Benchmarking The Fastchip

By Clyde Spencer

The FASTCHIP, from Newell Industries, replaces the existing math package chip in the Operating System (OS) card. This chip substantially decreases the execution time of arithmetic operations. To determine how much faster our ATARI is with the new chip installed we need to talk a little about benchmarks.

Benchmarks are simple programs that compare specific operations in a computer. They may be designed to test a particular ability, such as the time required to perform an addition or multiplication, or they may be designed to test all operations. Probably the most usable benchmarks are those which attempt to simulate average operating conditions.

There is no general agreement as to what constitutes average conditions, let alone what is a standard benchmark. Here are two benchmarks, with similar running times, that I have some familiarity with.

The first benchmark was originally suggested by Greg Dolkus, formerly of the Homebrew Computer Club. This short program exercises your Central Processing Unit (CPU) by calculating the first prime number larger than one million:

  
10 FOR I = 1000001 TO 1000003 STEP 2
20 FOR D = 3 to SQR (I) STEP 2
30 IF I/D = INT(I/D) THEN 60
40 NEXT D 
50 PRINT I
60 NEXT I

The correct answer is 1000003; not all computers offer enough precision to give the correct answer. The ATARI does. Greg had reported the following times for various machines:

Apple II...5 seconds
Commodore Pet...6 seconds
OSI...6 seconds
TRS-80...12 seconds

A significant increase in speed can be accomplished with the ATARI by turning the ANTIC chip off. This can be done by POKEing a 0 in decimal location 559. The ANTIC chip can be reactivated with a 34 POKEd into 559. Because of the different speed options available in the ATARI, I will list several benchmark times.

Atari 400/800 (ANTIC ON, with original OS)...15 seconds
Atari 400/800 (ANTIC OFF, with original OS) ...11 seconds
Atari 400/800 (ANTIC ON, with FASTCHIP)...9.5 seconds
Atari 400/800 (ANTIC OFF, with FASTCHIP)...6.5 seconds

BASIC A + by Optimized Systems Software appeared to run about 1/4 second faster in all cases. Microsoft BASIC was unavailable for comparison.

I recently received a different benchmark by R. Broucke, from the University of Texas at Austin. This program compares both the speed AND precision of most of the major microcomputers by computing the sum of a thousand squares:

  
50 S =0
100 X=0
200 FOR N = 1 TO 1000
300 S=S+X*X
400 X = X + 0.00123
500 NEXT N
600 PRINT S,X

Because of the repeated additions of floating point numbers of the same sign, this program does a good job of testing error propagation. The correct answers are:

S = 503.543802149
X = 1.23

Broucke states that those computers, such as the ATARI, that use a four byte mantissa for representing floating point numbers, can be expected to run about 25% slower than those that use a three byte mantissa, such as the IBM personal computer. The following abridged table lists some of the more popular computers along with times and answers:

         
 COMPUTER                                TIME     S             X        
 TRS color Computer                       37      503.543832	1.2300004
 Commodore Pet                            30      503.543832	1.23000004
 Commodore Vic-20                         27      503.543832	1.23000004	
 Apple 11                                 26      503.543832	1.23000004
 TRS-80 model II                          23      503.545       1.23
 Apple III                                20      503.545       1.23	
 Sinclair ZX-81                           13.5    503.54383     1.23
 Osborne I (MBASIC)                        8      503.545       1.23
 IBM Personal Computer                     7.5    503.545       1.230001
___________________________________________________________________________
 Atari 400/800 (ANTIC ON)                 15.5    503.543594    1.23
 Atari 400/800 (ANTIC OFF)                10.5    503.543594	1.23
 Atari 400/800 (ANTIC ON, with FASTCHIP)  11.5    503.543594	1.23
 Atari 400/800 (ANTIC OFF, with FASTCHIP)  8      503.543595	1.23

As you see, I left the best till last. The ATARI tests were done with the 8K cartridge BASIC. BASIC A + was about 1/4 second faster; Microsoft BASIC was unavailable for comparison. With the FASTCHIP installed and ANTIC turned off, the Atari is as fast as (and more precise than) the other two fastest machines.

Based on these particular benchmarks, one can expect a 23-41% increase in speed with FASTCHIP, the average being a little over 30%.