[<prev] [next>] [day] [month] [year] [list]
Date: Tue, 14 Jul 2015 01:52:02 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Agnieszka's weekly report #11
accomplishments:
-I added yescrypt on CPU
-added yescrypt on GPU and I made some optimizations(my first dumb
version had speed 140c/s and now it's 200 for GWS=256).
-revised printed SIMD type for phc finalist and I corrected them, I
think it's correct now but it will be better if somebody checked
-I modified pomelo to use *_region
I didn't do GPU benchmarks because I realized that I have 2 lacks
priorities:
- split kernel in pomelo
- split kernel in yescrypt
- ROM for yescrypt
- I will try to optimze yescrypt on GPU more
- auto tune lws number of previously implemented phc finalists
- lyra2 modify how it uses memory ->
http://www.openwall.com/lists/john-dev/2015/07/13/20
- and then benchamrks and I will document result
- http://www.openwall.com/lists/john-dev/2015/04/17/18 exploiting TMTO
so far my results for yescrypt:
none@...e ~/Desktop/job/run $ ./john --test --format=yescrypt
Will run 8 OpenMP threads
Benchmarking: yescrypt [Salsa20/8 AVX]... (8xOMP) DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 8, cost 3 (p) of 11, cost
4 (t) of 0, cost 5 (g) of 0
Many salts: 2106 c/s real, 278 c/s virtual
Only one salt: 2360 c/s real, 299 c/s virtual
none@...e ~/Desktop/job/run $ GWS=512 ./john --test --format=yescrypt-opencl
Benchmarking: yescrypt-opencl [Salsa20/8 OpenCL (inefficient,
development use only)]... Device 0: GeForce GTX 960M
Local worksize (LWS) 64, global worksize (GWS) 512
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 8, cost 3 (p) of 11, cost
4 (t) of 0, cost 5 (g) of 0
Many salts: 253 c/s real, 254 c/s virtual
Only one salt: 253 c/s real, 252 c/s virtual
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
