🚀 go-pugleaf

Reply To: adfh@village.ios.com

> 
> Super-mini's (Convex amoung others) often have specialized vector and matrix 
> hardware that allow it to perform the same operation on large portions of
> the vector with a single instruction cycle.  This requires specialized 
> optimizing compilers.  PERL wouldn't take advantage of the specialized 
> hardware/instruction set and thus would have a worse benchmark.
> 
> My guess is that the generic term "modern RISC machines" is probably wrong.
> Tom's original claim was probably for a UNIX desktop box and would
> still hold true.

The other issue, is : Is the Perl code readable? (then again, is *any* 
perl code readable?)
If he has to hand optimize and obfuscate the code, where a C programmer 
can write code that is a) clear, and b) effectively optimized by the 
compiler, then perl is still significantly slower where the same amount 
of coding effort is applied.
Secondly, is the C code being compared compiled with optimization? Is the 
executable stripped?

I've noticed before that stripping and optimizing some programs can make 
a greater than e times difference by itself. If the C code is already e 
times faster, the difference becomes appreciable, especially if a 
difference of 2e can be obtained without any hand optimization effort.