OpenCL vs CUDA +[Benchmark] Nvidia Quadro P4000 (Leadtek) , GT730 2GB (HP) & i3-4130
#1
Test machine
Ubuntu 20.04 , i3-4130, 8GB RAM
Cuda 11.4 and OpenCL 3.0

Code:
hashcat (v6.2.5) starting in benchmark mode

Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.

Unsupported AMD HIP runtime version '4.2' detected! Falling back to OpenCL...

* Device #3: This hardware has outdated CUDA compute capability (3.5).
            For modern OpenCL performance, upgrade to hardware that supports
            CUDA compute capability version 5.0 (Maxwell) or higher.
CUDA API (CUDA 11.4)
====================
* Device #1: NVIDIA GeForce GTX 1660 SUPER, 5877/5944 MB, 22MCU
* Device #2: Quadro P4000, 8038/8119 MB, 14MCU
* Device #3: NVIDIA GeForce GT 730, 1982/2002 MB, 2MCU

OpenCL API (OpenCL 3.0 PoCL 3.0-rc2  Linux, RelWithDebInfo, RELOC, SPIR, LLVM 10.0.0, SLEEF, POCL_DEBUG) - Platform #1 [The pocl project]
=========================================================================================================================================
* Device #4: pthread-Intel(R) Core(TM) i3-4130 CPU @ 3.40GHz, 2847/5758 MB (1024 MB allocatable), 4MCU

OpenCL API (OpenCL 2.0 AMD-APP (3314.0)) - Platform #2 [Advanced Micro Devices, Inc.]
=====================================================================================

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

-------------------
* Hash-Mode 0 (MD5)
-------------------

Speed.#1.........: 17269.3 MH/s (83.39ms) @ Accel:256 Loops:512 Thr:512 Vec:1
Speed.#2.........: 13818.9 MH/s (66.92ms) @ Accel:256 Loops:256 Thr:1024 Vec:1
Speed.#3.........:  895.2 MH/s (73.53ms) @ Accel:256 Loops:1024 Thr:128 Vec:2
Speed.#4.........:  276.1 MH/s (7.45ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........: 32259.6 MH/s

----------------------
* Hash-Mode 100 (SHA1)
----------------------

Speed.#1.........:  5928.4 MH/s (61.41ms) @ Accel:256 Loops:256 Thr:256 Vec:1
Speed.#2.........:  5469.6 MH/s (84.95ms) @ Accel:256 Loops:256 Thr:512 Vec:1
Speed.#3.........:  253.2 MH/s (65.19ms) @ Accel:128 Loops:1024 Thr:64 Vec:1
Speed.#4.........:  119.0 MH/s (16.71ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........: 11770.3 MH/s

---------------------------
* Hash-Mode 1400 (SHA2-256)
---------------------------

Speed.#1.........:  2588.3 MH/s (70.98ms) @ Accel:16 Loops:512 Thr:1024 Vec:1
Speed.#2.........:  2041.4 MH/s (57.31ms) @ Accel:32 Loops:256 Thr:1024 Vec:1
Speed.#3.........:  111.8 MH/s (73.91ms) @ Accel:8 Loops:512 Thr:1024 Vec:1
Speed.#4.........: 53338.8 kH/s (39.19ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  4794.8 MH/s

---------------------------
* Hash-Mode 1700 (SHA2-512)
---------------------------

Speed.#1.........:  862.3 MH/s (53.37ms) @ Accel:8 Loops:1024 Thr:256 Vec:1
Speed.#2.........:  658.0 MH/s (44.54ms) @ Accel:16 Loops:512 Thr:256 Vec:1
Speed.#3.........: 26638.0 kH/s (77.74ms) @ Accel:32 Loops:1024 Thr:32 Vec:1
Speed.#4.........: 15595.7 kH/s (67.14ms) @ Accel:256 Loops:1024 Thr:1 Vec:4
Speed.#*.........:  1562.6 MH/s

-------------------------------------------------------------
* Hash-Mode 22000 (WPA-PBKDF2-PMKID+EAPOL) [Iterations: 4095]
-------------------------------------------------------------

Speed.#1.........:  292.3 kH/s (74.24ms) @ Accel:16 Loops:512 Thr:512 Vec:1
Speed.#2.........:  285.1 kH/s (49.73ms) @ Accel:8 Loops:1024 Thr:512 Vec:1
Speed.#3.........:    12276 H/s (77.54ms) @ Accel:16 Loops:512 Thr:256 Vec:1
Speed.#4.........:    6038 H/s (83.33ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  595.8 kH/s

-----------------------
* Hash-Mode 1000 (NTLM)
-----------------------

Speed.#1.........: 31637.2 MH/s (90.61ms) @ Accel:128 Loops:1024 Thr:1024 Vec:1
Speed.#2.........: 23516.7 MH/s (78.22ms) @ Accel:256 Loops:512 Thr:1024 Vec:1
Speed.#3.........:  1413.4 MH/s (89.57ms) @ Accel:4096 Loops:256 Thr:64 Vec:4
Speed.#4.........:  402.1 MH/s (5.11ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........: 56969.4 MH/s

---------------------
* Hash-Mode 3000 (LM)
---------------------

Speed.#1.........: 17398.3 MH/s (41.93ms) @ Accel:1024 Loops:1024 Thr:32 Vec:1
Speed.#2.........: 14020.7 MH/s (66.65ms) @ Accel:1024 Loops:1024 Thr:64 Vec:1
Speed.#3.........:  489.6 MH/s (67.32ms) @ Accel:128 Loops:1024 Thr:128 Vec:1
Speed.#4.........: 52062.7 kH/s (39.17ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........: 31960.7 MH/s

--------------------------------------------
* Hash-Mode 5500 (NetNTLMv1 / NetNTLMv1+ESS)
--------------------------------------------

Speed.#1.........: 18163.7 MH/s (78.98ms) @ Accel:512 Loops:512 Thr:256 Vec:1
Speed.#2.........: 14033.8 MH/s (66.18ms) @ Accel:128 Loops:512 Thr:1024 Vec:1
Speed.#3.........:  916.7 MH/s (71.30ms) @ Accel:512 Loops:512 Thr:128 Vec:4
Speed.#4.........:  291.4 MH/s (7.09ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........: 33405.7 MH/s

----------------------------
* Hash-Mode 5600 (NetNTLMv2)
----------------------------

Speed.#1.........:  1336.4 MH/s (67.89ms) @ Accel:256 Loops:64 Thr:256 Vec:1
Speed.#2.........:  1054.6 MH/s (55.39ms) @ Accel:128 Loops:64 Thr:512 Vec:1
Speed.#3.........: 44933.0 kH/s (92.15ms) @ Accel:4 Loops:1024 Thr:512 Vec:2
Speed.#4.........: 21484.4 kH/s (48.70ms) @ Accel:512 Loops:512 Thr:1 Vec:8
Speed.#*.........:  2457.4 MH/s

--------------------------------------------------------
* Hash-Mode 1500 (descrypt, DES (Unix), Traditional DES)
--------------------------------------------------------

Speed.#1.........:  715.5 MH/s (64.24ms) @ Accel:16 Loops:1024 Thr:128 Vec:1
Speed.#2.........:  552.2 MH/s (52.97ms) @ Accel:32 Loops:1024 Thr:64 Vec:1
Speed.#3.........: 21461.6 kH/s (48.56ms) @ Accel:2 Loops:1024 Thr:256 Vec:1
Speed.#4.........:  2076.0 kH/s (59.07ms) @ Accel:32 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  1291.2 MH/s

------------------------------------------------------------------------------
* Hash-Mode 500 (md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5)) [Iterations: 1000]
------------------------------------------------------------------------------

Speed.#1.........:  6771.1 kH/s (82.58ms) @ Accel:32 Loops:1000 Thr:1024 Vec:1
Speed.#2.........:  5405.2 kH/s (66.97ms) @ Accel:32 Loops:1000 Thr:1024 Vec:1
Speed.#3.........:  309.1 kH/s (77.27ms) @ Accel:128 Loops:500 Thr:256 Vec:1
Speed.#4.........:    22753 H/s (86.97ms) @ Accel:512 Loops:1000 Thr:1 Vec:8
Speed.#*.........: 12508.1 kH/s

----------------------------------------------------------------
* Hash-Mode 3200 (bcrypt $2*$, Blowfish (Unix)) [Iterations: 32]
----------------------------------------------------------------

Speed.#1.........:    17638 H/s (55.92ms) @ Accel:64 Loops:32 Thr:16 Vec:1
Speed.#2.........:    10446 H/s (71.32ms) @ Accel:64 Loops:32 Thr:12 Vec:1
Speed.#3.........:      156 H/s (72.79ms) @ Accel:2 Loops:16 Thr:12 Vec:1
Speed.#4.........:      18 H/s (2.06ms) @ Accel:4 Loops:32 Thr:1 Vec:1
Speed.#*.........:    28258 H/s

--------------------------------------------------------------------
* Hash-Mode 1800 (sha512crypt $6$, SHA512 (Unix)) [Iterations: 5000]
--------------------------------------------------------------------

Speed.#1.........:  136.6 kH/s (47.12ms) @ Accel:512 Loops:512 Thr:128 Vec:1
Speed.#2.........:    85689 H/s (74.90ms) @ Accel:64 Loops:512 Thr:1024 Vec:1
Speed.#3.........:    5492 H/s (72.03ms) @ Accel:256 Loops:128 Thr:64 Vec:1
Speed.#4.........:    1004 H/s (50.19ms) @ Accel:512 Loops:512 Thr:1 Vec:4
Speed.#*.........:  228.8 kH/s

--------------------------------------------------------
* Hash-Mode 7500 (Kerberos 5, etype 23, AS-REQ Pre-Auth)
--------------------------------------------------------

Speed.#1.........:  318.5 MH/s (72.17ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#2.........:  226.5 MH/s (64.69ms) @ Accel:128 Loops:256 Thr:32 Vec:1
Speed.#3.........:  4880.8 kH/s (53.46ms) @ Accel:128 Loops:32 Thr:32 Vec:1
Speed.#4.........:  2020.7 kH/s (64.79ms) @ Accel:128 Loops:256 Thr:1 Vec:8
Speed.#*.........:  551.9 MH/s

-------------------------------------------------
* Hash-Mode 13100 (Kerberos 5, etype 23, TGS-REP)
-------------------------------------------------

Speed.#1.........:  315.9 MH/s (72.75ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#2.........:  226.6 MH/s (64.66ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#3.........:  4771.9 kH/s (54.60ms) @ Accel:64 Loops:64 Thr:32 Vec:1
Speed.#4.........:  1999.4 kH/s (65.46ms) @ Accel:32 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  549.3 MH/s

---------------------------------------------------------------
* Hash-Mode 15300 (DPAPI masterkey file v1) [Iterations: 23999]
---------------------------------------------------------------

Speed.#1.........:    51916 H/s (73.42ms) @ Accel:16 Loops:512 Thr:512 Vec:1
Speed.#2.........:    49991 H/s (47.25ms) @ Accel:8 Loops:1024 Thr:512 Vec:1
Speed.#3.........:    2125 H/s (78.15ms) @ Accel:16 Loops:1024 Thr:128 Vec:1
Speed.#4.........:    1063 H/s (79.73ms) @ Accel:512 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  105.1 kH/s

---------------------------------------------------------------
* Hash-Mode 15900 (DPAPI masterkey file v2) [Iterations: 12899]
---------------------------------------------------------------

Speed.#1.........:    28521 H/s (60.14ms) @ Accel:8 Loops:512 Thr:256 Vec:1
Speed.#2.........:    23251 H/s (47.20ms) @ Accel:2 Loops:1024 Thr:512 Vec:1
Speed.#3.........:    1100 H/s (71.15ms) @ Accel:2 Loops:512 Thr:512 Vec:1
Speed.#4.........:      576 H/s (68.21ms) @ Accel:256 Loops:512 Thr:1 Vec:4
Speed.#*.........:    53449 H/s

------------------------------------------------------------------
* Hash-Mode 7100 (macOS v10.8+ (PBKDF2-SHA512)) [Iterations: 1023]
------------------------------------------------------------------

Speed.#1.........:  357.0 kH/s (59.54ms) @ Accel:128 Loops:31 Thr:256 Vec:1
Speed.#2.........:  273.8 kH/s (49.41ms) @ Accel:64 Loops:31 Thr:512 Vec:1
Speed.#3.........:    13673 H/s (48.94ms) @ Accel:2 Loops:511 Thr:512 Vec:1
Speed.#4.........:    7111 H/s (57.06ms) @ Accel:512 Loops:255 Thr:1 Vec:4
Speed.#*.........:  651.6 kH/s

---------------------------------------------
* Hash-Mode 11600 (7-Zip) [Iterations: 16384]
---------------------------------------------

Speed.#1.........:  285.3 kH/s (65.22ms) @ Accel:16 Loops:4096 Thr:256 Vec:1
Speed.#2.........:  218.8 kH/s (58.57ms) @ Accel:4 Loops:4096 Thr:1024 Vec:1
Speed.#3.........:    13271 H/s (66.38ms) @ Accel:2 Loops:4096 Thr:1024 Vec:1
Speed.#4.........:    1140 H/s (55.77ms) @ Accel:64 Loops:4096 Thr:1 Vec:8
Speed.#*.........:  518.4 kH/s

------------------------------------------------
* Hash-Mode 12500 (RAR3-hp) [Iterations: 262144]
------------------------------------------------

Speed.#1.........:    44107 H/s (62.76ms) @ Accel:8 Loops:16384 Thr:256 Vec:1
Speed.#2.........:    31671 H/s (55.19ms) @ Accel:4 Loops:16384 Thr:512 Vec:1
Speed.#3.........:    1518 H/s (80.38ms) @ Accel:32 Loops:16384 Thr:32 Vec:1
Speed.#4.........:      177 H/s (90.14ms) @ Accel:64 Loops:16384 Thr:1 Vec:8
Speed.#*.........:    77474 H/s

--------------------------------------------
* Hash-Mode 13000 (RAR5) [Iterations: 32799]
--------------------------------------------

Speed.#1.........:    31599 H/s (43.84ms) @ Accel:128 Loops:64 Thr:256 Vec:1
Speed.#2.........:    24943 H/s (68.99ms) @ Accel:4 Loops:1024 Thr:1024 Vec:1
Speed.#3.........:    1422 H/s (87.96ms) @ Accel:16 Loops:128 Thr:1024 Vec:1
Speed.#4.........:      621 H/s (49.82ms) @ Accel:256 Loops:1024 Thr:1 Vec:8
Speed.#*.........:    58586 H/s

-----------------------------------------------------------------------
* Hash-Mode 6211 (TrueCrypt RIPEMD160 + XTS 512 bit) [Iterations: 1999]
-----------------------------------------------------------------------

Speed.#1.........:  225.9 kH/s (90.44ms) @ Accel:32 Loops:128 Thr:512 Vec:1
Speed.#2.........:  180.5 kH/s (73.76ms) @ Accel:8 Loops:256 Thr:1024 Vec:1
Speed.#3.........:    9277 H/s (50.38ms) @ Accel:4 Loops:128 Thr:1024 Vec:1
Speed.#4.........:    4176 H/s (59.29ms) @ Accel:128 Loops:1024 Thr:1 Vec:8
Speed.#*.........:  419.9 kH/s

-----------------------------------------------------------------------------------
* Hash-Mode 13400 (KeePass 1 (AES/Twofish) and KeePass 2 (AES)) [Iterations: 24569]
-----------------------------------------------------------------------------------

Speed.#1.........:    19087 H/s (48.98ms) @ Accel:32 Loops:128 Thr:256 Vec:1
Speed.#2.........:    21715 H/s (54.93ms) @ Accel:4 Loops:1024 Thr:512 Vec:1
Speed.#3.........:    1536 H/s (55.27ms) @ Accel:4 Loops:1024 Thr:256 Vec:1
Speed.#4.........:      476 H/s (89.52ms) @ Accel:512 Loops:512 Thr:1 Vec:8
Speed.#*.........:    42815 H/s

----------------------------------------------------------------
* Hash-Mode 6800 (LastPass + LastPass sniffed) [Iterations: 499]
----------------------------------------------------------------

Speed.#1.........:  1906.7 kH/s (37.83ms) @ Accel:128 Loops:62 Thr:256 Vec:1
Speed.#2.........:  1508.3 kH/s (55.60ms) @ Accel:32 Loops:124 Thr:1024 Vec:1
Speed.#3.........:    73897 H/s (56.35ms) @ Accel:8 Loops:249 Thr:1024 Vec:1
Speed.#4.........:    35818 H/s (51.20ms) @ Accel:512 Loops:499 Thr:1 Vec:8
Speed.#*.........:  3524.7 kH/s

--------------------------------------------------------------------
* Hash-Mode 11300 (Bitcoin/Litecoin wallet.dat) [Iterations: 200459]
--------------------------------------------------------------------

Speed.#1.........:    3893 H/s (85.43ms) @ Accel:2048 Loops:128 Thr:256 Vec:1
Speed.#2.........:    3016 H/s (55.20ms) @ Accel:256 Loops:128 Thr:1024 Vec:1
Speed.#3.........:      175 H/s (59.58ms) @ Accel:2 Loops:1024 Thr:1024 Vec:1
Speed.#4.........:      71 H/s (36.78ms) @ Accel:512 Loops:1024 Thr:1 Vec:4
Speed.#*.........:    7155 H/s

Started: Wed Jun 28 13:44:45 2023

Stopped: Wed Jun 28 14:04:53 2023

The following are benchmarks conducted in OpenCL for Nvidia GTX 1660 Super and GT730 GPUs. It has been observed that running certain algorithms in OpenCL is faster compared to CUDA.

Using the P4000 as the control card, OpenCL outperformed CUDA in 13 out of 25 benchmark tests. However, there were 6 algorithms where OpenCL was slower, and 6 others where the results were mixed or too close to determine a clear winner.

In hash mode 500 (md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5)), running in OpenCL showed an 18% improvement in speed compared to CUDA. However, in hash mode 3200, performance dropped to nearly 33% when running in OpenCL compared to CUDA.

Note: The asterisks (***) next to each algorithm indicate that it is faster in OpenCL, while the equal sign (=) denotes a tied or inconclusive result.

Overall, the benchmarks suggest that the performance of OpenCL versus CUDA varies depending on the specific algorithm and hash mode being use but CUDA is not always faster.

Code:
hashcat (v6.2.5) starting in benchmark mode

Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.

Unsupported AMD HIP runtime version '4.2' detected! Falling back to OpenCL...

* Device #7: This hardware has outdated CUDA compute capability (3.5).
            For modern OpenCL performance, upgrade to hardware that supports
            CUDA compute capability version 5.0 (Maxwell) or higher.
CUDA API (CUDA 11.4)
====================
* Device #1: NVIDIA GeForce GTX 1660 SUPER, skipped
* Device #2: Quadro P4000, 8038/8119 MB, 14MCU
* Device #3: NVIDIA GeForce GT 730, skipped

OpenCL API (OpenCL 3.0 PoCL 3.0-rc2  Linux, RelWithDebInfo, RELOC, SPIR, LLVM 10.0.0, SLEEF, POCL_DEBUG) - Platform #1 [The pocl project]
=========================================================================================================================================
* Device #4: pthread-Intel(R) Core(TM) i3-4130 CPU @ 3.40GHz, skipped

OpenCL API (OpenCL 2.0 AMD-APP (3314.0)) - Platform #2 [Advanced Micro Devices, Inc.]
=====================================================================================

OpenCL API (OpenCL 3.0 CUDA 11.4.402) - Platform #3 [NVIDIA Corporation]
========================================================================
* Device #5: NVIDIA GeForce GTX 1660 SUPER, 5824/5944 MB (1486 MB allocatable), 22MCU
* Device #6: Quadro P4000, skipped
* Device #7: NVIDIA GeForce GT 730, 1920/2002 MB (500 MB allocatable), 2MCU

Benchmark relevant options:
===========================
* --backend-devices=2,5,7
* --optimized-kernel-enable

-------------------
* Hash-Mode 0 (MD5)  ***
-------------------

Speed.#5.........: 17698.6 MH/s (41.57ms) @ Accel:128 Loops:1024 Thr:256 Vec:1
Speed.#2.........: 14185.2 MH/s (65.63ms) @ Accel:128 Loops:512 Thr:1024 Vec:1
Speed.#7.........:  877.1 MH/s (75.73ms) @ Accel:512 Loops:512 Thr:128 Vec:2
Speed.#*.........: 32761.0 MH/s

----------------------
* Hash-Mode 100 (SHA1) ***
----------------------

Speed.#5.........:  6081.3 MH/s (60.57ms) @ Accel:64 Loops:1024 Thr:256 Vec:1
Speed.#2.........:  5556.3 MH/s (84.06ms) @ Accel:128 Loops:512 Thr:512 Vec:1
Speed.#7.........:  259.1 MH/s (64.57ms) @ Accel:256 Loops:1024 Thr:32 Vec:1
Speed.#*.........: 11896.7 MH/s

---------------------------
* Hash-Mode 1400 (SHA2-256) ***
---------------------------

Speed.#5.........:  2591.4 MH/s (71.04ms) @ Accel:128 Loops:256 Thr:256 Vec:1
Speed.#2.........:  2069.1 MH/s (56.58ms) @ Accel:8 Loops:1024 Thr:1024 Vec:1
Speed.#7.........:  115.2 MH/s (72.45ms) @ Accel:16 Loops:1024 Thr:256 Vec:1
Speed.#*.........:  4775.7 MH/s

---------------------------
* Hash-Mode 1700 (SHA2-512)
---------------------------

Speed.#5.........:  772.5 MH/s (59.60ms) @ Accel:64 Loops:128 Thr:256 Vec:1
Speed.#2.........:  656.4 MH/s (89.23ms) @ Accel:16 Loops:1024 Thr:256 Vec:1
Speed.#7.........: 29507.0 kH/s (70.96ms) @ Accel:8 Loops:512 Thr:256 Vec:1
Speed.#*.........:  1458.4 MH/s

-------------------------------------------------------------
* Hash-Mode 22000 (WPA-PBKDF2-PMKID+EAPOL) [Iterations: 4095]  ***
-------------------------------------------------------------

Speed.#5.........:  300.6 kH/s (74.56ms) @ Accel:128 Loops:128 Thr:256 Vec:1
Speed.#2.........:  286.9 kH/s (49.44ms) @ Accel:8 Loops:1024 Thr:512 Vec:1
Speed.#7.........:    13600 H/s (74.22ms) @ Accel:64 Loops:128 Thr:256 Vec:1
Speed.#*.........:  601.1 kH/s

-----------------------
* Hash-Mode 1000 (NTLM)  ***
-----------------------

Speed.#5.........: 32281.5 MH/s (22.71ms) @ Accel:128 Loops:1024 Thr:256 Vec:1
Speed.#2.........: 23224.3 MH/s (39.81ms) @ Accel:1024 Loops:256 Thr:256 Vec:1
Speed.#7.........:  1429.0 MH/s (92.67ms) @ Accel:512 Loops:1024 Thr:128 Vec:4
Speed.#*.........: 56934.9 MH/s

---------------------
* Hash-Mode 3000 (LM)  ***
---------------------

Speed.#5.........: 17720.3 MH/s (41.50ms) @ Accel:256 Loops:1024 Thr:128 Vec:1
Speed.#2.........: 14068.6 MH/s (66.47ms) @ Accel:1024 Loops:1024 Thr:64 Vec:1
Speed.#7.........:  517.4 MH/s (64.35ms) @ Accel:128 Loops:1024 Thr:128 Vec:1
Speed.#*.........: 32306.3 MH/s

--------------------------------------------
* Hash-Mode 5500 (NetNTLMv1 / NetNTLMv1+ESS)
--------------------------------------------

Speed.#5.........: 17993.1 MH/s (40.86ms) @ Accel:128 Loops:1024 Thr:256 Vec:1
Speed.#2.........: 14074.8 MH/s (66.12ms) @ Accel:128 Loops:512 Thr:1024 Vec:1
Speed.#7.........:  870.2 MH/s (76.32ms) @ Accel:512 Loops:512 Thr:128 Vec:4
Speed.#*.........: 32938.1 MH/s

----------------------------
* Hash-Mode 5600 (NetNTLMv2)  ***
----------------------------

Speed.#5.........:  1356.1 MH/s (67.91ms) @ Accel:64 Loops:256 Thr:256 Vec:1
Speed.#2.........:  1045.3 MH/s (55.81ms) @ Accel:128 Loops:64 Thr:512 Vec:1
Speed.#7.........: 46537.0 kH/s (89.72ms) @ Accel:8 Loops:1024 Thr:256 Vec:2
Speed.#*.........:  2447.9 MH/s

--------------------------------------------------------
* Hash-Mode 1500 (descrypt, DES (Unix), Traditional DES)  ***
--------------------------------------------------------

Speed.#5.........:  715.1 MH/s (64.40ms) @ Accel:16 Loops:1024 Thr:128 Vec:1
Speed.#2.........:  554.0 MH/s (52.81ms) @ Accel:32 Loops:1024 Thr:64 Vec:1
Speed.#7.........: 22769.1 kH/s (91.66ms) @ Accel:4 Loops:1024 Thr:256 Vec:1
Speed.#*.........:  1291.9 MH/s

------------------------------------------------------------------------------
* Hash-Mode 500 (md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5)) [Iterations: 1000]  ***
------------------------------------------------------------------------------

Speed.#5.........:  7979.7 kH/s (82.50ms) @ Accel:128 Loops:1000 Thr:256 Vec:1
Speed.#2.........:  6010.3 kH/s (67.46ms) @ Accel:32 Loops:1000 Thr:1024 Vec:1
Speed.#7.........:  324.1 kH/s (76.02ms) @ Accel:128 Loops:1000 Thr:128 Vec:1
Speed.#*.........: 14314.1 kH/s

----------------------------------------------------------------
* Hash-Mode 3200 (bcrypt $2*$, Blowfish (Unix)) [Iterations: 32] 
----------------------------------------------------------------

Speed.#5.........:    11822 H/s (58.09ms) @ Accel:64 Loops:32 Thr:11 Vec:1
Speed.#2.........:    10435 H/s (71.73ms) @ Accel:64 Loops:32 Thr:12 Vec:1
Speed.#7.........:      147 H/s (72.10ms) @ Accel:2 Loops:16 Thr:11 Vec:1
Speed.#*.........:    22404 H/s

--------------------------------------------------------------------
* Hash-Mode 1800 (sha512crypt $6$, SHA512 (Unix)) [Iterations: 5000]  ***
--------------------------------------------------------------------

Speed.#5.........:  139.2 kH/s (46.59ms) @ Accel:1024 Loops:256 Thr:128 Vec:1
Speed.#2.........:    88517 H/s (72.90ms) @ Accel:512 Loops:128 Thr:512 Vec:1
Speed.#7.........:    5829 H/s (69.51ms) @ Accel:16 Loops:1024 Thr:128 Vec:1
Speed.#*.........:  233.6 kH/s

--------------------------------------------------------
* Hash-Mode 7500 (Kerberos 5, etype 23, AS-REQ Pre-Auth)
--------------------------------------------------------

Speed.#5.........:  305.2 MH/s (75.48ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#2.........:  227.1 MH/s (64.53ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#7.........:  4093.9 kH/s (63.91ms) @ Accel:128 Loops:32 Thr:32 Vec:1
Speed.#*.........:  536.4 MH/s

-------------------------------------------------
* Hash-Mode 13100 (Kerberos 5, etype 23, TGS-REP)
-------------------------------------------------

Speed.#5.........:  286.5 MH/s (80.42ms) @ Accel:32 Loops:1024 Thr:32 Vec:1
Speed.#2.........:  226.3 MH/s (64.77ms) @ Accel:256 Loops:128 Thr:32 Vec:1
Speed.#7.........:  4071.8 kH/s (64.27ms) @ Accel:64 Loops:64 Thr:32 Vec:1
Speed.#*.........:  516.9 MH/s

---------------------------------------------------------------
* Hash-Mode 15300 (DPAPI masterkey file v1) [Iterations: 23999]  =
---------------------------------------------------------------

Speed.#5.........:    51221 H/s (74.78ms) @ Accel:128 Loops:128 Thr:256 Vec:1
Speed.#2.........:    49625 H/s (47.82ms) @ Accel:8 Loops:1024 Thr:512 Vec:1
Speed.#7.........:    2312 H/s (74.98ms) @ Accel:64 Loops:256 Thr:128 Vec:1
Speed.#*.........:  103.2 kH/s

---------------------------------------------------------------
* Hash-Mode 15900 (DPAPI masterkey file v2) [Iterations: 12899]  =
---------------------------------------------------------------

Speed.#5.........:    29017 H/s (59.57ms) @ Accel:8 Loops:1024 Thr:128 Vec:1
Speed.#2.........:    22803 H/s (47.59ms) @ Accel:4 Loops:512 Thr:512 Vec:1
Speed.#7.........:    1051 H/s (73.67ms) @ Accel:4 Loops:512 Thr:256 Vec:1
Speed.#*.........:    52871 H/s

------------------------------------------------------------------
* Hash-Mode 7100 (macOS v10.8+ (PBKDF2-SHA512)) [Iterations: 1023]  =
------------------------------------------------------------------

Speed.#5.........:  364.7 kH/s (57.53ms) @ Accel:512 Loops:63 Thr:32 Vec:1
Speed.#2.........:  278.3 kH/s (47.65ms) @ Accel:32 Loops:63 Thr:512 Vec:1
Speed.#7.........:    11040 H/s (51.71ms) @ Accel:4 Loops:511 Thr:256 Vec:1
Speed.#*.........:  654.0 kH/s

---------------------------------------------
* Hash-Mode 11600 (7-Zip) [Iterations: 16384]  ***
---------------------------------------------

Speed.#5.........:  301.0 kH/s (66.05ms) @ Accel:16 Loops:4096 Thr:256 Vec:1
Speed.#2.........:  218.4 kH/s (58.56ms) @ Accel:4 Loops:4096 Thr:1024 Vec:1
Speed.#7.........:    15276 H/s (66.01ms) @ Accel:32 Loops:4096 Thr:64 Vec:1
Speed.#*.........:  534.6 kH/s

------------------------------------------------
* Hash-Mode 12500 (RAR3-hp) [Iterations: 262144]  ***
------------------------------------------------

Speed.#5.........:    44734 H/s (62.80ms) @ Accel:8 Loops:16384 Thr:256 Vec:1
Speed.#2.........:    32346 H/s (55.21ms) @ Accel:4 Loops:16384 Thr:512 Vec:1
Speed.#7.........:    1544 H/s (80.96ms) @ Accel:32 Loops:16384 Thr:32 Vec:1
Speed.#*.........:    78623 H/s

--------------------------------------------
* Hash-Mode 13000 (RAR5) [Iterations: 32799]  ***
--------------------------------------------

Speed.#5.........:    32321 H/s (86.87ms) @ Accel:64 Loops:256 Thr:256 Vec:1
Speed.#2.........:    24845 H/s (69.38ms) @ Accel:4 Loops:1024 Thr:1024 Vec:1
Speed.#7.........:    1320 H/s (46.96ms) @ Accel:4 Loops:1024 Thr:256 Vec:1
Speed.#*.........:    58485 H/s

-----------------------------------------------------------------------
* Hash-Mode 6211 (TrueCrypt RIPEMD160 + XTS 512 bit) [Iterations: 1999]  =
-----------------------------------------------------------------------

Speed.#5.........:  227.6 kH/s (91.19ms) @ Accel:64 Loops:128 Thr:256 Vec:1
Speed.#2.........:  175.8 kH/s (73.91ms) @ Accel:8 Loops:256 Thr:1024 Vec:1
Speed.#7.........:    9187 H/s (52.23ms) @ Accel:4 Loops:512 Thr:256 Vec:1
Speed.#*.........:  412.7 kH/s

-----------------------------------------------------------------------------------
* Hash-Mode 13400 (KeePass 1 (AES/Twofish) and KeePass 2 (AES)) [Iterations: 24569]
-----------------------------------------------------------------------------------

Speed.#5.........:    19030 H/s (49.29ms) @ Accel:16 Loops:256 Thr:256 Vec:1
Speed.#2.........:    21687 H/s (54.95ms) @ Accel:8 Loops:512 Thr:512 Vec:1
Speed.#7.........:    1478 H/s (57.41ms) @ Accel:32 Loops:128 Thr:256 Vec:1
Speed.#*.........:    42195 H/s

----------------------------------------------------------------
* Hash-Mode 6800 (LastPass + LastPass sniffed) [Iterations: 499] =
----------------------------------------------------------------

Speed.#5.........:  2031.6 kH/s (67.95ms) @ Accel:128 Loops:124 Thr:256 Vec:1
Speed.#2.........:  1542.2 kH/s (46.36ms) @ Accel:16 Loops:249 Thr:1024 Vec:1
Speed.#7.........:    71232 H/s (63.17ms) @ Accel:32 Loops:249 Thr:256 Vec:1
Speed.#*.........:  3645.1 kH/s

--------------------------------------------------------------------
* Hash-Mode 11300 (Bitcoin/Litecoin wallet.dat) [Iterations: 200459]  =
--------------------------------------------------------------------

Speed.#5.........:    3895 H/s (85.80ms) @ Accel:1024 Loops:256 Thr:256 Vec:1
Speed.#2.........:    3013 H/s (55.38ms) @ Accel:256 Loops:128 Thr:1024 Vec:1
Speed.#7.........:      149 H/s (70.23ms) @ Accel:8 Loops:1024 Thr:256 Vec:1
Speed.#*.........:    7057 H/s

Started: Wed Jun 28 23:12:02 2023

Stopped: Wed Jun 28 23:20:11 2023
Reply
#2
Some benchmarks will indeed show up faster for OpenCL, but CUDA is still the preferred runtime. Ultimate speed is not the only consideration being made. There are limitations that make OpenCL on Nvidia cards more difficult to work with or more inconsistent than CUDA. A great example is the memory limitations imposed by the OpenCL runtime that, while not directly impacting performance in your ideal work benchmark state, will impact your ability to load different hash lists or attacks. For some reason, Nvidia interprets the OpenCL spec as stating that single allocations are limited to 1/4 the total memory size, which means we must work around that with multiple allocations or be limited to only using 1/4 of the VRAM. CUDA, however, does not have this same limitation.
Reply
#3
That's excellent information that I wasn't aware of. Thank you for taking the time to explain it
Do you have any reference that I can dive into reading more ?

And how about ROCm/HIP ? Is it worth speeding any time and resource to use AMD.
Look like AMD is picking up some slack recently.
Reply