QEMU BNN performance (v3.61.3)

Hans Bezemer thebeez at xs4all.nl
Fri Sep 14 12:38:16 EDT 2012


On Friday 14 September 2012, you wrote:
> It would be fun to see how your 4tH performs in this environment
> as compared to running directly on Ben NN. On a sufficiently
> fast PC, my guess would be as good, maybe faster than Ben.

This is what bench/bench.4th returns:

Platform      OS       Forth       Compiler       Cell    Time
--------      --       -----       --------       ------  ----
Spectrum 48K  ZX-BASIC Artic Forth Z80 assembler  16 bit 53:50 mins
Sun Sp Ultra1 Solaris  4tH V3.2    GCC            32 bit  0:18 mins
RS/6000 250   AIX V3   4tH V3.2    XL C V1.3      32 bit  0:30 mins
P5/600        DOS V5   4tH V3.3    DJGPP V2.72    32 bit  0:05 mins
P5/600        Win 3.1  4tH V3.3    Turbo C++ V3.0 32 bit  0:06 mins
P5/166        DOS V5   4tH V3.2    DJGPP V2.72    32 bit  0:09 mins
P5/166        Win 3.1  4tH V3.2    Turbo C++ V3.0 32 bit  0:21 mins
486/33        DOS V5   4tH V3.2    Turbo C V2.0   32 bit  2:45 mins
486/33        DOS V5   4tH V3.2    DJGPP V2.72    32 bit  1:11 mins
486/33        DOS V5   FPC V3.55   8086 assembler 16 bit  0:29 mins
486/33        DOS V5   PFE V09.12  Unknown        32 bit  0:45 mins
486/33        DOS V5   CForth      Turbo C V2.0   16 bit 11:26 mins
486/66        DOS V5   NIB Forth   Unknown        16 bit 10:55 mins
486/66        Win V3.1 AtLast      Turbo C++ V3.0 16 bit  5:08 mins
486/66        Win V3.1 4tH V3.2    Turbo C++ V3.0 32 bit  1:23 mins
486/66        DOS V5   CForth      Turbo C V2.0   16 bit  5:45 mins
486/66        DOS V5   4tH V3.2    Turbo C V2.0   32 bit  1:22 mins
THIS COMPUTER Unknown  4tH V3.61   Unknown        32 bit  0:03 mins

root at BenNanoNote:~/4th#                                              

Try it on your own NanoNote and compare.

Hans Bezemer

-- 
Absolutely no trees were killed to produce this sig. Well, OK, we had to tie 
one up and torture it. That's it.

Visit our website! http://thebeez.home.xs4all.nl/4tH/

*** Home of the 4tH compiler! ***




More information about the discussion mailing list


interactive