Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Mon, 27 Jul 2015 09:47:52 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: Lyra2 vs yescrypt benchmarks 2

Lyra2

CPU on well - 3792
GeForce GTX 960M - 629
AMD Tahiti - 2844
GeForce GTX TITAN - 1638
memory: 1.5 MB

yescrypt

CPU on well - 4736
GeForce GTX 960M - 419
AMD Tahiti - 914
GeForce GTX TITAN - 1050
memory: 1.5 MB

output (not everything):

Lyra2 CPU

a@...l:~/m/run$ ./john --test --format=lyra2
Will run 8 OpenMP threads
Benchmarking: Lyra2 [Blake2 AVX]... (8xOMP)
memory per hash : 1.50 MB
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    3792 c/s real, 474 c/s virtual


Lyra2 AMD Tahiti

[a@...er run]$ ./john --test --format=lyra2-opencl --v=4
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         431 c/s         431 rounds/s 592.868ms per crypt_all()!
gws:       512         834 c/s         834 rounds/s 613.804ms per crypt_all()+
gws:      1024        1484 c/s        1484 rounds/s 690.006ms per crypt_all()+
Local worksize (LWS) 64, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    1473 c/s real, 204800 c/s virtual

[a@...er run]$ LWS=32 ./john --test --format=lyra2-opencl --v=4
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         758 c/s         758 rounds/s 337.492ms per crypt_all()!
gws:       512        1471 c/s        1471 rounds/s 348.015ms per crypt_all()+
gws:      1024        2312 c/s        2312 rounds/s 442.737ms per crypt_all()+
Local worksize (LWS) 32, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    2292 c/s real, 307200 c/s virtual

[a@...er run]$ LWS=16 ./john --test --format=lyra2-opencl --v=4
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256        1011 c/s        1011 rounds/s 253.080ms per crypt_all()!
gws:       512        1999 c/s        1999 rounds/s 256.024ms per crypt_all()+
gws:      1024        2708 c/s        2708 rounds/s 378.131ms per crypt_all()+
Local worksize (LWS) 16, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    2648 c/s real, 153600 c/s virtual

[a@...er run]$ LWS=8 ./john --test --format=lyra2-opencl --v=4
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256        1121 c/s        1121 rounds/s 228.188ms per crypt_all()!
gws:       512        2162 c/s        2162 rounds/s 236.790ms per crypt_all()+
gws:      1024        2913 c/s        2913 rounds/s 351.487ms per crypt_all()+
Local worksize (LWS) 8, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    2844 c/s real, 307200 c/s virtual


Lyra2 TITAN

[a@...er run]$ ./john --test --format=lyra2-opencl --v=4 --dev=5
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         275 c/s         275 rounds/s 928.547ms per crypt_all()!
gws:       512         550 c/s         550 rounds/s 929.863ms per crypt_all()+
Local worksize (LWS) 64, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    553 c/s real, 553 c/s virtual


[a@...er run]$ LWS=32 ./john --test --format=lyra2-opencl --v=4 --dev=5
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         275 c/s         275 rounds/s 930.093ms per crypt_all()!
gws:       512         561 c/s         561 rounds/s 911.119ms per crypt_all()!
Local worksize (LWS) 32, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    562 c/s real, 565 c/s virtual

[a@...er run]$ LWS=16 ./john --test --format=lyra2-opencl --v=4 --dev=5
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         476 c/s         476 rounds/s 537.400ms per crypt_all()!
gws:       512         948 c/s         948 rounds/s 539.760ms per crypt_all()+
Local worksize (LWS) 16, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    948 c/s real, 948 c/s virtual

[a@...er run]$ LWS=8 ./john --test --format=lyra2-opencl --v=4 --dev=5
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         722 c/s         722 rounds/s 354.485ms per crypt_all()!
gws:       512        1232 c/s        1232 rounds/s 415.283ms per crypt_all()+
Local worksize (LWS) 8, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    1228 c/s real, 1228 c/s virtual

[a@...er run]$ LWS=4 ./john --test --format=lyra2-opencl --v=4 --dev=5
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         894 c/s         894 rounds/s 286.124ms per crypt_all()!
gws:       512        1629 c/s        1629 rounds/s 314.276ms per crypt_all()+
Local worksize (LWS) 4, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    1638 c/s real, 1625 c/s virtual



Lyra2 960m

none@...e ~/Desktop/rrr/run $ LWS=8 ./john --test
--format=lyra2-opencl --v=4
Benchmarking: Lyra2-opencl [Lyra2 OpenCL]...
memory per hash : 1.50 MB
Device 0: GeForce GTX 960M
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=131090 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=256 -DSALT_SIZE=64
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws:       256         609 c/s         609 rounds/s 420.031ms per crypt_all()!
Local worksize (LWS) 8, global worksize (GWS) 256
using different password for benchmarking
DONE
Speed for cost 1 (t) of 1, cost 2 (m) of 64, cost 3 (c) of 256, cost 4 (p) of 1
Raw:    629 c/s real, 629 c/s virtual




yescrypt CPU

a@...l:~/m/run$ ./john --test --format=yescrypt
Will run 8 OpenMP threads
Benchmarking: yescrypt [pwxform Salsa20/8 AVX]... (8xOMP)
memory per hash : 1.51 MB
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    4736 c/s real, 592 c/s virtual



yescrypt AMD Tahiti

[a@...er run]$ LWS=32 GWS=1024 ./john --test --format=yescrypt-opencl --v=4
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Local worksize (LWS) 32, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    882 c/s real, 102400 c/s virtual

[a@...er run]$ LWS=16 GWS=1024 ./john --test --format=yescrypt-opencl --v=4
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Local worksize (LWS) 16, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    914 c/s real, 102400 c/s virtual

[a@...er run]$ LWS=8 GWS=1024 ./john --test --format=yescrypt-opencl --v=4
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 0: Tahiti [AMD Radeon HD 7900 Series]
Local worksize (LWS) 8, global worksize (GWS) 1024
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    914 c/s real, 102400 c/s virtual


yescrypt TITAN

[a@...er run]$ ./john --test --format=yescrypt-opencl --v=4 --dev=5
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=32 -DSALT_SIZE=64
-DPLAINTEXT_LENGTH=125 -DHASH_SIZE=44 -DKEY_SIZE=125
Calculating best global worksize (GWS); max. 100s total for crypt_all()
gws:       256         231 c/s         231 rounds/s    1.104s per crypt_all()!
gws:       512         470 c/s         470 rounds/s    1.088s per crypt_all()!
gws:      1024         827 c/s         827 rounds/s    1.237s per crypt_all()+
gws:      2048        1016 c/s        1016 rounds/s    2.014s per crypt_all()+
Local worksize (LWS) 64, global worksize (GWS) 2048
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    1013 c/s real, 1013 c/s virtual

[a@...er run]$ LWS=32 ./john --test --format=yescrypt-opencl --v=4 --dev=5
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 5: GeForce GTX TITAN
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=65554 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=32 -DSALT_SIZE=64
-DPLAINTEXT_LENGTH=125 -DHASH_SIZE=44 -DKEY_SIZE=125
Calculating best global worksize (GWS); max. 100s total for crypt_all()
gws:       256         231 c/s         231 rounds/s    1.105s per crypt_all()!
gws:       512         470 c/s         470 rounds/s    1.088s per crypt_all()!
gws:      1024         866 c/s         866 rounds/s    1.181s per crypt_all()+
gws:      2048        1045 c/s        1045 rounds/s    1.958s per crypt_all()+
Local worksize (LWS) 32, global worksize (GWS) 2048
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    1050 c/s real, 1044 c/s virtual



yescrypt 960m

none@...e ~/Desktop/rrr/run $ LWS=16 ./john --test
--format=yescrypt-opencl --v=4
Benchmarking: yescrypt-opencl [pwxform Salsa20/8 OpenCL]...
memory per hash : 1.51 MB
Device 0: GeForce GTX 960M
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose -D__GPU__
-DDEVICE_INFO=131090 -DDEV_VER_MAJOR=352 -DDEV_VER_MINOR=21
-D_OPENCL_COMPILER -DBINARY_SIZE=32 -DSALT_SIZE=64
-DPLAINTEXT_LENGTH=125 -DHASH_SIZE=44 -DKEY_SIZE=125
Calculating best global worksize (GWS); max. 100s total for crypt_all()
gws:       256         353 c/s         353 rounds/s 723.560ms per crypt_all()!
gws:       512         420 c/s         420 rounds/s    1.218s per crypt_all()+
gws:      1024         414 c/s         414 rounds/s    2.469s per crypt_all()
gws:      2048         412 c/s         412 rounds/s    4.965s per crypt_all()
Local worksize (LWS) 16, global worksize (GWS) 512
using different password for benchmarking
DONE
Speed for cost 1 (N) of 2048, cost 2 (r) of 6, cost 3 (p) of 1, cost 4
(t) of 0, cost 5 (g) of 0
Raw:    419 c/s real, 419 c/s virtual

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ