Can not compile rodinia_2.0-ft with cuda-12.8

[always-debug]

I am trying to compile rodinia_2.0-ft with cuda-12.8 within "gpu-app-collection" and facing the following error.
Does anyone have a solution for this?

Thanks

/usr/local/cuda/include/cuda_runtime_api.h:1169:46: note: declared here
 1169 | extern __CUDA_DEPRECATED __host__ cudaError_t CUDARTAPI cudaThreadSynchronize(void);
      |                                              ^~~~~~~~~~~~~~~~~~~~~
/usr/bin/ld: obj_12.6/x86_64/release/backprop_cuda.cu.o: relocation R_X86_64_32 against symbol `_Z22bpnn_layerforward_CUDAPfS_S_S_ii' can not be used when making a PIE object; recompile with -fPIE
/usr/bin/ld: failed to set dynamic section sizes: bad value
collect2: error: ld returned 1 exit status
make[1]: *** [../../../common/common.mk:471: /home/hoangt/WORK/CompArch/accel-sim/accel-sim-framework/gpu-app-collection/src/..//bin/12.6/release/backprop-rodinia-2.0-ft] Error 1
make[1]: Leaving directory '/media/hoangt/LINUX/CompArch/accel-sim/accel-sim-framework/gpu-app-collection/src/cuda/rodinia/2.0-ft/backprop'