What does Concurrent Coupling and Blackboard Reuse conclude, in numbers, about “Serial Fraction and Coherence Overhead: Why Throughput Has a Peak”?
Answer: Chapter 1 shows where the peak comes from, near 6.78 windows under illustrative parameters.
Scope of the numbers: Parameters are illustrative, data are synthetic, and every figure is generated by the book's programs; the book is not individual business advice and promises no speed-up. Chapter 1 shows where the peak comes from, near 6.78 windows under illustrative parameters.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 6.78
| A. speed-up by number of nodes, s = sigma | 0.08, kappa = 0.02 |
| N Amdahl Gustafson USL USL/N | |
| 1 | 1.00 1.00 1.00 1.000 |
| 2 | 1.85 1.92 1.79 0.893 |
| 4 | 3.23 3.76 2.70 0.676 |
| 6 | 4.29 5.60 3.00 0.500 |
| 7 | 4.73 6.52 3.02 0.431 |
| 8 | 5.13 7.44 2.99 0.373 |
| 12 | 6.38 11.12 2.65 0.221 |
| 16 | 7.27 14.80 2.29 0.143 |
| 24 | 8.45 22.16 1.73 0.072 |
| 32 | 9.20 29.52 1.37 0.043 |
| B. N* | 6.78; best integer N = 7, C = 3.017 |
| Amdahl ceiling 1/s | 12.5; USL at N = 32 is 0.455 of its peak |
| C. N* and peak C over a grid (illustrative) | |
| sigma kappa N* C(N*) | |
| 0.02 | 0.005 14.00 6.45 |
| 0.02 | 0.020 7.00 3.57 |
| 0.02 | 0.050 4.43 2.42 |
| 0.08 | 0.005 13.56 4.75 |
| 0.08 | 0.020 6.78 3.02 |
| 0.08 | 0.050 4.29 2.18 |
| 0.15 | 0.005 13.04 3.63 |
| 0.15 | 0.020 6.52 2.56 |
| 0.15 | 0.050 4.12 1.95 |
Show the full program
# Chapter 1. p11: Amdahl, Gustafson and the universal scalability law.
# Amdahl: S(N) = 1 / (s + (1 - s) / N), a fixed job split N ways.
# Gustafson: S(N) = N - s (N - 1), the job grows with N.
# USL (Gunther): C(N) = N / (1 + sigma (N - 1) + kappa N (N - 1)),
# peak at N* = sqrt((1 - sigma) / kappa). sigma = 0.08 and
# kappa = 0.02 are illustrative values for writing windows, not data.
import math
SIGMA = 0.08
KAPPA = 0.02
def amdahl(n, s):
return 1.0 / (s + (1.0 - s) / n)
def gustafson(n, s):
return n - s * (n - 1)
def usl(n, sigma, kappa):
return n / (1.0 + sigma * (n - 1) + kappa * n * (n - 1))
def peak(sigma, kappa):
return math.sqrt((1.0 - sigma) / kappa)
if __name__ == "__main__":
print("A. speed-up by number of nodes, s = sigma = {:.2f},"
" kappa = {:.2f}".format(SIGMA, KAPPA))
print(" N Amdahl Gustafson USL USL/N")
for n in (1, 2, 4, 6, 7, 8, 12, 16, 24, 32):
c = usl(n, SIGMA, KAPPA)
print(" {:>4} {:6.2f} {:7.2f} {:5.2f} {:5.3f}".format(
n, amdahl(n, SIGMA), gustafson(n, SIGMA), c, c / n))
ns = peak(SIGMA, KAPPA)
best = max(range(1, 65), key=lambda k: usl(k, SIGMA, KAPPA))
print("B. N* = {:.2f}; best integer N = {}, C = {:.3f}".format(
ns, best, usl(best, SIGMA, KAPPA)))
print(" Amdahl ceiling 1/s = {:.1f}; USL at N = 32 is {:.3f}"
" of its peak".format(1.0 / SIGMA,
usl(32, SIGMA, KAPPA)
/ usl(best, SIGMA, KAPPA)))
print("C. N* and peak C over a grid (illustrative)")
print(" sigma kappa N* C(N*)")
for s in (0.02, 0.08, 0.15):
for k in (0.005, 0.02, 0.05):
p = peak(s, k)
print(" {:.2f} {:.3f} {:5.2f} {:5.2f}".format(
s, k, p, usl(p, s, k)))Single source and citation
Fan, Y. (2026). Topological Coupling of Concurrent Multi-Core Operations: Lock-Free Blackboard Signalling and Cross-Node Emergent Gains (Version 1.0.0), Chapter 1: Serial Fraction and Coherence Overhead: Why Throughput Has a Peak. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-411 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026411,
author = {Fan, Yafu},
title = {Topological Coupling of Concurrent Multi-Core Operations: Lock-Free Blackboard Signalling and Cross-Node Emergent Gains},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 2 · Fitting σ and κ from Throughput Records: Least Squares, Bootstrap Intervals and Design
- Chapter 3 · Exclusive-Create Locks: Conflict Rates, the Cost of Moving On, and Lost Updates
- Chapter 4 · The Append-Only Blackboard: Lock-Free Reads, Hash De-duplication and the Cost of Subscribing
- Chapter 5 · Coupling Topology and Search: Isolation, Ring, Small World and Full Connection on NK Landscapes
- Chapter 6 · Emergence as Measurable Reuse: Hypergraph Incidence and the Net Gain of Coupling
- Chapter 7 · Eastern and Western Sources Examined: Sunzi on Division, the Analects on Harmony, Windowless Monads and Smith's Division of Labour
- Chapter 8 · Field Tools and Checker Specifications: the Concurrency Ledger, Four-Kit Clauses and a Pre-Registered Test