aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Don't allow zero second benchmarkslloyd2008-09-141-1/+1
|
* Increase default benchmark time to 5s... 1.5 seconds (old value) is toolloyd2008-09-141-2/+2
| | | | | low, can be easily thrown off by random background activity, especially on uniprocessor machines
* Enable square optimization for 16x16lloyd2008-09-131-2/+0
|
* Add IETF MODP 8192 DH grouplloyd2008-09-121-0/+47
|
* Padding changes in the PK benchmarks:lloyd2008-09-121-3/+3
| | | | | | RSA: EMSA4(SHA-1) -> EMSA1(SHA-1) RW: EMSA4(SHA-1) -> EMSA2(SHA-1) ELG: Raw -> EME1(SHA-1)
* In the benchmarks, replace Lion(MD5,WiderWake4+1-BE,65536) with1.7.11lloyd2008-09-111-4/+8
| | | | | Lion(SHA-256,Turing,8192) and replace Luby-Rackoff(SHA-1) with Luby-Rackoff(SHA-512)
* List Noekeon and Salsa20 in info.txtlloyd2008-09-111-17/+18
|
* Change readme.txt for 1.7.11 releaselloyd2008-09-111-1/+1
|
* Update log for 1.7.11 releaselloyd2008-09-111-2/+4
|
* Commentlloyd2008-09-111-0/+1
|
* Rewrite guess_cpulloyd2008-09-111-28/+32
|
* Guess the CPU based on {'archname'}, which works for at least Windows/x86 ↵lloyd2008-09-111-14/+24
| | | | and Linux/x86-64 (if /proc/cpuinfo and uname fail)
* Fix loop variable naming (i in outermost scope, then j, remove unneeded k)lloyd2008-09-111-20/+20
|
* Handle configuration of what kind of clock to use for benchmarking.lloyd2008-09-111-4/+39
| | | | | | Linux defaults to clock_gettime, FreeBSD defaults to gettimeofday, everything else defaults to clock (though it is easy to a timer on with -DUSE_<CLOCK_NAME>=1, eg -DUSE_GETTIMEOFDAY=1 or -DUSE_TIMES=1
* Default back to normal cross-version GCC flagslloyd2008-09-111-2/+1
|
* Hijack the <supports_shared> tag in the os configs. It had been forlloyd2008-09-112-2/+6
| | | | | | | the CPU type, however currently every OS has it set to 'all'. And since instead it seems I need to specialize on compiler, I've changed supports_shared to set that, and also changed the Windows config so it only attempts a DLL build with Visual Studio.
* Document some other recent updateslloyd2008-09-111-2/+4
|
* Use getlogin before getpwuid for Windowslloyd2008-09-111-1/+1
|
* Load asm_amd64 only on requestlloyd2008-09-101-1/+1
|
* Add (incomplete) x86-64 mp_mulop variantlloyd2008-09-102-0/+95
|
* Note new 16x16 Comba operationslloyd2008-09-101-0/+1
|
* Increase Karatsuba cutoffs from 12 to 32 wordslloyd2008-09-091-2/+2
|
* Add 16x16->32 word Comba multiply and squarelloyd2008-09-093-176/+719
|
* Hoist load, since compiler may not be able to do so due to aliasinglloyd2008-09-091-4/+7
|
* Undef macros at end of headerslloyd2008-09-092-1/+11
|
* Add comment about bigint_simple_sqr just being an optimization to work ↵lloyd2008-09-091-1/+6
| | | | around lack of restricted pointers
* Use individual variables intead of an array inside the Salsa20 function,lloyd2008-09-091-37/+65
| | | | shows a 35% speedup on my Core2 with G++ vs previous version.
* Add implementation of Salsa20 stream cipherlloyd2008-09-096-0/+503
|
* In get_cipher, do not call cipher->set_iv unless the IV is non-emptylloyd2008-09-091-1/+4
|
* Fix --bench-typelloyd2008-09-091-10/+17
|
* Add a little more detail to RSA example. Reword some intro text.lloyd2008-09-081-29/+39
|
* Add --test to OptionParser listlloyd2008-09-081-1/+1
|
* Last checkin would crash, because the destructor for the rng would notlloyd2008-09-081-60/+55
| | | | | | | | run until after the block ended, which was after set_global_state(0) had run, causing crashes in the destructors that attempted to free memory. Restructure the argument handling, it is significantly easier to understand now. Only create the rng where it is needed.
* Run test_types every time prior to initialization, instead of just duringlloyd2008-09-081-58/+66
| | | | | | | the test suite. Instead of exiting, just carry on; the full test suite will check if the problem is real or if std::numeric_limits is just wonky.
* New (GCC-generated) code for bigint_monty_redc)lloyd2008-09-081-110/+252
|
* Update release noteslloyd2008-09-071-0/+3
|
* Make text easier to understandlloyd2008-09-071-2/+5
|
* Add the username and hostname to build.hlloyd2008-09-072-4/+7
|
* Bump to 1.7.11 (pre)lloyd2008-09-073-2/+4
|
* Reindentlloyd2008-09-071-172/+172
|
* Disable extensive testing during benchmark key generation: throws off profilerlloyd2008-09-071-0/+3
|
* Comment fixlloyd2008-09-071-1/+1
|
* Do not enable by defaultlloyd2008-09-071-1/+1
|
* asm_amd64/lloyd2008-09-074-15/+227
| | | | Check in current state of the x86-64 assembly
* Reduce how often DSA and DH keys are generated during benchmarkslloyd2008-09-071-2/+2
|
* Disable mp_mulop.S until updatedlloyd2008-09-071-3/+3
|
* Disable mp_mulop.S until updatedlloyd2008-09-071-2/+2
|
* Remove bigint_mul_add_words. It was only used now in two callers,lloyd2008-09-073-33/+45
| | | | | | | bigint_simple_mul and bigint_simple_sqr. Examining these functions made it clear inlining would be beneficial, so these two functions have been moved from an anonymous namespace into mp_mulop.cpp (to allow assembly versions).
* Fix call to asmlloyd2008-09-071-1/+1
|
* Rename alg_amd64 to asm_amd64lloyd2008-09-076-8/+117
| | | | | | Namespace exposed SHA-1 function with botan_ prefix. Add start of mp_monty for x86-64 assembly
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-23 22:32:40 +0000