Changeset e2e927e

Timestamp:

Apr 10, 2026, 10:55:49 PM (25 hours ago)

Author:

Michael Brooks <mlbrooks@…>

Branches:

master

Children:

e8a7b66d

Parents:

d1ccc57

Message:

Add the list perf non-physical comparison (as promised).

This commit is a save-snapshot before I pivot this comparison to compare all first-order effects, which really is the right context.

Location:

doc/theses/mike_brooks_MMath

Files:

• list.tex (modified) (4 diffs)
• plots/ListCommon.py (modified) (1 diff)
• plots/list-op-fx.d (added)
• plots/list-op-fx.gp (added)
• plots/list-op-fx.py (added)

doc/theses/mike_brooks_MMath/list.tex

@@ -993 +993 @@
 \VRef[Figure]{fig:plot-list-zoomin} has the pair machines, each in a column.
 It also has a pair of operating scenarios, each in a row.
-The experiment runs twelve operating scenarios; the ones chosen for their variety happen to be items I and VIII from the listing of \MLB{TODO: cross reference}.
+The experiment runs twelve operating scenarios; the ones chosen for their variety happen to be items I and VIII from the listing of \VRef[Figure]{fig:plot-list-mchn-szz}.
 Note that LQ-list does not support queue operations, so this framework is absent from Operation VIII.
 
@@ -1010 +1010 @@
 So these zones are used for basing comparison.
 
+\MLB{Peter, caution beyond here.  I am reconsidering if this first-dismiss-physical approach to comparison is simplest.}
+
 \begin{figure}
   \centering
   \includegraphics{plot-list-mchn-szz.pdf}
-  \caption{Histogram of operation durations, decomposed by physical factos.
-  Measurements are included from only the sizes in the ``small'' and ``medium'' stable zones.}
+  \caption{Histogram of operation durations, decomposed by physical factors.
+  Measurements are included from only the sizes in the ``small'' and ``medium'' stable zones.
+  This breakdown divides the entire population of test results into four mutually disjoint constituents.}
   \label{fig:plot-list-mchn-szz}
 \end{figure}
@@ -1025 +1028 @@
 From the perspective of assessing winning/losing frameworks, these physical effects are noise.
 So, subsequent analysis conditions on the phisical effects.
-That is, it presents results relative to the mean of the physical quadrant (\VRef[fig]{fig:plot-list-mchn-szz} histogram) to which it belogs.
+That is, it supposes you are put into an unknown physical situation (that is one of the four being tested), then presents all the ways your outcome could change as a result of non-physical factors, assuming that the physical situation is kept constant.
+It does do by presenting results relative to the mean of the physical quadrant (\VRef[fig]{fig:plot-list-mchn-szz} histogram) to which it belogs.
 With this adjustment, absolute duration values (in nonsecods) are lost.
 In return, the physical quadrants are re-combined, enabling assessment of the non-physical factors.
 
-\MLB{Peter, stop here.  Graph and discussion of these non-physical factos is coming.}
+\begin{figure}
+  \centering
+  \includegraphics{plot-list-op-fx.pdf}
+  \caption{Histogram of operation durations, decomposed by non-physical factors.
+  The twelve-way by-operation breakdown, and the four-way by-framework breakdown, each divides the entire population of test results into its mutually disjoint constituents.}
+  \label{fig:plot-list-op-fx}
+\end{figure}
+
+\VRef[Figure]{fig:plot-list-op-fx} gives this non-physical decomposition.
+
+\MLB{Peter, stop here.  Discussion of these non-physical factos is coming.}
 
 \begin{comment}
@@ -1038 +1052 @@
 On the server, \CFA and \uCpp lists are can be fast by up to 100\%.
 Overall, LQ-tailq does the best at short lengths but loses out above a dozen elements.
-
-\VRef[Figure]{f:RelativeTime} shows the percentage difference by treating @tailq@ as the control benchmark, and showing the other list results relative to it.
-This change does not affect the who-wins statements, it just removes the ``sweet spot'' bend that the earlier discussion dismissed as incidental.
-Runs faster than @tailq@'s are below the zero and slower runs are above;
-@tailq@'s mean is always zero by definition, but its error bars, representing a single scenario's re-run stability, are still meaningful.
-With this bend straightened out, aggregating across lengths is feasible.
 \end{comment}
 
-\begin{figure}
-\centering
-  \setlength{\tabcolsep}{0pt}
-  \begin{tabular}{p{0.75in}p{2.75in}p{3in}}
-  &
-  \subfloat[Supersets, AMD]{\label{f:Superset-swift}
-        \hspace*{-0.75in}
-        \includegraphics{plot-list-cmp-exout-swift.pdf}
-  } % subfigure
-  &
-  \subfloat[Supersets, Intel]{\label{f:Superset-java}
-        \includegraphics{plot-list-cmp-exout-java.pdf}
-  } % subfigure
-  \\
-  &
-  \subfloat[1st Level Slice, AMD]{\label{f:1stLevelSlice-swift}
-        \hspace*{-0.75in}
-        \includegraphics{plot-list-cmp-survey-swift.pdf}
-  } % subfigure
-  &
-  \subfloat[1st Level Slice, Intel]{\label{f:1stLevelSlice-java}
-        \includegraphics{plot-list-cmp-survey-java.pdf}
-  } % subfigure
-  \end{tabular}
-  \caption{Operation duration ranges across operational scenarios.  (a) has the supersets of the running example operation.  (b) has the first-level slices of the full space of operations.}
-  \label{fig:plot-list-cmp-overall}
-\end{figure}
-
-\VRef[Figure]{fig:plot-list-cmp-overall} introduces alternative views of the data.
-Part \ref*{f:Superset-swift}--\ref*{f:Superset-java}'s first column summarizes all the data of \VRef{f:RelativeTime}.
-Its x-axis label, ``stack/insfirst/allhead,'' names the concrete scenario that has been discussed until now.
-Moving across the columns, the next three each stretch to include more scenarios on each of the operation dimensions, one at a time.
-The second column considers the scenarios $\{\mathrm{stack}\} \times \{\mathrm{insfirst}\} \times \{\mathrm{allhead}, \mathrm{inselem}, \mathrm{remelem}\}$,
-while the third stretches polarity and the fourth stretches accessor.
-Then next three columns each stretch two scenario dimensions and the last column stretches all three.
-The \CFA bar in the last column is summarizing 840 test-program runs: 14 list lengths, 2 movements, 2 polarities, 3 accessors and 5 repetitions.
-
-In the earlier plots of a single scenario broken down by length, each data point, with its error bars, represents just 5 repetitions.
-With a couple exceptions, this reproducibility error was small.
-Now, for a \CFA bar, summarizing 70 (first column) to 840 (last column) runs, a bar's height is dominated by the different behaviours of the scenarios and list lengths that it summarizes.
-Accordingly, the first column's bars are short and last one's are tall.
-A box represents the inner 68\% of the durations, while its lines extend to cover 95\%.
-The symbol on the bar is the mean duration.
-
-The chosen benchmark of LQ-@tailq@ is not shown in this format because it would be trivial here.
-With iter-scenario differences dominating the bar size, and @tailq@'s mean performance defined to be zero in all scenarios, a @tailq@ bar on this plot would only show @tailq@'s re-run stability, which is of no comparison value.
-
-The LQ-@list@ implementation does not support all scenarios, only stack movement with insert-first polarity.
-So, its 1, 3, 4 and 7\textsuperscript{th} bars all summarize the same set of points (those with accessor constrained to all-head), as do its 2, 5, 6 and 8\textsuperscript{th} (those with accessor unconstrained).
-
-Rather than exploring from one scenario out, \VRef{fig:plot-list-cmp-overall}-(b) gives a more systematic breakdown of the entire experimental space.
-Other than the last grand-total column, each breakdown column shows one value from one operation dimension.
-
-LQ-@list@'s partial scenario coverage gives missing bars where it does not support the operation.
-And, again, it gives repetition where all data points occur in several columns' intersection, such as stack/*/* and */insfirst/*.
-
+
+\MLB{Here is the conclusion of the earlier analysis. It basically stands, but needs refreshing.}
 In the grand total, and in all halves by movement or polarity, \CFA and uC++ are equivalent, while LQ-@list@ beats them slightly.
 Splitting on accessor, \CFA has a poor result on element removal, LQ-@list@ has a great result on the other accessors, and uC++ is unaffected.

doc/theses/mike_brooks_MMath/plots/ListCommon.py

@@ -488 +488 @@
         histo.insert(y_lo_col_loc + 1, "y_hi", histo["y_lo"].apply(topValOfBucketBotVal))
 
-        header = str.join(', ', dkey)
+        dkey_str = list( map( str, dkey ) )
+        header = str.join(', ', dkey_str)
         print(f'"{header}"')
         text = histo.to_csv(header=False, index=False, sep='\t')