mirror/tracy
1
0
Fork 0
mirror of https://github.com/wolfpld/tracy.git synced 2024-11-29 16:54:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add ARM64 NEON timings for DXT1 compression.

Browse Source
This commit is contained in:
Bartosz Taudul 2019-07-13 15:32:07 +02:00
parent 0c5ea710b0
commit 5633dc5a87
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
manual/tracy.tex
View File

@ -460,12 +460,16 @@ To further reduce image data size, frame images are internally compressed using
\begin{tabular}[h]{c|c|c} \begin{tabular}[h]{c|c|c}
\textbf{Implementation} & \textbf{Required define} & \textbf{Time} \\ \hline \textbf{Implementation} & \textbf{Required define} & \textbf{Time} \\ \hline
x86 Reference & --- & 228 \si{\micro\second} \\ x86 Reference & --- & 228 \si{\micro\second} \\
x86 SSE4.1 & \texttt{\_\_SSE4\_1\_\_} & 35.8 \si{\micro\second} \\ x86 SSE4.1\textsuperscript{a} & \texttt{\_\_SSE4\_1\_\_} & 35.8 \si{\micro\second} \\
x86 AVX2 & \texttt{\_\_AVX2\_\_} & 26.5 \si{\micro\second} \\ x86 AVX2 & \texttt{\_\_AVX2\_\_} & 26.5 \si{\micro\second} \\
ARM Reference & --- & 1.23 \si{\milli\second} \\ ARM Reference & --- & 1.23 \si{\milli\second} \\
ARM NEON & \texttt{\_\_ARM\_NEON} & 551 \si{\micro\second} ARM32 NEON\textsuperscript{b} & \texttt{\_\_ARM\_NEON} & 561 \si{\micro\second} \\
ARM64 NEON & \texttt{\_\_ARM\_NEON} & 473 \si{\micro\second}
\end{tabular} \end{tabular}
\caption{Compression time of $320\times180$ image. x86: i7 8700K; ARM: ODROID-C2}
\vspace{1em}
\textsuperscript{a)} VEX encoding; \hspace{0.5em} \textsuperscript{b)} ARM32 NEON code compiled for ARM64
\caption{Compression time of $320\times180$ image. x86: i7 8700K; ARM: ODROID-C2.}
\label{EtcSimd} \label{EtcSimd}
\end{table} \end{table}