Add more benchmark results

README.md

@@ -36,11 +36,11 @@ To run the benchmarks: `cargo bench --bench throughput` (don't forget the env fl
 
 | Method           |      4 |     16 |     64 |    256 |   1024 |   4096 |  16384 |
 | ---------------- | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
-| t1ha-0 AVX2      |  0.921 | 3.5989 | 11.858 | 32.581 | 52.552 | 60.746 | 65.863 |
+| fnv1a            | 1.1027 | 2.6723 | 1.4874 |  0.933 |  0.835 |  0.814 |  0.808 |
+| xxhash           | 1.2613 | 2.9158 | 5.6045 | 6.2078 | 6.2819 | 6.2689 | 6.2985 |
+| t1ha-0 AVX2      | 1.1442 | 4.3088 | 11.858 | 32.581 | 52.552 | 60.746 | 65.863 |
 | gxhash-0 AVX2    | 11.638 | 46.132 | 40.365 | 134.11 | 143.55 | 155.34 | 168.65 |
 
-| gxhash-0 AVX-512 | 10.927 | 43.136 | 40.365 | 68.942 | 136.63 | 112.16 | 105.32 |
-
 I suspect memory bandwidth to be very high on this GCP server, which is one less bottleneck for gxhash to achieve even greater throughput for small input sizes.
 
 ### AMD Ryzen 5 5625U

article/article.tex

@@ -574,12 +574,12 @@ \subsubsection{Quality Results}
 \hline
 \textbf{Function for MarkovWords dataset} & \textbf{Collisions} & \textbf{Bits Distribution} & \textbf{Distribution} & \textbf{Avalanche} \\
 \hline
-Int32 GxHash0(64)                & 0,0136\% & 0,001082  & 0,000002 & 0,00319 \\
-Int32 GxHash0(1000)              & 0,0119\% & 0,000894  & 0,000002 & 0,0034 \\
-Int32 HighwayHash(64)            & 0,0123\% & 0,000809  & 0,000002 & 0,00048 \\
-Int32 HighwayHash(1000)          & 0,0117\% & 0,00092   & 0,000002 & 0,00078 \\
-Int32 T1ha(64)                   & 0,0111\% & 0,000803  & 0,000002 & 0,00064 \\
-Int32 T1ha(1000)                 & 0,0123\% & 0,001175  & 0,000002 & 0,00135 \\
+UInt32 GxHash0(64)                & 0,0136\% & 0,001082  & 0,000002 & 0,00319 \\
+UInt32 GxHash0(1000)              & 0,0119\% & 0,000894  & 0,000002 & 0,0034 \\
+UInt32 HighwayHash(64)            & 0,0123\% & 0,000809  & 0,000002 & 0,00048 \\
+UInt32 HighwayHash(1000)          & 0,0117\% & 0,00092   & 0,000002 & 0,00078 \\
+UInt32 T1ha(64)                   & 0,0111\% & 0,000803  & 0,000002 & 0,00064 \\
+UInt32 T1ha(1000)                 & 0,0123\% & 0,001175  & 0,000002 & 0,00135 \\
 UInt32 XxHash(64)                & 0,0106\% & 0,000766  & 0,000002 & 0,00046 \\
 UInt32 XxHash(1000)              & 0,01\%   & 0,000892  & 0,000002 & 0,00021 \\
 UInt32 Fnv1a(64)                 & 0,0122\% & 0,000998  & 0,000002 & 0,08585 \\
@@ -592,6 +592,13 @@ \subsubsection{Quality Results}
 \label{tab:my_label}
 \end{table}
 
+\begin{figure}[H]
+\centering
+\includegraphics[width=1\textwidth]{quality-markov.png}
+\caption{Distribution map for markov dataset}
+\label{fig:quality-sequential}
+\end{figure}
+
 \clearpage
 \subsection{Performance}
 
@@ -600,10 +607,15 @@ \subsection{Performance}
 \begin{figure}[H]
 \centering
 \includegraphics[width=1\textwidth]{throughput.png}
-\caption{Throughput Benchmark Results}
 \label{fig:benchmark-throughput}
 \end{figure}
 
+\begin{figure}[H]
+\centering
+\includegraphics[width=1\textwidth]{throughput-gcp.png}
+\label{fig:benchmark-throughput-gcp}
+\end{figure}
+
 \section{Discussion}
 \subsection{Implications}
 \subsection{Limitations}