Closed hugocth closed 3 years ago
You may be using the x86 version. Please try using aarch64 version. ARM support was added starting NVBit version 1.3.1.
I'll update the NVBitFI instructions to reflect this change.
Thank you for your quick answer ! I'll try late and I'll update you.
Hi @sivahari, I tried both @hugocth and your ararch64 version but, got the same error as follows:
Step 0 (3): Build the nvbitfi injector and profiler tools
nvcc -ccbin=which gcc
-D_FORCE_INLINES -I../../../core -I../common -maxrregcount=16 -Xptxas -astoolspatch --keep-device-functions -arch=sm_35 -DDUMMY=0 -Xcompiler -Wall -Xcompiler -fPIC -c inject_funcs.cu -o inject_funcs.o
nvcc -ccbin=which gcc
-D_FORCE_INLINES -dc -c -std=c++11 -I../../../core -I../common -Xptxas -cloning=no -Xcompiler -Wall -arch=sm_35 -O3 -Xcompiler -fPIC injector.cu -o injector.o
nvcc -ccbin=which gcc
-D_FORCE_INLINES -arch=sm_35 -O3 inject_funcs.o injector.o -L../../../core -lnvbit -L/usr/local/cuda/lib64 -lcuda -lcudart_static -shared -o injector.so
nvlink warning : Skipping incompatible '../../../core/libnvbit.a' when searching for -lnvbit
/usr/bin/ld: skipping incompatible ../../../core/libnvbit.a when searching for -lnvbit
/usr/bin/ld: cannot find -lnvbit
/usr/lib/gcc/x86_64-linux-gnu/7/../../../x86_64-linux-gnu/libcuda.so: file not recognized: File truncated
collect2: error: ld returned 1 exit status
Makefile:27: recipe for target 'injector.so' failed
make: *** [injector.so] Error 1
Is there anything that I am missing? This is my system configuration:
NVIDIA-SMI 450.119.04
Driver Version: 450.119.04
CUDA Version: 11.0
gcc version: 7.5.0
nvcc version: release 10.2, V10.2.89
GPU model: Tesla P100
Thank you.
Hello, I'm an engineering student trying to run this benchmark on a Jetson Nano. I run Ubuntu 18.04 and Cuda 10.2, however when I run test.sh (after succesfully havig completed the previous instructions in the README), I get these errors. Do you have any ideas how to fix it ? I tried to Google it and I didn't find anything concerning the -lnvbit module ... Thanks a lot by advance !