mirror of
https://github.com/wolfpld/tracy.git
synced 2024-11-10 10:41:50 +00:00
Add ARM64 NEON timings for DXT1 compression.
This commit is contained in:
parent
0c5ea710b0
commit
5633dc5a87
@ -460,12 +460,16 @@ To further reduce image data size, frame images are internally compressed using
|
||||
\begin{tabular}[h]{c|c|c}
|
||||
\textbf{Implementation} & \textbf{Required define} & \textbf{Time} \\ \hline
|
||||
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} \\
|
||||
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}
|
||||
\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}
|
||||
\end{table}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user