

• Decentralized world computer: AO integrates scalable computing, storage, and data resources, providing a unified decentralized computing platform for all applications, with verifiable and trust-minimized characteristics. Applications only need to focus on business innovation, avoiding reinventing the wheel, making AO a public infrastructure for application innovation.

• On-chain shared data repository: Arweave can permanently store almost all types of data, becoming a never-ending 'Library of Alexandria'. Whether it is financial data or non-financial data, its immutable and verifiable characteristics make it a public good that can provide consensus value, supporting combinatorial innovation.

• Customizable security facilities: AO can provide customized security mechanisms for clients and applications based on different data types and values, achieving a balance between security, cost, and efficiency.

• Bridge between Web2 and Web3: AO operates off-chain, seamlessly integrating with on-chain and off-chain systems, becoming a connecting bridge between Web2 and Web3. Any Web2 application can initiate processes in AO through API and messaging mechanisms, invoking network units in AO to perform computations while customizing their security mechanisms.

2. Technical and application innovations

Blockchain has developed to date, with public chains primarily represented by Bitcoin, Ethereum, Solana, etc., and their applications still leaning toward the financial sector, such as asset issuance, trading, collateralized lending, derivatives, etc. This has led many to mistakenly believe that the role of blockchain is limited to this.

However, the innovative architecture of AO + Arweave adds new feasibility for technological innovation and application development in blockchain. In addition to supporting financial innovations typical of most public chains, AO, as a universal world computer, supports all data types and corresponding application innovations, especially non-financial data-driven application innovations.

• Loading AI models: The AO + Arweave architecture provides infinite computing, storage, and data resources, and with the support of three key technologies—WASM64, WeaveDrive, and Llama.cpp large language model inference engines—AO can directly run various open-source large language models in smart contracts, such as Llama 3 and GPT-2, enabling smart contracts to directly handle complex data and make concurrent decisions, such as the on-chain autonomous virtual world Llama Land driven by the AI-powered Llama 3 model.

• Creating Agents and AgentFi: Based on the inference capabilities of AI models and the ability of AO processes to respond to implicit messages based on time, awaken themselves, and execute actions, as well as the ability to 'subscribe' to a process by paying fees to MU in order to trigger computations at an appropriate frequency, AO supports Agents and AgentFi that satisfy complex business logic, predefined needs, and diversified autonomous strategies.

• Copyright management and creator markets (ContentFi): Arweave stores various types of data in the form of atomic assets, which can be easily identified and confirmed for ownership, allowing them to be monetized as a new form of digital asset. This facilitates price discovery through circulation and trading in the market, establishing clear benefit distribution and collaboration patterns, supporting copyright management and creator markets.

• Next-generation Internet framework Permaweb: Unlike the three-layer structure of the traditional Web2 internet application layer, service layer, and storage layer, Permaweb replaces the storage layer with Arweave's permanent storage solution, achieving permanent storage of all content in the form of atomic assets stored on Arweave. It builds various applications supporting AO super-parallel computing at the application layer based on SCP, creating a perpetual online, decentralized next-generation Internet framework. This framework integrates with Web2, providing a user experience indistinguishable from Web2, but there are significant differences. Permaweb is not a 'walled garden'. It provides a fair and open environment for developers, operators, and users: users own and control their data; data can flow freely between different applications; developers and operators can conduct business using data without special permission within established rules, thereby promoting mutual benefit and win-win outcomes.

The above are several typical application innovation directions supported by AO. Of course, AO can support more data types and broader scenarios for application innovation. Although the AO ecosystem is still in its early development stage and its technological and application innovations need time to be tested, we prefer to assess the significance and value of these innovations from the broader context of Web3 industry development stages and the characteristics of Web2 systems.

The current Web3 industry is exploring feasible paths for large-scale adoption, with many blockchains striving for it. For example, TON combined with Telegram aims to guide real Web2 users to real Web3 applications, intending to achieve large-scale value conversion from traffic to liquidity; CKB becoming the L2 of Bitcoin is building a lightning network based on CKB, intending to bring high-frequency, small-amount, large-scale peer-to-peer payments.

From the perspective of industry development, AO + Arweave redefines the implementation framework of decentralized computers, bringing system flexibility, security, and economic efficiency with an innovative architecture. It builds scalable system-level resources that continuously release resource potential, drive technological and application innovation, create and transfer value, and promote the integration of Web3 and Web2, providing a feasible path for large-scale adoption of Web3.

References

1. Arweave: A protocol for economically sustainably preserving information permanently

2. AO protocol: Decentralized, permissionless supercomputer:

https://x.com/kylewmi/status/1802131298724811108

3. Storage-based computing paradigm realized by Arweave:

https://news.ever.vision/a-storage-based-computation-paradigm-enabled-by-arweave-de799ae8c424

4. Technical details of the AO super-parallel computer:

https://www.chaincatcher.com/article/2121544

5. Interpreting SCP: A paradigm for trustless infrastructure beyond Rollup conventions:

https://mp.weixin.qq.com/s/BPRAsby78G2a835pX1l3iw

6. In-depth analysis of the Actor model (Part 1): Introduction to actors and applications in the gaming industry:

https://blog.csdn.net/weixin_44505163/article/details/121191182

7. Arweave permanent storage + AO super-parallel computer: Building a data consensus infrastructure:

https://www.chaincatcher.com/article/2141924