[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAN4B417EMF3keYJ9SO2qHxw0dd368jHMHQdiyqb5UFKDB-DvWw@mail.gmail.com>
Date: Tue, 2 Jun 2015 20:48:32 +0200
From: Luis Rocha <luiscrocha@...il.com>
To: john-users@...ts.openwall.com
Subject: Multiple GPU and Fork
Hello List,
I think it might be a basic issue but still could not find the issue.
I am trying to try JtR with 2 GPUs and --fork=2 but due to some reason it
"freezes"
Please see the output below ... if I run JtR just invoking 1 of the GPUs it
works great.
Any ideas?
Thx
Luis
# ./john --list=opencl-devices
Platform #0 name: AMD Accelerated Parallel Processing
Platform version: OpenCL 1.2 AMD-APP (1573.4)
Device #0 (0) name: Hawaii
Board name: AMD Radeon R9 200 Series
Device vendor: Advanced Micro Devices, Inc.
Device type: GPU (LE)
Device version: OpenCL 1.2 AMD-APP (1573.4)
Driver version: 1573.4 (VM) - Catalyst 14.9 (Mantle)
[recommended]
Native vector widths: char 4, short 2, int 1, long 1
Preferred vector width: char 4, short 2, int 1, long 1
Global Memory: 3.0 GB
Global Memory Cache: 16.0 KB
Local Memory: 32.0 KB (Local)
Max memory alloc. size: 2.0 GB
Max clock (MHz): 1040
Profiling timer res.: 1 ns
Max Work Group Size: 256
Parallel compute cores: 44
Stream processors: 2816 (44 x 64)
PCI device topology: 01:00.0
ADL: Overdrive6, device id 0
Fan speed: 20%
Temperature: 70°C
Utilization: 82%
Device #1 (1) name: Pitcairn
Device vendor: Advanced Micro Devices, Inc.
Device type: GPU (LE)
Device version: OpenCL 1.2 AMD-APP (1573.4)
Driver version: 1573.4 (VM) - Catalyst 14.9 (Mantle)
[recommended]
Native vector widths: char 4, short 2, int 1, long 1
Preferred vector width: char 4, short 2, int 1, long 1
Global Memory: 1.0 GB
Global Memory Cache: 16.0 KB
Local Memory: 32.0 KB (Local)
Max memory alloc. size: 1.0 GB
Max clock (MHz): 1100
Profiling timer res.: 1 ns
Max Work Group Size: 256
Parallel compute cores: 20
Stream processors: 1280 (20 x 64)
PCI device topology: 06:00.0
ADL: Overdrive0, device id -1
Device #2 (2) name: Intel(R) Core(TM) i3-4160 CPU @ 3.60GHz
Device vendor: GenuineIntel
Device type: CPU (LE)
Device version: OpenCL 1.2 AMD-APP (1573.4)
Driver version: 1573.4 (sse2,avx)
Native vector widths: char 16, short 8, int 4, long 2
Preferred vector width: char 16, short 8, int 4, long 2
Global Memory: 3.0 GB
Global Memory Cache: 32.0 KB
Local Memory: 32.0 KB (Global)
Max memory alloc. size: 2.0 GB
Max clock (MHz): 3600
Profiling timer res.: 1 ns
Max Work Group Size: 1024
Parallel compute cores: 4
PCI device topology: 00:00.0
# ./john 3-base.md5crypt.pw --format=md5crypt-opencl --dev=0
initUnicode(UNICODE, ASCII/ASCII)
ASCII -> ASCII -> ASCII
Device 0: Hawaii [AMD Radeon R9 200 Series]
Loaded 1726 password hashes with 1726 different salts (md5crypt-opencl,
crypt(3) $1$ [MD5 OpenCL])
Calculating best global worksize (GWS); max. 500ms single kernel invocation.
Raw speed figures including buffer transfers:
pass xfer: 3.852us, crypt: 3.321ms, result xfer: 5.482us
gws: 1024 307459 c/s 307459000 rounds/s 3.330ms per
crypt_all()!
pass xfer: 5.629us, crypt: 3.912ms, result xfer: 4.592us
gws: 2048 522093 c/s 522093000 rounds/s 3.922ms per
crypt_all()+
pass xfer: 9.629us, crypt: 9.084ms, result xfer: 7.556us
gws: 4096 450014 c/s 450014000 rounds/s 9.101ms per
crypt_all()
pass xfer: 17.037us, crypt: 24.863ms, result xfer: 13.482us
gws: 8192 329080 c/s 329080000 rounds/s 24.893ms per
crypt_all()
pass xfer: 32.592us, crypt: 56.462ms, result xfer: 25.926us
gws: 16384 289872 c/s 289872000 rounds/s 56.521ms per
crypt_all()
pass xfer: 63.260us, crypt: 19.288ms, result xfer: 50.074us
gws: 32768 1688904 c/s 1688904000 rounds/s 19.401ms per
crypt_all()!
pass xfer: 124.593us, crypt: 28.311ms, result xfer: 99.556us
gws: 65536 2296655 c/s 2296655000 rounds/s 28.535ms per
crypt_all()+
pass xfer: 247.704us, crypt: 57.554ms, result xfer: 198.074us
gws: 131072 2259833 c/s 2259833000 rounds/s 58ms per
crypt_all()
pass xfer: 496.148us, crypt: 116.169ms, result xfer: 530.074us
gws: 262144 2236799 c/s 2236799000 rounds/s 117.196ms per
crypt_all()
pass xfer: 2.724ms, crypt: 231.913ms, result xfer: 921.037us
gws: 524288 2225711 c/s 2225711000 rounds/s 235.559ms per
crypt_all()
pass xfer: 3.171ms, crypt: 463.897ms, result xfer: 1.669ms
gws: 1048576 2237014 c/s 2237014000 rounds/s 468.738ms per
crypt_all()
pass xfer: 3.953ms, crypt: 1.022s (exceeds 500ms)
Local worksize (LWS) 64, global worksize (GWS) 65536
Press 'q' or Ctrl-C to abort, almost any other key for status
0g 0:00:00:23 41.09% 2/3 (ETA: 20:42:11) 0g/s 0p/s 2080Kc/s 2080KC/s
GPU:84°C util:43% fan:20% 123456..gbby
0g 0:00:00:25 2/3 0g/s 0p/s 2033Kc/s 2033KC/s GPU:83°C fan:20% 123456..gbby
Session aborted
# ./john 3-base.md5crypt.pw --format=md5crypt-opencl --dev=1
initUnicode(UNICODE, ASCII/ASCII)
ASCII -> ASCII -> ASCII
Device 1: Pitcairn
Loaded 1726 password hashes with 1726 different salts (md5crypt-opencl,
crypt(3) $1$ [MD5 OpenCL])
Calculating best global worksize (GWS); max. 500ms single kernel invocation.
Raw speed figures including buffer transfers:
pass xfer: 33.481us, crypt: 8.397ms, result xfer: 14.518us
gws: 1024 121250 c/s 121250000 rounds/s 8.445ms per
crypt_all()!
pass xfer: 31.852us, crypt: 7.656ms, result xfer: 24us
gws: 2048 265565 c/s 265565000 rounds/s 7.711ms per
crypt_all()!
pass xfer: 58.222us, crypt: 4.849ms, result xfer: 41.333us
gws: 4096 827660 c/s 827660000 rounds/s 4.948ms per
crypt_all()!
pass xfer: 124.148us, crypt: 6.809ms, result xfer: 78.518us
gws: 8192 1168332 c/s 1168332000 rounds/s 7.011ms per
crypt_all()+
pass xfer: 217.481us, crypt: 14.812ms, result xfer: 157.037us
gws: 16384 1078841 c/s 1078841000 rounds/s 15.186ms per
crypt_all()
pass xfer: 428us, crypt: 30.948ms, result xfer: 309.482us
gws: 32768 1034145 c/s 1034145000 rounds/s 31.686ms per
crypt_all()
pass xfer: 853.630us, crypt: 62.616ms, result xfer: 614.667us
gws: 65536 1022638 c/s 1022638000 rounds/s 64.085ms per
crypt_all()
pass xfer: 1.698ms, crypt: 126.760ms, result xfer: 1.233ms
gws: 131072 1010639 c/s 1010639000 rounds/s 129.692ms per
crypt_all()
pass xfer: 3.377ms, crypt: 254.863ms, result xfer: 2.463ms
gws: 262144 1005520 c/s 1005520000 rounds/s 260.704ms per
crypt_all()
pass xfer: 6.748ms, crypt: 509.383ms (exceeds 500ms)
Local worksize (LWS) 64, global worksize (GWS) 8192
Press 'q' or Ctrl-C to abort, almost any other key for status
0g 0:00:00:15 10.74% 2/3 (ETA: 20:44:17) 0g/s 521.1p/s 1290Kc/s 1290KC/s
fireballs..faithfaith
0g 0:00:00:17 2/3 0g/s 459.1p/s 1286Kc/s 1286KC/s fireballs..faithfaith
Session aborted
# ./john 3-base.md5crypt.pw --format=md5crypt-opencl --dev=0,1 --fork=2
initUnicode(UNICODE, ASCII/ASCII)
ASCII -> ASCII -> ASCII
Loaded 1726 password hashes with 1726 different salts (md5crypt-opencl,
crypt(3) $1$ [MD5 OpenCL])
Node numbers 1-2 of 2 (fork)
Device id 0 not working correctly, skipping.
Device id 1 not working correctly, skipping.
No OpenCL devices found
Device 0: Hawaii [AMD Radeon R9 200 Series]
Calculating best global worksize (GWS); max. 500ms single kernel invocation.
Raw speed figures including buffer transfers:
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.
