Bug1244:added code for pospopcount

diff --git a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
index c699eed90538f1390c2917664939339f92bf6f3c..fcdccdbc536f910c892fa59aff41f80d22ceaeb2 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/fosdem2024_ddffirst.tex
@@ -180,9 +180,34 @@ function op\_cmpi(BA, RA, SI) # cmpi not vector-cmpi!
   \end{itemize}
 }
 \frame{\frametitle{Pospopcount}
-  \begin{itemize}
-       \item "TODO
-  \end{itemize}        
+       \begin{semiverbatim}
+        // Copyright (c) 2020 Robert Clausecker <fuz@fuz.su>
+       // count8 reference implementation for tests.  Do not alter.
+       func count8safe(counts *[8]int, buf []uint8) {
+               for i := range buf {
+                       for j := 0; j < 8; j++ {
+                               counts[j] += int(buf[i] >> j & 1)
+                       }
+               }
+       }
+
+   A simple but still hardware-paralleliseable SVP64 assembler for 8-bit input values (count8safe) is as follows:
+
+       mtspr 9, 3                 # move r3 to CTR
+       setvl 3,0,8,0,1,1          # set MVL=8, VL=r3=MIN(MVL,CTR)
+       # load VL bytes (update r4 addr) but compressed (dw=8)
+       addi 6, 0, 0               # initialise all 64-bits of r6 to zero
+       sv.lbzu/pi/dw=8 *6, 1(4)   # should be /lf here as well
+       # gather performs the transpose (which gets us to positional..)
+       gbbd 8,6
+       # now those bits have been turned around, popcount and sum them
+       setvl 0,0,8,0,1,1          # set MVL=VL=8
+       sv.popcntd/sw=8 *24,*8     # do the (now transposed) popcount
+       sv.add *16,*16,*24         # and accumulate in results
+       # branch back if CTR still non-zero. works even though VL=8
+       sv.bc/all 16, *0, -0x28   # reduce CTR by VL and stop if -ve
+       \end{semiverbatim}
+
 }
 \frame{\frametitle{strncpy}
   \begin{itemize}