Nvidia 3060ti Benchmark
#1
OpenCL API (OpenCL 3.0 CUDA 11.3.113) - Platform #1 [NVIDIA Corporation]
========================================================================
* Device #1: NVIDIA GeForce RTX 3060 Ti, 7360/8192 MB (2048 MB allocatable), 38MCU

Benchmark relevant options:
===========================
* --optimized-kernel-enable

Hashmode: 0 - MD5

Speed.#1.........: 33671.6 MH/s (75.64ms) @ Accel:64 Loops:1024 Thr:1024 Vec:8

Hashmode: 100 - SHA1

Speed.#1.........: 10585.2 MH/s (60.13ms) @ Accel:16 Loops:1024 Thr:1024 Vec:1

Hashmode: 1400 - SHA2-256

Speed.#1.........:  4525.3 MH/s (70.35ms) @ Accel:8 Loops:1024 Thr:1024 Vec:1

Hashmode: 1700 - SHA2-512

Speed.#1.........:  1339.9 MH/s (59.38ms) @ Accel:32 Loops:64 Thr:1024 Vec:1

Hashmode: 22000 - WPA-PBKDF2-PMKID+EAPOL (Iterations: 4095)

Speed.#1.........:  526.8 kH/s (73.67ms) @ Accel:8 Loops:512 Thr:1024 Vec:1

Hashmode: 1000 - NTLM

Speed.#1.........: 60355.6 MH/s (42.16ms) @ Accel:64 Loops:1024 Thr:1024 Vec:8

Hashmode: 3000 - LM

Speed.#1.........: 31777.2 MH/s (80.10ms) @ Accel:1024 Loops:1024 Thr:64 Vec:1

Hashmode: 5500 - NetNTLMv1 / NetNTLMv1+ESS

Speed.#1.........: 31880.2 MH/s (79.89ms) @ Accel:64 Loops:1024 Thr:1024 Vec:2

Hashmode: 5600 - NetNTLMv2

Speed.#1.........:  2355.5 MH/s (67.57ms) @ Accel:32 Loops:128 Thr:1024 Vec:1

Hashmode: 1500 - descrypt, DES (Unix), Traditional DES

Speed.#1.........:  1283.7 MH/s (61.94ms) @ Accel:32 Loops:1024 Thr:64 Vec:1

Hashmode: 500 - md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5) (Iterations: 1000)

Speed.#1.........: 14898.9 kH/s (81.25ms) @ Accel:64 Loops:500 Thr:1024 Vec:1

Hashmode: 3200 - bcrypt $2*$, Blowfish (Unix) (Iterations: 32)

Speed.#1.........:    43820 H/s (37.18ms) @ Accel:8 Loops:16 Thr:11 Vec:1

Hashmode: 1800 - sha512crypt $6$, SHA512 (Unix) (Iterations: 5000)

Speed.#1.........:  230.4 kH/s (67.14ms) @ Accel:8 Loops:256 Thr:1024 Vec:1

Hashmode: 7500 - Kerberos 5, etype 23, AS-REQ Pre-Auth

Speed.#1.........:  710.3 MH/s (56.00ms) @ Accel:256 Loops:128 Thr:32 Vec:1

Hashmode: 13100 - Kerberos 5, etype 23, TGS-REP

Speed.#1.........:  703.4 MH/s (56.55ms) @ Accel:256 Loops:128 Thr:32 Vec:1

Hashmode: 15300 - DPAPI masterkey file v1 (Iterations: 23999)

Speed.#1.........:    89767 H/s (73.65ms) @ Accel:8 Loops:512 Thr:1024 Vec:1

Hashmode: 15900 - DPAPI masterkey file v2 (Iterations: 12899)

Speed.#1.........:    51615 H/s (59.00ms) @ Accel:4 Loops:256 Thr:1024 Vec:1

Hashmode: 7100 - macOS v10.8+ (PBKDF2-SHA512) (Iterations: 1023)

Speed.#1.........:  641.3 kH/s (40.10ms) @ Accel:2 Loops:511 Thr:1024 Vec:1

Hashmode: 11600 - 7-Zip (Iterations: 16384)

Speed.#1.........:  553.8 kH/s (68.47ms) @ Accel:4 Loops:4096 Thr:1024 Vec:1

Hashmode: 12500 - RAR3-hp (Iterations: 262144)

Speed.#1.........:    71211 H/s (68.18ms) @ Accel:16 Loops:16384 Thr:128 Vec:1

Hashmode: 13000 - RAR5 (Iterations: 32799)

Speed.#1.........:    57234 H/s (84.83ms) @ Accel:8 Loops:512 Thr:1024 Vec:1

Hashmode: 6211 - TrueCrypt RIPEMD160 + XTS 512 bit (Iterations: 1999)

Speed.#1.........:  403.2 kH/s (88.97ms) @ Accel:4 Loops:512 Thr:1024 Vec:1

Hashmode: 13400 - KeePass 1 (AES/Twofish) and KeePass 2 (AES) (Iterations: 24569)

Speed.#1.........:    67008 H/s (96.70ms) @ Accel:4 Loops:1024 Thr:1024 Vec:1

Hashmode: 6800 - LastPass + LastPass sniffed (Iterations: 499)

Speed.#1.........:  3709.1 kH/s (82.04ms) @ Accel:8 Loops:499 Thr:1024 Vec:1

Hashmode: 11300 - Bitcoin/Litecoin wallet.dat (Iterations: 200459)

Speed.#1.........:    6938 H/s (57.25ms) @ Accel:8 Loops:256 Thr:1024 Vec:1

Started: Thu Jul 01 20:57:39 2021
Stopped: Thu Jul 01 21:01:05 2021
Reply
#2
Hashcat v6.2.2 on windows 10.
Reply
#3
If possible try to find the ideal -n value for -m 8900, then print it here please. This card has a good potential for scrypt base cracking not because of total speed but from price/speed ratio (after it felt back to regular price).
Reply
#4
Hello

I am trully disappointed with the RTX 3060 Ti
I did not run benchmarks tests on the GPU but for comparison here is a current run of GTX 1080 Ti (-m22000 / )
WPA-PBKDF2-PMKID+EAPOL)

Speed.#3.........:  645.3 kH/s (346.62ms) @ Accel:32 Loops:1024 Thr:1024 Vec:1

NVIDIA-SMI 460.73.01
CUDA Version: 11.2

PL 180W / no OC
Reply
#5
(07-01-2021, 09:19 PM)atom Wrote: If possible try to find the ideal -n value for -m 8900, then print it here please. This card has a good potential for scrypt base cracking not because of total speed but from price/speed ratio (after it felt back to regular price).

Never used the -n ( --kernel-accel) parameter, could you give me some details about how to use it?
Reply
#6
This is more a development fine tuning thing. Just run -b -m 8900 --force -n 1 and then increase the 1 up to 39 and find the best spot. Probably 14, 28 or 39.
Reply
#7
Are there any tests of 3070/3080 Ti's?
Reply
#8
hashcat.exe -b -m 8900 --force -n 38 OpenCL API (OpenCL 3.0 CUDA 11.3.113) - Platform #1 [NVIDIA Corporation] ======================================================================== * Device #1: NVIDIA GeForce RTX 3060 Ti, 7360/8192 MB (2048 MB allocatable), 38MCU Benchmark relevant options: =========================== * --force * --optimized-kernel-enable * --kernel-accel=38 Hashmode: 8900 - scrypt (Iterations: 16384) Speed.#1.........: 1274 H/s (42.65ms) @ Accel:38 Loops:1024 Thr:32 Vec:1 Started: Sat Jul 03 08:39:22 2021 Stopped: Sat Jul 03 08:39:24 2021
Reply
#9
(07-02-2021, 09:44 PM)atom Wrote: This is more a development fine tuning thing. Just run -b -m 8900 --force -n 1 and then increase the 1 up to 39 and find the best spot. Probably 14, 28 or 39.

-n 28 & 38 retunrned the top values for -m 8900
Reply
#10
Thanks. Scrypt 1274 H/s is pretty good for 16k:8:1
Reply