mirror of
https://github.com/wolfpld/tracy.git
synced 2024-11-25 15:34:36 +00:00
Update DXT1 benchmark with Ryzen timings.
Measured at the most commonly reached frequency. Data for peak at max achieved frequency: Reference: 173.2 us SSE: 22.2 us AVX2: 13.4 us
This commit is contained in:
parent
29dfb151cb
commit
b7f32c2a4c
@ -687,9 +687,9 @@ To further reduce image data size, frame images are internally compressed using
|
||||
\centering
|
||||
\begin{tabular}[h]{c|c|c}
|
||||
\textbf{Implementation} & \textbf{Required define} & \textbf{Time} \\ \hline
|
||||
x86 Reference & --- & 194.5 \si{\micro\second} \\
|
||||
x86 SSE4.1\textsuperscript{a} & \texttt{\_\_SSE4\_1\_\_} & 32 \si{\micro\second} \\
|
||||
x86 AVX2 & \texttt{\_\_AVX2\_\_} & 18.5 \si{\micro\second} \\
|
||||
x86 Reference & --- & 198.2 \si{\micro\second} \\
|
||||
x86 SSE4.1\textsuperscript{a} & \texttt{\_\_SSE4\_1\_\_} & 25.4 \si{\micro\second} \\
|
||||
x86 AVX2 & \texttt{\_\_AVX2\_\_} & 15.3 \si{\micro\second} \\
|
||||
ARM Reference & --- & 1.04 \si{\milli\second} \\
|
||||
ARM32 NEON\textsuperscript{b} & \texttt{\_\_ARM\_NEON} & 529 \si{\micro\second} \\
|
||||
ARM64 NEON & \texttt{\_\_ARM\_NEON} & 438 \si{\micro\second}
|
||||
@ -697,7 +697,7 @@ ARM64 NEON & \texttt{\_\_ARM\_NEON} & 438 \si{\micro\second}
|
||||
|
||||
\vspace{1em}
|
||||
\textsuperscript{a)} VEX encoding; \hspace{0.5em} \textsuperscript{b)} ARM32 NEON code compiled for ARM64
|
||||
\caption{Client compression time of $320\times180$ image. x86: i7 8700K (MSVC); ARM: ODROID-C2 (gcc).}
|
||||
\caption{Client compression time of $320\times180$ image. x86: Ryzen 9 3900X (MSVC); ARM: ODROID-C2 (gcc).}
|
||||
\label{EtcSimd}
|
||||
\end{table}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user