hexagon: bump the thread count in the adb wrapper scripts

We can use more CPU cores now that the dedicated dspqueue polling threads are not used (ie no contention).
Also enable more agressive polling for now since we still map Flash Attention (and a few other kernels) to
the CPU and those dspqueue threads were keeping the CPU cores are higher clock freqs.

Author: max-krasnyansky

scripts/snapdragon/adb/run-bench.sh

@@ -35,5 +35,6 @@ adb $adbserial shell " \
   LD_LIBRARY_PATH=$basedir/$branch/lib   \
   ADSP_LIBRARY_PATH=$basedir/$branch/lib \
     $ndev $nhvx $opmask ./$branch/bin/llama-bench --device $device --mmap 0 -m $basedir/../gguf/$model \
-        -t 4 --batch-size 128 -ngl 99 $@ \
+        --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 \
+        --batch-size 128 -ngl 99 $@ \
 "

scripts/snapdragon/adb/run-cli.sh

@@ -45,8 +45,9 @@ adb $adbserial shell " \
   cd $basedir; ulimit -c unlimited;        \
     LD_LIBRARY_PATH=$basedir/$branch/lib   \
     ADSP_LIBRARY_PATH=$basedir/$branch/lib \
-    $verbose $experimental $sched $opmask $profile $nhvx $ndev           \
-      ./$branch/bin/llama-cli --no-mmap -m $basedir/../gguf/$model       \
-         -t 4 --ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on \
+    $verbose $experimental $sched $opmask $profile $nhvx $ndev       \
+      ./$branch/bin/llama-cli --no-mmap -m $basedir/../gguf/$model   \
+         --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1             \
+         --ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on \
          -ngl 99 --device $device $cli_opts $@ \
 "