Alexandre Savard | 1b09e31 | 2012-08-07 20:33:29 -0400 | [diff] [blame] | 1 | <OBSOLETE> |
| 2 | |
| 3 | All assember in this directory are just version of the file |
| 4 | crypto/bn/bn_asm.c. |
| 5 | |
| 6 | Quite a few of these files are just the assember output from gcc since on |
| 7 | quite a few machines they are 2 times faster than the system compiler. |
| 8 | |
| 9 | For the x86, I have hand written assember because of the bad job all |
| 10 | compilers seem to do on it. This normally gives a 2 time speed up in the RSA |
| 11 | routines. |
| 12 | |
| 13 | For the DEC alpha, I also hand wrote the assember (except the division which |
| 14 | is just the output from the C compiler pasted on the end of the file). |
| 15 | On the 2 alpha C compilers I had access to, it was not possible to do |
| 16 | 64b x 64b -> 128b calculations (both long and the long long data types |
| 17 | were 64 bits). So the hand assember gives access to the 128 bit result and |
| 18 | a 2 times speedup :-). |
| 19 | |
| 20 | There are 3 versions of assember for the HP PA-RISC. |
| 21 | |
| 22 | pa-risc.s is the origional one which works fine and generated using gcc :-) |
| 23 | |
| 24 | pa-risc2W.s and pa-risc2.s are 64 and 32-bit PA-RISC 2.0 implementations |
| 25 | by Chris Ruemmler from HP (with some help from the HP C compiler). |
| 26 | |
| 27 | </OBSOLETE> |