whitespace

[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..06301e8998b12505898bd0677ce316c5830e362e 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
@@ -84,7 +84,7 @@
                heat sink normally not required (simplifies overall design)
                \vspace{3pt}
    \item Fully-integrated peripherals (not Northbridge/Southbridge)\\
-         USB, HDMI, RGB/TTL, SD/MMC, I2C, UART, SPI, GPIO etc. etc. 
+         USB, HDMI, RGB/TTL, SD/MMC, I2C, UART, SPI, GPIO etc. etc.
          \vspace{3pt}
    \item Built-in GPU (shared memory bus, 3rd party licensed) \vspace{3pt}
    \item Built-in VPU (likewise, proprietary)\vspace{3pt}
@@ -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}
@@ -174,18 +183,26 @@ 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
+    \item https://github.com/clausecker/pospop
+
    \end{itemize}
        
        \lstinputlisting[language={}]{pospopcount.c}
+
        
 }
 
 \frame{\frametitle{Pospopcount}
        
        \begin{center}
-               \includegraphics[width=0.6\textwidth]{pospopcount.png}
+               \includegraphics[width=0.5\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 +210,14 @@ 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 standard popcount.
+                          (gbbd is based on Power ISA vgbbd, v3.1 p445)
+       
+       \end{itemize}
        
 }
 
@@ -206,16 +231,13 @@ 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}
 
@@ -243,7 +265,7 @@ for (i = 0; i < VL; i++)
          development costs for customers
    \item It also happens to be fascinating, deeply rewarding technically
          challenging, and funded by NLnet
-         
+
   \end{itemize}
 }
 
@@ -255,7 +277,7 @@ for (i = 0; i < VL; i++)
                   Questions?\vspace{12pt}
        }
   \end{center}
-  
+
   \begin{itemize}
        \item Discussion: http://lists.libre-soc.org
        \item Freenode IRC \#libre-soc