As on https://github.com/feeley/gambit/blob/master/include/gambit.h.in line 2615
I guess 'min' procedure is just a C macro ....


...
/* APPLY-able operations */


#define ___FIX_0 ___FIX(0)
#define ___FIXPOS(x)((___WORD)(x))


#define ___FIXMAX(x,y)(((x)<(y))?(y):(x))  

#define ___FIXMIN(x,y)(((x)<(y))?(x):(y))  <----------- the line in question

#define ___FIXADD(x,y)((___WORD)((x)+(y)))


...

this way there is no call frame. Maybe later Marc can put some light to the matter.



obs: I didn't know if I could call you Marc or Mr. Feely, but given the informal nature  of the mailing-list I prefer call people by their first name/nick, I hope you don't mind.

On Sun, Nov 4, 2012 at 9:12 PM, tcl super dude <tcleval@gmail.com> wrote:
here I have the expansion, assembly, C, and scheme


On Sun, Nov 4, 2012 at 8:01 PM, Mikael <mikael.rcv@gmail.com> wrote:
What about you catch a copy of the C code post- macro expansion, and a copy of the assembly output too, and have a look?

Let the ml know what you found.


2012/11/5 tcl super dude <tcleval@gmail.com>
Now scheme min is even faster.. that is ok. But what I don't understand is how that simple C implementation get so low performance.


abs:
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (abs i)) (loop-i (fx+ 1 i))))))
    1 ms real time
    0 ms cpu time (0 user, 0 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults
abs-integer:
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (abs-integer j)) (loop-j (fx+ 1 j))))))
    18 ms real time
    17 ms cpu time (17 user, 0 system)
    no collections
    no bytes allocated
    1 minor fault
    no major faults
min:
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (min i result)) (loop-i (fx+ 1 i))))))
    0 ms real time
    0 ms cpu time (0 user, 0 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults
min-integer:
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (min-integer j result)) (loop-j (fx+ 1 j))))))
    26 ms real time
    26 ms cpu time (23 user, 3 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults


On Sun, Nov 4, 2012 at 7:31 PM, Mikael More <mikael.more@gmail.com> wrote:
Ah, also throw in the following:
 * (declare (not interrupts-enabled))

   This might be a big deal - when it's off, Gambit doesn't produce any hooks for stack overflow or thread system interrupts but executes your code according to a typical C model

 * (declare (standard-bindings) (extended-bindings)) too?


What is the performance you get from Gambit now, and what kind of performance is it you want to get?


2012/11/4 tcl super dude <tcleval@gmail.com>
I assumed I could get a bit of performance improvement over min procedure because I don't do any branch. I' thought  min-integer to be at least close to gambit-c time. The problem is that those operations and a few more are performed thousands of times. Gambit loops are usually 2x slower than C, so I hoped I could improve some basic operations as I only perform them on integers. I don't Understand how a simple shift to extract the lower bits could make so much difference. Maybe if someone point me to the implementation of min and abs on gambit, I can understand the difference. I ve looked for these procedures on gambit's source but could not point it out.

I'll try to implement them using vectors and see what happens.

now compiled with (block):


abs:                                                                                                                                          
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (abs i)) (loop-i (fx+ 1 i))))))                                                  
    2 ms real time                                                                                                                            
    3 ms cpu time (3 user, 0 system)                                                                                                          
    no collections                                                                                                                            
    no bytes allocated                                                                                                                        
    no minor faults                                                                                                                           
    no major faults                                                                                                                           
abs-integer:                                                                                                                                  
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (abs-integer j)) (loop-j (fx+ 1 j))))))                                          
    19 ms real time                                                                                                                           
    20 ms cpu time (17 user, 3 system)                                                                                                        
    no collections                                                                                                                            
    no bytes allocated                                                                                                                        
    2 minor faults                                                                                                                            
    no major faults                                                                                                                           
min:                                                                                                                                          
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (min i result)) (loop-i (fx+ 1 i))))))                                           
    2 ms real time                                                                                                                            
    3 ms cpu time (0 user, 3 system)                                                                                                          
    no collections                                                                                                                            
    no bytes allocated                                                                                                                        
    no minor faults
    no major faults
min-integer:
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (min-integer j result)) (loop-j (fx+ 1 j))))))
    27 ms real time
    27 ms cpu time (27 user, 0 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults


On Sun, Nov 4, 2012 at 5:15 PM, Mikael <mikael.rcv@gmail.com> wrote:
First, please add (declare (block)) and re-compile, this way Gambit won't need to re-look up the procedures in the global namespace that you call, on each invocation. Please report what kind of improvement you got with this.


Now just to make this round of emails complete:

What would be good/very good performance in your view?

Could you send jobs in some kind of batch format to C?

Note that Gambit-internal fxnum variables have a special encoding (the lowermost two(?) bits are object type identifier, which are shifted out when converting them to C int), this takes a little bit of time.

If for instance you make u32vectors/s32vectors/etc. [and send batch ops made on those to C to be performed etc.] then you can just read out the content of those vectors 'raw' in C, there's no interconversion there.

Brgds

2012/11/4 tcl super dude <tcleval@gmail.com>
Hi everyone,

I have been working on an image processing library that I want to use on android. I know that performance is a bit of a problem on image processing, so I started to study some bit hacking to improve the performance on my integer operations.  My problem now is that I don't know why my c-lambdas take so much time to execute. All operations take constant time and there is no branching. Probably is some sort of conversion time between C types and GAMBIT types. I expected min-integer and abs-integer to be a lot faster than min and abs, respectively. Any help is appreciated. 

URL REFERENCE: 

MY ENVIRONMENT:
Linux casa 3.6.4-1-ARCH #1 SMP PREEMPT Mon Oct 29 15:13:56 CET 2012 i686 GNU/Linux

gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/i686-pc-linux-gnu/4.7.2/lto-wrapper
Target: i686-pc-linux-gnu
Configured with: /build/src/gcc-4.7.2/configure --prefix=/usr --libdir=/usr/lib --libexecdir=/usr/lib --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=https://bugs.archlinux.org/ --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++ --enable-shared --enable-threads=posix --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-clocale=gnu --disable-libstdcxx-pch --enable-libstdcxx-time --enable-gnu-unique-object --enable-linker-build-id --with-ppl --enable-cloog-backend=isl --disable-ppl-version-check --disable-cloog-version-check --enable-lto --enable-gold --enable-ld=default --enable-plugin --with-plugin-ld=ld.gold --with-linker-hash-style=gnu --disable-multilib --disable-libssp --disable-build-with-cxx --disable-build-poststage1-with-cxx --enable-checking=release
Thread model: posix
gcc version 4.7.2 (GCC) 

Gambit v4.6.6 (SINGLE HOST and GCC extensions enabled)


SCHEME CODE: compiled with ---> gambitc -exe   bithacks.scm

;; bithacks.scm


(declare
 (not safe)
 (fixnum)
 (inline)
 (inline-primitives))

;; INTEGER ABSOLUTE
(define abs-integer 
  (c-lambda (int) int
    "// we want to find the absolute value of arg1
     int const mask = ___arg1 >> sizeof(int) * CHAR_BIT - 1;
     ___result = (___arg1 + mask) ^ mask;"))


(define min-integer
  (c-lambda (int int) int
    "// find the smaller of arg1 arg2
     ___result = ___arg2 ^ ((___arg1 ^ ___arg2) & -(___arg1 < ___arg2));"))

(define (test-abs)
  (let ((result 0))
    (begin
      (display "abs:\n")
      (time 
       (let loop-i ((i 0))
         (cond ((fx< i 100000)
                (set! result (abs i))
                (loop-i (fx+ 1 i))))))
      (display "abs-integer:\n")
      (time
       (let loop-j ((j 0))
         (cond ((fx< j 100000)
                (set! result (abs-integer j))
                (loop-j (fx+ 1 j))))))))) 

(define (test-min)
  (let ((result 0))
    (begin
      (display "min:\n")
      (time 
       (let loop-i ((i 0))
         (cond ((fx< i 100000)
                (set! result (min i result))
                (loop-i (fx+ 1 i))))))
      (display "min-integer:\n")
      (time
       (let loop-j ((j 0))
         (cond ((fx< j 100000)
                (set! result (min-integer j result))
                (loop-j (fx+ 1 j))))))))) 

;; run tests

(test-abs)
(test-min)

;;;;;;;;;;;;;;;;;;;;;; RESULTS;;;;;;;;;;;;;;;;;;;;;

abs:
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (abs i)) (loop-i (fx+ 1 i))))))
    2 ms real time
    3 ms cpu time (3 user, 0 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults
abs-integer:
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (abs-integer j)) (loop-j (fx+ 1 j))))))
    22 ms real time
    23 ms cpu time (23 user, 0 system)
    no collections
    no bytes allocated
    2 minor faults
    no major faults
min:
(time (let loop-i ((i 0)) (cond ((fx< i 100000) (set! result (min i result)) (loop-i (fx+ 1 i))))))
    2 ms real time
    3 ms cpu time (0 user, 3 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults
min-integer:
(time (let loop-j ((j 0)) (cond ((fx< j 100000) (set! result (min-integer j result)) (loop-j (fx+ 1 j))))))
    28 ms real time
    30 ms cpu time (27 user, 3 system)
    no collections
    no bytes allocated
    no minor faults
    no major faults


_______________________________________________
Gambit-list mailing list
Gambit-list@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/gambit-list




_______________________________________________
Gambit-list mailing list
Gambit-list@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/gambit-list




_______________________________________________
Gambit-list mailing list
Gambit-list@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/gambit-list