8dddba4f6e
Work around ORCA/C bug that affects lower optimization levels.
2017-07-05 12:24:37 -05:00
4c0265d921
Work around ORCA/C bug.
2017-07-05 11:44:22 -05:00
5b7c832600
One more tweak to MD5 rotate optimizations.
2017-07-04 14:42:01 -05:00
2f34f006ba
Force MD5 tables to be page-aligned, which should save a cycle in some cases.
2017-07-04 14:37:17 -05:00
e90af7c1a4
Small optimization to eliminate some unnecessary loads in MD5.
2017-07-04 14:31:04 -05:00
129f371902
Add zero bytes to optimize some rotates in MD5.
2017-07-04 14:17:51 -05:00
1d1d5251f6
Optimize the operations used for various shift sizes in MD5.
2017-07-04 13:57:01 -05:00
748e0b5c24
Small optimizations for MD5.
2017-07-04 12:39:11 -05:00
0f144df99b
Add implementation of MD5 hash function.
2017-07-04 12:15:00 -05:00
015ae8559f
Add makefile entries for SHA-256 programs.
2017-07-03 23:58:57 -05:00
1f3d51a5c9
Add sha256sum program.
2017-07-03 23:56:36 -05:00
e7aa261e19
Add update and finalize functions for SHA-256.
2017-07-03 23:53:43 -05:00
458e769212
Add initialization function to permit computation of SHA-224 hashes.
...
SHA-224 uses the exact same computation as SHA-256, just with different initial values.
2017-07-03 23:40:36 -05:00
11148c78d1
Remove unused macros.
2017-07-03 23:05:51 -05:00
bcc0efc327
Add zero bytes around SHA-256 state variables to optimize rotates.
2017-07-03 22:58:58 -05:00
239024c3ce
Remove unneeded instruction.
2017-07-03 20:46:26 -05:00
7034be04fb
Use more efficient approach for addressing into k array in SHA-256 computation.
2017-07-03 20:41:53 -05:00
f0f034760b
Optimize SHA-256 computations to save instructions in various places.
2017-07-03 20:03:45 -05:00
d2bf9a782e
Use shifts when called for, rather than more expensive rotates.
2017-07-03 17:12:13 -05:00
011628d3ce
More rotate optimizations for SHA-256.
2017-07-03 15:50:20 -05:00
6891b77fbc
Additional small rotate optimizations in SHA-256.
2017-07-03 15:30:46 -05:00
6940f1fef4
Use operations on bytes to rotate by multiples of 8 in SHA-256.
2017-07-03 15:15:18 -05:00
64fc1e62bb
Do some optimization of the rotates in SHA-256.
2017-07-03 14:46:46 -05:00
61bc8f8b4f
Reduce duplicated code in SHA-256 implementation.
2017-07-03 14:33:17 -05:00
91c107eb98
Add initial implementation of the basic block-processing function for SHA-256.
2017-07-03 14:27:19 -05:00
2c34d17925
Typos
2017-07-02 22:54:18 -05:00
58a3945d53
Add basic makefile.
2017-07-02 20:26:20 -05:00
a04d36eb6c
Add copyright notices and comments.
2017-07-02 18:41:21 -05:00
cfadee23bb
Add implementation and test for AES CTR mode.
2017-07-02 18:25:43 -05:00
924789510b
Optimize AES CBC operations a bit.
2017-07-02 16:24:00 -05:00
6532a3abc4
Add timing tests for AES CBC encryption and decryption.
2017-07-02 15:56:22 -05:00
c8b0fb904b
Add .gitignore file.
2017-07-02 15:29:51 -05:00
4e0903a708
Add simple toy program for encrypting/decrypting files with AES.
2017-07-02 15:24:49 -05:00
60a7aec49c
Add functions for AES CBC mode encryption and decryption.
2017-07-01 23:29:17 -05:00
0386f928ff
Add comments and copyright notices, and rename chunk to block.
2017-07-01 17:53:49 -05:00
b2d3d3ffa8
Add sha1sum program as a test/application of the SHA-1 computation.
2017-07-01 15:11:13 -05:00
0ad5d39f07
Tweaks to SHA-1 update and finalization code.
2017-07-01 14:27:25 -05:00
8b17a15ada
Add implementations of the SHA-1 update and finalize operations.
...
The definition of the context structure is also cleaned up a bit.
2017-06-30 23:55:03 -05:00
3aa0d1b89f
Update SHA-1 test program.
2017-06-30 13:35:33 -05:00
97fc1ce981
Small cleanups in SHA-1.
2017-06-30 13:23:29 -05:00
6c1d703b84
Don't duplicate identical code for the last three schedule computation phases.
...
This shrinks code size and is probably faster with accelerators due to caching.
2017-06-30 12:49:51 -05:00
d97e0c0153
Don't update index value in each unrolled loop iteration.
2017-06-30 00:52:25 -05:00
2d8c85bd98
Unroll SHA-1 loop with variables substituted to avoid cycling values around.
...
SHA-1 has five state variables (a,b,c,d,e), and each iteration of the core loop cycles their values around (e.g. a->b), in some cases with modifications. By unrolling the loop by a factor of five and appropriately substituting the values operated on in each iteration, we can avoid actually doing the copies implied by this cycling, which gives a fairly significant performance gain.
2017-06-30 00:33:16 -05:00
aab47e38e7
Compute SHA-1 message schedule 20 elements at a time, reusing storage.
...
The reduces the storage needed and boosts performance, since the whole schedule is contained in the direct page.
2017-06-29 22:22:06 -05:00
7182fc5817
Use separate loops for the four parts of the SHA-1 computation.
2017-06-29 20:51:36 -05:00
dfdb3186fd
Add macros for rotates.
2017-06-29 20:41:49 -05:00
ad4e0a0dd5
More SHA-1 optimizations.
2017-06-29 20:16:22 -05:00
13654c0888
Small optimizations in SHA-1 computation.
2017-06-29 19:52:52 -05:00
a519776847
Add implementation of the basic block-processing function for SHA-1.
2017-06-29 16:54:49 -05:00
1cb8841a46
state -> context
2017-06-29 16:52:34 -05:00
Stephen Heumann