Computer Architecture

Hennessy, J. L., & Patterson, D. A. (2019). Computer Architecture: A Quantitative Approach. Morgan Kaufmann.

Type

Book

Intellectual base

Review or monograph

Year

2019

Link

https://www.elsevier.com/books/computer-architecture/hennessy/978-0-12-811905-1

Cited from

economics_finance, engineering_design, pharmacology_toxicology

Cited by

5 citations across 5 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Loading Dose
  • In cache and memory systems, cache warming, prefetching, and buffer pre-population at startup spare the first request the empty-cache penalty.

    This sourceCompulsory (cold-start) cache misses and hardware/software prefetching to pre-populate the cache and avoid the empty-cache penalty on first access.

• Reserve
  • Computing: Memory buffers, free-list headroom, swap space, and CPU headroom — all surpluses held against bursty demand, GC pauses, or peak-load spikes, with Hennessy and Patterson (2019) treating the memory hierarchy itself as a stack of reserves sized against access-time and bandwidth contingencies.

    This sourceMorgan Kaufmann. Treats the memory hierarchy — register file, multi-level cache, main memory, swap — as a stack of capacity reserves sized against access-time, bandwidth, and miss-rate contingencies; the canonical computing reference for headroom-as-reserve.

• Specialization
  • Hennessy and Patterson (2019) frame domain-specific architectures as the central response to the end of general-purpose scaling — fixed-function silicon wins decisively on its target workload precisely by surrendering the breadth of a CPU.

    This sourceMorgan Kaufmann. Treats the memory hierarchy — register file, multi-level cache, main memory, swap — as a stack of capacity reserves sized against access-time, bandwidth, and miss-rate contingencies; the canonical computing reference for headroom-as-reserve.

Domain-specific

• Memory-bound function
  • … constitutive identity and a convenient observable transfers from A canonical example satisfies the full defining rule of Memory-bound function with assumptions and conventions explicit. to A careful use of Memory-bound function tests the constitutive rule and nearest confusable rather than relying on the label alone..
• Parallel computing
  • Parallel computing is computation in which multiple operations make physical progress at the same time, using bit-, instruction-, data-, task-, or pipeline-level parallelism across hardware resources.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:c92103557bae · see in the full table