e-ago
Cuda error in file 'main.cu' in line 66 : system has unsupported display driver / cuda driver combination On GTX1650 SUPER
I have a MSI GTX 1650 SUPER VENTUS XS OC EDITION and I can't get the cracker to work, here's where I have gotten so far.
Note: I'm using NVIDIA driver metapackage from nvidia-driver-525 (propietary)
and I'm running Xubuntu 22.04 LTS
sudo lshw -C display
Result:
*-display
description: VGA compatible controller
product: TU116 [GeForce GTX 1650 SUPER]
vendor: NVIDIA Corporation
physical id: 0
bus info: pci@0000:01:00.0
version: a1
width: 64 bits
clock: 33MHz
capabilities: pm msi pciexpress vga_controller bus_master cap_list rom
configuration: driver=nvidia latency=0
resources: irq:33 memory:f6000000-f6ffffff memory:e0000000-efffffff memory:f0000000-f1ffffff ioport:e000(size=128) memory:c0000-dffff
*-graphics
product: VESA VGA
physical id: 1
logical name: /dev/fb0
capabilities: fb
configuration: depth=32 resolution=640,480
CUDA src MakeFile for bitcracker_cuda
bitcracker_cuda:
nvcc -gencode arch=compute_86,code=sm_87 -Xptxas -v -o bitcracker_cuda main.cu cuda_attack.cu utils.cu w_blocks.cu
clean:
rm -rf *.o
rm -rf ../build/bitcracker_cuda
Build Result From build.sh
====== Build BitCracker CUDA version ======
rm -rf *.o
rm -rf ../build/bitcracker_cuda
nvcc -gencode arch=compute_86,code=sm_87 -Xptxas -v -o bitcracker_cuda main.cu cuda_attack.cu utils.cu w_blocks.cu
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : Compiling entry function '_Z20decrypt_vmk_with_maciPiPhS0_S0_S0_S0_iiiijjjjiPjS1_' for 'sm_87'
ptxas info : Function properties for _Z20decrypt_vmk_with_maciPiPhS0_S0_S0_S0_iiiijjjjiPjS1_
264 bytes stack frame, 280 bytes spill stores, 532 bytes spill loads
ptxas info : Used 64 registers, 464 bytes cmem[0], 16 bytes cmem[2]
ptxas info : Compiling entry function '_Z11decrypt_vmkiPiPhS0_iiiiijjjjiPjS1_' for 'sm_87'
ptxas info : Function properties for _Z11decrypt_vmkiPiPhS0_iiiiijjjjiPjS1_
0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info : Used 60 registers, 440 bytes cmem[0], 16 bytes cmem[2]
utils.cu(84): warning #177-D: variable "tmp" was declared but never referenced
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : Compiling entry function '_Z16w_block_evaluatePhiS_Pj' for 'sm_87'
ptxas info : Function properties for _Z16w_block_evaluatePhiS_Pj
0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info : Used 64 registers, 384 bytes cmem[0]
Error while trying to attack "Recovery Key Method"
---------> BitCracker: BitLocker password cracking tool <---------
Cuda error in file 'main.cu' in line 66 : system has unsupported display driver / cuda driver combination.
Note: I searched for the CUDA gencode that I have on msi nvidia gtx 1650 super.
arch=compute_86,code=sm_87
and found it on this website in the comments section
also I visited the Nvidia CUDA compute capability page
and tried the CUDA 7.5. which is the arch=compute_35,code=sm_35
here's the build result:
====== Build BitCracker CUDA version ======
rm -rf *.o
rm -rf ../build/bitcracker_cuda
nvcc -gencode arch=compute_35,code=sm_35 -Xptxas -v -o bitcracker_cuda main.cu cuda_attack.cu utils.cu w_blocks.cu
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : Compiling entry function '_Z20decrypt_vmk_with_maciPiPhS0_S0_S0_S0_iiiijjjjiPjS1_' for 'sm_35'
ptxas info : Function properties for _Z20decrypt_vmk_with_maciPiPhS0_S0_S0_S0_iiiijjjjiPjS1_
272 bytes stack frame, 300 bytes spill stores, 440 bytes spill loads
ptxas info : Used 64 registers, 432 bytes cmem[0], 8 bytes cmem[2]
ptxas info : Compiling entry function '_Z11decrypt_vmkiPiPhS0_iiiiijjjjiPjS1_' for 'sm_35'
ptxas info : Function properties for _Z11decrypt_vmkiPiPhS0_iiiiijjjjiPjS1_
0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info : Used 54 registers, 408 bytes cmem[0], 8 bytes cmem[2]
utils.cu(84): warning #177-D: variable "tmp" was declared but never referenced
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : 0 bytes gmem, 12584 bytes cmem[3]
ptxas info : Compiling entry function '_Z16w_block_evaluatePhiS_Pj' for 'sm_35'
ptxas info : Function properties for _Z16w_block_evaluatePhiS_Pj
0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info : Used 64 registers, 352 bytes cmem[0], 8 bytes cmem[2]
but faced the same issue Error while trying to attack "Recovery Key Method" for the 2nd try
---------> BitCracker: BitLocker password cracking tool <---------
Cuda error in file 'main.cu' in line 66 : system has unsupported display driver / cuda driver combination.
Note: I use this command to preform the attack:
sudo ./build/bitcracker_cuda -f hash_recv_pass.txt -d bitcracker_wlrp_0.txt -t 1 -b 80 -g 0 -r
any thoughts on how to get it to work?
I'm leaning towards that the driver is the problem,, but it works perfectly fine for my setup. I'm thinking to change it to open-source
The GTX 1650 is a Turing card (TU116) which is CUDA 10 and SM75.
I would try installing the CUDA 10 drives and re-compiling using arch=compute_75,code=sm_75
