gladman
|
7979d75874
|
|
2009-05-28 15:49:07 +00:00 |
|
wbhart
|
b96d7f466b
|
Tuning parameters for Core2.
|
2009-05-28 09:20:35 +00:00 |
|
wbhart
|
b0db490a0b
|
K8 tuning values.
|
2009-05-28 00:12:42 +00:00 |
|
jasonmoxham
|
2fff63ed30
|
nehalem mparam update
|
2009-05-27 23:02:45 +00:00 |
|
wbhart
|
5a67fa8b45
|
Added K10 tuning values.
|
2009-05-27 22:27:18 +00:00 |
|
wbhart
|
f33c6a799e
|
Tuning parameters for penryn.
|
2009-05-27 19:34:25 +00:00 |
|
gladman
|
41e79780c3
|
|
2009-05-27 16:10:04 +00:00 |
|
wbhart
|
0d90e4faa8
|
Fixed a bug in FFT squaring code.
|
2009-05-27 15:58:27 +00:00 |
|
jasonmoxham
|
749c195a7c
|
Convert new divrem to yasm format
|
2009-05-27 14:28:30 +00:00 |
|
wbhart
|
c605f1e498
|
Removed some compiler warnings for MSVC from mul_fft.c.
|
2009-05-27 13:00:01 +00:00 |
|
jasonmoxham
|
1ff359d28a
|
divrem_2 speedup
|
2009-05-27 11:21:58 +00:00 |
|
gladman
|
2bf84f6a74
|
|
2009-05-20 20:58:09 +00:00 |
|
gladman
|
dea89e4760
|
Update windows build for latest assembler
|
2009-05-20 20:09:06 +00:00 |
|
jasonmoxham
|
61cd1223a3
|
New asm function mpn_divrem_euclidean_qr_2 for X86_64
|
2009-05-20 17:58:41 +00:00 |
|
jasonmoxham
|
5e1c28e1df
|
divrem_2 generic correction
|
2009-05-20 17:34:55 +00:00 |
|
jasonmoxham
|
e788f8b9b4
|
mul_basecase to yasm
|
2009-05-20 13:03:53 +00:00 |
|
jasonmoxham
|
5fb3fafe42
|
mul_basecase for GAS, so I know what the yasm conversion is of
|
2009-05-20 00:01:35 +00:00 |
|
gladman
|
659df23bbc
|
1. Improve g2y.py
2. Add divrem changes to Windows build
3. Add new x64 mpn_mul_basecase assembler to Windows
|
2009-05-19 19:53:15 +00:00 |
|
jasonmoxham
|
01da1f0caa
|
divrem update
|
2009-05-19 12:48:09 +00:00 |
|
jasonmoxham
|
483fe4ed21
|
divrem updates
|
2009-05-19 12:27:10 +00:00 |
|
jasonmoxham
|
b5980c95b1
|
divrem bits
|
2009-05-19 09:51:30 +00:00 |
|
gladman
|
0af849c1f2
|
1. Fix minor bug in Windows build
2. change gcdext.c to avoid C99 features
|
2009-05-19 09:44:06 +00:00 |
|
jasonmoxham
|
9c68614d77
|
Add new function generic mpn_divrem_euclidean_qr_2
|
2009-05-19 09:30:34 +00:00 |
|
wbhart
|
a49b4e2337
|
More tuning values, not that they make any difference.
|
2009-05-19 05:44:48 +00:00 |
|
wbhart
|
3d66bd5322
|
Added tuning values for core2 and fixed a minor bug in mul_n.c.
|
2009-05-19 04:03:49 +00:00 |
|
wbhart
|
d96ef5e5d9
|
Reverted a change which slows things down on k8.
|
2009-05-19 02:04:09 +00:00 |
|
wbhart
|
e330cc79bc
|
Fixed some bugs related to tuning gcdext and added tuning for toom4 and
toom7 squaring code.
|
2009-05-19 00:57:17 +00:00 |
|
wbhart
|
cfb5f9c0b2
|
Added copyright notice.
|
2009-05-18 21:00:51 +00:00 |
|
wbhart
|
2bf28e3c63
|
Added toom7 squaring and sped up multiplication slightly by better use
of the FFT.
|
2009-05-18 20:55:01 +00:00 |
|
wbhart
|
de64002818
|
Slight memory usage improvement for toom4 squaring code.
|
2009-05-18 07:28:48 +00:00 |
|
wbhart
|
8d8a26e60b
|
Added toom4 squaring code - no tuning code yet!
|
2009-05-18 07:13:00 +00:00 |
|
wbhart
|
6b1c6afdbe
|
Added half gcd implementation based on the original ngcd implementation
of Niels Mohler.
|
2009-05-16 21:57:44 +00:00 |
|
gladman
|
2cd6ee00c5
|
|
2009-05-14 20:35:12 +00:00 |
|
jasonmoxham
|
2768eeaaf0
|
New asm functions mpn_store MPN_ZERO for k8/k10/nehalem
|
2009-05-14 20:30:27 +00:00 |
|
jasonmoxham
|
a1b14414c6
|
New generic mpn_store and tests/tune etc
|
2009-05-14 19:29:28 +00:00 |
|
jasonmoxham
|
3b7c555c8e
|
New generic functions/macros mpn_lshift2 mpn_rshift2 and tests/speed etc
|
2009-05-14 02:44:19 +00:00 |
|
jasonmoxham
|
ccf3200d93
|
mul_basecase tweeks
|
2009-05-13 22:51:35 +00:00 |
|
jasonmoxham
|
6ee4e35940
|
New asm function mpn_mul_basecase for K8/K10/Core2/Penryn/Nehalem
|
2009-05-13 19:49:42 +00:00 |
|
gladman
|
d6962d575f
|
1. Add new/changed Core2 assembler files to the Windows build
2. Workaround VC++ optimisation bug in mul_fft.c
|
2009-05-13 09:54:24 +00:00 |
|
gladman
|
47c7c6b832
|
Further update to Windows K8 build
|
2009-05-12 21:33:52 +00:00 |
|
gladman
|
9918886c2f
|
Update Windows K8 build to add new assembler
|
2009-05-12 19:37:47 +00:00 |
|
wbhart
|
21f51a706c
|
Added toom32 for unbalanced multiplications.
|
2009-05-12 18:28:20 +00:00 |
|
wbhart
|
c6881fa3a9
|
Fixed bugs in Toom3 code.
|
2009-05-12 09:22:27 +00:00 |
|
wbhart
|
fb914ab4ac
|
Fixed some buglets in toom4.
|
2009-05-11 15:16:53 +00:00 |
|
wbhart
|
ae48f90e2f
|
Fix speed regression in mul.c, switch unbalanced toom back on. Add
missing toom3_interpolate prototype.
|
2009-05-11 12:30:17 +00:00 |
|
wbhart
|
4babcebbfa
|
Turned off unbalanced multiplications as they slow things down.
-This line, and those below, will be ignored--
M mpn/generic/mul.c
|
2009-05-11 11:06:38 +00:00 |
|
wbhart
|
9e56c61071
|
Added toom42 and code to handle unbalanced multiplication.
|
2009-05-11 10:09:09 +00:00 |
|
jasonmoxham
|
0a1d07af4e
|
New asm function mpn_sublsh1_n for K8/K10
|
2009-05-10 20:03:47 +00:00 |
|
jasonmoxham
|
574f3be308
|
New asm function mpn_divexact_byff for K8/K10/Core2/penryn/nehalem
|
2009-05-10 19:35:54 +00:00 |
|
jasonmoxham
|
359fab42b5
|
New asm functions mpn_rsh1add_n mpn_rsh1sub_n for K8/K10/Core2/penryn/nehalem
|
2009-05-10 18:46:48 +00:00 |
|