make test use simulation mode

Author: benvanwerkhoven

kernel_tuner/energy/energy.py

@@ -41,7 +41,7 @@
 }
 """
 
-def get_frequency_power_relation_fp32(device, n_samples=10, nvidia_smi_fallback=None, use_locked_clocks=False, cache=None):
+def get_frequency_power_relation_fp32(device, n_samples=10, nvidia_smi_fallback=None, use_locked_clocks=False, cache=None, simulation_mode=None):
     """ Use NVML and PyCUDA with a synthetic kernel to obtain samples of frequency-power pairs """
 
     # get some numbers about the device
@@ -85,7 +85,7 @@ def get_frequency_power_relation_fp32(device, n_samples=10, nvidia_smi_fallback=
 
     results, _ = tune_kernel("fp32_kernel", fp32_kernel_string, problem_size=(multiprocessor_count, 64),
                              arguments=arguments, tune_params=tune_params, observers=[nvmlobserver],
-                             verbose=False, quiet=True, metrics=metrics, iterations=10,
+                             verbose=False, quiet=True, metrics=metrics, iterations=10, simulation_mode=simulation_mode,
                              grid_div_x=[], grid_div_y=[], cache=cache or f"synthetic_fp32_cache_{device_name}.json")
 
     freqs = np.array([res["core_freq"] for res in results])
@@ -147,7 +147,7 @@ def fit_power_frequency_model(freqs, nvml_power):
     return clock_threshold + clock_min, fit_parameters, scale_parameters
 
 
-def create_power_frequency_model(device=0, n_samples=10, verbose=False, nvidia_smi_fallback=None, use_locked_clocks=False, cache=None):
+def create_power_frequency_model(device=0, n_samples=10, verbose=False, nvidia_smi_fallback=None, use_locked_clocks=False, cache=None, simulation_mode=None):
     """ Calculate the most energy-efficient clock frequency of device
 
     This function uses a performance model to fit the power-frequency curve
@@ -181,7 +181,7 @@ def create_power_frequency_model(device=0, n_samples=10, verbose=False, nvidia_s
     :rtype: float
 
     """
-    freqs, nvml_power = get_frequency_power_relation_fp32(device, n_samples, nvidia_smi_fallback, use_locked_clocks, cache=cache)
+    freqs, nvml_power = get_frequency_power_relation_fp32(device, n_samples, nvidia_smi_fallback, use_locked_clocks, cache=cache, simulation_mode=simulation_mode)
 
     if verbose:
         print("Clock frequencies:", freqs.tolist())

test/test_energy.py

@@ -5,9 +5,9 @@
 
 cache_filename = os.path.dirname(os.path.realpath(__file__)) + "/synthetic_fp32_cache_NVIDIA_RTX_A4000.json"
 
-@skip_if_no_pycuda
+
 def test_create_power_frequency_model():
 
-    ridge_frequency, freqs, nvml_power, fitted_params, scaling = energy.create_power_frequency_model(cache=cache_filename)
+    ridge_frequency, freqs, nvml_power, fitted_params, scaling = energy.create_power_frequency_model(cache=cache_filename, simulation_mode=True)
     assert ridge_frequency == 1350