Commit 82f4858291901582b7975bd46c349860c6ee1858

Tom St Denis 2003-03-13T02:11:11

added libtommath-0.14

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
diff --git a/bn.pdf b/bn.pdf
index 6b5a2d1..59de4e3 100644
Binary files a/bn.pdf and b/bn.pdf differ
diff --git a/bn.tex b/bn.tex
index 5c40174..d5a34db 100644
--- a/bn.tex
+++ b/bn.tex
@@ -1,15 +1,15 @@
 \documentclass{article}
 \begin{document}
 
-\title{LibTomMath v0.13 \\ A Free Multiple Precision Integer Library}
+\title{LibTomMath v0.14 \\ A Free Multiple Precision Integer Library \\ http://math.libtomcrypt.org }
 \author{Tom St Denis \\ tomstdenis@iahu.ca}
 \maketitle
 \newpage
 
 \section{Introduction}
-``LibTomMath'' is a free and open source library that provides multiple-precision integer functions required to form a basis
-of a public key cryptosystem.  LibTomMath is written entire in portable ISO C source code and designed to have an application
-interface much like that of MPI from Michael Fromberger.  
+``LibTomMath'' is a free and open source library that provides multiple-precision integer functions required to form a 
+basis of a public key cryptosystem.  LibTomMath is written entire in portable ISO C source code and designed to have an 
+application interface much like that of MPI from Michael Fromberger.  
 
 LibTomMath was written from scratch by Tom St Denis but designed to be  drop in replacement for the MPI package.  The 
 algorithms within the library are derived from descriptions as provided in the Handbook of Applied Cryptography and Knuth's
@@ -23,8 +23,7 @@ LibTomMath was designed with the following goals in mind:
 \item Be written entirely in portable C.
 \end{enumerate}
 
-All three goals have been achieved.  Particularly the speed increase goal.  For example, a 512-bit modular exponentiation 
-is eight times faster\footnote{On an Athlon XP with GCC 3.2} with LibTomMath compared to MPI.
+All three goals have been achieved to one extent or another (actual figures depend on what platform you are using).
 
 Being compatible with MPI means that applications that already use it can be ported fairly quickly.  Currently there are 
 a few differences but there are many similarities.  In fact the average MPI based application can be ported in under 15
@@ -54,16 +53,26 @@ make install
 
 Now within your application include ``tommath.h'' and link against libtommath.a to get MPI-like functionality.
 
+\subsection{Microsoft Visual C++}
+A makefile is also provided for MSVC (\textit{tested against MSVC 6.00 with SP5}) which allows the library to be used
+with that compiler as well.  To build the library type
+
+\begin{verbatim}
+nmake -f makefile.msvc
+\end{verbatim}
+
+Which will build ``tommath.lib''.  
+
 \section{Programming with LibTomMath}
 
 \subsection{The mp\_int Structure}
 All multiple precision integers are stored in a structure called \textbf{mp\_int}.  A multiple precision integer is
-essentially an array of \textbf{mp\_digit}.  mp\_digit is defined at the top of bn.h.  Its type can be changed to suit
-a particular platform.  
+essentially an array of \textbf{mp\_digit}.  mp\_digit is defined at the top of ``tommath.h''.  The type can be changed 
+to suit a particular platform.  
 
-For example, when \textbf{MP\_8BIT} is defined\footnote{When building bn.c.} a mp\_digit is a unsigned char and holds 
-seven bits.  Similarly when \textbf{MP\_16BIT} is defined a mp\_digit is a unsigned short and holds 15 bits.  
-By default a mp\_digit is a unsigned long and holds 28 bits.  
+For example, when \textbf{MP\_8BIT} is defined a mp\_digit is a unsigned char and holds seven bits.  Similarly 
+when \textbf{MP\_16BIT} is defined a mp\_digit is a unsigned short and holds 15 bits.   By default a mp\_digit is a 
+unsigned long and holds 28 bits which is optimal for most 32 and 64 bit processors.
 
 The choice of digit is particular to the platform at hand and what available multipliers are provided.  For 
 MP\_8BIT either a $8 \times 8 \Rightarrow 16$ or $16 \times 16 \Rightarrow 16$ multiplier is optimal.  When 
@@ -83,20 +92,19 @@ $W$ is the number of bits in a digit (default is 28).
 
 \subsection{Calling Functions}
 Most functions expect pointers to mp\_int's as parameters.   To save on memory usage it is possible to have source
-variables as destinations.  For example:
+variables as destinations.  The arguements are read left to right so to compute $x + y = z$ you would pass the arguments
+in the order $x, y, z$.  For example:
 \begin{verbatim}
    mp_add(&x, &y, &x);           /* x = x + y */
-   mp_mul(&x, &z, &x);           /* x = x * z */
-   mp_div_2(&x, &x);             /* x = x / 2 */
+   mp_mul(&y, &x, &z);           /* z = y * x */
+   mp_div_2(&x, &y);             /* y = x / 2 */
 \end{verbatim}
 
-\section{Quick Overview}
+\subsection{Return Values}
+All functions that return errors will return \textbf{MP\_OKAY} if the function was succesful.  It will return 
+\textbf{MP\_MEM} if it ran out of heap memory or \textbf{MP\_VAL} if one of the arguements is out of range.  
 
 \subsection{Basic Functionality}
-Essentially all LibTomMath functions return one of three values to indicate if the function worked as desired.  A 
-function will return \textbf{MP\_OKAY} if the function was successful.  A function will return \textbf{MP\_MEM} if
-it ran out of memory and \textbf{MP\_VAL} if the input was invalid.  
-
 Before an mp\_int can be used it must be initialized with 
 
 \begin{verbatim}
@@ -106,7 +114,7 @@ int mp_init(mp_int *a);
 For example, consider the following.
 
 \begin{verbatim}
-#include "bn.h"
+#include "tommath.h"
 int main(void)
 {
    mp_int num;
@@ -383,6 +391,18 @@ in $c$ and returns success.
 
 This function requires $O(N)$ additional digits of memory and $O(2 \cdot N)$ time.
 
+\subsubsection{mp\_mul\_2(mp\_int *a, mp\_int *b)}
+Multiplies $a$ by two and stores in $b$.  This function is hard coded todo a shift by one place so it is faster
+than calling mp\_mul\_2d with a count of one.  
+
+This function requires $O(N)$ additional digits of memory and $O(N)$ time.
+
+\subsubsection{mp\_div\_2(mp\_int *a, mp\_int *b)}
+Divides $a$ by two and stores in $b$.  This function is hard coded todo a shift by one place so it is faster
+than calling mp\_div\_2d with a count of one.
+
+This function requires $O(N)$ additional digits of memory and $O(N)$ time.
+
 \subsubsection{mp\_mod\_2d(mp\_int *a, int b, mp\_int *c)}
 Performs the action of reducing $a$ modulo $2^b$ and stores the result in $c$.  If the shift count $b$ is less than 
 or equal to zero the function places $a$ in $c$ and returns success.  
@@ -412,7 +432,7 @@ of $c$ is the maximum length of the two inputs.
 \subsection{Basic Arithmetic}
 
 \subsubsection{mp\_cmp(mp\_int *a, mp\_int *b)}
-Performs a \textbf{signed} comparison between $a$ and $b$ returning \textbf{MP\_GT} is $a$ is larger than $b$.
+Performs a \textbf{signed} comparison between $a$ and $b$ returning \textbf{MP\_GT} if $a$ is larger than $b$.
 
 This function requires no additional memory and $O(N)$ time.
 
@@ -559,57 +579,6 @@ A very useful observation is that multiplying by $R = \beta^n$ amounts to perfor
 requires no single precision multiplications.  
 
 \section{Timing Analysis}
-\subsection{Observed Timings}
-A simple test program ``demo.c'' was developed which builds with either MPI or LibTomMath (without modification).  The
-test was conducted on an AMD Athlon XP processor with 266Mhz DDR memory and the GCC 3.2 compiler\footnote{With build
-options ``-O3 -fomit-frame-pointer -funroll-loops''}.    The multiplications and squarings were repeated 100,000 times 
-each while the modular exponentiation (exptmod) were performed 50 times each.  The ``inversions'' refers to multiplicative
-inversions modulo an odd number of a given size.  The RDTSC (Read Time Stamp Counter) instruction was used to measure the 
-time the entire iterations took and was divided by the number of iterations to get an average.  The following results 
-were observed.
-
-\begin{small}
-\begin{center}
-\begin{tabular}{c|c|c|c}
-\hline \textbf{Operation} & \textbf{Size (bits)} & \textbf{Time with MPI (cycles)} & \textbf{Time with LibTomMath (cycles)} \\
-\hline
-Inversion & 128 & 264,083  & 59,782   \\
-Inversion & 256 & 549,370  & 146,915   \\
-Inversion & 512 & 1,675,975  & 367,172   \\
-Inversion & 1024 & 5,237,957  & 1,054,158   \\
-Inversion & 2048 & 17,871,944  & 3,459,683   \\
-Inversion & 4096 & 66,610,468  & 11,834,556   \\
-\hline
-Multiply & 128 & 1,426   & 451     \\
-Multiply & 256 & 2,551   & 958     \\
-Multiply & 512 & 7,913   & 2,476     \\
-Multiply & 1024 & 28,496   & 7,927   \\
-Multiply & 2048 & 109,897   & 28,224     \\
-Multiply & 4096 & 469,970   & 101,171     \\
-\hline 
-Square & 128 & 1,319   & 511     \\
-Square & 256 & 1,776   & 947     \\
-Square & 512 & 5,399  & 2,153    \\
-Square & 1024 & 18,991  & 5,733     \\
-Square & 2048 & 72,126  & 17,621    \\
-Square & 4096 & 306,269  & 67,576   \\
-\hline 
-Exptmod & 512 & 32,021,586  & 3,118,435 \\
-Exptmod & 768 & 97,595,492  & 8,493,633 \\
-Exptmod & 1024 & 223,302,532  & 17,715,899     \\
-Exptmod & 2048 & 1,682,223,369   & 114,936,361      \\
-Exptmod & 2560 & 3,268,615,571   & 229,402,426       \\
-Exptmod & 3072 & 5,597,240,141   & 367,403,840      \\
-Exptmod & 4096 & 13,347,270,891   & 779,058,433      
-
-\end{tabular}
-\end{center}
-\end{small}
-
-Note that the figures do fluctuate but their magnitudes are relatively intact.  The purpose of the chart is not to
-get an exact timing but to compare the two libraries.  For example, in all of the tests the exact time for a 512-bit
-squaring operation was not the same.  The observed times were all approximately 2,500 cycles, more importantly they
-were always faster than the timings observed with MPI by about the same magnitude.  
 
 \subsection{Digit Size}
 The first major constribution to the time savings is the fact that 28 bits are stored per digit instead of the MPI 
@@ -619,29 +588,59 @@ A savings of $64^2 - 37^2 = 2727$ single precision multiplications.
 
 \subsection{Multiplication Algorithms}
 For most inputs a typical baseline $O(n^2)$ multiplier is used which is similar to that of MPI.  There are two variants 
-of the baseline multiplier.  The normal and the fast variants.  The normal baseline multiplier is the exact same as the
-algorithm from MPI.  The fast baseline multiplier is optimized for cases where the number of input digits $N$ is less
-than or equal to $2^{w}/\beta^2$.  Where $w$ is the number of bits in a \textbf{mp\_word}.  By default a mp\_word is
-64-bits which means $N \le 256$ is allowed which represents numbers upto $7168$ bits.
-
-The fast baseline multiplier is optimized by removing the carry operations from the inner loop.  This is often referred
-to as the ``comba'' method since it computes the products a columns first then figures out the carries.  This has the
-effect of making a very simple and paralizable inner loop.
-
-For large inputs, typically 80 digits\footnote{By default that is 2240-bits or more.} or more the Karatsuba method is 
-used.  This method has significant overhead but an asymptotic running time of $O(n^{1.584})$ which means for fairly large
-inputs this method is faster.  The Karatsuba implementation is recursive which means for extremely large inputs they
-will benefit from the algorithm.
+of the baseline multiplier.  The normal and the fast comba variant.  The normal baseline multiplier is the exact same as 
+the algorithm from MPI.  The fast comba baseline multiplier is optimized for cases where the number of input digits $N$ 
+is less than or equal to $2^{w}/\beta^2$.  Where $w$ is the number of bits in a \textbf{mp\_word} or simply $lg(\beta)$.
+By default a mp\_word is 64-bits which means $N \le 256$ is allowed which represents numbers upto $7,168$ bits.  However,
+since the Karatsuba multiplier (discussed below) will kick in before that size the slower baseline algorithm (that MPI
+uses) should never really be used in a default configuration.  
+
+The fast comba baseline multiplier is optimized by removing the carry operations from the inner loop.  This is often 
+referred to as the ``comba'' method since it computes the products a columns first then figures out the carries.  To
+accomodate this the result of the inner multiplications must be stored in words large enough not to lose the carry bits.  
+This is why there is a limit of $2^{w}/\beta^2$ digits in the input.  This optimization has the effect of making a 
+very simple and efficient inner loop.
+
+\subsubsection{Karatsuba Multiplier}
+For large inputs, typically 80 digits\footnote{By default that is 2240-bits or more.} or more the Karatsuba multiplication
+method is used.  This method has significant overhead but an asymptotic running time of $O(n^{1.584})$ which means for 
+fairly large inputs this method is faster than the baseline (or comba) algorithm.  The Karatsuba implementation is 
+recursive which means for extremely large inputs they will benefit from the algorithm.
+
+The algorithm is based on the observation that if 
+
+\begin{eqnarray}
+x = x_0 + x_1\beta \nonumber \\
+y = y_0 + y_1\beta
+\end{eqnarray}
+
+Where $x_0, x_1, y_0, y_1$ are half the size of their respective summand than 
+
+\begin{equation}
+x \cdot y = x_1y_1\beta^2 + ((x_1 - y_1)(x_0 - y_0) + x_0y_0 + x_1y_1)\beta + x_0y_0
+\end{equation}
+
+It is trivial that from this only three products have to be produced: $x_0y_0, x_1y_1, (x_1-y_1)(x_0-y_0)$ which
+are all of half size numbers.  A multiplication of two half size numbers requires only $1 \over 4$ of the
+original work which means with no recursion the Karatsuba algorithm achieves a running time of ${3n^2}\over 4$.  
+The routine provided does recursion which is where the $O(n^{1.584})$ work factor comes from.
+
+The multiplication by $\beta$ and $\beta^2$ amount to digit shift operations.  
+The extra overhead in the Karatsuba method comes from extracting the half size numbers $x_0, x_1, y_0, y_1$ and
+performing the various smaller calculations.  
+
+The library has been fairly optimized to extract the digits using hard-coded routines instead of the hire
+level functions however there is still significant overhead to optimize away.
 
 MPI only implements the slower baseline multiplier where carries are dealt with in the inner loop.  As a result even at
 smaller numbers (below the Karatsuba cutoff) the LibTomMath multipliers are faster.
 
 \subsection{Squaring Algorithms}
 
-Similar to the multiplication algorithms there are two baseline squaring algorithms.  Both have an asymptotic running
-time of $O((t^2 + t)/2)$.  The normal baseline squaring is the same from MPI and the fast is a ``comba'' squaring
-algorithm.  The comba method is used if the number of digits $N$ is less than $2^{w-1}/\beta^2$ which by default 
-covers numbers upto $3584$ bits.  
+Similar to the multiplication algorithms there are two baseline squaring algorithms.  Both have an asymptotic 
+running time of $O((t^2 + t)/2)$.  The normal baseline squaring is the same from MPI and the fast method is 
+a ``comba'' squaring algorithm.  The comba method is used if the number of digits $N$ is less than 
+$2^{w-1}/\beta^2$ which by default covers numbers upto $3,584$ bits.  
 
 There is also a Karatsuba squaring method which achieves a running time of $O(n^{1.584})$ after considerably large
 inputs.
@@ -653,25 +652,31 @@ than MPI is.
 
 LibTomMath implements a sliding window $k$-ary left to right exponentiation algorithm.  For a given exponent size $L$ an
 appropriate window size $k$ is chosen.  There are always at most $L$ modular squarings and $\lfloor L/k \rfloor$ modular
-multiplications.   The $k$-ary method works by precomputing values $g(x) = b^x$ for $0 \le x < 2^k$ and a given base 
+multiplications.   The $k$-ary method works by precomputing values $g(x) = b^x$ for $2^{k-1} \le x < 2^k$ and a given base 
 $b$.  Then the multiplications are grouped in windows of $k$ bits.  The sliding window technique has the benefit 
 that it can skip multiplications if there are zero bits following or preceding a window.  Consider the exponent 
 $e = 11110001_2$ if $k = 2$ then there will be a two squarings, a multiplication of $g(3)$, two squarings, a multiplication
-of $g(3)$, four squarings and and a multiplication by $g(1)$.  In total there are 8 squarings and 3 multiplications.  
+of $g(3)$, four squarings and and a multiplication by $g(1)$.  In total there are 8 squarings and 3 multiplications.
 
-MPI uses a binary square-multiply method.  For the same exponent $e$ it would have had 8 squarings and 5 multiplications.  
-There is a precomputation phase for the method LibTomMath uses but it generally cuts down considerably on the number
-of multiplications.  Consider a 512-bit exponent.  The worst case for the LibTomMath method results in 512 squarings and 
-124 multiplications.  The MPI method would have 512 squarings and 512 multiplications.  Randomly every $2k$ bits another 
-multiplication is saved via the sliding-window technique on top of the savings the $k$-ary method provides.
+MPI uses a binary square-multiply method for exponentiation.  For the same exponent $e = 11110001_2$ it would have had to
+perform 8 squarings and 5 multiplications.  There is a precomputation phase for the method LibTomMath uses but it 
+generally cuts down considerably on the number of multiplications.  Consider a 512-bit exponent.  The worst case for the 
+LibTomMath method results in 512 squarings and 124 multiplications.  The MPI method would have 512 squarings 
+and 512 multiplications.  Randomly every $2k$ bits another multiplication is saved via the sliding-window 
+technique on top of the savings the $k$-ary method provides.
 
 Both LibTomMath and MPI use Barrett reduction instead of division to reduce the numbers modulo the modulus given.
 However, LibTomMath can take advantage of the fact that the multiplications required within the Barrett reduction
-do not have to give full precision.  As a result the reduction step is much faster and just as accurate.  The LibTomMath code
-will automatically determine at run-time (e.g. when its called) whether the faster multiplier can be used.  The
+do not have to give full precision.  As a result the reduction step is much faster and just as accurate.  The LibTomMath 
+code will automatically determine at run-time (e.g. when its called) whether the faster multiplier can be used.  The
 faster multipliers have also been optimized into the two variants (baseline and comba baseline).
 
 LibTomMath also has a variant of the exptmod function that uses Montgomery reductions instead of Barrett reductions
-which is faser.  As a result of all these changes exponentiation in LibTomMath is much faster than compared to MPI.  
+which is faster.  The code will automatically detect when the Montgomery version can be used (\textit{Requires the
+modulus to be odd and below the MONTGOMERY\_EXPT\_CUTOFF size}).  The Montgomery routine is essentially a copy of the 
+Barrett exponentiation routine except it uses Montgomery reduction.
+
+As a result of all these changes exponentiation in LibTomMath is much faster than compared to MPI.  On most ALU-strong
+processors (AMD Athlon for instance) exponentiation in LibTomMath is often more then ten times faster than MPI.   
 
 \end{document}
diff --git a/bn_fast_mp_invmod.c b/bn_fast_mp_invmod.c
index 249ff43..1cd0150 100644
--- a/bn_fast_mp_invmod.c
+++ b/bn_fast_mp_invmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_fast_mp_montgomery_reduce.c b/bn_fast_mp_montgomery_reduce.c
index 2e03936..17be2e4 100644
--- a/bn_fast_mp_montgomery_reduce.c
+++ b/bn_fast_mp_montgomery_reduce.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -100,14 +100,18 @@ fast_mp_montgomery_reduce (mp_int * a, mp_int * m, mp_digit mp)
     W[ix + 1] += W[ix] >> ((mp_word) DIGIT_BIT);
   }
 
-  /* nox fix rest of carries */
-  for (++ix; ix <= m->used * 2 + 1; ix++) {
-    W[ix] += (W[ix - 1] >> ((mp_word) DIGIT_BIT));
-  }
 
   {
     register mp_digit *tmpa;
-    register mp_word *_W;
+    register mp_word *_W, *_W1;
+
+    /* nox fix rest of carries */
+    _W1 = W + ix;
+    _W = W + ++ix;
+
+    for (; ix <= m->used * 2 + 1; ix++) {
+      *_W++ += *_W1++ >> ((mp_word) DIGIT_BIT);
+    }
 
     /* copy out, A = A/b^n
      *
diff --git a/bn_fast_s_mp_mul_digs.c b/bn_fast_s_mp_mul_digs.c
index dc0c33e..3cba3e1 100644
--- a/bn_fast_s_mp_mul_digs.c
+++ b/bn_fast_s_mp_mul_digs.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_fast_s_mp_mul_high_digs.c b/bn_fast_s_mp_mul_high_digs.c
index 3458d96..4a21441 100644
--- a/bn_fast_s_mp_mul_high_digs.c
+++ b/bn_fast_s_mp_mul_high_digs.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_fast_s_mp_sqr.c b/bn_fast_s_mp_sqr.c
index 2b945ba..093bc89 100644
--- a/bn_fast_s_mp_sqr.c
+++ b/bn_fast_s_mp_sqr.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_2expt.c b/bn_mp_2expt.c
index 71d04e9..415aa1e 100644
--- a/bn_mp_2expt.c
+++ b/bn_mp_2expt.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_abs.c b/bn_mp_abs.c
index 9e6956e..60a3470 100644
--- a/bn_mp_abs.c
+++ b/bn_mp_abs.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_add.c b/bn_mp_add.c
index a8addfb..02f130a 100644
--- a/bn_mp_add.c
+++ b/bn_mp_add.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_add_d.c b/bn_mp_add_d.c
index 1b30fa4..0fe5ad3 100644
--- a/bn_mp_add_d.c
+++ b/bn_mp_add_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_addmod.c b/bn_mp_addmod.c
index abc3719..4ad89e0 100644
--- a/bn_mp_addmod.c
+++ b/bn_mp_addmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_and.c b/bn_mp_and.c
index 6c05d68..8c18fdc 100644
--- a/bn_mp_and.c
+++ b/bn_mp_and.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_clamp.c b/bn_mp_clamp.c
index 3741f62..f2839a1 100644
--- a/bn_mp_clamp.c
+++ b/bn_mp_clamp.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_clear.c b/bn_mp_clear.c
index e88e95a..8273ac9 100644
--- a/bn_mp_clear.c
+++ b/bn_mp_clear.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_cmp.c b/bn_mp_cmp.c
index ca0c463..391eca3 100644
--- a/bn_mp_cmp.c
+++ b/bn_mp_cmp.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_cmp_d.c b/bn_mp_cmp_d.c
index 1506b87..f2725cf 100644
--- a/bn_mp_cmp_d.c
+++ b/bn_mp_cmp_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_cmp_mag.c b/bn_mp_cmp_mag.c
index 6d4a02d..a40b518 100644
--- a/bn_mp_cmp_mag.c
+++ b/bn_mp_cmp_mag.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_copy.c b/bn_mp_copy.c
index 68705a4..10ab6a6 100644
--- a/bn_mp_copy.c
+++ b/bn_mp_copy.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_count_bits.c b/bn_mp_count_bits.c
index 09992d4..3833ce6 100644
--- a/bn_mp_count_bits.c
+++ b/bn_mp_count_bits.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_div.c b/bn_mp_div.c
index 3954c9f..96e7e6f 100644
--- a/bn_mp_div.c
+++ b/bn_mp_div.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_div_2.c b/bn_mp_div_2.c
index 284f330..787f87a 100644
--- a/bn_mp_div_2.c
+++ b/bn_mp_div_2.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -46,6 +46,7 @@ mp_div_2 (mp_int * a, mp_int * b)
       *tmpb++ = 0;
     }
   }
+  b->sign = a->sign;
   mp_clamp (b);
   return MP_OKAY;
 }
diff --git a/bn_mp_div_2d.c b/bn_mp_div_2d.c
index 9d24e10..c208f5e 100644
--- a/bn_mp_div_2d.c
+++ b/bn_mp_div_2d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -51,7 +51,9 @@ mp_div_2d (mp_int * a, int b, mp_int * c, mp_int * d)
   }
 
   /* shift by as many digits in the bit count */
-  mp_rshd (c, b / DIGIT_BIT);
+  if (b >= DIGIT_BIT) {
+     mp_rshd (c, b / DIGIT_BIT);
+  }     
 
   /* shift any bit count < DIGIT_BIT */
   D = (mp_digit) (b % DIGIT_BIT);
diff --git a/bn_mp_div_d.c b/bn_mp_div_d.c
index e43802a..b7de4d1 100644
--- a/bn_mp_div_d.c
+++ b/bn_mp_div_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_exch.c b/bn_mp_exch.c
index 2ccaf9e..526c4c9 100644
--- a/bn_mp_exch.c
+++ b/bn_mp_exch.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_expt_d.c b/bn_mp_expt_d.c
index e5106be..602785b 100644
--- a/bn_mp_expt_d.c
+++ b/bn_mp_expt_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_exptmod.c b/bn_mp_exptmod.c
index ea58a4f..8b3f27f 100644
--- a/bn_mp_exptmod.c
+++ b/bn_mp_exptmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_exptmod_fast.c b/bn_mp_exptmod_fast.c
index fe0dfcb..902a894 100644
--- a/bn_mp_exptmod_fast.c
+++ b/bn_mp_exptmod_fast.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_gcd.c b/bn_mp_gcd.c
index 35b287e..df68841 100644
--- a/bn_mp_gcd.c
+++ b/bn_mp_gcd.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_grow.c b/bn_mp_grow.c
index 91c1867..0a0a33b 100644
--- a/bn_mp_grow.c
+++ b/bn_mp_grow.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_init.c b/bn_mp_init.c
index 024bfd9..ae5c30f 100644
--- a/bn_mp_init.c
+++ b/bn_mp_init.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_init_copy.c b/bn_mp_init_copy.c
index f79d2b1..f87ad16 100644
--- a/bn_mp_init_copy.c
+++ b/bn_mp_init_copy.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_init_size.c b/bn_mp_init_size.c
index 4dc46b0..ce25b91 100644
--- a/bn_mp_init_size.c
+++ b/bn_mp_init_size.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_invmod.c b/bn_mp_invmod.c
index 006efd2..4e2c1f7 100644
--- a/bn_mp_invmod.c
+++ b/bn_mp_invmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_jacobi.c b/bn_mp_jacobi.c
index 95aee42..bfe7bfc 100644
--- a/bn_mp_jacobi.c
+++ b/bn_mp_jacobi.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_karatsuba_mul.c b/bn_mp_karatsuba_mul.c
index bee8eaa..79358fb 100644
--- a/bn_mp_karatsuba_mul.c
+++ b/bn_mp_karatsuba_mul.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -37,8 +37,7 @@ int
 mp_karatsuba_mul (mp_int * a, mp_int * b, mp_int * c)
 {
   mp_int  x0, x1, y0, y1, t1, t2, x0y0, x1y1;
-  int     B, err, x;
-
+  int     B, err;
 
   err = MP_MEM;
 
@@ -59,13 +58,13 @@ mp_karatsuba_mul (mp_int * a, mp_int * b, mp_int * c)
     goto Y0;
 
   /* init temps */
-  if (mp_init (&t1) != MP_OKAY)
+  if (mp_init_size (&t1, B * 2) != MP_OKAY)
     goto Y1;
-  if (mp_init (&t2) != MP_OKAY)
+  if (mp_init_size (&t2, B * 2) != MP_OKAY)
     goto T1;
-  if (mp_init (&x0y0) != MP_OKAY)
+  if (mp_init_size (&x0y0, B * 2) != MP_OKAY)
     goto T2;
-  if (mp_init (&x1y1) != MP_OKAY)
+  if (mp_init_size (&x1y1, B * 2) != MP_OKAY)
     goto X0Y0;
 
   /* now shift the digits */
@@ -76,18 +75,32 @@ mp_karatsuba_mul (mp_int * a, mp_int * b, mp_int * c)
   x1.used = a->used - B;
   y1.used = b->used - B;
 
-  /* we copy the digits directly instead of using higher level functions
-   * since we also need to shift the digits
-   */
-  for (x = 0; x < B; x++) {
-    x0.dp[x] = a->dp[x];
-    y0.dp[x] = b->dp[x];
-  }
-  for (x = B; x < a->used; x++) {
-    x1.dp[x - B] = a->dp[x];
-  }
-  for (x = B; x < b->used; x++) {
-    y1.dp[x - B] = b->dp[x];
+  {
+    register int x;
+    register mp_digit *tmpa, *tmpb, *tmpx, *tmpy;
+
+    /* we copy the digits directly instead of using higher level functions
+     * since we also need to shift the digits
+     */
+    tmpa = a->dp;
+    tmpb = b->dp;
+
+    tmpx = x0.dp;
+    tmpy = y0.dp;
+    for (x = 0; x < B; x++) {
+      *tmpx++ = *tmpa++;
+      *tmpy++ = *tmpb++;
+    }
+
+    tmpx = x1.dp;
+    for (x = B; x < a->used; x++) {
+      *tmpx++ = *tmpa++;
+    }
+
+    tmpy = y1.dp;
+    for (x = B; x < b->used; x++) {
+      *tmpy++ = *tmpb++;
+    }
   }
 
   /* only need to clamp the lower words since by definition the upper words x1/y1 must
diff --git a/bn_mp_karatsuba_sqr.c b/bn_mp_karatsuba_sqr.c
index 3078588..241b392 100644
--- a/bn_mp_karatsuba_sqr.c
+++ b/bn_mp_karatsuba_sqr.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -23,8 +23,7 @@ int
 mp_karatsuba_sqr (mp_int * a, mp_int * b)
 {
   mp_int  x0, x1, t1, t2, x0x0, x1x1;
-  int     B, err, x;
-
+  int     B, err;
 
   err = MP_MEM;
 
@@ -41,22 +40,31 @@ mp_karatsuba_sqr (mp_int * a, mp_int * b)
     goto X0;
 
   /* init temps */
-  if (mp_init (&t1) != MP_OKAY)
+  if (mp_init_size (&t1, a->used * 2) != MP_OKAY)
     goto X1;
-  if (mp_init (&t2) != MP_OKAY)
+  if (mp_init_size (&t2, a->used * 2) != MP_OKAY)
     goto T1;
-  if (mp_init (&x0x0) != MP_OKAY)
+  if (mp_init_size (&x0x0, B * 2) != MP_OKAY)
     goto T2;
-  if (mp_init (&x1x1) != MP_OKAY)
+  if (mp_init_size (&x1x1, (a->used - B) * 2) != MP_OKAY)
     goto X0X0;
 
-  /* now shift the digits */
-  for (x = 0; x < B; x++) {
-    x0.dp[x] = a->dp[x];
-  }
+  {
+    register int x;
+    register mp_digit *dst, *src;
+
+    src = a->dp;
+
+    /* now shift the digits */
+    dst = x0.dp;
+    for (x = 0; x < B; x++) {
+      *dst++ = *src++;
+    }
 
-  for (x = B; x < a->used; x++) {
-    x1.dp[x - B] = a->dp[x];
+    dst = x1.dp;
+    for (x = B; x < a->used; x++) {
+      *dst++ = *src++;
+    }
   }
 
   x0.used = B;
@@ -77,7 +85,7 @@ mp_karatsuba_sqr (mp_int * a, mp_int * b)
     goto X1X1;			/* t1 = (x1 - x0) * (y1 - y0) */
 
   /* add x0y0 */
-  if (mp_add (&x0x0, &x1x1, &t2) != MP_OKAY)
+  if (s_mp_add (&x0x0, &x1x1, &t2) != MP_OKAY)
     goto X1X1;			/* t2 = x0y0 + x1y1 */
   if (mp_sub (&t2, &t1, &t1) != MP_OKAY)
     goto X1X1;			/* t1 = x0y0 + x1y1 - (x1-x0)*(y1-y0) */
diff --git a/bn_mp_lcm.c b/bn_mp_lcm.c
index 60d5461..75b5829 100644
--- a/bn_mp_lcm.c
+++ b/bn_mp_lcm.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_lshd.c b/bn_mp_lshd.c
index 44b0588..6242957 100644
--- a/bn_mp_lshd.c
+++ b/bn_mp_lshd.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -31,16 +31,31 @@ mp_lshd (mp_int * a, int b)
     return res;
   }
 
-  /* increment the used by the shift amount than copy upwards */
-  a->used += b;
-  for (x = a->used - 1; x >= b; x--) {
-    a->dp[x] = a->dp[x - b];
-  }
+  {
+    register mp_digit *tmpa, *tmpaa;
+
+    /* increment the used by the shift amount than copy upwards */
+    a->used += b;
+    
+    /* top */
+    tmpa = a->dp + a->used - 1;
+    
+    /* base */
+    tmpaa = a->dp + a->used - 1 - b;
+
+    /* much like mp_rshd this is implemented using a sliding window
+     * except the window goes the otherway around.  Copying from
+     * the bottom to the top.  see bn_mp_rshd.c for more info.
+     */
+    for (x = a->used - 1; x >= b; x--) {
+      *tmpa-- = *tmpaa--;
+    }
 
-  /* zero the lower digits */
-  for (x = 0; x < b; x++) {
-    a->dp[x] = 0;
+    /* zero the lower digits */
+    tmpa = a->dp;
+    for (x = 0; x < b; x++) {
+      *tmpa++ = 0;
+    }
   }
-  mp_clamp (a);
   return MP_OKAY;
 }
diff --git a/bn_mp_mod.c b/bn_mp_mod.c
index c4a7374..e6027ce 100644
--- a/bn_mp_mod.c
+++ b/bn_mp_mod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_mod_2d.c b/bn_mp_mod_2d.c
index 4c6f1f1..fda6335 100644
--- a/bn_mp_mod_2d.c
+++ b/bn_mp_mod_2d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_mod_d.c b/bn_mp_mod_d.c
index b557381..42f3807 100644
--- a/bn_mp_mod_d.c
+++ b/bn_mp_mod_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_montgomery_calc_normalization.c b/bn_mp_montgomery_calc_normalization.c
index 06252de..b942eba 100644
--- a/bn_mp_montgomery_calc_normalization.c
+++ b/bn_mp_montgomery_calc_normalization.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_montgomery_reduce.c b/bn_mp_montgomery_reduce.c
index 586142a..e64435c 100644
--- a/bn_mp_montgomery_reduce.c
+++ b/bn_mp_montgomery_reduce.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_montgomery_setup.c b/bn_mp_montgomery_setup.c
index c739895..dfdc51a 100644
--- a/bn_mp_montgomery_setup.c
+++ b/bn_mp_montgomery_setup.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -18,36 +18,29 @@
 int
 mp_montgomery_setup (mp_int * a, mp_digit * mp)
 {
-  mp_int  t, tt;
-  int     res;
+  unsigned long x, b;
 
-  if ((res = mp_init (&t)) != MP_OKAY) {
-    return res;
-  }
+/* fast inversion mod 2^32 
+ *
+ * Based on the fact that 
+ *
+ * XA = 1 (mod 2^n)  =>  (X(2-XA)) A = 1 (mod 2^2n)
+ *                   =>  2*X*A - X*X*A*A = 1
+ *                   =>  2*(1) - (1)     = 1
+ */
+  b = a->dp[0];
 
-  if ((res = mp_init (&tt)) != MP_OKAY) {
-    goto __T;
+  if ((b & 1) == 0) {
+    return MP_VAL;
   }
 
-  /* tt = b */
-  tt.dp[0] = 0;
-  tt.dp[1] = 1;
-  tt.used = 2;
-
-  /* t = m mod b */
-  t.dp[0] = a->dp[0];
-  t.used = 1;
-
-  /* t = 1/m mod b */
-  if ((res = mp_invmod (&t, &tt, &t)) != MP_OKAY) {
-    goto __TT;
-  }
+  x = (((b + 2) & 4) << 1) + b;	/* here x*a==1 mod 2^4 */
+  x *= 2 - b * x;		/* here x*a==1 mod 2^8 */
+  x *= 2 - b * x;		/* here x*a==1 mod 2^16; each step doubles the nb of bits */
+  x *= 2 - b * x;		/* here x*a==1 mod 2^32 */
 
   /* t = -1/m mod b */
-  *mp = ((mp_digit) 1 << ((mp_digit) DIGIT_BIT)) - t.dp[0];
+  *mp = ((mp_digit) 1 << ((mp_digit) DIGIT_BIT)) - (x & MP_MASK);
 
-  res = MP_OKAY;
-__TT:mp_clear (&tt);
-__T:mp_clear (&t);
-  return res;
+  return MP_OKAY;
 }
diff --git a/bn_mp_mul.c b/bn_mp_mul.c
index 064fc85..5ccd6e4 100644
--- a/bn_mp_mul.c
+++ b/bn_mp_mul.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_mul_2.c b/bn_mp_mul_2.c
index 8174d0a..fca7125 100644
--- a/bn_mp_mul_2.c
+++ b/bn_mp_mul_2.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -50,6 +50,11 @@ mp_mul_2 (mp_int * a, mp_int * b)
 	if ((res = mp_grow (b, b->used + 1)) != MP_OKAY) {
 	  return res;
 	}
+
+	/* after the grow *tmpb is no longer valid so we have to reset it! 
+	 * (this bug took me about 17 minutes to find...!)
+	 */
+	tmpb = b->dp + b->used;
       }
       /* add a MSB of 1 */
       *tmpb = 1;
@@ -61,5 +66,6 @@ mp_mul_2 (mp_int * a, mp_int * b)
       *tmpb++ = 0;
     }
   }
+  b->sign = a->sign;
   return MP_OKAY;
 }
diff --git a/bn_mp_mul_2d.c b/bn_mp_mul_2d.c
index 97ee26c..faa9a7f 100644
--- a/bn_mp_mul_2d.c
+++ b/bn_mp_mul_2d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -32,9 +32,11 @@ mp_mul_2d (mp_int * a, int b, mp_int * c)
   }
 
   /* shift by as many digits in the bit count */
-  if ((res = mp_lshd (c, b / DIGIT_BIT)) != MP_OKAY) {
-    return res;
-  }
+  if (b >= DIGIT_BIT) {
+     if ((res = mp_lshd (c, b / DIGIT_BIT)) != MP_OKAY) {
+       return res;
+     }
+  }     
   c->used = c->alloc;
 
   /* shift any bit count < DIGIT_BIT */
diff --git a/bn_mp_mul_d.c b/bn_mp_mul_d.c
index 164bcac..f4458bb 100644
--- a/bn_mp_mul_d.c
+++ b/bn_mp_mul_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_mulmod.c b/bn_mp_mulmod.c
index abdf77b..2e3400a 100644
--- a/bn_mp_mulmod.c
+++ b/bn_mp_mulmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_n_root.c b/bn_mp_n_root.c
index eb49b3f..1e12fee 100644
--- a/bn_mp_n_root.c
+++ b/bn_mp_n_root.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_neg.c b/bn_mp_neg.c
index fd2e497..73f948a 100644
--- a/bn_mp_neg.c
+++ b/bn_mp_neg.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_or.c b/bn_mp_or.c
index e821bac..466a171 100644
--- a/bn_mp_or.c
+++ b/bn_mp_or.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_rand.c b/bn_mp_rand.c
index dc13534..b944d57 100644
--- a/bn_mp_rand.c
+++ b/bn_mp_rand.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_read_signed_bin.c b/bn_mp_read_signed_bin.c
index 8a9df88..448e327 100644
--- a/bn_mp_read_signed_bin.c
+++ b/bn_mp_read_signed_bin.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_read_unsigned_bin.c b/bn_mp_read_unsigned_bin.c
index 16e2f29..378d1fa 100644
--- a/bn_mp_read_unsigned_bin.c
+++ b/bn_mp_read_unsigned_bin.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_reduce.c b/bn_mp_reduce.c
index 8f15458..5d85f42 100644
--- a/bn_mp_reduce.c
+++ b/bn_mp_reduce.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_rshd.c b/bn_mp_rshd.c
index 39e631e..ef1a6bf 100644
--- a/bn_mp_rshd.c
+++ b/bn_mp_rshd.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -20,7 +20,6 @@ mp_rshd (mp_int * a, int b)
 {
   int     x;
 
-
   /* if b <= 0 then ignore it */
   if (b <= 0) {
     return;
@@ -32,14 +31,34 @@ mp_rshd (mp_int * a, int b)
     return;
   }
 
-  /* shift the digits down */
-  for (x = 0; x < (a->used - b); x++) {
-    a->dp[x] = a->dp[x + b];
-  }
+  {
+    register mp_digit *tmpa, *tmpaa;
+
+    /* shift the digits down */
+
+    /* base */
+    tmpa = a->dp;
+    
+    /* offset into digits */
+    tmpaa = a->dp + b;
+    
+    /* this is implemented as a sliding window where the window is b-digits long
+     * and digits from the top of the window are copied to the bottom
+     *
+     * e.g.
+     
+     b-2 | b-1 | b0 | b1 | b2 | ... | bb |   ---->
+                 /\                   |      ---->
+                  \-------------------/      ---->
+    */         
+    for (x = 0; x < (a->used - b); x++) {
+      *tmpa++ = *tmpaa++;
+    }
 
-  /* zero the top digits */
-  for (; x < a->used; x++) {
-    a->dp[x] = 0;
+    /* zero the top digits */
+    for (; x < a->used; x++) {
+      *tmpa++ = 0;
+    }
   }
   mp_clamp (a);
 }
diff --git a/bn_mp_set.c b/bn_mp_set.c
index aeaf9cd..d749463 100644
--- a/bn_mp_set.c
+++ b/bn_mp_set.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_set_int.c b/bn_mp_set_int.c
index f22ab69..1d6bce7 100644
--- a/bn_mp_set_int.c
+++ b/bn_mp_set_int.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_shrink.c b/bn_mp_shrink.c
index 3cc506b..c3f1aa9 100644
--- a/bn_mp_shrink.c
+++ b/bn_mp_shrink.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_signed_bin_size.c b/bn_mp_signed_bin_size.c
index d50ae7a..fe8f499 100644
--- a/bn_mp_signed_bin_size.c
+++ b/bn_mp_signed_bin_size.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_sqr.c b/bn_mp_sqr.c
index c8b5cb7..99ebdf0 100644
--- a/bn_mp_sqr.c
+++ b/bn_mp_sqr.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_sqrmod.c b/bn_mp_sqrmod.c
index 44f608f..c32d562 100644
--- a/bn_mp_sqrmod.c
+++ b/bn_mp_sqrmod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_sub.c b/bn_mp_sub.c
index 1366c55..6558e5d 100644
--- a/bn_mp_sub.c
+++ b/bn_mp_sub.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_sub_d.c b/bn_mp_sub_d.c
index aebc414..7ca565e 100644
--- a/bn_mp_sub_d.c
+++ b/bn_mp_sub_d.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_submod.c b/bn_mp_submod.c
index 16fee71..1606ff0 100644
--- a/bn_mp_submod.c
+++ b/bn_mp_submod.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_to_signed_bin.c b/bn_mp_to_signed_bin.c
index 41abac1..023c80f 100644
--- a/bn_mp_to_signed_bin.c
+++ b/bn_mp_to_signed_bin.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_to_unsigned_bin.c b/bn_mp_to_unsigned_bin.c
index eec9f75..8f5eeb7 100644
--- a/bn_mp_to_unsigned_bin.c
+++ b/bn_mp_to_unsigned_bin.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_unsigned_bin_size.c b/bn_mp_unsigned_bin_size.c
index bee88e6..558efb0 100644
--- a/bn_mp_unsigned_bin_size.c
+++ b/bn_mp_unsigned_bin_size.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_xor.c b/bn_mp_xor.c
index 4a2ff9b..6622074 100644
--- a/bn_mp_xor.c
+++ b/bn_mp_xor.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_mp_zero.c b/bn_mp_zero.c
index 27ca5bd..c86cabd 100644
--- a/bn_mp_zero.c
+++ b/bn_mp_zero.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_radix.c b/bn_radix.c
index 205c148..1f06389 100644
--- a/bn_radix.c
+++ b/bn_radix.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_reverse.c b/bn_reverse.c
index 50109d7..c24aa27 100644
--- a/bn_reverse.c
+++ b/bn_reverse.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_s_mp_add.c b/bn_s_mp_add.c
index 328ec06..314db79 100644
--- a/bn_s_mp_add.c
+++ b/bn_s_mp_add.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
@@ -55,8 +55,14 @@ s_mp_add (mp_int * a, mp_int * b, mp_int * c)
     register int i;
 
     /* alias for digit pointers */
+    
+    /* first input */
     tmpa = a->dp;
+    
+    /* second input */
     tmpb = b->dp;
+    
+    /* destination */
     tmpc = c->dp;
 
     u = 0;
diff --git a/bn_s_mp_mul_digs.c b/bn_s_mp_mul_digs.c
index f2b0d13..0243449 100644
--- a/bn_s_mp_mul_digs.c
+++ b/bn_s_mp_mul_digs.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_s_mp_mul_high_digs.c b/bn_s_mp_mul_high_digs.c
index a43a593..ba52d11 100644
--- a/bn_s_mp_mul_high_digs.c
+++ b/bn_s_mp_mul_high_digs.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_s_mp_sqr.c b/bn_s_mp_sqr.c
index a0ec38b..fcb2767 100644
--- a/bn_s_mp_sqr.c
+++ b/bn_s_mp_sqr.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bn_s_mp_sub.c b/bn_s_mp_sub.c
index fe15d23..a5683dd 100644
--- a/bn_s_mp_sub.c
+++ b/bn_s_mp_sub.c
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
diff --git a/bncore.c b/bncore.c
index 8863935..ba9fbf9 100644
--- a/bncore.c
+++ b/bncore.c
@@ -10,10 +10,13 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #include <tommath.h>
 
-int     KARATSUBA_MUL_CUTOFF = 80,	/* Min. number of digits before Karatsuba multiplication is used. */
-        KARATSUBA_SQR_CUTOFF = 80,	/* Min. number of digits before Karatsuba squaring is used. */
-        MONTGOMERY_EXPT_CUTOFF = 74;	/* max. number of digits that montgomery reductions will help for */
+/* configured for a AMD Duron Morgan core with etc/tune.c */
+int     KARATSUBA_MUL_CUTOFF = 73,	/* Min. number of digits before Karatsuba multiplication is used. */
+        KARATSUBA_SQR_CUTOFF = 121,	/* Min. number of digits before Karatsuba squaring is used. */
+        MONTGOMERY_EXPT_CUTOFF = 128;	/* max. number of digits that montgomery reductions will help for */
+
+
diff --git a/changes.txt b/changes.txt
index c31526e..284d40e 100644
--- a/changes.txt
+++ b/changes.txt
@@ -1,3 +1,16 @@
+Mar 15th, 2003
+v0.14  -- Tons of manual updates
+       -- cleaned up the directory
+       -- added MSVC makefiles
+       -- source changes [that I don't recall]
+       -- Fixed up the lshd/rshd code to use pointer aliasing
+       -- Fixed up the mul_2d and div_2d to not call rshd/lshd unless needed
+       -- Fixed up etc/tune.c a tad
+       -- fixed up demo/demo.c to output comma-delimited results of timing
+          also fixed up timing demo to use a finer granularity for various functions
+       -- fixed up demo/demo.c testing to pause during testing so my Duron won't catch on fire
+          [stays around 31-35C during testing :-)]
+       
 Feb 13th, 2003
 v0.13  -- tons of minor speed-ups in low level add, sub, mul_2 and div_2 which propagate 
           to other functions like mp_invmod, mp_div, etc...
diff --git a/demo/demo.c b/demo/demo.c
index 8bf9acd..0d79021 100644
--- a/demo/demo.c
+++ b/demo/demo.c
@@ -69,18 +69,32 @@ int mp_reduce_setup(mp_int *a, mp_int *b)
    }
    return mp_div(a, b, a, NULL);
 }
+
+int mp_rand(mp_int *a, int c)
+{
+   long z = abs(rand()) & 65535;
+   mp_set(a, z?z:1);
+   while (c--) {
+      s_mp_lshd(a, 1);
+      mp_add_d(a, abs(rand()), a);
+   }
+   return MP_OKAY;
+}
 #endif
 
    char cmd[4096], buf[4096];
 int main(void)
 {
    mp_int a, b, c, d, e, f;
-   unsigned long expt_n, add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, inv_n;
+   unsigned long expt_n, add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, inv_n,
+                 div2_n, mul2_n;
    unsigned rr;
+   int cnt;
 
 #ifdef TIMER
    int n;
    ulong64 tt;
+   FILE *log;
 #endif
 
    mp_init(&a);
@@ -90,60 +104,66 @@ int main(void)
    mp_init(&e);
    mp_init(&f);
 
-
 #ifdef TIMER
-goto multtime;
-
       printf("CLOCKS_PER_SEC == %lu\n", CLOCKS_PER_SEC);
-      mp_read_radix(&a, "340282366920938463463374607431768211455", 10);
-      mp_read_radix(&b, "340282366920938463463574607431768211455", 10);
-      while (a.used * DIGIT_BIT < 8192) {
+goto expttime;      
+
+      log = fopen("add.log", "w");
+      for (cnt = 4; cnt <= 128; cnt += 4) {
+         mp_rand(&a, cnt);
+         mp_rand(&b, cnt);
          reset();
          for (rr = 0; rr < 10000000; rr++) {
              mp_add(&a, &b, &c);
          }
          tt = rdtsc();
          printf("Adding\t\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
-         mp_sqr(&a, &a);
-         mp_sqr(&b, &b);
+         fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
       }
+      fclose(log);
  
-      mp_read_radix(&a, "340282366920938463463374607431768211455", 10);
-      mp_read_radix(&b, "340282366920938463463574607431768211455", 10);
-      while (a.used * DIGIT_BIT < 8192) {
+      log = fopen("sub.log", "w");
+      for (cnt = 4; cnt <= 128; cnt += 4) {
+         mp_rand(&a, cnt);
+         mp_rand(&b, cnt);
          reset();
          for (rr = 0; rr < 10000000; rr++) {
              mp_sub(&a, &b, &c);
          }
          tt = rdtsc();
-         printf("Subtracting\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
-         mp_sqr(&a, &a);
-         mp_sqr(&b, &b);
+         printf("Subtracting\t\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
+         fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
       }
+      fclose(log);
       
 multtime:      
 
-   mp_read_radix(&a, "340282366920938463463374607431768211455", 10);
-   while (a.used * DIGIT_BIT < 8192) {
+   log = fopen("sqr.log", "w");
+   for (cnt = 4; cnt <= 128; cnt += 4) {
+      mp_rand(&a, cnt);
       reset();
       for (rr = 0; rr < 250000; rr++) {
           mp_sqr(&a, &b);
       }
       tt = rdtsc();
       printf("Squaring\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
-      mp_copy(&b, &a);
+      fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
    }
+   fclose(log);
    
-   mp_read_radix(&a, "340282366920938463463374607431768211455", 10);
-   while (a.used * DIGIT_BIT < 8192) {
+   log = fopen("mult.log", "w");
+   for (cnt = 4; cnt <= 128; cnt += 4) {
+      mp_rand(&a, cnt);
+      mp_rand(&b, cnt);
       reset();
       for (rr = 0; rr < 250000; rr++) {
-          mp_mul(&a, &a, &b);
+          mp_mul(&a, &b, &c);
       }
       tt = rdtsc();
       printf("Multiplying\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
-      mp_copy(&b, &a);
+      fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
    }
+   fclose(log);
 
 expttime:  
    {
@@ -157,6 +177,7 @@ expttime:
          "1214855636816562637502584060163403830270705000634713483015101384881871978446801224798536155406895823305035467591632531067547890948695117172076954220727075688048751022421198712032848890056357845974246560748347918630050853933697792254955890439720297560693579400297062396904306270145886830719309296352765295712183040773146419022875165382778007040109957609739589875590885701126197906063620133954893216612678838507540777138437797705602453719559017633986486649523611975865005712371194067612263330335590526176087004421363598470302731349138773205901447704682181517904064735636518462452242791676541725292378925568296858010151852326316777511935037531017413910506921922450666933202278489024521263798482237150056835746454842662048692127173834433089016107854491097456725016327709663199738238442164843147132789153725513257167915555162094970853584447993125488607696008169807374736711297007473812256272245489405898470297178738029484459690836250560495461579533254473316340608217876781986188705928270735695752830825527963838355419762516246028680280988020401914551825487349990306976304093109384451438813251211051597392127491464898797406789175453067960072008590614886532333015881171367104445044718144312416815712216611576221546455968770801413440778423979",
          NULL         
       };
+   log = fopen("expt.log", "w");
    for (n = 0; primes[n]; n++) {
       mp_read_radix(&a, primes[n], 10);
       mp_zero(&b);
@@ -183,12 +204,21 @@ expttime:
          exit(0);
       }
       printf("Exponentiating\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
+      fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
    }
    }   
-
-   mp_read_radix(&a, "340282366920938463463374607431768211455", 10);
-   mp_read_radix(&b, "234892374891378913789237289378973232333", 10);
-   while (a.used * DIGIT_BIT < 8192) {
+   fclose(log);
+invtime:
+   log = fopen("invmod.log", "w");
+   for (cnt = 4; cnt <= 128; cnt += 4) {
+      mp_rand(&a, cnt);
+      mp_rand(&b, cnt);
+      
+      do {
+         mp_add_d(&b, 1, &b);
+         mp_gcd(&a, &b, &c);
+      } while (mp_cmp_d(&c, 1) != MP_EQ);
+      
       reset();
       for (rr = 0; rr < 10000; rr++) {
           mp_invmod(&b, &a, &c);
@@ -200,16 +230,18 @@ expttime:
          return 0;
       }
       printf("Inverting mod\t%4d-bit => %9llu/sec, %9llu ticks\n", mp_count_bits(&a), (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt, tt);
-      mp_sqr(&a, &a);
-      mp_sqr(&b, &b);
+      fprintf(log, "%d,%9llu\n", cnt, (((unsigned long long)rr)*CLOCKS_PER_SEC)/tt);
    }
+   fclose(log);
    
    return 0;
   
 #endif
 
-   inv_n = expt_n = lcm_n = gcd_n = add_n = sub_n = mul_n = div_n = sqr_n = mul2d_n = div2d_n = 0;   
+   div2_n = mul2_n = inv_n = expt_n = lcm_n = gcd_n = add_n = 
+   sub_n = mul_n = div_n = sqr_n = mul2d_n = div2d_n = cnt = 0;
    for (;;) {
+       if (!(++cnt & 15)) sleep(3);
    
        /* randomly clear and re-init one variable, this has the affect of triming the alloc space */
        switch (abs(rand()) % 7) {
@@ -223,7 +255,7 @@ expttime:
        }
    
    
-       printf("%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%5d\r", add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, expt_n, inv_n, _ifuncs);
+       printf("%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu/%7lu ", add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, expt_n, inv_n, div2_n, mul2_n);
        fgets(cmd, 4095, stdin);
        cmd[strlen(cmd)-1] = 0;
        printf("%s  ]\r",cmd); fflush(stdout);
@@ -386,7 +418,29 @@ draw(&a);draw(&b);draw(&c);draw(&d);
                 return 0;
              }
                 
-       }
+       } else if (!strcmp(cmd, "div2")) { ++div2_n;
+             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 10);
+             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 10);
+             mp_div_2(&a, &c);
+             if (mp_cmp(&c, &b) != MP_EQ) {
+                 printf("div_2 %lu failure\n", div2_n);
+                 draw(&a);
+                 draw(&b);
+                 draw(&c);
+                 return 0;
+             }
+       } else if (!strcmp(cmd, "mul2")) { ++mul2_n;
+             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 10);
+             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 10);
+             mp_mul_2(&a, &c);
+             if (mp_cmp(&c, &b) != MP_EQ) {
+                 printf("mul_2 %lu failure\n", mul2_n);
+                 draw(&a);
+                 draw(&b);
+                 draw(&c);
+                 return 0;
+             }
+       }             
        
    }
    return 0;   
diff --git a/etc/makefile b/etc/makefile
index bf4befb..81f692c 100644
--- a/etc/makefile
+++ b/etc/makefile
@@ -17,4 +17,4 @@ mersenne: mersenne.o
 	$(CC) mersenne.o $(LIBNAME) -o mersenne
         
 clean:
-	rm -f *.o *.exe pprime tune mersenne 
\ No newline at end of file
+	rm -f *.log *.o *.obj *.exe pprime tune mersenne 
\ No newline at end of file
diff --git a/etc/makefile.msvc b/etc/makefile.msvc
new file mode 100644
index 0000000..6011cf3
--- /dev/null
+++ b/etc/makefile.msvc
@@ -0,0 +1,14 @@
+#MSVC Makefile
+#
+#Tom St Denis
+
+CFLAGS = /I../ /Ogityb2 /Gs /DWIN32 /W3
+
+pprime: pprime.obj
+	cl pprime.obj ../tommath.lib 
+
+mersenne: mersenne.obj
+	cl mersenne.obj ../tommath.lib
+	
+tune: tune.obj
+	cl tune.obj ../tommath.lib	
\ No newline at end of file
diff --git a/etc/mersenne.c b/etc/mersenne.c
index 04b2d98..fa6a856 100644
--- a/etc/mersenne.c
+++ b/etc/mersenne.c
@@ -3,14 +3,14 @@
  * Tom St Denis, tomstdenis@iahu.ca
  */
 #include <time.h>
-#include <bn.h>
+#include <tommath.h>
 
 int
 is_mersenne (long s, int *pp)
 {
-  mp_int    n, u, mu;
-  int       res, k;
-  long      ss;
+  mp_int  n, u, mu;
+  int     res, k;
+  long    ss;
 
   *pp = 0;
 
@@ -85,7 +85,7 @@ __N:mp_clear (&n);
 long
 i_sqrt (long x)
 {
-  long      x1, x2;
+  long    x1, x2;
 
   x2 = 16;
   do {
@@ -104,7 +104,7 @@ i_sqrt (long x)
 int
 isprime (long k)
 {
-  long      y, z;
+  long    y, z;
 
   y = i_sqrt (k);
   for (z = 2; z <= y; z++) {
@@ -118,9 +118,9 @@ isprime (long k)
 int
 main (void)
 {
-  int       pp;
-  long      k;
-  clock_t   tt;
+  int     pp;
+  long    k;
+  clock_t tt;
 
   k = 3;
 
diff --git a/etc/pprime.c b/etc/pprime.c
index 6fea3da..6285924 100644
--- a/etc/pprime.c
+++ b/etc/pprime.c
@@ -8,10 +8,10 @@
 #include "tommath.h"
 
 /* fast square root */
-static    mp_digit
+static  mp_digit
 i_sqrt (mp_word x)
 {
-  mp_word   x1, x2;
+  mp_word x1, x2;
 
   x2 = x;
   do {
@@ -28,10 +28,10 @@ i_sqrt (mp_word x)
 
 
 /* generates a prime digit */
-static    mp_digit
+static  mp_digit
 prime_digit ()
 {
-  mp_digit  r, x, y, next;
+  mp_digit r, x, y, next;
 
   /* make a DIGIT_BIT-bit random number */
   for (r = x = 0; x < DIGIT_BIT; x++) {
@@ -141,8 +141,8 @@ prime_digit ()
 int
 pprime (int k, int li, mp_int * p, mp_int * q)
 {
-  mp_int    a, b, c, n, x, y, z, v;
-  int       res, ii;
+  mp_int  a, b, c, n, x, y, z, v;
+  int     res, ii;
   static const mp_digit bases[] = { 2, 3, 5, 7, 11, 13, 17, 19 };
 
   /* single digit ? */
@@ -329,10 +329,10 @@ __C:mp_clear (&c);
 int
 main (void)
 {
-  mp_int    p, q;
-  char      buf[4096];
-  int       k, li;
-  clock_t   t1;
+  mp_int  p, q;
+  char    buf[4096];
+  int     k, li;
+  clock_t t1;
 
   srand (time (NULL));
 
diff --git a/etc/tune.c b/etc/tune.c
index 73a44b7..f50edab 100644
--- a/etc/tune.c
+++ b/etc/tune.c
@@ -8,19 +8,19 @@
 clock_t
 time_mult (void)
 {
-  clock_t   t1;
-  int       x, y;
-  mp_int    a, b, c;
+  clock_t t1;
+  int     x, y;
+  mp_int  a, b, c;
 
   mp_init (&a);
   mp_init (&b);
   mp_init (&c);
 
   t1 = clock ();
-  for (x = 8; x <= 128; x += 8) {
-    for (y = 0; y < 1000; y++) {
-      mp_rand (&a, x);
-      mp_rand (&b, x);
+  for (x = 4; x <= 128; x += 4) {
+    mp_rand (&a, x);
+    mp_rand (&b, x);
+    for (y = 0; y < 10000; y++) {
       mp_mul (&a, &b, &c);
     }
   }
@@ -33,17 +33,17 @@ time_mult (void)
 clock_t
 time_sqr (void)
 {
-  clock_t   t1;
-  int       x, y;
-  mp_int    a, b;
+  clock_t t1;
+  int     x, y;
+  mp_int  a, b;
 
   mp_init (&a);
   mp_init (&b);
 
   t1 = clock ();
-  for (x = 8; x <= 128; x += 8) {
-    for (y = 0; y < 1000; y++) {
-      mp_rand (&a, x);
+  for (x = 4; x <= 128; x += 4) {
+    mp_rand (&a, x);
+    for (y = 0; y < 10000; y++) {
       mp_sqr (&a, &b);
     }
   }
@@ -52,20 +52,54 @@ time_sqr (void)
   return clock () - t1;
 }
 
+clock_t
+time_expt (void)
+{
+  clock_t t1;
+  int     x, y;
+  mp_int  a, b, c, d;
+
+  mp_init (&a);
+  mp_init (&b);
+  mp_init (&c);
+  mp_init (&d);
+
+  t1 = clock ();
+  for (x = 4; x <= 128; x += 4) {
+    mp_rand (&a, x);
+    mp_rand (&b, x);
+    mp_rand (&c, x);
+    if (mp_iseven (&c) != 0) {
+      mp_add_d (&c, 1, &c);
+    }
+    for (y = 0; y < 10; y++) {
+      mp_exptmod (&a, &b, &c, &d);
+    }
+  }
+  mp_clear (&d);
+  mp_clear (&c);
+  mp_clear (&b);
+  mp_clear (&a);
+
+  return clock () - t1;
+}
+
 int
 main (void)
 {
-  int       best_mult, best_square;
-  clock_t   best, ti;
+  int     best_mult, best_square, best_exptmod;
+  clock_t best, ti;
+  FILE   *log;
 
-  best_mult = best_square = 0;
+  best_mult = best_square = best_exptmod = 0;
 
   /* tune multiplication first */
+  log = fopen ("mult.log", "w");
   best = CLOCKS_PER_SEC * 1000;
-  for (KARATSUBA_MUL_CUTOFF = 8; KARATSUBA_MUL_CUTOFF <= 128;
-       KARATSUBA_MUL_CUTOFF++) {
+  for (KARATSUBA_MUL_CUTOFF = 8; KARATSUBA_MUL_CUTOFF <= 128; KARATSUBA_MUL_CUTOFF++) {
     ti = time_mult ();
     printf ("%4d : %9lu\r", KARATSUBA_MUL_CUTOFF, ti);
+    fprintf (log, "%d, %lu\n", KARATSUBA_MUL_CUTOFF, ti);
     fflush (stdout);
     if (ti < best) {
       printf ("New best: %lu, %d         \n", ti, KARATSUBA_MUL_CUTOFF);
@@ -73,13 +107,15 @@ main (void)
       best_mult = KARATSUBA_MUL_CUTOFF;
     }
   }
+  fclose (log);
 
   /* tune squaring */
+  log = fopen ("sqr.log", "w");
   best = CLOCKS_PER_SEC * 1000;
-  for (KARATSUBA_SQR_CUTOFF = 8; KARATSUBA_SQR_CUTOFF <= 128;
-       KARATSUBA_SQR_CUTOFF++) {
+  for (KARATSUBA_SQR_CUTOFF = 8; KARATSUBA_SQR_CUTOFF <= 128; KARATSUBA_SQR_CUTOFF++) {
     ti = time_sqr ();
     printf ("%4d : %9lu\r", KARATSUBA_SQR_CUTOFF, ti);
+    fprintf (log, "%d, %lu\n", KARATSUBA_SQR_CUTOFF, ti);
     fflush (stdout);
     if (ti < best) {
       printf ("New best: %lu, %d         \n", ti, KARATSUBA_SQR_CUTOFF);
@@ -87,10 +123,30 @@ main (void)
       best_square = KARATSUBA_SQR_CUTOFF;
     }
   }
+  fclose (log);
+
+  /* tune exptmod */
+  KARATSUBA_MUL_CUTOFF = best_mult;
+  KARATSUBA_SQR_CUTOFF = best_square;
+
+  log = fopen ("expt.log", "w");
+  best = CLOCKS_PER_SEC * 1000;
+  for (MONTGOMERY_EXPT_CUTOFF = 8; MONTGOMERY_EXPT_CUTOFF <= 192; MONTGOMERY_EXPT_CUTOFF++) {
+    ti = time_expt ();
+    printf ("%4d : %9lu\r", MONTGOMERY_EXPT_CUTOFF, ti);
+    fflush (stdout);
+    fprintf (log, "%d : %lu\r", MONTGOMERY_EXPT_CUTOFF, ti);
+    if (ti < best) {
+      printf ("New best: %lu, %d\n", ti, MONTGOMERY_EXPT_CUTOFF);
+      best = ti;
+      best_exptmod = MONTGOMERY_EXPT_CUTOFF;
+    }
+  }
+  fclose (log);
 
   printf
-    ("\n\n\nKaratsuba Multiplier Cutoff: %d\nKaratsuba Squaring Cutoff: %d\n",
-     best_mult, best_square);
+    ("\n\n\nKaratsuba Multiplier Cutoff: %d\nKaratsuba Squaring Cutoff: %d\nMontgomery exptmod Cutoff: %d\n",
+     best_mult, best_square, best_exptmod);
 
   return 0;
 }
diff --git a/makefile b/makefile
index 9e6127d..856274b 100644
--- a/makefile
+++ b/makefile
@@ -1,6 +1,6 @@
 CFLAGS  +=  -I./ -Wall -W -Wshadow -O3 -fomit-frame-pointer -funroll-loops
 
-VERSION=0.13
+VERSION=0.14
 
 default: libtommath.a
 
@@ -60,7 +60,7 @@ docs:	docdvi
 	rm -f bn.log bn.aux bn.dvi
 	
 clean:
-	rm -f *.pdf *.o *.a *.exe etclib/*.o demo/demo.o test ltmtest mpitest mtest/mtest mtest/mtest.exe \
+	rm -f *.pdf *.o *.a *.obj *.lib *.exe etclib/*.o demo/demo.o test ltmtest mpitest mtest/mtest mtest/mtest.exe \
         bn.log bn.aux bn.dvi *.log *.s mpi.c 
 	cd etc ; make clean
 
diff --git a/makefile.msvc b/makefile.msvc
new file mode 100644
index 0000000..7c5f763
--- /dev/null
+++ b/makefile.msvc
@@ -0,0 +1,26 @@
+#MSVC Makefile
+#
+#Tom St Denis
+
+CFLAGS = /I. /Ogityb2 /Gs /DWIN32 /W3
+
+default: library
+
+OBJECTS=bncore.obj bn_mp_init.obj bn_mp_clear.obj bn_mp_exch.obj bn_mp_grow.obj bn_mp_shrink.obj \
+bn_mp_clamp.obj bn_mp_zero.obj  bn_mp_set.obj bn_mp_set_int.obj bn_mp_init_size.obj bn_mp_copy.obj \
+bn_mp_init_copy.obj bn_mp_abs.obj bn_mp_neg.obj bn_mp_cmp_mag.obj bn_mp_cmp.obj bn_mp_cmp_d.obj \
+bn_mp_rshd.obj bn_mp_lshd.obj bn_mp_mod_2d.obj bn_mp_div_2d.obj bn_mp_mul_2d.obj bn_mp_div_2.obj \
+bn_mp_mul_2.obj bn_s_mp_add.obj bn_s_mp_sub.obj bn_fast_s_mp_mul_digs.obj bn_s_mp_mul_digs.obj \
+bn_fast_s_mp_mul_high_digs.obj bn_s_mp_mul_high_digs.obj bn_fast_s_mp_sqr.obj bn_s_mp_sqr.obj \
+bn_mp_add.obj bn_mp_sub.obj bn_mp_karatsuba_mul.obj bn_mp_mul.obj bn_mp_karatsuba_sqr.obj \
+bn_mp_sqr.obj bn_mp_div.obj bn_mp_mod.obj bn_mp_add_d.obj bn_mp_sub_d.obj bn_mp_mul_d.obj \
+bn_mp_div_d.obj bn_mp_mod_d.obj bn_mp_expt_d.obj bn_mp_addmod.obj bn_mp_submod.obj \
+bn_mp_mulmod.obj bn_mp_sqrmod.obj bn_mp_gcd.obj bn_mp_lcm.obj bn_fast_mp_invmod.obj bn_mp_invmod.obj \
+bn_mp_reduce.obj bn_mp_montgomery_setup.obj bn_fast_mp_montgomery_reduce.obj bn_mp_montgomery_reduce.obj \
+bn_mp_exptmod_fast.obj bn_mp_exptmod.obj bn_mp_2expt.obj bn_mp_n_root.obj bn_mp_jacobi.obj bn_reverse.obj \
+bn_mp_count_bits.obj bn_mp_read_unsigned_bin.obj bn_mp_read_signed_bin.obj bn_mp_to_unsigned_bin.obj \
+bn_mp_to_signed_bin.obj bn_mp_unsigned_bin_size.obj bn_mp_signed_bin_size.obj bn_radix.obj \
+bn_mp_xor.obj bn_mp_and.obj bn_mp_or.obj bn_mp_rand.obj bn_mp_montgomery_calc_normalization.obj
+
+library: $(OBJECTS)
+	lib /out:tommath.lib $(OBJECTS)
diff --git a/mtest/mtest.c b/mtest/mtest.c
index 3759d15..245c0d7 100644
--- a/mtest/mtest.c
+++ b/mtest/mtest.c
@@ -41,7 +41,7 @@ void rand_num(mp_int *a)
    unsigned char buf[512];
 
 top:
-   size = 1 + ((fgetc(rng)*fgetc(rng)) % 96);
+   size = 1 + ((fgetc(rng)*fgetc(rng)) % 512);
    buf[0] = (fgetc(rng)&1)?1:0;
    fread(buf+1, 1, size, rng);
    for (n = 0; n < size; n++) {
@@ -57,7 +57,7 @@ void rand_num2(mp_int *a)
    unsigned char buf[512];
 
 top:
-   size = 1 + ((fgetc(rng)*fgetc(rng)) % 96);
+   size = 1 + ((fgetc(rng)*fgetc(rng)) % 512);
    buf[0] = (fgetc(rng)&1)?1:0;
    fread(buf+1, 1, size, rng);
    for (n = 0; n < size; n++) {
@@ -72,6 +72,8 @@ int main(void)
    int n;
    mp_int a, b, c, d, e;
    char buf[4096];
+   
+   static int tests[] = { 11, 12 };
 
    mp_init(&a);
    mp_init(&b);
@@ -89,7 +91,7 @@ int main(void)
    }
 
    for (;;) {
-       n = 4; // fgetc(rng) % 11;
+       n =  fgetc(rng) % 13;
 
    if (n == 0) {
        /* add tests */
@@ -235,7 +237,24 @@ int main(void)
       printf("%s\n", buf);      
       mp_todecimal(&c, buf);
       printf("%s\n", buf);      
-   } 
+   } else if (n == 11) {
+      rand_num(&a);
+      mp_mul_2(&a, &a);
+      mp_div_2(&a, &b);
+      printf("div2\n");
+      mp_todecimal(&a, buf);
+      printf("%s\n", buf);      
+      mp_todecimal(&b, buf);
+      printf("%s\n", buf);
+   } else if (n == 12) {
+      rand_num2(&a);
+      mp_mul_2(&a, &b);
+      printf("mul2\n");
+      mp_todecimal(&a, buf);
+      printf("%s\n", buf);      
+      mp_todecimal(&b, buf);
+      printf("%s\n", buf);
+   }
    }
    fclose(rng);
    return 0;
diff --git a/timings.txt b/timings.txt
deleted file mode 100644
index 128649e..0000000
--- a/timings.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-CLOCKS_PER_SEC == 1000
-Adding           128-bit =>  14534883/sec,       688 ticks
-Adding           256-bit =>  11037527/sec,       906 ticks
-Adding           512-bit =>   8650519/sec,      1156 ticks
-Adding          1024-bit =>   5871990/sec,      1703 ticks
-Adding          2048-bit =>   3575259/sec,      2797 ticks
-Adding          4096-bit =>   2018978/sec,      4953 ticks
-Subtracting      128-bit =>  11025358/sec,       907 ticks
-Subtracting      256-bit =>   9149130/sec,      1093 ticks
-Subtracting      512-bit =>   7440476/sec,      1344 ticks
-Subtracting     1024-bit =>   5078720/sec,      1969 ticks
-Subtracting     2048-bit =>   3168567/sec,      3156 ticks
-Subtracting     4096-bit =>   1833852/sec,      5453 ticks
-Squaring         128-bit =>   3205128/sec,        78 ticks
-Squaring         256-bit =>   1592356/sec,       157 ticks
-Squaring         512-bit =>    696378/sec,       359 ticks
-Squaring        1024-bit =>    266808/sec,       937 ticks
-Squaring        2048-bit =>     85999/sec,      2907 ticks
-Squaring        4096-bit =>     21949/sec,     11390 ticks
-Multiplying      128-bit =>   3205128/sec,        78 ticks
-Multiplying      256-bit =>   1592356/sec,       157 ticks
-Multiplying      512-bit =>    615763/sec,       406 ticks
-Multiplying     1024-bit =>    192752/sec,      1297 ticks
-Multiplying     2048-bit =>     53510/sec,      4672 ticks
-Multiplying     4096-bit =>     14801/sec,     16890 ticks
-Exponentiating   513-bit =>       531/sec,        47 ticks
-Exponentiating   769-bit =>       177/sec,       141 ticks
-Exponentiating  1025-bit =>        88/sec,       282 ticks
-Exponentiating  2049-bit =>        13/sec,      1890 ticks
-Exponentiating  2561-bit =>         6/sec,      3812 ticks
-Exponentiating  3073-bit =>         4/sec,      6031 ticks
-Exponentiating  4097-bit =>         1/sec,     12843 ticks
-Inverting mod    128-bit =>     19160/sec,      5219 ticks
-Inverting mod    256-bit =>      8290/sec,     12062 ticks
-Inverting mod    512-bit =>      3565/sec,     28047 ticks
-Inverting mod   1024-bit =>      1305/sec,     76594 ticks
\ No newline at end of file
diff --git a/timings2.txt b/timings2.txt
deleted file mode 100644
index 0b87e21..0000000
--- a/timings2.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-CLOCKS_PER_SEC == 1000
-Adding           128-bit =>  15600624/sec,       641 ticks
-Adding           256-bit =>  12804097/sec,       781 ticks
-Adding           512-bit =>  10000000/sec,      1000 ticks
-Adding          1024-bit =>   7032348/sec,      1422 ticks
-Adding          2048-bit =>   4076640/sec,      2453 ticks
-Adding          4096-bit =>   2424242/sec,      4125 ticks
-Subtracting      128-bit =>  10845986/sec,       922 ticks
-Subtracting      256-bit =>   9416195/sec,      1062 ticks
-Subtracting      512-bit =>   7710100/sec,      1297 ticks
-Subtracting     1024-bit =>   5159958/sec,      1938 ticks
-Subtracting     2048-bit =>   3299241/sec,      3031 ticks
-Subtracting     4096-bit =>   1987676/sec,      5031 ticks
-Squaring         128-bit =>   3205128/sec,        78 ticks
-Squaring         256-bit =>   1592356/sec,       157 ticks
-Squaring         512-bit =>    696378/sec,       359 ticks
-Squaring        1024-bit =>    266524/sec,       938 ticks
-Squaring        2048-bit =>     86505/sec,      2890 ticks
-Squaring        4096-bit =>     22471/sec,     11125 ticks
-Multiplying      128-bit =>   3205128/sec,        78 ticks
-Multiplying      256-bit =>   1592356/sec,       157 ticks
-Multiplying      512-bit =>    615763/sec,       406 ticks
-Multiplying     1024-bit =>    190548/sec,      1312 ticks
-Multiplying     2048-bit =>     54418/sec,      4594 ticks
-Multiplying     4096-bit =>     14897/sec,     16781 ticks
-Exponentiating   513-bit =>       531/sec,        47 ticks
-Exponentiating   769-bit =>       177/sec,       141 ticks
-Exponentiating  1025-bit =>        84/sec,       297 ticks
-Exponentiating  2049-bit =>        13/sec,      1875 ticks
-Exponentiating  2561-bit =>         6/sec,      3766 ticks
-Exponentiating  3073-bit =>         4/sec,      6000 ticks
-Exponentiating  4097-bit =>         1/sec,     12750 ticks
-Inverting mod    128-bit =>     17301/sec,       578 ticks
-Inverting mod    256-bit =>      8103/sec,      1234 ticks
-Inverting mod    512-bit =>      3422/sec,      2922 ticks
-Inverting mod   1024-bit =>      1330/sec,      7516 ticks
\ No newline at end of file
diff --git a/timings3.txt b/timings3.txt
deleted file mode 100644
index f269c2b..0000000
--- a/timings3.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-Exponentiating   513-bit =>       531/sec,        94 ticks
-Exponentiating   769-bit =>       187/sec,       266 ticks
-Exponentiating  1025-bit =>        88/sec,       562 ticks
-Exponentiating  2049-bit =>        13/sec,      3719 ticks
-
diff --git a/tommath.h b/tommath.h
index 9db1781..eb8a488 100644
--- a/tommath.h
+++ b/tommath.h
@@ -10,7 +10,7 @@
  * The library is free for all purposes without any express
  * guarantee it works.
  *
- * Tom St Denis, tomstdenis@iahu.ca, http://libtommath.iahu.ca
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
  */
 #ifndef BN_H_
 #define BN_H_