hashcat Forum

Here are some benchmarks from my cards running in 3way SLI mode.

System is
Case: Corsair Carbide Series Air 540 High Airflow ATX Cube Case CC-9011030-WW - Black
MB: Gigabyte X99 UD4
CPU: Intel i7 5820k 6 core cpu, 28 pcie lanes
CPU Cooler: Corsair Hydro Series Extreme Performance Liquid CPU Cooler H100i 26,27 Celsius idle
RAM: 8gb x2 Crucial 16GB Kit (8GBx2) DDR4 2133 MT/s (PC4-17000) CL15 SR x8 Unbuffered DIMM 288-Pin Desktop Memory CT2K4G4DFS8213
Power: EVGA Supernova 1200 P2 Power Supply 80PLUS Platinum Certified 1200W ATX Power Supply with ATX12V 1200 220-P2-1200-X1
SSD : Samsung XP941 256GB M.2 PCIe SSD
Video: Currently 3x EVGA GTX SC 970 Gaming in SLI, fans set to 100% idle temps 28 and 29 Celsius
Fan Controller Kingwin FPX-001 4-Channel Fan Controller
Fans: Front intake fans 2 of AeroCool Fan Cooling for PC, DS 120mm (Blue) + 1x Cooler Master JetFlo 120 - POM Bearing 120mm Red LED High Performance Silent Fan
Fans: Exhaust AeroCool Shark 140m White Cooling Fan EN55512
Lighting Kit: NZXT CB-LED20-RD 2-Metres Light Sensitivity Sleeved LED Kit (Red)

OS: Windows 8.1 x 64, I had 7 but I get better performance in windows 8 honestly.
Headphone: Logitech G930 for night time and 2 bose standard speakers


cudaHashcat v1.31 starting in benchmark-mode...

Device #1: GeForce GTX 970, 4096MB, 1279Mhz, 13MCU
Device #2: GeForce GTX 970, 4096MB, 1279Mhz, 13MCU
Device #3: GeForce GTX 970, 4096MB, 1279Mhz, 13MCU

Hashtype: MD4
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 16396.2 MH/s
Speed.GPU.#2.: 16792.9 MH/s
Speed.GPU.#3.: 16796.3 MH/s
Speed.GPU.#*.: 49985.4 MH/s

Hashtype: MD5
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 9097.2 MH/s
Speed.GPU.#2.: 9172.6 MH/s
Speed.GPU.#3.: 9176.3 MH/s
Speed.GPU.#*.: 27446.1 MH/s

Hashtype: SHA1
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 3238.6 MH/s
Speed.GPU.#2.: 3240.1 MH/s
Speed.GPU.#3.: 3238.8 MH/s
Speed.GPU.#*.: 9717.5 MH/s

Hashtype: SHA256
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 1115.6 MH/s
Speed.GPU.#2.: 1119.5 MH/s
Speed.GPU.#3.: 1185.9 MH/s
Speed.GPU.#*.: 3421.0 MH/s

Hashtype: SHA512
Workload: 256 loops, 256 accel

Speed.GPU.#1.: 215.9 MH/s
Speed.GPU.#2.: 266.0 MH/s
Speed.GPU.#3.: 266.1 MH/s
Speed.GPU.#*.: 748.0 MH/s

Hashtype: SHA-3(Keccak)
Workload: 128 loops, 32 accel

Speed.GPU.#1.: 279.2 MH/s
Speed.GPU.#2.: 288.7 MH/s
Speed.GPU.#3.: 288.0 MH/s
Speed.GPU.#*.: 856.0 MH/s

Hashtype: RipeMD160
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 1877.1 MH/s
Speed.GPU.#2.: 2011.6 MH/s
Speed.GPU.#3.: 2012.8 MH/s
Speed.GPU.#*.: 5901.5 MH/s

Hashtype: Whirlpool
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 86510.4 kH/s
Speed.GPU.#2.: 138.5 MH/s
Speed.GPU.#3.: 173.2 MH/s
Speed.GPU.#*.: 398.2 MH/s

Hashtype: GOST R 34.11-94
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 37631.3 kH/s
Speed.GPU.#2.: 75471.4 kH/s
Speed.GPU.#3.: 75520.7 kH/s
Speed.GPU.#*.: 188.6 MH/s

Hashtype: SAP CODVN B (BCODE)
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 683.3 MH/s
Speed.GPU.#2.: 758.2 MH/s
Speed.GPU.#3.: 758.7 MH/s
Speed.GPU.#*.: 2200.1 MH/s

Hashtype: SAP CODVN F/G (PASSCODE)
Workload: 1024 loops, 32 accel

Speed.GPU.#1.: 372.8 MH/s
Speed.GPU.#2.: 397.3 MH/s
Speed.GPU.#3.: 397.3 MH/s
Speed.GPU.#*.: 1167.4 MH/s

Hashtype: Lotus Notes/Domino 5
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 92033.6 kH/s
Speed.GPU.#2.: 103.8 MH/s
Speed.GPU.#3.: 103.8 MH/s
Speed.GPU.#*.: 299.6 MH/s

Hashtype: Lotus Notes/Domino 6
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 22649.7 kH/s
Speed.GPU.#2.: 30885.4 kH/s
Speed.GPU.#3.: 30901.5 kH/s
Speed.GPU.#*.: 84436.5 kH/s

Hashtype: Lotus Notes/Domino 8
Workload: 5000 loops, 64 accel

Speed.GPU.#1.: 270.3 kH/s
Speed.GPU.#2.: 271.5 kH/s
Speed.GPU.#3.: 271.5 kH/s
Speed.GPU.#*.: 813.3 kH/s

Hashtype: SHA-1(Base64), nsldap, Netscape LDAP SHA
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 2990.0 MH/s
Speed.GPU.#2.: 3341.0 MH/s
Speed.GPU.#3.: 3341.0 MH/s
Speed.GPU.#*.: 9671.9 MH/s

Hashtype: SSHA-1(Base64), nsldaps, Netscape LDAP SSHA
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 2971.0 MH/s
Speed.GPU.#2.: 3342.4 MH/s
Speed.GPU.#3.: 3342.4 MH/s
Speed.GPU.#*.: 9655.8 MH/s

Hashtype: descrypt, DES(Unix), Traditional DES
Workload: 128 loops, 256 accel

Speed.GPU.#1.: 66013.8 kH/s
Speed.GPU.#2.: 82973.9 kH/s
Speed.GPU.#3.: 91524.2 kH/s
Speed.GPU.#*.: 240.5 MH/s

Hashtype: md5crypt, MD5(Unix), FreeBSD MD5, Cisco-IOS MD5
Workload: 1000 loops, 32 accel

Speed.GPU.#1.: 4325.3 kH/s
Speed.GPU.#2.: 4253.9 kH/s
Speed.GPU.#3.: 4393.7 kH/s
Speed.GPU.#*.: 12972.9 kH/s

Hashtype: sha256crypt, SHA256(Unix)
Workload: 5000 loops, 4 accel

Speed.GPU.#1.: 185.0 kH/s
Speed.GPU.#2.: 191.3 kH/s
Speed.GPU.#3.: 196.0 kH/s
Speed.GPU.#*.: 572.4 kH/s

Hashtype: sha512crypt, SHA512(Unix)
Workload: 5000 loops, 8 accel

Speed.GPU.#1.: 34804 H/s
Speed.GPU.#2.: 39342 H/s
Speed.GPU.#3.: 41386 H/s
Speed.GPU.#*.: 115.5 kH/s

Hashtype: bcrypt, Blowfish(OpenBSD)
Workload: 32 loops, 2 accel

Speed.GPU.#1.: 5949 H/s
Speed.GPU.#2.: 6100 H/s
Speed.GPU.#3.: 6102 H/s
Speed.GPU.#*.: 18151 H/s

Hashtype: LM
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 1248.8 MH/s
Speed.GPU.#2.: 1390.0 MH/s
Speed.GPU.#3.: 1390.8 MH/s
Speed.GPU.#*.: 4029.6 MH/s

Hashtype: Oracle 11g/12c
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 2900.3 MH/s
Speed.GPU.#2.: 3340.8 MH/s
Speed.GPU.#3.: 3340.8 MH/s
Speed.GPU.#*.: 9581.9 MH/s

Hashtype: NTLM
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 16418.9 MH/s
Speed.GPU.#2.: 16943.5 MH/s
Speed.GPU.#3.: 16943.3 MH/s
Speed.GPU.#*.: 50305.8 MH/s

Hashtype: DCC, mscash
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 4425.5 MH/s
Speed.GPU.#2.: 4686.3 MH/s
Speed.GPU.#3.: 4703.2 MH/s
Speed.GPU.#*.: 13815.1 MH/s

Hashtype: NetNTLMv1-VANILLA / NetNTLMv1+ESS
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 4120.8 MH/s
Speed.GPU.#2.: 4383.6 MH/s
Speed.GPU.#3.: 4383.3 MH/s
Speed.GPU.#*.: 12887.7 MH/s

Hashtype: NetNTLMv2
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 286.9 MH/s
Speed.GPU.#2.: 359.6 MH/s
Speed.GPU.#3.: 431.8 MH/s
Speed.GPU.#*.: 1078.3 MH/s

Hashtype: Kerberos 5 AS-REQ Pre-Auth etype 23
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 87905.4 kH/s
Speed.GPU.#2.: 91076.4 kH/s
Speed.GPU.#3.: 91098.1 kH/s
Speed.GPU.#*.: 270.1 MH/s

Hashtype: EPiServer 6.x < v4
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 1090.4 MH/s
Speed.GPU.#2.: 1639.5 MH/s
Speed.GPU.#3.: 1644.2 MH/s
Speed.GPU.#*.: 4374.1 MH/s

Hashtype: EPiServer 6.x > v4
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 1051.2 MH/s
Speed.GPU.#2.: 1183.2 MH/s
Speed.GPU.#3.: 1183.3 MH/s
Speed.GPU.#*.: 3417.7 MH/s

Hashtype: MSSQL(2000)
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 3059.0 MH/s
Speed.GPU.#2.: 3347.0 MH/s
Speed.GPU.#3.: 3347.2 MH/s
Speed.GPU.#*.: 9753.3 MH/s

Hashtype: MSSQL(2005)
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 3154.0 MH/s
Speed.GPU.#2.: 3343.7 MH/s
Speed.GPU.#3.: 3343.8 MH/s
Speed.GPU.#*.: 9841.5 MH/s

Hashtype: MSSQL(2012)
Workload: 256 loops, 256 accel

Speed.GPU.#1.: 235.1 MH/s
Speed.GPU.#2.: 268.9 MH/s
Speed.GPU.#3.: 269.1 MH/s
Speed.GPU.#*.: 773.1 MH/s

Hashtype: MySQL323
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 22219.5 MH/s
Speed.GPU.#2.: 22527.8 MH/s
Speed.GPU.#3.: 22525.1 MH/s
Speed.GPU.#*.: 67272.3 MH/s

Jolly good speeds!
Since the cards have a boost clock, at which core clocks were they running when you benchmarked them?
Were they 1.317GHz, 1.165Ghz or something in-between ?

I bumped them up a little, I also have a thread going on another forum for Gaming benchmarks but I use this as a VM machine and security/gaming


https://linustechtips.com/main/topic/2273...tyle-info/

Just popped back both MSI's and they are like 20c cooler on load



cudaHashcat v1.31 starting in benchmark-mode...

Device #1: GeForce GTX 970, 4096MB, 1253Mhz, 13MCU
Device #2: GeForce GTX 970, 4096MB, 1253Mhz, 13MCU

Hashtype: MD4
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 17231.3 MH/s
Speed.GPU.#2.: 17383.7 MH/s
Speed.GPU.#*.: 34615.0 MH/s

Hashtype: MD5
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 9455.2 MH/s
Speed.GPU.#2.: 9422.6 MH/s
Speed.GPU.#*.: 18877.8 MH/s

Hashtype: SHA1
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 3318.8 MH/s
Speed.GPU.#2.: 3318.8 MH/s
Speed.GPU.#*.: 6637.5 MH/s

Hashtype: SHA256
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 1264.5 MH/s
Speed.GPU.#2.: 1266.4 MH/s
Speed.GPU.#*.: 2530.9 MH/s

Hashtype: SHA512
Workload: 256 loops, 256 accel

Speed.GPU.#1.: 265.2 MH/s
Speed.GPU.#2.: 266.2 MH/s
Speed.GPU.#*.: 531.4 MH/s

Hashtype: SHA-3(Keccak)
Workload: 128 loops, 32 accel

Speed.GPU.#1.: 301.1 MH/s
Speed.GPU.#2.: 302.6 MH/s
Speed.GPU.#*.: 603.6 MH/s

Hashtype: RipeMD160
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 2044.2 MH/s
Speed.GPU.#2.: 2047.4 MH/s
Speed.GPU.#*.: 4091.6 MH/s

Hashtype: Whirlpool
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 172.0 MH/s
Speed.GPU.#2.: 172.2 MH/s
Speed.GPU.#*.: 344.2 MH/s

Hashtype: GOST R 34.11-94
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 74311.5 kH/s
Speed.GPU.#2.: 74641.2 kH/s
Speed.GPU.#*.: 149.0 MH/s

Hashtype: SAP CODVN B (BCODE)
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 743.2 MH/s
Speed.GPU.#2.: 746.7 MH/s
Speed.GPU.#*.: 1489.9 MH/s

Hashtype: SAP CODVN F/G (PASSCODE)
Workload: 1024 loops, 32 accel

Speed.GPU.#1.: 403.8 MH/s
Speed.GPU.#2.: 403.8 MH/s
Speed.GPU.#*.: 807.6 MH/s

Hashtype: Lotus Notes/Domino 5
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 103.4 MH/s
Speed.GPU.#2.: 103.4 MH/s
Speed.GPU.#*.: 206.8 MH/s

Hashtype: Lotus Notes/Domino 6
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 30686.2 kH/s
Speed.GPU.#2.: 30691.0 kH/s
Speed.GPU.#*.: 61377.2 kH/s

Hashtype: Lotus Notes/Domino 8
Workload: 5000 loops, 64 accel

Speed.GPU.#1.: 277.4 kH/s
Speed.GPU.#2.: 277.1 kH/s
Speed.GPU.#*.: 554.5 kH/s

Hashtype: SHA-1(Base64), nsldap, Netscape LDAP SHA
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 3304.0 MH/s
Speed.GPU.#2.: 3307.7 MH/s
Speed.GPU.#*.: 6611.8 MH/s

Hashtype: SSHA-1(Base64), nsldaps, Netscape LDAP SSHA
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 3305.9 MH/s
Speed.GPU.#2.: 3305.9 MH/s
Speed.GPU.#*.: 6611.8 MH/s

Hashtype: descrypt, DES(Unix), Traditional DES
Workload: 128 loops, 256 accel

Speed.GPU.#1.: 91185.4 kH/s
Speed.GPU.#2.: 91325.5 kH/s
Speed.GPU.#*.: 182.5 MH/s

Hashtype: md5crypt, MD5(Unix), FreeBSD MD5, Cisco-IOS MD5
Workload: 1000 loops, 32 accel

Speed.GPU.#1.: 4452.8 kH/s
Speed.GPU.#2.: 4451.3 kH/s
Speed.GPU.#*.: 8904.1 kH/s

Hashtype: sha256crypt, SHA256(Unix)
Workload: 5000 loops, 4 accel

Speed.GPU.#1.: 195.4 kH/s
Speed.GPU.#2.: 196.0 kH/s
Speed.GPU.#*.: 391.4 kH/s

Hashtype: sha512crypt, SHA512(Unix)
Workload: 5000 loops, 8 accel

Speed.GPU.#1.: 40338 H/s
Speed.GPU.#2.: 40343 H/s
Speed.GPU.#*.: 80680 H/s

Hashtype: bcrypt, Blowfish(OpenBSD)
Workload: 32 loops, 2 accel

Speed.GPU.#1.: 6139 H/s
Speed.GPU.#2.: 6031 H/s
Speed.GPU.#*.: 12170 H/s

Hashtype: LM
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 1383.3 MH/s
Speed.GPU.#2.: 1388.3 MH/s
Speed.GPU.#*.: 2771.6 MH/s

Hashtype: Oracle 11g/12c
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 3318.1 MH/s
Speed.GPU.#2.: 3314.4 MH/s
Speed.GPU.#*.: 6632.5 MH/s

Hashtype: NTLM
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 16945.1 MH/s
Speed.GPU.#2.: 17175.2 MH/s
Speed.GPU.#*.: 34120.3 MH/s

Hashtype: DCC, mscash
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 4680.4 MH/s
Speed.GPU.#2.: 4684.5 MH/s
Speed.GPU.#*.: 9364.9 MH/s

Hashtype: NetNTLMv1-VANILLA / NetNTLMv1+ESS
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 4363.3 MH/s
Speed.GPU.#2.: 4371.6 MH/s
Speed.GPU.#*.: 8734.9 MH/s

Hashtype: NetNTLMv2
Workload: 1024 loops, 256 accel

Speed.GPU.#1.: 427.4 MH/s
Speed.GPU.#2.: 429.1 MH/s
Speed.GPU.#*.: 856.4 MH/s

Hashtype: Kerberos 5 AS-REQ Pre-Auth etype 23
Workload: 256 loops, 32 accel

Speed.GPU.#1.: 90119.0 kH/s
Speed.GPU.#2.: 90644.7 kH/s
Speed.GPU.#*.: 180.8 MH/s

Hashtype: EPiServer 6.x < v4
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 1598.9 MH/s
Speed.GPU.#2.: 1609.9 MH/s
Speed.GPU.#*.: 3208.8 MH/s

Hashtype: EPiServer 6.x > v4
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 1180.2 MH/s
Speed.GPU.#2.: 1178.9 MH/s
Speed.GPU.#*.: 2359.1 MH/s

Hashtype: MSSQL(2000)
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 3320.6 MH/s
Speed.GPU.#2.: 3319.8 MH/s
Speed.GPU.#*.: 6640.4 MH/s

Hashtype: MSSQL(2005)
Workload: 512 loops, 256 accel

Speed.GPU.#1.: 3324.1 MH/s
Speed.GPU.#2.: 3323.9 MH/s
Speed.GPU.#*.: 6648.0 MH/s

Still, looking at performance only, it's still possible to build whole system for one GTX970 price to get performance of two of them (hashcracking, also excluding some 64 bit algos ).

For future searchers, note that SLI is not necessary for hashcat - and adds overhead that actually impacts performance. Instead, allow hashcat to handle the multiple GPUs directly.

https://hashcat.net/wiki/doku.php?id=fre...ia_bridges