nvapi gpu thermal info

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi everyone,
I wrote a code, using the library nvapi, in order to monitor the temperature of my graphics card (tesla k40m) when executing a kernel.

NvPhysicalGpuHandle phys[NVAPI_MAX_PHYSICAL_GPUS*2];

        ret = NvAPI_EnumTCCPhysicalGPUs(phys, &cnt);

        if (ret != NVAPI_OK){
            NvAPI_ShortString string;
            NvAPI_GetErrorMessage(ret, string);
    	}

        NvAPI_ShortString name;
    	
        NV_GPU_THERMAL_SETTINGS thermal;

        ret = NvAPI_GPU_GetFullName(*phys, name);
        if (ret != NVAPI_OK){
            NvAPI_ShortString string;
            NvAPI_GetErrorMessage(ret, string);
            //printf("NVAPI NvAPI_GPU_GetFullName: %s\n", string);
        }

        //printf("Name: %s\n", name);
        thermal.version = NV_GPU_THERMAL_SETTINGS_VER;
        ret = NvAPI_GPU_GetThermalSettings(*phys,0, &thermal);

        if (ret != NVAPI_OK){
            NvAPI_ShortString string;
            NvAPI_GetErrorMessage(ret, string);
            //printf("NVAPI NvAPI_GPU_GetThermalSettings: %s\n", string);
        }

        return thermal.sensor[0].currentTemp;

My problem is that I get output values that are very different from those of other test software found online (like gpu-z).
What am I doing wrong?

Thanks in advance

Domenico