[gambit-list] Speed on XML-parsing

Marc Feeley feeley at iro.umontreal.ca
Sat Aug 16 10:09:33 EDT 2008


If you are really into optimizing the I/O, I suggest you implement  
your own special purpose string-port I/O layer.  Basically you  
redefine read-char to read from a string.  The code below shows that  
this can be over 20 times faster than Gambit's built-in string ports.   
The main reasons for the difference are function inlining and locking  
(to support multithreading).

(define (convoluted-string-length1 str) ;; uses standard string ports
   (declare (standard-bindings) (fixnum) (not safe))
   (let ((port (open-input-string str)))
     (let loop ((i 0))
       (let ((c (read-char port)))
         (if (char? c)
             (loop (+ i 1))
             i)))))

(define-macro (macro-open-input-string str)
   `(let ((str ,str))
      (declare (standard-bindings) (fixnum) (not safe))
      (cons str 0)))

(define-macro (macro-read-char my-port)
   `(let ((my-port ,my-port))
      (declare (standard-bindings) (fixnum) (not safe))
      (let ((str (car my-port))
            (pos (cdr my-port)))
        (if (< pos (string-length str))
            (let ((c (string-ref str pos)))
              (set-cdr! my-port (+ 1 pos))
              c)
            #!eof))))

(define-macro (open-input-string str) `(macro-open-input-string ,str))
(define-macro (read-char port) `(macro-read-char ,port))

;; insert your code after this point, for example:

(define (convoluted-string-length2 str) ;; uses "fast" string ports
   (declare (standard-bindings) (fixnum) (not safe))
   (let ((port (open-input-string str)))
     (let loop ((i 0))
       (let ((c (read-char port)))
         (if (char? c)
             (loop (+ i 1))
             i)))))

(define (test)
   (let ((s (make-string 4000000 #\!)))
     (pretty-print (time (convoluted-string-length1 s)))
     (pretty-print (time (convoluted-string-length2 s)))))

(test)

;; (time (convoluted-string-length1 s))
;;     704 ms real time
;;     703 ms cpu time (661 user, 42 system)
;;     1 collection accounting for 50 ms real time (32 user, 19 system)
;;     36023288 bytes allocated
;;     no minor faults
;;     no major faults
;; 4000000
;; (time (convoluted-string-length2 s))
;;     26 ms real time
;;     25 ms cpu time (25 user, 0 system)
;;     no collections
;;     24 bytes allocated
;;     no minor faults
;;     no major faults
;; 4000000




More information about the Gambit-list mailing list