🚀 go-pugleaf

In article <1992Aug14.075240.8875@Informatik.TU-Muenchen.DE> MeyerGru@Informatik.TU-Muenchen.DE (Uwe Meyer-Gruhl) writes:

>The actual number I am using is even larger, I use 384 buffers, but that
>is probably too much for most people. So here is the corrected sdmach.binpatch
>with 128 buffers:
>
>sdmach.binpatch:
>---- CUT HERE ----
>334079 166 116
>334080  20 161
>334081  43 116
>334082 303 161
>334083   4 116
>334084  11 161
>334085  70 116
>334086  24 161
>579602   0   1
>579607 240 217
>579608 214 206
>604776   0 200
>---- CUT HERE ----

Hi,

I had a quick question for you concerning this patch.  I have been using
a similar modification consisting of only the word at 604776 and I do see
a noticeable difference in performance.  Do have any evidence to confirm
that it is necessary to NOP out the other instructions that you refer to?

--Marc

P.S.  I'm glad to see that binpatch has proved to be useful.  It's neat to
      hear about other people's experiences with *fixing* binaries.

P.P.S  I have been using 0x40 = 0100 = 64 = 512KB of buffers on a 40MB cube.
       Did you do any testing with differing values and if so what did you
       find?  It would be nice if NeXT had some sort of adaptive algorithm
       based on the amount of total system RAM.