update fosdem 2024 ddffirst strncpy section on slides

diff --git a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
index c02d755c2b5197daa67d39bf8dc47e0f1c65a83b..de1d19eb076dd3c5295fc723a8433986ce62e9ba 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
@@ -102,12 +102,6 @@ for (i = 0; i < VL; i++)
         identical to general-purpose Simple-V DD-FFirst...
     \end{itemize}
 
-}Po
-
-\frame{\frametitle{maxloc}
-  \begin{itemize}
-        \item "TODO
-  \end{itemize}
 }
 
 \frame{\frametitle{Pospopcount}
@@ -153,26 +147,34 @@ for (i = 0; i < VL; i++)
 
 }
 
-\frame{\frametitle{Pospopcount.s}
+\frame{\frametitle{pospopcount assembler}
 
 
 \lstinputlisting[language={}]{pospopcount.s}
 
 }
 
-
 \frame{\frametitle{strncpy}
 
     \lstinputlisting[language={}]{strncpy.c}
   \begin{itemize}
-    \item two simple-looking for-loops, unfortunately sequentially
+    \item two simple-looking for-loops,
           data-dependent in the first.
-     \item Power ISA added a hard-coded variant of this inner
-          data-dependent capacity into VSX - only for strcpy!
+    \item sv.cmpi stops at the first zero, /vli includes the zero
+          in VL.
+    \item note the post-increment Load/Store: saves       
+          pre-decrementing
+    \item a Vector of CRs is produced which then get tested
+          by the sv.bc/all instruction, counting down CTR
+          per item tested.
+     \item Power ISA added hard-coded data-dependent capacity
+           into vstribr, where SVP64 it is generic (applies
+           to any instruction)
      \item even the null-ing part is not straightforward as
           it could be mis-aligned compared to the VSX width.
-     \item end-result is that assembler-optimised strncpy on Power
-           ISA v3.0 is a whopping 240 instructions. SVP64 is 10
+     \item end-result: assembler-optimised  strncpy on Power
+          ISA v3.0 is a whopping 240 instructions. SVP64 is 10
+          and parallel in HW
  \end{itemize}
 }
 
@@ -214,6 +216,12 @@ for (i = 0; i < VL; i++)
        \end{center}
 }
 
+\frame{\frametitle{maxloc}
+       \begin{itemize}
+               \item "TODO
+       \end{itemize}
+}
+
 \frame{\frametitle{Summary}
 
  \begin{itemize}

diff --git a/conferences/fosdem2024/fosdem2024_ddffirst/strncpy.c b/conferences/fosdem2024/fosdem2024_ddffirst/strncpy.c
index 0c76efa2a41ba75d806383b48340f49cb9a06134..af65f16de3949af83b805473f9b4e5ecd247e6ea 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/strncpy.c
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/strncpy.c
@@ -1,4 +1,2 @@
-for (i = 0; i < n && src[i] != chr(0); i++)
-    dest[i] = src[i];
-for ( ; i < n; i++)
-    dest[i] = chr(0);
+for (i=0; i<n && src[i]!=0; i++) dest[i] = src[i];
+for (   ; i<n             ; i++) dest[i] = chr(0);