12-05-2022, 04:46 PM
Has anyone used the RTX4090 on vast ai ? I have tried to have a play but can't get it to work. Have used 2080ti, 3060, 3090's and A6000 all work fine other than cuda errors. Vast ai help suggest it's a hashcat issue and a newer version docker image might be needed. I am using the dizca latest image. Have run with --backend-ignore-cuda makes no difference. Tried sudo apt remove libnvrtc* did nothing.
vast-hashcat-I-info.jpg (Size: 139.41 KB / Downloads: 27)
vast-rtx-4090-iissue.jpg (Size: 177.73 KB / Downloads: 22)
One of my attempts
hashcat -b -m 1400 -w 3
hashcat (v6.1.1-19-gcdd06d4) starting in benchmark mode...
* Device #1: CUDA SDK Toolkit installation NOT detected.
CUDA SDK Toolkit installation required for proper device support and utilization
Falling back to OpenCL Runtime
* Device #1: WARNING! Kernel exec timeout is not disabled.
This may cause "CL_OUT_OF_RESOURCES" or related errors.
To disable the timeout, see: https://hashcat.net/q/timeoutpatch
OpenCL API (OpenCL 3.0 CUDA 11.8.87) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #1: NVIDIA GeForce RTX 4090, 23808/24253 MB (6063 MB allocatable), 128MCU
Benchmark relevant options:
===========================
* --workload-profile=3
Hashmode: 1400 - SHA2-256
clBuildProgram(): CL_BUILD_PROGRAM_FAILURE
* Device #1: Kernel /usr/local/share/hashcat/OpenCL/shared.cl build failed.
Started: Sat Dec 3 03:51:31 2022
Stopped: Sat Dec 3 03:51:34 2022
Backend Info :
CUDA.Version.: 11.8
Backend Device ID #1 (Alias: #3)
Name...........: NVIDIA GeForce RTX 4090
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB
Memory.Free....: 23870 MB
PCI.Addr.BDFe..: 0000:44:00.0
Backend Device ID #2 (Alias: #4)
Name...........: NVIDIA GeForce RTX 4090
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB
Memory.Free....: 23870 MB
PCI.Addr.BDFe..: 0000:82:00.0
OpenCL Info:
============
OpenCL Platform ID #1
Vendor..: NVIDIA Corporation
Name....: NVIDIA CUDA
Version.: OpenCL 3.0 CUDA 11.8.87
Backend Device ID #3 (Alias: #1)
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce RTX 4090
Version........: OpenCL 3.0 CUDA
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB (limited to 6063 MB allocatable in one block)
Memory.Free....: 23808 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 520.56.06
PCI.Addr.BDF...: 44:00.0
Backend Device ID #4 (Alias: #2)
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce RTX 4090
Version........: OpenCL 3.0 CUDA
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB (limited to 6063 MB allocatable in one block)
Memory.Free....: 23808 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 520.56.06
PCI.Addr.BDF...: 82:00.0
Any help would be appreciated .. One of the attached images shows with and without cuda, maybe not that it matters...THANKS
vast-hashcat-I-info.jpg (Size: 139.41 KB / Downloads: 27)
vast-rtx-4090-iissue.jpg (Size: 177.73 KB / Downloads: 22)
vast-hashcat-I-info.jpg (Size: 139.41 KB / Downloads: 27)
vast-rtx-4090-iissue.jpg (Size: 177.73 KB / Downloads: 22)
One of my attempts
hashcat -b -m 1400 -w 3
hashcat (v6.1.1-19-gcdd06d4) starting in benchmark mode...
* Device #1: CUDA SDK Toolkit installation NOT detected.
CUDA SDK Toolkit installation required for proper device support and utilization
Falling back to OpenCL Runtime
* Device #1: WARNING! Kernel exec timeout is not disabled.
This may cause "CL_OUT_OF_RESOURCES" or related errors.
To disable the timeout, see: https://hashcat.net/q/timeoutpatch
OpenCL API (OpenCL 3.0 CUDA 11.8.87) - Platform #1 [NVIDIA Corporation]
=======================================================================
* Device #1: NVIDIA GeForce RTX 4090, 23808/24253 MB (6063 MB allocatable), 128MCU
Benchmark relevant options:
===========================
* --workload-profile=3
Hashmode: 1400 - SHA2-256
clBuildProgram(): CL_BUILD_PROGRAM_FAILURE
* Device #1: Kernel /usr/local/share/hashcat/OpenCL/shared.cl build failed.
Started: Sat Dec 3 03:51:31 2022
Stopped: Sat Dec 3 03:51:34 2022
Backend Info :
CUDA.Version.: 11.8
Backend Device ID #1 (Alias: #3)
Name...........: NVIDIA GeForce RTX 4090
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB
Memory.Free....: 23870 MB
PCI.Addr.BDFe..: 0000:44:00.0
Backend Device ID #2 (Alias: #4)
Name...........: NVIDIA GeForce RTX 4090
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB
Memory.Free....: 23870 MB
PCI.Addr.BDFe..: 0000:82:00.0
OpenCL Info:
============
OpenCL Platform ID #1
Vendor..: NVIDIA Corporation
Name....: NVIDIA CUDA
Version.: OpenCL 3.0 CUDA 11.8.87
Backend Device ID #3 (Alias: #1)
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce RTX 4090
Version........: OpenCL 3.0 CUDA
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB (limited to 6063 MB allocatable in one block)
Memory.Free....: 23808 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 520.56.06
PCI.Addr.BDF...: 44:00.0
Backend Device ID #4 (Alias: #2)
Type...........: GPU
Vendor.ID......: 32
Vendor.........: NVIDIA Corporation
Name...........: NVIDIA GeForce RTX 4090
Version........: OpenCL 3.0 CUDA
Processor(s)...: 128
Clock..........: 2520
Memory.Total...: 24255 MB (limited to 6063 MB allocatable in one block)
Memory.Free....: 23808 MB
OpenCL.Version.: OpenCL C 1.2
Driver.Version.: 520.56.06
PCI.Addr.BDF...: 82:00.0
Any help would be appreciated .. One of the attached images shows with and without cuda, maybe not that it matters...THANKS
vast-hashcat-I-info.jpg (Size: 139.41 KB / Downloads: 27)
vast-rtx-4090-iissue.jpg (Size: 177.73 KB / Downloads: 22)