remove enough chars to get slide onto 1 page, pospopcount.s

diff --git a/conferences/fosdem2024/fosdem2024_ddffirst/pospopcount.s b/conferences/fosdem2024/fosdem2024_ddffirst/pospopcount.s
index c8347927f930cd08dfe62ce3b550b6892a3e1f4e..2b905f13557ed8c58a0d1f9ef34d32b8e19bdd89 100644 (file)
--- a/conferences/fosdem2024/fosdem2024_ddffirst/pospopcount.s
+++ b/conferences/fosdem2024/fosdem2024_ddffirst/pospopcount.s
@@ -1,14 +1,13 @@
-
-       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
\ No newline at end of file
+mtspr 9, 3              # move r3 to CTR
+setvl 3,0,8,0,1,1       # MVL=8, VL=r3=MIN(MVL,CTR)
+# load VL bytes (update r4 addr) but width=8 (dw=8)
+addi 6, 0, 0            # set 64-bits of r6=0
+sv.lbzu/pi/dw=8 *6, 1(4) 
+# gather performs transpose (gets us to positional)
+gbbd 8,6
+# now bits are turned around, popcount and sum them
+setvl 0,0,8,0,1,1       # set MVL=VL=8
+sv.popcntd/sw=8 *24,*8  # do (transposed) popcnt
+sv.add *16,*16,*24      # accumulate in results
+# branch back if CTR non-zero. works even when VL=8
+sv.bc/all 16, *0, -0x28 # reduce CTR by VL