COMMENT ⊗   VALID 00003 PAGES
C REC  PAGE   DESCRIPTION
C00001 00001
C00002 00002	Here is the raw data. As you can see, the FFT benchmark shows
C00007 00003	(fasload fft)
C00008 ENDMK
C⊗;
Here is the raw data. As you can see, the FFT benchmark shows
longer wholine time than the Model A time. This may be due to the
load average. FFT does floating arithmetic.

;;; BROWSE 100. 10. 4. (Model A)
(fasload browse)
(timit)
Timing performed on Sunday 02/13/83 at 14:27:32.
Cpu (- GC) Time = 13.896
Elapsed Time = 218.533333
Wholine Time = 100.266666
GC Time = 39.704
Load Average Before  = 2.77352154
Load Average After   = 2.62624335
Average Load Average = 2.69988245

type (13.896-12.043)/13.896
(13.896-12.043)/13.896 = .133347726
type (100.2666-82.68333)/100.2666
(100.2666-82.68333)/100.2666 = .175365176

;;; SAIL 100. 10. 4. (model B)
(fasload browse)
(timit)
Timing performed on Sunday 02/27/83 at 20:20:13.
Cpu (- GC) Time = 12.043
Elapsed Time = 274.05
Wholine Time = 82.683333
GC Time = 35.696
Load Average Before  = 0.76563597
Load Average After   = 3.6514511
Average Load Average = 2.20854354
NIL 

;;; PUZZLE (Model A)
(fasload puzzle)
(timit)
success in 2005 trials
Cpu Time = 8.736
Elapsed Time = 15.4666667
Wholine Time = 12.85
GC time = 0.421
Load Average Before = 0.560385704
Load Average After  = 0.62576735

type (8.736-7.865)/8.736
(8.736-7.865)/8.736 =  .099702381
type (12.85-11.8333)/12.85
(12.85-11.8333)/12.85 = .0791206226

;;; PUZZLE (model B)
success in 2005 trials
Cpu Time = 7.865
Elapsed Time = 14.5666667
Wholine Time = 11.8333334
GC time = 0.0
Load Average Before = 0.63950753
Load Average After  = 0.70015371
NIL 

;;; FFT  (Model A)
;;; (This one does floating arithmetic. Different load averages
;;;  may explain slower WHOLINE (???))
(fasload fft)
(fasload ttime fas dsk (mac lsp))
(timit)

Cpu Time = 4.392
Elapsed Time = 8.15
Wholine Time = 8.1333333
GC time = 1.463
Load Average Before = 0.32191658
Load Average After  = 0.361239552

type (4.392-4.004)/4.392
(4.392-4.004)/4.392 =  .0883424408
type (8.1333-9.8666)/8.1333
(8.1333-9.8666)/8.1333 = -.213111529

;;; FFT (Model B)
Cpu Time = 4.004
Elapsed Time = 23.9
Wholine Time = 9.8666667
GC time = 1.833
Load Average Before = 1.12649739
Load Average After  = 1.4469099


rpg - Actually my results are mixed and disappointing. I ran 3 benchmarks
from my suite of Lisp benchmarks - the benchmarks I use to compare Lisp
implementations. I gather more information from these benchmarks than shown
below; I am only reporting the percentage improvement in CPU and WHOLINE
times by the Model B CPU over the Model A CPU.  I would say that the new CPU
is 10% faster than the old CPU. The WHOLINE times, which estimates CPU plus
memory box activity, vary between 17.5% faster and 21% slower than before.
I have at least 3 runs of each benchmark on each CPU, and these are the
best shown improvements.

The first benchmark creates a AI-style data base using property lists
and browses that data base, performing pattern matches. The second
is Forest Baskett's PUZZLE benchmark translated from PASCAL to Lisp. The
last is the Harry Barrow FFT benchmark; it is floating-point arithmetic 
intensive.

13.33 (cpu)
17.54 (wholine)

9.97 (cpu)
7.91 (wholine)

8.83 (cpu)
-21.31 (wholine)
(fasload fft)
(fasload ttime fas dsk (mac lsp))
(timit)

Cpu Time = 4.0
Elapsed Time = 10.4166666
Wholine Time = 9.3833333
GC time = 2.914
Load Average Before = 0.296131015
Load Average After  = 0.35368061
NIL 

Cpu Time = 4.001
Elapsed Time = 10.3833333
Wholine Time = 9.4666667
GC time = 2.902
Load Average Before = 0.337160707
Load Average After  = 0.392315626
NIL 

Cpu Time = 4.0
Elapsed Time = 11.4833333
Wholine Time = 9.65
GC time = 2.906
Load Average Before = 0.380419016
Load Average After  = 0.451439977
NIL