| Commit message (Expand) | Author | Age | Files | Lines |
... | |
* | | | Inline all of the AES tables into an anon namespace in aes.cpp. Turns out | lloyd | 2009-11-11 | 3 | -411/+399 |
* | | | Almost double the speed of MARS; from 55 MiB/s to 102 on my Core2. | lloyd | 2009-11-11 | 3 | -231/+216 |
* | | | Slightly cleaner SHA-256 F1 func; ~1% faster | lloyd | 2009-11-10 | 1 | -3/+3 |
* | | | Use memcpy for bulk loads if algorithm endianness matches CPU endianess. | lloyd | 2009-11-10 | 1 | -0/+9 |
* | | | Remove SSE4 dependency in AES-192 key schedule, and also avoid requiring | lloyd | 2009-11-10 | 2 | -26/+25 |
* | | | Add AES-192 using AES-NI. Tested OK with Intel's simulator. | lloyd | 2009-11-10 | 3 | -9/+276 |
* | | | Also #undef bool after including <altivec.h> | lloyd | 2009-11-10 | 1 | -0/+1 |
* | | | Rename CPUID::has_intel_aes to has_aes_intel, and add CPUID::has_aes_via, | lloyd | 2009-11-10 | 2 | -4/+13 |
* | | | Add unrolled versions of AES-NI code that will handle 4 blocks in parallel. | lloyd | 2009-11-10 | 1 | -12/+176 |
* | | | Fix errors in the AES-256 key schedule for the AES-NI version. Now passes | lloyd | 2009-11-10 | 3 | -197/+170 |
* | | | Add AES-256 using AES-NI | lloyd | 2009-11-10 | 3 | -3/+243 |
* | | | Make the AES implementation using Intel's AES instruction extension official; | lloyd | 2009-11-10 | 2 | -7/+7 |
* | | | Add Nehalem/Westmere tags for ICC | lloyd | 2009-11-10 | 1 | -3/+7 |
* | | | Make set_all_values in {ECDSA,ECKAEG}_{Public,Private}Key all non-virtual; | lloyd | 2009-11-10 | 2 | -6/+6 |
* | | | Cleanups - remove emails from source files, they should only live in | lloyd | 2009-11-10 | 18 | -59/+35 |
* | | | Remove my email address from the copyright headers in the tss files, not | lloyd | 2009-11-10 | 2 | -2/+2 |
* | | | In creating X.509 certificates and PKCS #10 requests, let (actually: require) | lloyd | 2009-11-09 | 4 | -31/+75 |
|/ / |
|
* | | Clean up aes_128_key_expansion | lloyd | 2009-11-06 | 1 | -24/+18 |
* | | GCC doesn't know what Nehalem or Westmere are, though it does know about | lloyd | 2009-11-06 | 1 | -0/+3 |
* | | Dename unused length field | lloyd | 2009-11-06 | 1 | -1/+1 |
* | | Add a new need_isa marker for info.txt that lets a module depend | lloyd | 2009-11-06 | 5 | -20/+11 |
* | | Add a complete but untested AES-128 using the AES-NI intrinsics. | lloyd | 2009-11-06 | 3 | -68/+147 |
* | | Stub for AES class using Intel's AES-NI instructions and an engine for | lloyd | 2009-11-06 | 7 | -0/+238 |
* | | The default_submodel option was used by configure.pl but configure.py | lloyd | 2009-11-06 | 16 | -37/+7 |
* | | The code for handling SIMD ISA extensions actually works fine for general | lloyd | 2009-11-06 | 5 | -15/+21 |
* | | Tick to 1.9.3-dev | lloyd | 2009-11-06 | 3 | -28/+15 |
* | | Generate SIMD macro flags for build.h from data in build-data/arch for | lloyd | 2009-11-06 | 5 | -0/+27 |
|/ |
|
* | Add an andc operation, in SSE2 and AltiVec, may be useful for Serpent sboxes | lloyd | 2009-11-04 | 4 | -4/+22 |
* | Indent and avoid one extra assignment | lloyd | 2009-11-04 | 1 | -3/+2 |
* | propagate from branch 'net.randombit.botan.1_8' (head 6e8c18515725a70923b3411... | lloyd | 2009-11-03 | 500 | -3763/+9419 |
|\ |
|
| * | Conver the rest of the hash functions to use the array-based load instructions. | lloyd | 2009-11-03 | 5 | -40/+41 |
| * | Slight cleanups in the Altivec detection code for readability. | lloyd | 2009-10-29 | 1 | -5/+12 |
| * | Add a new looping load_be / load_le for loading large arrays at once, and | lloyd | 2009-10-29 | 11 | -49/+104 |
| * | Fix cpuid with icc (tested with 11.1) | lloyd | 2009-10-29 | 1 | -2/+2 |
| * | propagate from branch 'net.randombit.botan' (head 4fd7eb9630271d3c1dfed21987e... | lloyd | 2009-10-29 | 28 | -964/+1719 |
| |\ |
|
| | * | Clean up prep00_15 - same speed on Core2 | lloyd | 2009-10-29 | 1 | -16/+10 |
| | * | Clean up the SSE2 SHA-1 code quite a bit, make better use of C++ features | lloyd | 2009-10-29 | 2 | -308/+267 |
| | * | Format for easier reading | lloyd | 2009-10-29 | 1 | -31/+43 |
| | * | Small cleanups (remove tab characters, change macros to fit the rest of | lloyd | 2009-10-29 | 1 | -123/+121 |
| | * | Give each version of SIMD_32 a public bswap() | lloyd | 2009-10-29 | 3 | -11/+29 |
| | * | Add new function enabled() to each of the SIMD_32 instantiations which | lloyd | 2009-10-29 | 3 | -1/+9 |
| | * | No ||= operator! | lloyd | 2009-10-29 | 1 | -7/+7 |
| | * | Add CPUID::have_altivec for AltiVec runtime detection. | lloyd | 2009-10-29 | 2 | -0/+61 |
| | * | Rename sse2 engine to simd | lloyd | 2009-10-29 | 2 | -2/+2 |
| | * | Use register writes in the Altivec code for stores because Altivec's handling | lloyd | 2009-10-29 | 1 | -7/+16 |
| | * | Kill realnames on new modules not in mailine | lloyd | 2009-10-29 | 3 | -5/+0 |
| | * | propagate from branch 'net.randombit.botan' (head 54d2cc7b00ecd5f41295e147d23... | lloyd | 2009-10-29 | 22 | -621/+1322 |
| | |\ |
|
| | | * | propagate from branch 'net.randombit.botan' (head 8fb69dd1c599ada1008c4cab2a6... | lloyd | 2009-10-29 | 22 | -621/+1322 |
| | | |\ |
|
| | | | * | Rename SSE2 stuff to be generally SIMD since it supports at least SSE2 | lloyd | 2009-10-29 | 16 | -135/+126 |
| | | | * | Add copyright + license on the new SIMD files | lloyd | 2009-10-28 | 4 | -2/+14 |