Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 28 Sep 2014 21:25:21 -0800
From: Royce Williams <royce@...ho.org>
To: john-dev <john-dev@...ts.openwall.com>
Subject: Re: NVIDIA GTX 970 (Maxwell 2 / GM204) opencl benchmarks

On Sun, Sep 28, 2014 at 8:44 PM, Royce Williams <royce@...ho.org> wrote:
> Sayantan said that GTX 970 benchmarks might be useful for john-dev, so
> here are opencl-specific benchmarks for the EVGA model 04G-P4-0972-KR,
> non-overclocked.  I wrote a quick wrapper to only run --test for the
> the *-opencl formats; I can post full results or other results if
> needed.

Sorry - CUDA wasn't working.  Here are results for both -opencl and
-cuda formats.

Royce

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 8192
Benchmarking: 7z-opencl, 7-Zip [SHA256 AES OPENCL]... DONE
Raw:	1113 c/s real, 1113 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: agilekeychain-opencl, 1Password Agile Keychain [PBKDF2-SHA1 OpenCL AES]... DONE
Raw:	684356 c/s real, 691200 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 8, Global worksize (GWS) 1024
Benchmarking: bcrypt-opencl ("$2a$05", 32 iterations) [Blowfish OpenCL]... DONE
Raw:	4830 c/s real, 4830 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 368640
Benchmarking: blockchain-opencl, blockchain My Wallet [PBKDF2-SHA1 OpenCL AES]... DONE
Raw:	1293K c/s real, 1293K c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 16384
Benchmarking: descrypt-opencl, traditional crypt(3) [DES OpenCL]... DONE
Many salts:	36855K c/s real, 37224K c/s virtual
Only one salt:	25165K c/s real, 24916K c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: dmg-opencl, Apple DMG [PBKDF2-SHA1 OpenCL 3DES/AES]... DONE
Raw:	21942 c/s real, 22074 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 16384
Benchmarking: encfs-opencl, EncFS [PBKDF2-SHA1 OpenCL AES/Blowfish]... DONE
Raw:	2250 c/s real, 2281 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 8192
Benchmarking: gpg-opencl, OpenPGP / GnuPG Secret Key [SHA1 OpenCL]... DONE
Raw:	238601 c/s real, 238601 c/s virtual

Device 0: GeForce GTX 970
Benchmarking: GRUB-opencl [PBKDF2-SHA512 OpenCL]... DONE
Raw:	5152 c/s real, 5152 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: keychain-opencl, Mac OS X Keychain [PBKDF2-SHA1 OpenCL 3DES]... DONE
Raw:	209869 c/s real, 230400 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 8192
Benchmarking: keyring-opencl, GNOME Keyring [SHA256 OpenCL AES]... FAILED (cmp_all(1))

Device 0: GeForce GTX 970
Local worksize (LWS) 32, Global worksize (GWS) 8388608
Benchmarking: krb5pa-md5-opencl, Kerberos 5 AS-REQ Pre-Auth etype 23 [MD4 HMAC-MD5 RC4 OpenCL]... DONE
Many salts:	15679K c/s real, 15679K c/s virtual
Only one salt:	13210K c/s real, 13107K c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 1024, Global worksize (GWS) 1048576
Benchmarking: krb5pa-sha1-opencl, Kerberos 5 AS-REQ Pre-Auth etype 17/18 [PBKDF2-SHA1 OpenCL]... DONE
Raw:	107106 c/s real, 107106 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 256, Global worksize (GWS) 1048576
Benchmarking: lotus5-opencl, Lotus Notes/Domino 5 [OpenCL]... DONE
Raw:	16448K c/s real, 16448K c/s virtual

Benchmarking: md5crypt-cuda, crypt(3) $1$ [MD5 CUDA]... DONE
Raw:	375798 c/s real, 390981 c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 1024, Global worksize (GWS) 8192
Benchmarking: md5crypt-opencl, crypt(3) $1$ [MD5 OpenCL]... DONE
Raw:	1974K c/s real, 1994K c/s virtual

Benchmarking: mscash2-cuda, MS Cache Hash 2 (DCC2) [PBKDF2-SHA1 CUDA]... DONE
Raw:	7859 c/s real, 7859 c/s virtual

Device 0: GeForce GTX 970
Optimal Work Group Size:1024
Kernel Execution Speed (Higher is better):1.828947
Optimal Global Work Size:303104
Benchmarking: mscash2-opencl, MS Cache Hash 2 (DCC2) [PBKDF2-SHA1 OpenCL]... DONE
Raw:	115688 c/s real, 115248 c/s virtual

Benchmarking: mscash-cuda, MS Cache Hash (DCC) [MD4 CUDA (inefficient, development use only)]... DONE
Many salts:	8752K c/s real, 8752K c/s virtual
Only one salt:	6935K c/s real, 6935K c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 32, Global worksize (GWS) 16775936
Benchmarking: mysql-sha1-opencl, MySQL 4.1+ [SHA1 OpenCL (inefficient, development use only)]... DONE
Raw:	32574K c/s real, 32893K c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 32, Global worksize (GWS) 4194304
Benchmarking: ntlmv2-opencl, NTLMv2 C/R [MD4 HMAC-MD5 OpenCL]... DONE
Many salts:	189154K c/s real, 189154K c/s virtual
Only one salt:	41943K c/s real, 42719K c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 524288
Benchmarking: nt-opencl, NT [MD4 OpenCL (inefficient, development use only)]... DONE
Raw:	20447K c/s real, 20244K c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 32, global worksize (GWS) 262144
Benchmarking: o5logon-opencl, Oracle O5LOGON protocol [SHA1 OpenCL AES 32/64]... DONE
Raw:	2246K c/s real, 2246K c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: ODF-AES-opencl [SHA256 OpenCL AES]... DONE
Raw:	66421 c/s real, 67025 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: ODF-opencl [SHA1 OpenCL Blowfish]... DONE
Raw:	21105 c/s real, 21267 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 262144
Benchmarking: office2007-opencl, MS Office 2007 (50,000 iterations) [SHA1 OpenCL AES]... DONE
Raw:	42904 c/s real, 42974 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
/-Local worksize (LWS) 64, Global worksize (GWS) 131072
Benchmarking: office2010-opencl, MS Office 2010 (100,000 iterations) [SHA1 OpenCL AES]... DONE
Raw:	21881 c/s real, 21918 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
/Local worksize (LWS) 64, Global worksize (GWS) 4096
Benchmarking: office2013-opencl, MS Office 2013 (100,000 iterations) [SHA512 OpenCL AES]... DONE
Raw:	648 c/s real, 648 c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 64, global worksize (GWS) 262144
Benchmarking: PBKDF2-HMAC-SHA1-opencl [PBKDF2-SHA1 OpenCL]... DONE
Raw:	1120K c/s real, 1139K c/s virtual

Device 0: GeForce GTX 970
/-Local worksize (LWS) 128, global worksize (GWS) 262144
Benchmarking: PBKDF2-HMAC-SHA256-opencl [PBKDF2-SHA256 OpenCL]... DONE
Raw:	40454 c/s real, 40516 c/s virtual

Benchmarking: phpass-cuda ($P$9 lengths 0 to 15) [MD5 CUDA]... DONE
Raw:	926162 c/s real, 944872 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 24576
Benchmarking: phpass-opencl ($P$9 lengths 0 to 15) [MD5 OpenCL]... DONE
Raw:	2457K c/s real, 2434K c/s virtual

Benchmarking: pwsafe-cuda, Password Safe [SHA256 CUDA]... DONE
Raw:	153121 c/s real, 151703 c/s virtual

Device 0: GeForce GTX 970
/Local worksize (LWS) 512, global worksize (GWS) 65536
Benchmarking: pwsafe-opencl, Password Safe [SHA256 OpenCL]... DONE
Many salts:	463971 c/s real, 459901 c/s virtual
Only one salt:	454209 c/s real, 454209 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 128, global worksize (GWS) 131072
Benchmarking: RAKP-opencl, IPMI 2.0 RAKP (RMCP+) [HMAC-SHA1 OpenCL]... DONE
Many salts:	61079K c/s real, 61079K c/s virtual
Only one salt:	31326K c/s real, 31326K c/s virtual

Device 0: GeForce GTX 970
/Local worksize (LWS) 128, global worksize (GWS) 8192
Benchmarking: RAR5-opencl [PBKDF2-SHA256 OpenCL]... DONE
Raw:	14499 c/s real, 14499 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
/Local worksize (LWS) 64, global worksize (GWS) 4096
Benchmarking: rar-opencl, RAR3 (length 5) [SHA1 OpenCL AES]... DONE
Raw:	15603 c/s real, 15456 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 32, global worksize (GWS) 262144
Benchmarking: Raw-MD4-opencl [MD4 OpenCL (inefficient, development use only)]... OpenCL error (CL_INVALID_COMMAND_QUEUE) in file (opencl_rawmd4_fmt_plug.c) at line (301) - (failed in reading data back)
Device 0: GeForce GTX 970
Local worksize (LWS) 32, global worksize (GWS) 524288
Benchmarking: Raw-MD5-opencl [MD5 OpenCL (inefficient, development use only)]... OpenCL error (CL_INVALID_COMMAND_QUEUE) in file (opencl_rawmd5_fmt_plug.c) at line (298) - (failed in reading data back)
Device 0: GeForce GTX 970
/Local worksize (LWS) 32, global worksize (GWS) 524288
Benchmarking: Raw-SHA1-opencl [SHA1 OpenCL (inefficient, development use only)]... -OpenCL error (CL_INVALID_COMMAND_QUEUE) in file (opencl_rawsha1_fmt_plug.c) at line (347) - (failed in clFinish)
Benchmarking: Raw-SHA224-cuda [SHA224 CUDA (inefficient, development use mostly)]... DONE
Raw:	20795K c/s real, 20597K c/s virtual

Benchmarking: Raw-SHA256-cuda [SHA256 CUDA (inefficient, development use mostly)]... DONE
Raw:	19466K c/s real, 19859K c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 512, global worksize (GWS) 4194304
Benchmarking: Raw-SHA256-opencl [SHA256 OpenCL (inefficient, development use mostly)]... DONE
Raw:	41120K c/s real, 41120K c/s virtual

Benchmarking: Raw-SHA512-cuda [SHA512 CUDA (inefficient, development use mostly)]... DONE
Raw:	20560K c/s real, 20763K c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 64, global worksize (GWS) 2097152
Benchmarking: Raw-SHA512-opencl [SHA512 OpenCL (inefficient, development use mostly)]... DONE
Raw:	22396K c/s real, 22396K c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 128, global worksize (GWS) 8192
Benchmarking: sha1crypt-opencl, (NetBSD) [PBKDF1-SHA1 OpenCL]... DONE
Raw:	23574 c/s real, 23574 c/s virtual

Benchmarking: sha256crypt-cuda, crypt(3) $5$ (rounds=5000) [SHA256 CUDA]... DONE
Raw:	8885 c/s real, 8960 c/s virtual

Device 0: GeForce GTX 970
/Local worksize (LWS) 128, global worksize (GWS) 32768
Benchmarking: sha256crypt-opencl, crypt(3) $5$ (rounds=5000) [SHA256 OpenCL]... DONE
Raw:	48545 c/s real, 48545 c/s virtual

Benchmarking: sha512crypt-cuda, crypt(3) $6$ (rounds=5000) [SHA512 CUDA]... DONE
Raw:	6023 c/s real, 6023 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 512, global worksize (GWS) 13312
Benchmarking: sha512crypt-opencl, crypt(3) $6$ (rounds=5000) [SHA512 OpenCL]... DONE
Raw:	19433 c/s real, 19433 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 256, Global worksize (GWS) 1048576
Benchmarking: ssha-opencl, Netscape LDAP {SSHA} [SHA1 OpenCL (inefficient, development use mostly)]... DONE
Many salts:	37748K c/s real, 38130K c/s virtual
Only one salt:	27756K c/s real, 27756K c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: strip-opencl, STRIP Password Manager [PBKDF2-SHA1 OpenCL]... DONE
Raw:	125266 c/s real, 124061 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 36864
Benchmarking: sxc-opencl, StarOffice .sxc [PBKDF2-SHA1 OpenCL Blowfish]... DONE
Raw:	21684 c/s real, 22207 c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Benchmarking: wpapsk-cuda, WPA/WPA2 PSK [PBKDF2-SHA1 CUDA]... DONE
Raw:	5535 c/s real, 5535 c/s virtual

Device 0: GeForce GTX 970
Local worksize (LWS) 64, global worksize (GWS) 131072
Benchmarking: wpapsk-opencl, WPA/WPA2 PSK [PBKDF2-SHA1 OpenCL]... DONE
Raw:	138700 c/s real, 139438 c/s virtual

Benchmarking: xsha512-cuda, Mac OS X 10.7+ [SHA512 CUDA (efficient at "many salts" only)]... FAILED (get_hash[0](0))

Device 0: GeForce GTX 970
Local worksize (LWS) 256, global worksize (GWS) 2097152
Benchmarking: XSHA512-opencl, Mac OS X 10.7 salted [SHA512 OpenCL (inefficient, development use mostly)]... DONE
Many salts:	89284K c/s real, 88409K c/s virtual
Only one salt:	31655K c/s real, 31655K c/s virtual

Warning: OpenMP is disabled; a non-OpenMP build may be faster
Device 0: GeForce GTX 970
Local worksize (LWS) 64, Global worksize (GWS) 9216
Benchmarking: zip-opencl, ZIP [PBKDF2-SHA1 OpenCL AES]... DONE
Raw:	361411 c/s real, 364990 c/s virtual

Powered by blists - more mailing lists

Your e-mail address:

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