Posts: 8
Threads: 1
Joined: Jul 2022
Hello.
I bought 5 Nvidia 1080 TI Turbo with 11 GB of RAM.
I have some problem to make it work Ubuntu 20.04.4 LTS
I followed this guide ( https://www.unix-ninja.com/p/Building_a_...-_Part_III), the installation of NVIDIA driver seems good but when I start hashcat, I always have this error :
Code: No devices found/left.
When I run lspci, I correctly see my 1080 TI.
thank you for your precious help
Posts: 64
Threads: 1
Joined: Mar 2017
(07-25-2022, 03:39 PM)fl0at0xff Wrote: Hello.
I bought 5 Nvidia 1080 TI Turbo with 11 GB of RAM.
I have some problem to make it work Ubuntu 20.04.4 LTS
I followed this guide (https://www.unix-ninja.com/p/Building_a_...-_Part_III), the installation of NVIDIA driver seems good but when I start hashcat, I always have this error :
Code: No devices found/left.
When I run lspci, I correctly see my 1080 TI.
thank you for your precious help
Those instructions are five years old, which counts as ancient lore in GPU land. Install the latest NVIDIA drivers and CUDA toolkit that are available for the 1080.
from hashcat.net: "NVIDIA GPUs require "NVIDIA Driver" (440.64 or later) and "CUDA Toolkit" (9.0 or later)"
Posts: 8
Threads: 1
Joined: Jul 2022
(07-25-2022, 03:49 PM)pdo Wrote: Those instructions are five years old, which counts as ancient lore in GPU land. Install the latest NVIDIA drivers and CUDA toolkit that are available for the 1080.
from hashcat.net: "NVIDIA GPUs require "NVIDIA Driver" (440.64 or later) and "CUDA Toolkit" (9.0 or later)"
Hum now seems better. I installed drivers version 515.57 with CUDA 11.7.
I can run nvidia-smi and the output show me the result.
It is important to not forget to blacklist Nouveau driver.
Now, how can I test if hashcat is working correctly with my GPU ?
Posts: 64
Threads: 1
Joined: Mar 2017
(07-25-2022, 04:41 PM)fl0at0xff Wrote: (07-25-2022, 03:49 PM)pdo Wrote: Those instructions are five years old, which counts as ancient lore in GPU land. Install the latest NVIDIA drivers and CUDA toolkit that are available for the 1080.
from hashcat.net: "NVIDIA GPUs require "NVIDIA Driver" (440.64 or later) and "CUDA Toolkit" (9.0 or later)"
Hum now seems better. I installed drivers version 515.57 with CUDA 11.7.
I can run nvidia-smi and the output show me the result.
It is important to not forget to blacklist Nouveau driver.
Now, how can I test if hashcat is working correctly with my GPU ?
just run the benchmark: hashcat -b
Posts: 8
Threads: 1
Joined: Jul 2022
(07-25-2022, 04:51 PM)pdo Wrote: just run the benchmark: hashcat -b
Ok. I always tried to crack a simple sha512crypt password "Password" using this command :
Code: hashcat -m 1800 hash.txt ../wordlist/SecLists/Passwords/Common-Credentials/500-worst-passwords.txt
where hash.txt contains
Quote:$6$uwAT6nE2C3o0THWW$QsErk0YrwCmQdr0XLiJ34ZJlA0lGZ9cEvJxt9NvG4E9lVUwCvhj1h8rkGpA3q8vhTcSL4PkKm9Sf3JhG/WaNH.
Seems correct ? I Have this output but this seems not working.
Code: OpenCL Platform #1: NVIDIA Corporation
======================================
* Device #1: NVIDIA GeForce GTX 1080 Ti, 2794/11176 MB allocatable, 28MCU
* Device #2: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
* Device #3: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
OpenCL Platform #2: The pocl project
====================================
* Device #4: pthread-Intel(R) Core(TM) i3-7100 CPU @ 3.90GHz, skipped.
Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1
Applicable optimizers:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit
Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256
ATTENTION! Pure (unoptimized) OpenCL kernels selected.
This enables cracking passwords and salts > length 32 but for the price of drastically reduced performance.
If you want to switch to optimized OpenCL kernels, append -O to your commandline.
Watchdog: Temperature abort trigger set to 90c
* Device #1: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
* Device #2: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
* Device #3: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
Dictionary cache built:
* Filename..: ../wordlist/SecLists/Passwords/Common-Credentials/500-worst-passwords.txt
* Passwords.: 499
* Bytes.....: 3491
* Keyspace..: 499
* Runtime...: 0 secs
Posts: 64
Threads: 1
Joined: Mar 2017
(07-25-2022, 04:58 PM)fl0at0xff Wrote: (07-25-2022, 04:51 PM)pdo Wrote: just run the benchmark: hashcat -b
Ok. I always tried to crack a simple sha512crypt password "Password" using this command :
Code: hashcat -m 1800 hash.txt ../wordlist/SecLists/Passwords/Common-Credentials/500-worst-passwords.txt
where hash.txt contains
Quote:$6$uwAT6nE2C3o0THWW$QsErk0YrwCmQdr0XLiJ34ZJlA0lGZ9cEvJxt9NvG4E9lVUwCvhj1h8rkGpA3q8vhTcSL4PkKm9Sf3JhG/WaNH.
Seems correct ? I Have this output but this seems not working.
Code: OpenCL Platform #1: NVIDIA Corporation
======================================
* Device #1: NVIDIA GeForce GTX 1080 Ti, 2794/11176 MB allocatable, 28MCU
* Device #2: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
* Device #3: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
OpenCL Platform #2: The pocl project
====================================
* Device #4: pthread-Intel(R) Core(TM) i3-7100 CPU @ 3.90GHz, skipped.
Hashes: 1 digests; 1 unique digests, 1 unique salts
Bitmaps: 16 bits, 65536 entries, 0x0000ffff mask, 262144 bytes, 5/13 rotates
Rules: 1
Applicable optimizers:
* Zero-Byte
* Single-Hash
* Single-Salt
* Uses-64-Bit
Minimum password length supported by kernel: 0
Maximum password length supported by kernel: 256
ATTENTION! Pure (unoptimized) OpenCL kernels selected.
This enables cracking passwords and salts > length 32 but for the price of drastically reduced performance.
If you want to switch to optimized OpenCL kernels, append -O to your commandline.
Watchdog: Temperature abort trigger set to 90c
* Device #1: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
* Device #2: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
* Device #3: build_opts '-cl-std=CL1.2 -I OpenCL -I /usr/share/hashcat/OpenCL -D LOCAL_MEM_TYPE=1 -D VENDOR_ID=32 -D CUDA_ARCH=601 -D AMD_ROCM=0 -D VECT_SIZE=1 -D DEVICE_TYPE=4 -D DGST_R0=0 -D DGST_R1=1 -D DGST_R2=2 -D DGST_R3=3 -D DGST_ELEM=16 -D KERN_TYPE=1800 -D _unroll'
Dictionary cache built:
* Filename..: ../wordlist/SecLists/Passwords/Common-Credentials/500-worst-passwords.txt
* Passwords.: 499
* Bytes.....: 3491
* Keyspace..: 499
* Runtime...: 0 secs
Not sure what's going on there, but it doesn't look like you've got CUDA installed (correctly?)
Posts: 8
Threads: 1
Joined: Jul 2022
(07-25-2022, 05:02 PM)pdo Wrote: Not sure what's going on there, but it doesn't look like you've got CUDA installed (correctly?)
CUDA seems installed but I don't know how to check if I use it.
Code: god@crackfarm:~/test$ nvidia-smi
Mon Jul 25 15:07:30 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.226.00 Driver Version: 515.57 CUDA Version: 11.7 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... Off | 00000000:01:00.0 Off | N/A |
| 24% 36C P0 54W / 250W | 87MiB / 11264MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce ... Off | 00000000:03:00.0 Off | N/A |
| 23% 37C P0 54W / 250W | 85MiB / 11264MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 NVIDIA GeForce ... Off | 00000000:04:00.0 Off | N/A |
| 16% 44C P0 56W / 250W | 85MiB / 11264MiB | 3% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| No running processes found |
Posts: 8
Threads: 1
Joined: Jul 2022
(07-25-2022, 05:08 PM)fl0at0xff Wrote: (07-25-2022, 05:02 PM)pdo Wrote: Not sure what's going on there, but it doesn't look like you've got CUDA installed (correctly?)
CUDA seems installed but I don't know how to check if I use it.
Code: god@crackfarm:~/test$ nvidia-smi
Mon Jul 25 15:07:30 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.226.00 Driver Version: 515.57 CUDA Version: 11.7 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... Off | 00000000:01:00.0 Off | N/A |
| 24% 36C P0 54W / 250W | 87MiB / 11264MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce ... Off | 00000000:03:00.0 Off | N/A |
| 23% 37C P0 54W / 250W | 85MiB / 11264MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 NVIDIA GeForce ... Off | 00000000:04:00.0 Off | N/A |
| 16% 44C P0 56W / 250W | 85MiB / 11264MiB | 3% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| No running processes found |
After installed the latest version of hc, it working better.
When I launch benchmark, the GUI stucks after some minutes. do you have idea ? I still can press "S" for status but nothing is updated. All numbers and statistics are the same and the "q" key for quit does not quit the process.
Posts: 890
Threads: 15
Joined: Sep 2017
use to see which devices and how these are recognized (cuda or failback opencl), please post your output
given this last post:
OpenCL Platform #1: NVIDIA Corporation
======================================
* Device #1: NVIDIA GeForce GTX 1080 Ti, 2794/11176 MB allocatable, 28MCU
* Device #2: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
* Device #3: NVIDIA GeForce GTX 1080 Ti, 2794/11178 MB allocatable, 28MCU
OpenCL Platform #2: The pocl project
====================================
* Device #4: pthread-Intel(R) Core(TM) i3-7100 CPU @ 3.90GHz, skipped.
it seems hahscat didnt use cuda for your cards, next, only 3 cards are recognized, you said 5?
Posts: 8
Threads: 1
Joined: Jul 2022
07-26-2022, 04:32 PM
(This post was last modified: 07-26-2022, 04:33 PM by fl0at0xff.)
hello, below the output. Seems to have some bug with CUDA. I only connected 3 GPU for now.
Code: Successfully initialized NVIDIA CUDA library.
Failed to initialize NVIDIA RTC library.
* Device #1: CUDA SDK Toolkit not installed or incorrectly installed.
CUDA SDK Toolkit required for proper device support and utilization.
Falling back to OpenCL runtime.
Successfully initialized NVIDIA CUDA library.
Failed to initialize NVIDIA RTC library.
* Device #2: CUDA SDK Toolkit not installed or incorrectly installed.
CUDA SDK Toolkit required for proper device support and utilization.
Falling back to OpenCL runtime.
Successfully initialized NVIDIA CUDA library.
Failed to initialize NVIDIA RTC library.
* Device #3: CUDA SDK Toolkit not installed or incorrectly installed.
CUDA SDK Toolkit required for proper device support and utilization.
Falling back to OpenCL runtime.
* Device #4: Outdated POCL OpenCL driver detected!
OpenCL Info:
============
OpenCL Platform ID #1
Vendor..: NVIDIA Corporation
Name....: NVIDIA CUDA
Version.: OpenCL 3.0 CUDA 11.7.99
Backend Device ID #1
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce GTX 1080 Ti
Version........: OpenCL 3.0 CUDA
Processor(s)...: 28
Clock..........: 1582
Memory.Total...: 11176 MB (limited to 2794 MB allocatable in one block)
Memory.Free....: 11008 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 515.57
PCI.Addr.BDF...: 01:00.0
Backend Device ID #2
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce GTX 1080 Ti
Version........: OpenCL 3.0 CUDA
Processor(s)...: 28
Clock..........: 1582
Memory.Total...: 11178 MB (limited to 2794 MB allocatable in one block)
Memory.Free....: 11008 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 515.57
PCI.Addr.BDF...: 03:00.0
Backend Device ID #3
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce GTX 1080 Ti
Version........: OpenCL 3.0 CUDA
Processor(s)...: 28
Clock..........: 1582
Memory.Total...: 11178 MB (limited to 2794 MB allocatable in one block)
Memory.Free....: 11008 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 515.57
PCI.Addr.BDF...: 04:00.0
OpenCL Platform ID #2
Vendor..: The pocl project
Name....: Portable Computing Language
Version.: OpenCL 1.2 pocl 1.4, None+Asserts, LLVM 9.0.1, RELOC, SLEEF, DISTRO, POCL_DEBUG
Backend Device ID #4
Type...........: CPU
Vendor.ID......: 128
Vendor.........: GenuineIntel
Name...........: pthread-Intel(R) Core(TM) i3-7100 CPU @ 3.90GHz
Version........: OpenCL 1.2 pocl HSTR: pthread-x86_64-pc-linux-gnu-skylake
Processor(s)...: 4
Clock..........: 3900
Memory.Total...: 5873 MB (limited to 1024 MB allocatable in one block)
Memory.Free....: 2904 MB
OpenCL.Version.: OpenCL C 1.2 pocl
Driver.Version.: 1.4
I think I need to install CUDA SDK too ?
|
