Alignment of data

[Christophe Papazian <christophe.papazian@gmail.com>]

Dear users and developers of OCAML,

I am working on some ppc architecture, and I realize that I have a  
(very) big slowdown due to bad alignment of data by ocamlopt. I need  
to have my data aligned in memory depending of the size of the data :  
floats are to be aligned on 8 bytes, int on 4 bytes, etc....
BUT, after verification, I remark that ocamlopt doesn't align as I  
need. I tried to use ARCH_ALIGN_DOUBLE, but it doesn't seem to be what  
I thought, and doesn't change anything for my needs. Is there ANY way  
to obtain what I need easily or at least quickly ?

You can use the following code to test your alignment on your  
architecture :
[ compile with ocamlopt align_stubs.c align.ml -o align ]

######### align.ml #########
open Obj

external get_addr : 'a -> int * string = "get_addr"

let rec align acc r =
   if r mod 2 = 1 then acc else align (acc*2) (r/2)

let get_addr_print v = let a,b = get_addr v in Printf.printf "%6X %s 
\n" a b; a

let rec get_align acc = function
     h::q as l -> get_align (acc lor get_addr_print l) q
   | [] -> acc

let  f block s l =
   let r =
     if block then (* if the element is a block, consider it like a  
pointer *)
       List.fold_left (fun r e -> r lor get_addr_print e) 0 l
     else get_align 0 l
   in
   Printf.printf "%s are aligned on %i bytes\n%!" s (align 1 r)

let build_list v l = List.map (fun i -> Array.make i v) l

let main =
   f false "Chars" ['a';'b';'c';'d';'e'];
   f false "Integers" [0;1;2;3;4];
   f true "Floats" [0.;1./.3.;2./.5.;3./.7.;4./.9.];
   f true "Int Arrays" (build_list  37 [3;4;5;6;7]);
   f true "Float Arrays" (build_list  (1./.3.) [2;3;4;5;6]);
   f true "Other Float Arrays" [Array.make 1 max_float;Array.make 2  
0.;Array.make 3 0.;Array.make 37 0.;Array.make 17 0.];

####### align_stubs.c ########

#include <stdio.h>

#include <caml/memory.h>
#include <caml/mlvalues.h>
#include <caml/custom.h>
#include <caml/alloc.h>

CAMLprim
value get_addr(value v)
{
   CAMLparam1 (v);
   char *repr = malloc(9);
   value res = alloc_tuple(2);
   Field(res,0) = Val_int((unsigned int) v);
   sprintf(repr,"%8X", *((int*)v));
   Field(res,1) = (caml_copy_string(repr));
   CAMLreturn(res);
}

######### Results ##########

  1D8C0       C3
  1D8CC       C5
  1D8D8       C7
  1D8E4       C9
  1D8F0       CB
Chars are aligned on 4 bytes
  1D878        1
  1D884        3
  1D890        5
  1D89C        7
  1D8A8        9
Integers are aligned on 4 bytes
  1D85C        0
  7612C 55555555
  76114 9999999A
  760FC DB6DB6DB
  760E4 1C71C71C
Floats are aligned on 4 bytes
  74A2C       4B
  74A18       4B
  74A00       4B
  749E4       4B
  749C4       4B
Int Arrays are aligned on 4 bytes
  732C0 55555555
  732A4 55555555
  73280 55555555
  73254 55555555
  73220 55555555
Float Arrays are aligned on 4 bytes
  71928 FFFFFFFF
  71940        0
  71960        0
  71988        0
  71AC0        0
Other Float Arrays are aligned on 8 bytes

You can see the addresses in memory of each element of the lists and  
it's internal representation (to check
if the memory pointer really point to the right value : you can even  
see that 31 bit ocaml integer (and Chars) i have a C representation of  
2*i+1).
It seems that small values
are on the minor heap, and large values are on major heap.
Note that the last array is correctly aligned, but it's just a matter  
of luck : If I change
something else before this line in my code, I usually get the last  
array aligned on 4 bytes.
(But I can't find a way to obtain a float array aligned on 8 bytes  
with the use of "build_list")

Si if you have any idea of how to get floats and floats arrays aligned  
on 8 bytes both on major and minor heap, please answer me !

Thank you very much

	Christophe