For these tables to fit column width of 2c builds, make changes as
follows:
- Move prefix of "Same-CPU", "In-Core", etc. to a separate
row.
- Add \midrule between different classes of counterpart CPUs.
- Stop coloring alternative rows.
- Shrink "CPUs" column width by spanning two rows.
Define \tcresizewidth{} ("tc" stands for "two column") and use it
for slightly wide tables in 2c builds.
To improve consistency among these tables:
- Uppercase "In-Core", "Off-Core", Off-System", and "Blind CAS".
Reported-by: Leonardo Bras <leobras.c@xxxxxxxxx>
Link: [1] https://www.spinics.net/lists/perfbook/msg03827.html
Signed-off-by: Akira Yokosawa <akiyks@xxxxxxxxx>
---
cpu/overheads.tex | 143 +++++++++++++++++++++++++++++-----------------
perfbook-lt.tex | 6 ++
2 files changed, 97 insertions(+), 52 deletions(-)
diff --git a/cpu/overheads.tex b/cpu/overheads.tex
index a89c71158bf9..7ae99ed6cb7b 100644
--- a/cpu/overheads.tex
+++ b/cpu/overheads.tex
@@ -133,44 +133,62 @@ optimization.
\subsection{Costs of Operations}
\label{sec:cpu:Costs of Operations}
-\begin{table*}
-\rowcolors{1}{}{lightgray}
+\begin{table}
+%\rowcolors{1}{}{lightgray}
\renewcommand*{\arraystretch}{1.1}
\centering\small
-\ebresizewidth{
+\tcresizewidth{
\begin{tabular}
{
- l
+ ll
S[table-format = 9.1]
S[table-format = 9.1]
r
}
\toprule
- Operation & \multicolumn{1}{r}{Cost (ns)}
+ \multicolumn{2}{l}{Operation}
+ & \multicolumn{1}{r}{Cost (ns)}
& {\parbox[b]{.7in}{\raggedleft Ratio\\(cost/clock)}}
& CPUs \\
\midrule
- Clock period & 0.5 & 1.0 & \\
- Same-CPU CAS & 7.0 & 14.6 & 0 \\
- Same-CPU lock & 15.4 & 32.3 & 0 \\
- In-core blind CAS & 7.2 & 15.2 & 224 \\
- In-core CAS & 18.0 & 37.7 & 224 \\
- Off-core blind CAS & 47.5 & 99.8 & 1--27,225--251 \\
- Off-core CAS & 101.9 & 214.0 & 1--27,225--251 \\
- Off-socket blind CAS & 148.8 & 312.5 & 28--111,252--335 \\
- Off-socket CAS & 442.9 & 930.1 & 28--111,252--335 \\
- Cross-interconnect blind CAS & 336.6 & 706.8 & 112--223,336--447 \\
- Cross-interconnect CAS & 944.8 & 1984.2 & 112--223,336--447 \\
+ \multicolumn{2}{l}{Clock period}
+ & 0.5 & 1.0 & \\
+ \midrule
+ \multicolumn{2}{l}{Same-CPU}
+ & & & 0 \\
+ & CAS & 7.0 & 14.6 & \\
+ & lock & 15.4 & 32.3 & \\
\midrule
- Off-System & & & \\
- Comms Fabric & 5 000 & 10 500 & \\
- Global Comms & 195 000 000 & 409 500 000 & \\
+ \multicolumn{2}{l}{In-Core}
+ & & & 224 \\
+ & Blind CAS& 7.2 & 15.2 & \\
+ & CAS & 18.0 & 37.7 & \\
+ \midrule
+ \multicolumn{2}{l}{Off-Core}
+ & & & 1--27 \\
+ & Blind CAS& 47.5 & 99.8 & 225--251 \\
+ & CAS & 101.9 & 214.0 & \\
+ \midrule
+ \multicolumn{2}{l}{Off-Socket}
+ & & & 28--111 \\
+ & Blind CAS& 148.8 & 312.5 & 252--335 \\
+ & CAS & 442.9 & 930.1 & \\
+ \midrule
+ \multicolumn{2}{l}{Cross-Interconnect}
+ & & & 112--223 \\
+ & Blind CAS& 336.6 & 706.8 & 336--447 \\
+ & CAS & 944.8 & 1984.2 & \\
+ \midrule
+ \multicolumn{2}{l}{Off-System}
+ & & & \\
+ & Comms Fabric & 5 000 & 10 500 & \\
+ & Global Comms & 195 000 000 & 409 500 000 & \\
\bottomrule
\end{tabular}
}
\caption{CPU 0 View of Synchronization Mechanisms on 8-Socket System With Intel Xeon Platinum 8176 CPUs @ 2.10\,GHz}
\label{tab:cpu:CPU 0 View of Synchronization Mechanisms on 8-Socket System With Intel Xeon Platinum 8176 CPUs at 2.10GHz}
-\end{table*}
+\end{table}
The overheads of some common operations important to parallel programs are
displayed in
@@ -311,36 +329,47 @@ thousand clock cycles.
\end{enumerate}
\begin{table}
-\rowcolors{1}{}{lightgray}
+%\rowcolors{1}{}{lightgray}
\renewcommand*{\arraystretch}{1.1}
\centering\small
\begin{tabular}
{
- l
+ ll
S[table-format = 9.1]
S[table-format = 9.1]
}
\toprule
- Operation & \multicolumn{1}{r}{Cost (ns)}
+ \multicolumn{2}{l}{Operation}
+ & \multicolumn{1}{r}{Cost (ns)}
& {\parbox[b]{.7in}{\raggedleft Ratio\\(cost/clock)}} \\
\midrule
- Clock period & 0.4 & 1.0 \\
- Same-CPU CAS & 12.2 & 33.8 \\
- Same-CPU lock & 25.6 & 71.2 \\
- Blind CAS & 12.9 & 35.8 \\
- CAS & 7.0 & 19.4 \\
+ \multicolumn{2}{l}{Clock period}
+ & 0.4 & 1.0 \\
+ \midrule
+ \multicolumn{2}{l}{Same-CPU}
+ & & \\
+ & CAS & 12.2 & 33.8 \\
+ & lock & 25.6 & 71.2 \\
+ \midrule
+ \multicolumn{2}{l}{In-Core}
+ & & \\
+ & Blind CAS & 12.9 & 35.8 \\
+ & CAS & 7.0 & 19.4 \\
\midrule
- Off-Core & & \\
- Blind CAS & 31.2 & 86.6 \\
- CAS & 31.2 & 86.5 \\
+ \multicolumn{2}{l}{Off-Core}
+ & & \\
+ & Blind CAS & 31.2 & 86.6 \\
+ & CAS & 31.2 & 86.5 \\
\midrule
- Off-Socket & & \\
- Blind CAS & 92.4 & 256.7 \\
- CAS & 95.9 & 266.4 \\
+ \multicolumn{2}{l}{Off-Socket}
+ & & \\
+ & Blind CAS & 92.4 & 256.7 \\
+ & CAS & 95.9 & 266.4 \\
\midrule
- Off-System & & \\
- Comms Fabric & 2 600 & 7 220 \\
- Global Comms & 195 000 000 & 542 000 000 \\
+ \multicolumn{2}{l}{Off-System}
+ & & \\
+ & Comms Fabric & 2 600 & 7 220 \\
+ & Global Comms & 195 000 000 & 542 000 000 \\
\bottomrule
\end{tabular}
\caption{Performance of Synchronization Mechanisms on 16-CPU 2.8\,GHz Intel X5550 (Nehalem) System}
@@ -366,38 +395,48 @@ thousand clock cycles.
\cref{tab:cpu:CPU 0 View of Synchronization Mechanisms on 8-Socket System With Intel Xeon Platinum 8176 CPUs at 2.10GHz}
down to and including the two ``Off-core'' rows.
-\begin{table*}
-\rowcolors{1}{}{lightgray}
+\begin{table}
+%\rowcolors{1}{}{lightgray}
\renewcommand*{\arraystretch}{1.1}
\centering\small
+\tcresizewidth{
\begin{tabular}
{
- l
+ ll
S[table-format = 9.1]
S[table-format = 9.1]
r
}
\toprule
- Operation & \multicolumn{1}{r}{Cost (ns)}
+ \multicolumn{2}{l}{Operation}
+ & \multicolumn{1}{r}{Cost (ns)}
& {\parbox[b]{.7in}{\raggedleft Ratio\\(cost/clock)}}
& CPUs \\
\midrule
- Clock period & 0.5 & 1.0 & \\
- Same-CPU CAS & 6.2 & 13.6 & 0 \\
- Same-CPU lock & 13.5 & 29.6 & 0 \\
- In-core blind CAS & 6.5 & 14.3 & 6 \\
- In-core CAS & 16.2 & 35.6 & 6 \\
- Off-core blind CAS & 22.2 & 48.8 & 1--5,7--11 \\
- Off-core CAS & 53.6 & 117.9 & 1--5,7--11 \\
+ \multicolumn{2}{l}{Clock period}
+ & 0.5 & 1.0 & \\
+ \midrule
+ \multicolumn{2}{l}{Same-CPU} & & & 0 \\
+ & CAS & 6.2 & 13.6 & \\
+ & lock & 13.5 & 29.6 & \\
+ \midrule
+ \multicolumn{2}{l}{In-Core} & & & 6 \\
+ & Blind CAS & 6.5 & 14.3 & \\
+ & CAS & 16.2 & 35.6 & \\
+ \midrule
+ \multicolumn{2}{l}{Off-Core} & & & 1--5 \\
+ & Blind CAS & 22.2 & 48.8 & 7--11 \\
+ & CAS & 53.6 & 117.9 & \\
\midrule
- Off-System & & & \\
- Comms Fabric & 5 000 & 11 000 & \\
- Global Comms & 195 000 000 & 429 000 000 & \\
+ \multicolumn{2}{l}{Off-System}& & & \\
+ & Comms Fabric & 5 000 & 11 000 & \\
+ & Global Comms & 195 000 000 & 429 000 000 & \\
\bottomrule
\end{tabular}
+}
\caption{CPU 0 View of Synchronization Mechanisms on 12-CPU Intel Core i7-8750H CPU @ 2.20\,GHz}
\label{tab:cpu:CPU 0 View of Synchronization Mechanisms on 12-CPU Intel Core i7-8750H CPU @ 2.20GHz}
-\end{table*}
+\end{table}
Furthermore, newer small-scale single-socket systems such
as the laptop on which I am typing this also have more
diff --git a/perfbook-lt.tex b/perfbook-lt.tex
index 13dd88b32d94..f970212cb194 100644
--- a/perfbook-lt.tex
+++ b/perfbook-lt.tex
@@ -533,6 +533,12 @@
\newcommand\ebFloatBarrier{}
}
+\IfTwoColumn{
+\newcommand{\tcresizewidth}[1]{\resizebox{\columnwidth}{!}{#1}}
+}{
+\newcommand{\tcresizewidth}[1]{#1}
+}
+
% Glossaries dictionary and custom settings
\input{glsdict}
--
2.25.1
