GET EXCITED! 1.2 rel vs 1.31 rc2
#1
Howdy folks.

Here's a benchmark of cudahc v1.2 'release' versus cudahc v1.31 'rc2' on GTX Titan @ 1.045 GHz.
Due to a discovery made by Jens, which resulted in an optimization for both NV and AMD GPUs, many algos got a decent boost in speed.

Top boosted algos:
SHA256(crypt) (+224%)
MD5(crypt) (+176%)
HMAC-SHA512 (+177%)
HMAC-SHA256 (+110%)
EPiS >4 (+109%)
DNSSEC (+106%)
DES(crypt) (+105%)

A bunch of algos lost a decent amount of speed (HMAC-SHA1 lost 84%, but Jens told me this may be a bug), full info below.

Code:
W:\cudaHashcat-1.31-rc2\cudaHashcat-1.31>                 W:\cudaHashcat-1.20\cudaHashcat-1.20>                          
Device #1: GeForce GTX TITAN, 6144MB, 928Mhz, 14MCU       Device #1: GeForce GTX TITAN, 6144MB, 928Mhz, 14MCU
                                                          
Hashtype: MD5                                             Hashtype: MD5
Speed.GPU.#1.:  7304.0 MH/s                               Speed.GPU.#1.:  4900.1 MH/s                     delta: +49.05%
                                                          
Hashtype: SHA1                                            Hashtype: SHA1
Speed.GPU.#1.:  1747.6 MH/s                               Speed.GPU.#1.:  2220.8 MH/s                     delta: -21.30%
                                                          
Hashtype: SHA256                                          Hashtype: SHA256
Speed.GPU.#1.:   619.7 MH/s                               Speed.GPU.#1.:   379.1 MH/s                     delta: +63.46%
                                                          
Hashtype: SHA512                                          Hashtype: SHA512
Speed.GPU.#1.:   147.4 MH/s                               Speed.GPU.#1.: 80356.7 kH/s                     delta: +83.43%
                                                          
Hashtype: SHA-3(Keccak)                                   Hashtype: SHA-3(Keccak)
Speed.GPU.#1.:   219.9 MH/s                               Speed.GPU.#1.:   118.2 MH/s                     delta: +86.04%
                                                          
Hashtype: SAP CODVN B (BCODE)                             Hashtype: SAP CODVN B (BCODE)
Speed.GPU.#1.:   376.4 MH/s                               Speed.GPU.#1.:   308.9 MH/s                     delta: +21.85
                                                          
Hashtype: SHA-1(Base64), nsldap, Netscape LDAP SHA                
Speed.GPU.#1.:  1747.9 MH/s                               Speed.GPU.#1.:  2220.5 MH/s                     delta: -21.28
                                                          
Hashtype: SSHA-1(Base64), nsldaps, Netscape LDAP SSHA         
Speed.GPU.#1.:  1744.2 MH/s                               Speed.GPU.#1.:  1505.0 MH/s                     delta: +15.89
                                                          
Hashtype: descrypt, DES(Unix), Traditional DES            
Speed.GPU.#1.: 72239.6 kH/s                               Speed.GPU.#1.: 35149.3 kH/s                     delta: +105.52%
                                                          
Hashtype: md5crypt, MD5(Unix), FreeBSD MD5, Cisco-IOS MD5
Speed.GPU.#1.:  3202.3 kH/s                               Speed.GPU.#1.:  1157.3 kH/s                     delta: +176.70%
                                                          
Hashtype: sha256crypt, SHA256(Unix)                       Hashtype: sha256crypt, SHA256(Unix)
Speed.GPU.#1.:    71855 H/s                               Speed.GPU.#1.:    22174 H/s                     delta: +224.05%
                                                          
Hashtype: sha512crypt, SHA512(Unix)                       Hashtype: sha512crypt, SHA512(Unix)
Speed.GPU.#1.:    26750 H/s                               Speed.GPU.#1.:    10831 H/s                     delta: +146.97%
                                                          
Hashtype: bcrypt, Blowfish(OpenBSD)                       Hashtype: bcrypt, Blowfish(OpenBSD)
Speed.GPU.#1.:      896 H/s                               Speed.GPU.#1.:      957 H/s                     delta: -6.3%
                                                          
Hashtype: LM                                              Hashtype: LM
Speed.GPU.#1.:   839.9 MH/s                               Speed.GPU.#1.:   566.8 MH/s                     delta: +48.18%
                                                          
Hashtype: NTLM                                            Hashtype: NTLM
Speed.GPU.#1.: 12373.9 MH/s                               Speed.GPU.#1.: 11014.3 MH/s                     delta: +12.34%
                                                          
Hashtype: DCC, mscash                                     Hashtype: DCC, mscash
Speed.GPU.#1.:  3362.0 MH/s                               Speed.GPU.#1.:  2790.7 MH/s                     delta: +20.47%
                                                               
Hashtype: NetNTLMv1-VANILLA / NetNTLMv1+ESS              
Speed.GPU.#1.:  3334.8 MH/s                               Speed.GPU.#1.:  2520.6 MH/s                     delta: +32.30%
                                                          
Hashtype: NetNTLMv2                                       Hashtype: NetNTLMv2
Speed.GPU.#1.:   284.9 MH/s                               Speed.GPU.#1.:   322.9 MH/s                     delta: -11.76%
                                                          
Hashtype: EPiServer 6.x < v4                              Hashtype: EPiServer 6.x < v4
Speed.GPU.#1.:   643.8 MH/s                               Speed.GPU.#1.:  1758.6 MH/s                     delta: -63.39%
                                                          
Hashtype: EPiServer 6.x > v4                              Hashtype: EPiServer 6.x > v4
Speed.GPU.#1.:   591.3 MH/s                               Speed.GPU.#1.:   282.3 MH/s                     delta: +109.45%
                                                          
Hashtype: MSSQL(2000)                                     Hashtype: MSSQL(2000)
Speed.GPU.#1.:  1755.8 MH/s                               Speed.GPU.#1.:  1496.2 MH/s                     delta: +17.35%
                                                          
Hashtype: MSSQL(2005)                                     Hashtype: MSSQL(2005)
Speed.GPU.#1.:  1755.6 MH/s                               Speed.GPU.#1.:  1497.5 MH/s                     delta: +17.23%
                                                          
Hashtype: MSSQL(2012)                                     Hashtype: MSSQL(2012)
Speed.GPU.#1.:   149.6 MH/s                               Speed.GPU.#1.: 80277.4 kH/s                     delta: +86.35%
                                                          
Hashtype: MySQL323                                        Hashtype: MySQL323
Speed.GPU.#1.: 18473.9 MH/s                               Speed.GPU.#1.:  9653.0 MH/s                     delta: +91.37%
                                                          
Hashtype: Oracle 7-10g                                    Hashtype: Oracle 7-10g
Speed.GPU.#1.:   174.0 MH/s                               Speed.GPU.#1.:   110.6 MH/s                     delta: +57.32%
                                                          
Hashtype: Sybase ASE                                      Hashtype: Sybase ASE
Speed.GPU.#1.: 47525.3 kH/s                               Speed.GPU.#1.: 36255.9 kH/s                     delta: +31.08%
                                                          
Hashtype: OSX v10.4, v10.5, v10.6                         Hashtype: OSX v10.4, v10.5, v10.6
Speed.GPU.#1.:   643.4 MH/s                               Speed.GPU.#1.:  1750.7 MH/s                     delta: -63.24%
                                                          
Hashtype: OSX v10.7                                       Hashtype: OSX v10.7
Speed.GPU.#1.:   148.0 MH/s                               Speed.GPU.#1.: 75087.2 kH/s                      delta: +97.10%
                                                          
Hashtype: OSX v10.8 / v10.9                               Hashtype: OSX v10.8 / v10.9
Speed.GPU.#1.:     1874 H/s                               Speed.GPU.#1.:     1060 H/s                      delta: +76.79%
                                                          
Hashtype: Cisco-PIX MD5                                   Hashtype: Cisco-PIX MD5
Speed.GPU.#1.:  5049.2 MH/s                               Speed.GPU.#1.:  4231.9 MH/s                      delta: +19.31%
                                                          
Hashtype: Cisco-ASA MD5                                   Hashtype: Cisco-ASA MD5
Speed.GPU.#1.:  5042.5 MH/s                               Speed.GPU.#1.:  4217.7 MH/s                      delta: +19.55%
                                                          
Hashtype: Cisco-IOS SHA256                                Hashtype: Cisco-IOS SHA256
Speed.GPU.#1.:   619.7 MH/s                               Speed.GPU.#1.:   380.3 MH/s                      delta: +62.95%
                                                          
Hashtype: DNSSEC (NSEC3)                                  Hashtype: DNSSEC (NSEC3)
Speed.GPU.#1.:   810.3 MH/s                               Speed.GPU.#1.:   393.0 MH/s                      delta: +106.1%
                                                          
Hashtype: WPA/WPA2                                        Hashtype: WPA/WPA2
Speed.GPU.#1.:    99550 H/s                               Speed.GPU.#1.:   112.0 kH/s                      delta: -11.11%
                                                          
Hashtype: IKE-PSK MD5                                     Hashtype: IKE-PSK MD5
Speed.GPU.#1.:   159.0 MH/s                               Speed.GPU.#1.:   349.3 MH/s                      delta: -54.48%
                                                          
Hashtype: 1Password, cloudkeychain                        Hashtype: 1Password, cloudkeychain
Speed.GPU.#1.:     1637 H/s                               Speed.GPU.#1.:      928 H/s                      delta: +76.4%
                                                          
Hashtype: TrueCrypt 5.0+ PBKDF2-HMAC-SHA512 + AES        
Speed.GPU.#1.:    64397 H/s                               Speed.GPU.#1.:    36654 H/s                      delta: +75.68%
                                                          
Hashtype: Drupal7                                         Hashtype: Drupal7
Speed.GPU.#1.:     8983 H/s                               Speed.GPU.#1.:     4569 H/s                      delta: +96.6%
                                                          
Hashtype: HMAC-MD5 (key = $pass)                          Hashtype: HMAC-MD5 (key = $pass)
Speed.GPU.#1.:   344.2 MH/s                               Speed.GPU.#1.:   610.3 MH/s                      delta: -43.6%
                                                          
Hashtype: HMAC-MD5 (key = $salt)                          Hashtype: HMAC-MD5 (key = $salt)
Speed.GPU.#1.:  1704.7 MH/s                               Speed.GPU.#1.:  1154.2 MH/s                      delta: +47.69%
                                                          
Hashtype: HMAC-SHA1 (key = $pass)                         Hashtype: HMAC-SHA1 (key = $pass)
Speed.GPU.#1.: 75191.3 kH/s                               Speed.GPU.#1.:   177.8 MH/s                      delta: -57.71%
                                                          
Hashtype: HMAC-SHA1 (key = $salt)                         Hashtype: HMAC-SHA1 (key = $salt)
Speed.GPU.#1.:   139.0 MH/s                               Speed.GPU.#1.:   872.9 MH/s                      delta: -84.07%
                                                          
Hashtype: HMAC-SHA256 (key = $pass)                       Hashtype: HMAC-SHA256 (key = $pass)
Speed.GPU.#1.:   129.2 MH/s                               Speed.GPU.#1.: 61299.1 kH/s                      delta: +110.76%
                                                          
Hashtype: HMAC-SHA256 (key = $salt)                       Hashtype: HMAC-SHA256 (key = $salt)
Speed.GPU.#1.:   267.6 MH/s                               Speed.GPU.#1.:   144.3 MH/s                      delta: +85.44%
                                                          
Hashtype: HMAC-SHA512 (key = $pass)                       Hashtype: HMAC-SHA512 (key = $pass)
Speed.GPU.#1.: 29651.9 kH/s                               Speed.GPU.#1.: 10671.4 kH/s                      delta: +177.86%
                                                          
Hashtype: HMAC-SHA512 (key = $salt)                       Hashtype: HMAC-SHA512 (key = $salt)
Speed.GPU.#1.: 58030.8 kH/s                               Speed.GPU.#1.: 37228.9 kH/s                      delta: +55.87%
                                                          
Hashtype: IPMI2 RAKP HMAC-SHA1                            Hashtype: IPMI2 RAKP HMAC-SHA1
Speed.GPU.#1.:   424.6 MH/s                               Speed.GPU.#1.:   814.9 MH/s                      delta: -47.89%
                                                          
Hashtype: Double MD5                                      Hashtype: Double MD5
Speed.GPU.#1.:   885.4 MH/s                               Speed.GPU.#1.:  1367.0 MH/s                      delta: -35.23%
                                                          
Hashtype: GRUB 2                                          Hashtype: GRUB 2
Speed.GPU.#1.:     6553 H/s                               Speed.GPU.#1.:     3704 H/s                      delta: +76.91%
                                                          
Hashtype: phpass, MD5(Wordpress), MD5(phpBB3), MD5(Joomla)
Speed.GPU.#1.:  2033.0 kH/s                               Speed.GPU.#1.:  1430.0 kH/s                      delta: +42.16%
                                                          
Hashtype: Joomla < 2.5.18                                 Hashtype: Joomla < 2.5.18
Speed.GPU.#1.:  7285.8 MH/s                               Speed.GPU.#1.:  5144.8 MH/s                      delta: +41.61%
                                                          
Hashtype: osCommerce, xt:Commerce                         Hashtype: osCommerce, xt:Commerce
Speed.GPU.#1.:  3983.9 MH/s                               Speed.GPU.#1.:  2768.8 MH/s                      delta: +43.88
                                                          
Hashtype: IPB2+, MyBB1.2+                                 Hashtype: IPB2+, MyBB1.2+
Speed.GPU.#1.:   468.7 MH/s                               Speed.GPU.#1.:   929.3 MH/s                      delta: -49.56%
                                                          
Hashtype: vBulletin < v3.8.5                              Hashtype: vBulletin < v3.8.5
Speed.GPU.#1.:   886.3 MH/s                               Speed.GPU.#1.:  1367.3 MH/s                      delta: -35.17%
                                                          
Hashtype: vBulletin > v3.8.5                              Hashtype: vBulletin > v3.8.5
Speed.GPU.#1.:   448.7 MH/s                               Speed.GPU.#1.:   900.9 MH/s                      delta: -50.19%
                                                          
Hashtype: SMF > v1.1                                      Hashtype: SMF > v1.1
Speed.GPU.#1.:   645.5 MH/s                               Speed.GPU.#1.:  1752.0 MH/s                      delta: -63.15%
#2
Thanks Rolf for the comparison, good work!

For all others, keep in mind that those changes only reflect the change for GTX TITAN. Previous TITAN support wasn't perfect (as you can see).

There's of course performance increase for other NV cards as well, but they look very different.
#3
Can Maxwell, potentially, be tested using frankenstein kernels on 1.2?
I'm very interested in SM_52's results, because GTX 980 is now faster than vanilla Titan.
#4
That will not work (or at least very unfair) because of the newly added instructions that make Maxwell that fast. I'm sure CUDA runtime will complain