Bug 1244: changes to description pospopcount

[libreriscv.git] / conferences / fosdem2024 / fosdem2024_ddffirst / fosdem2024_ddffirst.tex

diff --git a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
index b40245d2889646abb2931cbd83cc56e4ea2abe97..58550e9924ebba6c72e407f02f245cbe5dddb5ca 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
@@ -161,7 +161,16 @@ for (i = 0; i < VL; i++)
        \end{itemize}
 \end{frame}
 
-
+\frame{\frametitle{Power ISA v3.1 vstribr}
+       
+       \lstinputlisting[language={}]{vstribr.txt}
+       
+       \begin{itemize}
+               \item ironically this hard-coded instruction is
+               identical to general-purpose Simple-V DD-FFirst...
+       \end{itemize}
+       
+}Po
 
 \frame{\frametitle{maxloc}
   \begin{itemize}
@@ -174,6 +183,7 @@ for (i = 0; i < VL; i++)
   \begin{itemize}
        \item   Positional popcount adds up the totals of each bit set to 1 in each bit-position, of an array of input values.
        \item   Notoriously difficult to do in SIMD assembler: typically 550 lines
+
    \end{itemize}
        
        \lstinputlisting[language={}]{pospopcount.c}
@@ -185,7 +195,12 @@ for (i = 0; i < VL; i++)
        \begin{center}
                \includegraphics[width=0.6\textwidth]{pospopcount.png}
        \end{center}
-       
+         \begin{itemize}
+               \item   The challenge is to perform an appropriate transpose of the data (the CPU can only work on registers, horizontally),
+               in blocks that suit the processor and the ISA capacity.
+
+               
+       \end{itemize}
 }
 
 \frame{\frametitle{Pospopcount}
@@ -193,6 +208,14 @@ for (i = 0; i < VL; i++)
        \begin{center}
                \includegraphics[width=0.6\textwidth]{array_popcnt.png}
        \end{center}
+
+  \begin{itemize}
+
+               \item   The draft gbbd instruction implements the transpose (shown above), 
+                               preparing the data to use the standard popcount instruction.
+
+       
+       \end{itemize}
        
 }
 
@@ -206,16 +229,13 @@ for (i = 0; i < VL; i++)
 
 \frame{\frametitle{strncpy}
 
+       \lstinputlisting[language={}]{strncpy.c}
   \begin{itemize}
        \item "TODO
  \end{itemize} 
 }
 
-\frame{\frametitle{strncpy.c}
-       
-       \lstinputlisting[language={}]{strncpy.c}
-       
-}
+
 
 \frame{\frametitle{strncpy assembler}