资源、性能与 benchmarkbenchmark
Decoder 延迟与吞吐 benchmark
在指定 syndrome 流和部署环境上测量解码器平均与尾延迟、持续吞吐、积压和准确率。
- 成熟度
- research
- 重要度
- 核心主题
- 证据
- 3 篇代表来源
01
范围与辨析
必须报告处理器或 FPGA/ASIC、并行度、批量或流式模式、码距、轮速、尾延迟分位数、积压规则和解码质量;离线平均时间不能代表闭环能力。
02
核心机制与研究判断
核心机制
- tail latency
- sustained throughput
- backlog
- deployment target
- accuracy trade-off
适用与评测约束
- Provenance
- sourceRelationIds required
- Uncertainty
- required or not reported
- Artifact Version
- required or not found
- Source Checked At
- 2026-07-28
03
全栈位置与直接关系
benchmark/decoder/latency-throughput04
代表证据
前沿代表2025
Sparse Blossom: correcting a million errors per core second with minimum-weight matchingOscar Higgott and Craig GidneyBenchmark2023
Parallel window decoding enables scalable fault tolerant quantum computationLuka Skoric, Dan E. Browne, Kenton M. Barnes, Neil I. Gillespie and Earl T. CampbellBenchmark2025
A real-time, scalable, fast and resource-efficient decoder for a quantum computerBen Barber et al.