Architecture Glossary

Terms you must own

• IPC — instructions retired per cycle on a named workload.

• MPKI — cache misses per thousand instructions.

• MSHR — miss status holding register; limits memory-level parallelism.

• Roofline — binds compute peak and memory bandwidth against arithmetic intensity.

• MESI/MOESI — cache coherence states governing sharing and ownership.

• VC — virtual channel in NoCs; isolates traffic classes and helps avoid protocol deadlock.

• QoS — quality of service; protects latency-critical traffic under contention.

• False sharing — independent data in the same cache line causing coherence traffic.

• Arithmetic intensity — operations per byte moved from memory.

• Tail latency — high-percentile latency, often more important than average.

Architecture deep dive

Computer architecture decisions must be tied to workload metrics and silicon constraints.

Concept diagram

ARCHITECTURE DECISION LOOP

workload → metric → bottleneck mechanism → experiment → design option → validation

Metric graph

METRIC TREND

bad run  ██████████
base     ██████████████
target   ████████████████████

Metrics and artifacts

• IPC/CPI

• latency

• bandwidth

• power

• area

• verification risk

Mini case study

A senior architecture review converts a vague performance issue into a metric, a mechanism, an experiment, and a bounded design choice.

Debug branches

• If the metric is not workload-specific, do not accept the conclusion.

• If the fix has no PPA and verification statement, the review is incomplete.

Senior review question

Ask: what single metric would prove this concept is working or failing on your workload?

Key takeaways

• Connect every architecture claim to a workload and measurable metric.

• State verification and PPA impact before proposing design changes.

Common pitfalls

• Feature-driven design without MPKI/IPC/bandwidth evidence.

• Ignoring coherency and NoC traffic in cache and accelerator sizing.