Thanks to Helge, my minor porting job on the old Green Book benchmarks
has been brought up to 2.8 capability.

http://sumeru.stanford.edu/tim/pooters/SqFiles/deltas/sqBenchmarks.cs

Just FYI, my 5 year old Acorn, running a 200MHz cpu with 16Kb(count'em!)
caches, 16MHz memory and no FPU compiled with a four year old
compiler gets:-

BitBLT		158.3333333333333
TextScanning		31200.0
ClassOrganizer		238.1889763779527
PrintDefinition		555.5555555555555
PrintHierachy		1162.790697674418
AllCallsOn		48.7540628385699
AllImplementors		179.5580110497238
Inspect		298.360655737705
Compiler		524.705882352941
Decompiler		248.0
KeyboardLookAhead		236.1111111111111
KeyboardSingle		262.019230769231
TextDisplay		126.1083743842364
TextFormatting		404.9295774647886
TextEditing		362.2317596566523
Performance Rating		367.0434379525636261594634083
and 0 tinyBenchmarks returns
10322580 bytecodes/sec and 373349 sends.sec

whereas my brand new 600MHz pentium3 with 1Mb caches, 133MHz memory and
an fpu compiled on the latest gcc gets
BitBLT		1257.48502994012
TextScanning		43943.661971831
ClassOrganizer		1495.488814732419
PrintDefinition		4607.046070460704
PrintHierachy		7507.50750750751
AllCallsOn		313.7583015217277
AllImplementors		1791.62072767365
Inspect		2721.29186602871
Compiler		4188.580015026296
Decompiler		1798.404641044235
KeyboardLookAhead		3143.491124260355
KeyboardSingle		2625.2408477842
TextDisplay		734.155434470892
TextFormatting		3954.607977991747
TextEditing		2136.708860759493
Performance Rating		2600.91381625157627578
and 0 tinyBenchmarks returns
44475330 bytecodes/sec and 1458439 sends.sec

Not too bad.

-- 
Tim Rowledge, tim at sumeru.stanford.edu, http://sumeru.stanford.edu/tim
It's 10 o'clock.  Do you know where your child processes are?