GridSMR speeds up blockchain cross-shard operations by reducing delays
GridSMR: Causal Compression for Sharded Blockchains
Distributed, Parallel, and Cluster Computing
Summary
Blockchains often split work across different groups called shards to handle lots of transactions, but these shards usually have to wait for each other to keep everything correct, which slows things down. The authors created GridSMR, a system that lets dependent tasks across shards happen sooner without waiting for full agreement right away. It uses a two-step approach where operations run first and consensus happens later, which reduces delays that usually grow with the complexity of the transaction chain. This means GridSMR can process many transactions quickly while cutting the time it takes for operations to finish across different shards.
What this means in practice
- •For blockchain platform engineers: Build scalable blockchains that process dependent cross-shard transactions faster without increased latency for complex workflows.
- •For distributed database developers: Improve coordination latency in distributed transaction processing by adopting asynchronous execution before agreement.
Authors
Shir Cohen, Adam Alon, Raz Omessi, Amir Sarid, Dana Shamir, Ofir Zohar
Abstract
We present GridSMR, a sharded blockchain that scales execution horizontally while allowing dependent cross-shard operations to progress within a single block. Existing sharded systems typically place coordination between dependent cross-shard steps, making latency grow with causal depth. GridSMR localizes atomicity to individual accounts and executes cross-account work asynchronously. Using an execute-before-agree architecture, dependent operations execute across shards as they become available, while consensus later validates and commits the resulting schedule. This enables Causal Compression: cross-shard latency need not grow with the causal depth of a computation. GridSMR scales single-validator execution to 1.07M requests/s and four-validator execution to 193K committed requests/s, while reducing 16-hop causal-chain latency by 8.2x versus deferred execution.