Chia-Network / bladebit

A high-performance k32-only, Chia (XCH) plotter supporting in-RAM and disk-based plotting
Apache License 2.0
339 stars 109 forks source link

bladebit-cuda alpha3 crashes when running ramplot with compression #313

Open llowrey opened 1 year ago

llowrey commented 1 year ago

I had a GPU installed in this machine and was able to run cudaplot successfully. Unfortunately, the GPU failed and I am waiting for a replacement. In the mean time, I decided to try plotting compressed plots using ramplot. It works fine with -z 0 but any value other than 0 (1-7) fails. Bellow is an example with -z 1.

Bladebit Chia Plotter
Version      : 3.0.0-alpha3
Git Commit   : eb6df030b555fb35addc3d6762424d52826a5d82
Compiled With: gcc 9.2.1

[Global Plotting Config]
 Will create plots indefinitely.
 Thread count          : 32
 Warm start enabled    : false
 NUMA disabled         : false
 CPU affinity disabled : false
 Farmer public key     : <farmer pk>
 Pool contract address : <contract address>
 Compression Level     : 1
 Benchmark mode        : disabled

System Memory: 502/503 GiB.
Memory required: 416 GiB.
Allocating buffers.

*** Crashed! ***
/home/llowrey/bladebit_cuda[0x4c7cb5]
/lib64/libc.so.6(+0x3cb20)[0x7fb03f659b20]
/lib64/libc.so.6(+0x16e82e)[0x7fb03f78b82e]
/home/llowrey/bladebit_cuda[0x408376]
/lib64/libc.so.6(+0x27510)[0x7fb03f644510]
/lib64/libc.so.6(__libc_start_main+0x89)[0x7fb03f6445c9]
/home/llowrey/bladebit_cuda[0x40963e]
Dumping crash to crash.log

CPU: Dual Opteron 16-core (4 numa nodes) RAM: 512GB DDR3 ECC OS: Fedora 37 Kernel: 6.1.15-200.fc37.x86_64

cuda-12.1.0-1.x86_64
cuda-12-1-12.1.0-1.x86_64
cuda-cccl-12-1-12.1.55-1.x86_64
cuda-command-line-tools-12-1-12.1.0-1.x86_64
cuda-compiler-12-1-12.1.0-1.x86_64
cuda-cudart-12-1-12.1.55-1.x86_64
cuda-cudart-devel-12-1-12.1.55-1.x86_64
cuda-cuobjdump-12-1-12.1.55-1.x86_64
cuda-cupti-12-1-12.1.62-1.x86_64
cuda-cuxxfilt-12-1-12.1.55-1.x86_64
cuda-demo-suite-12-1-12.1.55-1.x86_64
cuda-documentation-12-1-12.1.55-1.x86_64
cuda-driver-devel-12-1-12.1.55-1.x86_64
cuda-drivers-530.30.02-1.x86_64
cuda-gdb-12-1-12.1.55-1.x86_64
cuda-libraries-12-1-12.1.0-1.x86_64
cuda-libraries-devel-12-1-12.1.0-1.x86_64
cuda-nsight-12-1-12.1.55-1.x86_64
cuda-nsight-compute-12-1-12.1.0-1.x86_64
cuda-nsight-systems-12-1-12.1.0-1.x86_64
cuda-nvcc-12-1-12.1.66-1.x86_64
cuda-nvdisasm-12-1-12.1.55-1.x86_64
cuda-nvml-devel-12-1-12.1.55-1.x86_64
cuda-nvprof-12-1-12.1.55-1.x86_64
cuda-nvprune-12-1-12.1.55-1.x86_64
cuda-nvrtc-12-1-12.1.55-1.x86_64
cuda-nvrtc-devel-12-1-12.1.55-1.x86_64
cuda-nvtx-12-1-12.1.66-1.x86_64
cuda-nvvp-12-1-12.1.55-1.x86_64
cuda-opencl-12-1-12.1.56-1.x86_64
cuda-opencl-devel-12-1-12.1.56-1.x86_64
cuda-profiler-api-12-1-12.1.55-1.x86_64
cuda-runtime-12-1-12.1.0-1.x86_64
cuda-sanitizer-12-1-12.1.55-1.x86_64
cuda-toolkit-12-1-12.1.0-1.x86_64
cuda-toolkit-12-1-config-common-12.1.55-1.noarch
cuda-toolkit-12-config-common-12.1.55-1.noarch
cuda-toolkit-config-common-12.1.55-1.noarch
cuda-tools-12-1-12.1.0-1.x86_64
cuda-visual-tools-12-1-12.1.0-1.x86_64
kmod-nvidia-latest-dkms-530.30.02-1.fc37.x86_64
nvidia-driver-530.30.02-1.fc37.x86_64
nvidia-driver-cuda-530.30.02-1.fc37.x86_64
nvidia-driver-cuda-libs-530.30.02-1.fc37.x86_64
nvidia-driver-devel-530.30.02-1.fc37.x86_64
nvidia-driver-libs-530.30.02-1.fc37.x86_64
nvidia-driver-NvFBCOpenGL-530.30.02-1.fc37.x86_64
nvidia-driver-NVML-530.30.02-1.fc37.x86_64
nvidia-gpu-firmware-20230210-147.fc37.noarch
nvidia-kmod-common-530.30.02-1.fc37.noarch
nvidia-libXNVCtrl-530.30.02-1.fc37.x86_64
nvidia-libXNVCtrl-devel-530.30.02-1.fc37.x86_64
nvidia-modprobe-530.30.02-1.fc37.x86_64
nvidia-persistenced-530.30.02-1.fc37.x86_64
nvidia-settings-530.30.02-1.fc37.x86_64
nvidia-xconfig-530.30.02-1.fc37.x86_64