Ethereum's RISC-V Shift Could Cut Zero-Knowledge Proof Costs by 99 Percent
Ethereum's potential shift to RISC-V architecture could slash the computational cost of zero-knowledge proofs by up to 99 percent, according to early research cited by Vitalik Buterin. The move would represent one of the most significant technical overhauls in Ethereum's history, but could unlock new scaling possibilities for the world's largest smart contract platform.
Why Is Ethereum Considering a Move Away From the EVM?
Since last year, Ethereum's co-founder Vitalik Buterin has discussed plans to explore migrating Ethereum's runtime environment from the current Ethereum Virtual Machine (EVM) to RISC-V, an open-source instruction set architecture used in about 15 percent of microchips globally. The EVM is the software engine that executes smart contracts on Ethereum, but it was not designed with efficient verification in mind.
The core problem is that the EVM operates on 256-bit words, whereas most computations require much smaller values, creating unnecessary computational overhead. Additionally, the EVM uses a stack-based architecture that makes it harder for provers to track every transition in the execution process. In contrast, RISC-V uses 32 to 64-bit words and allows values to be placed in 32 general-purpose registers, making computation tracking far more efficient.
Initial research by Succinct Labs, cited by Buterin, indicates that using zero-knowledge (ZK) proofs to verify Ethereum blocks on the EVM currently incurs 100 to 1,000 times the overhead of RISC-V. This massive efficiency gap is the primary driver behind the proposed migration.
How Would RISC-V Improve Zero-Knowledge Proof Verification?
Zero-knowledge proofs are cryptographic tools that allow one party to prove a computation was performed correctly without revealing the underlying data or requiring the other party to re-execute the computation. For Ethereum to scale, validators currently must individually re-execute every transaction in each block to confirm the accuracy of proposed state changes. ZK proofs could eliminate this redundancy, but only if the underlying architecture supports efficient proof generation.
RISC-V's register-based architecture enables much faster prover performance. Linea, an Ethereum Layer 2 (L2) scaling solution developed by Consensys, cited the register-based architecture as the core reason for planning to migrate to RISC-V, as it enables a much faster prover. Linea plans to deploy RISC-V compatibility on mainnet by the end of summer 2026.
The practical impact is already visible in real-world testing. SP1, one of eight zero-knowledge virtual machines (zkVMs) currently being developed and tested, already handles "real-time proving," meaning it can prove a mainnet block within the roughly 12-second window before the next block arrives. When SP1 launched on mainnet in November 2025, it proved 99.7 percent of Layer 1 Ethereum blocks on 16 graphics processing units (GPUs) in under 12 seconds, and 95.4 percent in under 10 seconds. As of May 2026, the v6 version of SP1 generates proofs six times as fast as earlier versions.
What Are the Technical and Practical Implications?
The migration would require a major technical overhaul that Buterin outlined would take at least 18 months. However, the benefits extend beyond just ZK proof efficiency. RISC-V is an open-source instruction set architecture known for its simplicity, performance, and active development across industries outside blockchain. Major companies such as Google, Intel, and NVIDIA are part of the RISE collaborative effort to accelerate RISC-V software development.
The Ethereum Foundation plans to integrate zkVMs to generate proofs of Ethereum blocks and allow clients to verify them in the consensus layer as part of its 2026 roadmap. Their expectation is for the zkVM to use RISC-V or a similar architecture, consuming a guest program consisting of the block and witness needed to verify the block.
Steps to Understanding RISC-V's Role in Ethereum's Future
- Current Bottleneck: The EVM was not designed with efficient verification in mind, leading to long prover times and computational effort required to generate zero-knowledge proofs that verify block correctness without re-execution.
- RISC-V Advantage: RISC-V's register-based architecture and smaller word sizes (32-64 bits versus 256 bits) reduce the computational overhead of generating ZK proofs by 100 to 1,000 times compared to the EVM.
- Ecosystem Development: Eight zkVMs are currently being developed and tested to meet Ethereum Foundation expectations, with SP1 already demonstrating the ability to prove mainnet blocks in real-time within the 12-second block window.
- Developer Experience: Migration to RISC-V would expand programming language options beyond Solidity and Vyper, allowing developers to write smart contracts in virtually any language that compiles to RISC-V.
- Timeline and Scope: Linea plans to deploy RISC-V compatibility by the end of summer 2026, while the broader Ethereum migration would require at least 18 months of technical implementation.
What Does This Mean for Ethereum's Scaling Future?
The shift to RISC-V represents a fundamental rethinking of how Ethereum handles computation verification. Rather than asking validators to re-execute transactions, the network could rely on cryptographic proofs generated by specialized zkVMs. This approach could dramatically reduce the computational burden on validators while maintaining security guarantees.
The Ethereum Foundation's 2026 roadmap explicitly calls for zkVM integration, signaling that zero-knowledge proof verification is becoming a core part of Ethereum's scaling strategy. The fact that multiple zkVMs are being built to RISC-V specifications suggests the ecosystem is already moving in this direction, even before a formal EVM migration occurs.
However, the migration is not without challenges. The Ethereum Foundation ruled out other popular instruction set architectures such as x86, WASM, and ARM, choosing RISC-V because it is simpler, more actively developed, and better suited to Ethereum's needs. Still, the technical complexity of such a migration means it remains a long-term initiative rather than an immediate change.