- 03 8月, 1999 12 次提交
-
-
由 Bodo Möller 提交于
-
由 Ben Laurie 提交于
-
由 Ben Laurie 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
(because now SSL_new makes a copy).
-
- 01 8月, 1999 3 次提交
-
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Andy Polyakov 提交于
the remainder left in %edx. Here is the resulting performance improvement matrix (improvement as a result of this *and* previous tune-up committed two days ago). The results were obtained by profiling the "div" part of the crypto/bn/bnspeed.c. CPU BN_div bn_div_words overall comment ------------------------------------------------------------------------ PII +16% accumulated by +2-3% PII multiplies damn fast! Taking inlining multiplication out of the loop didn't make too much difference. Eliminating of the multiplication involved in remainder calculation is the major factor. Pentium +45% accumulated by +7-9% mull isn't that fast and replacing inlining multiplications with additions in the loop has more visible effect:-) MIPS +75% +12% +20-25% In addition to the taking mults R10000 out of the loop (giving 12% in the asm/mips3.s) three mults were eliminated in BN_div. Alpha +30% +50% +10-15% Same as above. But remember that EV4 bn_div_words is a C implementation. It takes 4 Alpha mults in C to do the same thing as 1 MIPS mult in assembler does. So the effect (50%) is more impressive. But not the overall one... Well, if Alpha bn_mul_add would be implemented in assembler overall improvement would be closer to MIPS...
-
- 31 7月, 1999 1 次提交
-
-
由 Bodo Möller 提交于
-
- 30 7月, 1999 7 次提交
-
-
由 Andy Polyakov 提交于
loop body and replace 'em with addition/subtraction.
-
由 Bodo Möller 提交于
-
由 Dr. Stephen Henson 提交于
for encrypted data, rather than hard coding '8'.
-
由 Dr. Stephen Henson 提交于
recipient.
-
由 Dr. Stephen Henson 提交于
-
由 Ulf Möller 提交于
-
由 Ulf Möller 提交于
to Kerberos.
-
- 29 7月, 1999 5 次提交
-
-
由 Ulf Möller 提交于
-
由 Ulf Möller 提交于
Configure didn't generate the file in Windows builds).
-
由 Bodo Möller 提交于
Using different files caused problems because the dependencies in the Makefiles produced by mk1mf.pl were for the standard case, i.e. mentioned buildinf.h and not mk1mfinf.h.
-
由 Ulf Möller 提交于
definitions such as C_Block earlier).
-
由 Ulf Möller 提交于
Submitted by: Richard Levitte <levitte@stacken.kth.se>
-
- 28 7月, 1999 2 次提交
-
-
由 Dr. Stephen Henson 提交于
-
由 Dr. Stephen Henson 提交于
-
- 27 7月, 1999 3 次提交
-
-
由 Andy Polyakov 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
- 26 7月, 1999 5 次提交
-
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Bodo Möller 提交于
-
由 Andy Polyakov 提交于
./config sences whole range of SPARC instruction sets. Do note that it favors Sun C now if both gcc and cc 4.2 or later are present!
-
由 Andy Polyakov 提交于
-
- 25 7月, 1999 2 次提交
-
-
由 Andy Polyakov 提交于
-
由 Andy Polyakov 提交于
-