A Deep Dive from Jito to Solayer: How SVM is Reshaping Solana's Scaling Game

Let’s talk about the recent strong performance of the Secondary Market $LAYER@solayer_labs. In particular, why is the InfiniSVM technology roadmap attracting so much attention? What are the characteristics of the hardware-accelerated SVM scaling solutions? And how will the industry landscape of the Solana ecosystem change after hardware acceleration? Next, let me share my forward-looking observations:

1. Unlike the previous Ethereum-dominated horizontal scalability approach, the Solayer team presents a completely different scalability idea in the infiniSVM white paper: by hardware-accelerating and deeply optimizing SVM, creating a million TPS blockchain network, which essentially involves a scalability solution that deeply integrates hardware and software.

If we look back at the entire history of blockchain scaling, the earliest idea of on-chain scaling is achieved through parameter adjustment (larger blocks, shorter block generation time), but this idea is easy to touch on the impossible triangle dilemma of the blockchain; Later, the layer2 scaling idea is a horizontal scaling, and the core purpose is to divert transactions through layer2 (state channels, sidechains, rollups, etc.), which will undoubtedly sacrifice some global atomicity; The hardware acceleration route explored by InfiniSVM is a new route that upgrades the concept of capacity expansion, while maintaining a single global state, to break through the performance bottleneck with specialized hardware.

In simple terms: InfiniSVM's scaling method does not rely solely on algorithm optimization, but rather reconstructs the SVM execution environment through microservices architecture and hardware acceleration, delegating some key tasks to dedicated hardware, thereby achieving atomicity and consistency under global states in high-load conditions.

2. Following this line of thought, many friends must be wondering why the SVM execution environment of Solana requires hardware acceleration? From the data provided in the Solayer white paper, it can be seen that current Solana validator nodes already require a CPU of over 3.1GHz, over 500GB of high-speed memory, and over 2.5TB of high-throughput NVMe storage. Even with such high configurations, the CPU utilization is only about 30% under high load, and the P2P communication is close to the consumer-grade network 1Gbps bandwidth limit.

The question arises, since the CPU is not fully utilized, why do we need stronger hardware? This actually exposes that Solana's current performance bottleneck lies more in other aspects beyond CPU computing power, such as: microservice processing architecture, which can isolate different processing stages and match more suitable hardware resources; dedicated accelerators, which can assign specific tasks like certain signatures to dedicated hardware, and so on.

You see, InfiniSVM is not just a simple hardware upgrade, but a complete redesign of the execution environment, providing more specialized hardware optimization solutions for each bottleneck link. It's similar to improving workshop production efficiency, which requires restructuring the entire production line's hardware and software, rather than simply increasing the number of workers in a crude manner.

3. So, what features of InfiniSVM's hardware acceleration scheme are worth sharing?

1. Distributed microservice processing architecture, the previous Solana monolithic transaction processing process can be decomposed into multiple extended processing links such as signature verification, deduplication, scheduling, storage, etc., while each link in the InfiniSVM architecture can be processed independently, avoiding the big problem of "one link is stuck and waiting for the whole line";

2. Intelligent transaction scheduling system, originally when Solana reads and writes transactions, it still has to queue up when it belongs to the same account, but InfiniSVM realizes that even under the same account, it can make operations not interfere with each other, and then greatly improve its parallel processing capabilities. To put it bluntly, it has further enhanced the ability of fine management;

3. RDMA low-latency communication technology requires at least essential steps such as packaging, delivery, and unpacking for normal communication between nodes, whereas RDMA can directly transfer data from one node to another's memory, achieving a breakthrough in communication technology from milliseconds to microseconds, significantly reducing state access conflicts.

4. Distributed intelligent storage network, if a single account is allowed to undertake its account data, Solana was limited by 10MB in the past, but InfiniSVM adopts a distributed cloud storage solution, so that the data is distributed to different nodes, marked as fast lane, slow lane, etc., which not only breaks through the capacity limit, but also optimizes the data access speed.

4. After explaining the technical upgrade roadmap, it's likely that many voices questioning "what's the use" have emerged. Overall, with the support of hardware acceleration, Solana can further enhance its competitive advantage in the layer1 competition. Moreover, compared to the scalability achievements of Ethereum layer2 that require application data support in the ecosystem to manifest, this performance breakthrough of achieving millions of TPS through hardware may only need the integration of a few specific vertical scenarios to directly validate it, making the implementation path somewhat shorter.

Let's change our perspective and take @jito_sol as an example. As Solana MEV infrastructure, it has ecological value in transaction ordering optimization, MEV extraction, validator revenue, and other aspects. If it couldn't prove itself before the Solana MEME craze, then after the MEME boom in the past year, Jito's method of optimizing transaction processing has become an indispensable part.

In fact, Solayer's current technical positioning is also similar. Its upgrade method, which enhances trading performance in the system, is not clearly reflected solely in financial trading scenarios. However, if we think about the large-scale implementation of PayFi in the future, in order for Solana to perfectly support high throughput and low latency payment settlement infrastructure functions, the performance of TPS will be significantly noticeable. Additionally, there is also the DePIN ecosystem and complex chain games, AI Agent application scenarios, etc.

In any case, looking ahead to define the value of a technology-based infrastructure project is clearer than just relying on whether it has Utility at the moment.