|
Name |
|
Date |
Size |
#Lines |
LOC |
| .. | | - | - |
| x86/ | | 03-May-2024 | - | 679 | 513 |
| README | D | 03-May-2024 | 1 KiB | 28 | 19 |
| alpha-mont.pl | D | 03-May-2024 | 5.5 KiB | 322 | 256 |
| armv4-mont.pl | D | 03-May-2024 | 5.2 KiB | 202 | 149 |
| armv4-mont.s | D | 03-May-2024 | 3.2 KiB | 146 | 127 |
| bn-586.pl | D | 03-May-2024 | 16 KiB | 775 | 636 |
| co-586.pl | D | 03-May-2024 | 5.5 KiB | 288 | 219 |
| ia64.S | D | 03-May-2024 | 44.3 KiB | 1,556 | 1,142 |
| mips3-mont.pl | D | 03-May-2024 | 5.2 KiB | 328 | 269 |
| mips3.s | D | 03-May-2024 | 36.7 KiB | 2,202 | 2,012 |
| pa-risc2.s | D | 03-May-2024 | 47.5 KiB | 1,619 | 1,353 |
| pa-risc2W.s | D | 03-May-2024 | 45.6 KiB | 1,606 | 1,332 |
| ppc-mont.pl | D | 03-May-2024 | 7.2 KiB | 324 | 263 |
| ppc.pl | D | 03-May-2024 | 43.7 KiB | 1,982 | 1,774 |
| ppc64-mont.pl | D | 03-May-2024 | 21.8 KiB | 919 | 743 |
| s390x-mont.pl | D | 03-May-2024 | 5.1 KiB | 226 | 157 |
| s390x.S | D | 03-May-2024 | 12.3 KiB | 679 | 544 |
| sparcv8.S | D | 03-May-2024 | 27.6 KiB | 1,459 | 1,257 |
| sparcv8plus.S | D | 03-May-2024 | 32.4 KiB | 1,559 | 1,229 |
| sparcv9-mont.pl | D | 03-May-2024 | 13.4 KiB | 607 | 502 |
| sparcv9a-mont.pl | D | 03-May-2024 | 20.2 KiB | 883 | 703 |
| via-mont.pl | D | 03-May-2024 | 8.8 KiB | 243 | 116 |
| x86-mont.pl | D | 03-May-2024 | 16.1 KiB | 592 | 465 |
| x86.pl | D | 03-May-2024 | 623 | 29 | 21 |
| x86_64-gcc.c | D | 03-May-2024 | 13.2 KiB | 607 | 498 |
| x86_64-mont.pl | D | 03-May-2024 | 7 KiB | 331 | 267 |
README
1<OBSOLETE>
2
3All assember in this directory are just version of the file
4crypto/bn/bn_asm.c.
5
6Quite a few of these files are just the assember output from gcc since on
7quite a few machines they are 2 times faster than the system compiler.
8
9For the x86, I have hand written assember because of the bad job all
10compilers seem to do on it. This normally gives a 2 time speed up in the RSA
11routines.
12
13For the DEC alpha, I also hand wrote the assember (except the division which
14is just the output from the C compiler pasted on the end of the file).
15On the 2 alpha C compilers I had access to, it was not possible to do
1664b x 64b -> 128b calculations (both long and the long long data types
17were 64 bits). So the hand assember gives access to the 128 bit result and
18a 2 times speedup :-).
19
20There are 3 versions of assember for the HP PA-RISC.
21
22pa-risc.s is the origional one which works fine and generated using gcc :-)
23
24pa-risc2W.s and pa-risc2.s are 64 and 32-bit PA-RISC 2.0 implementations
25by Chris Ruemmler from HP (with some help from the HP C compiler).
26
27</OBSOLETE>
28