This page was generated from docs/examples/DataSet/Benchmarking.ipynb. Interactive online version: . View in nbviewer.

Dataset Benchmarking

This notebook is a behind-the-scenes benchmarking notebook, mainly for use by developers. The recommended way for users to interact with the dataset is via the Measurement object and its associated context manager. See the corresponding notebook for a comprehensive toturial on how to use those.

%matplotlib inline
from pathlib import Path

import numpy as np

import qcodes as qc
from qcodes.dataset import (
    ParamSpec,
    initialise_or_create_database_at,
    load_or_create_experiment,
    new_data_set,
)

qc.config.core.db_location

'~/experiments.db'

initialise_or_create_database_at(
    Path.cwd().parent / "example_output" / "benchmarking.db"
)

Setup

exp = load_or_create_experiment("benchmarking", sample_name="the sample is a lie")
exp

benchmarking#the sample is a lie#1@/home/runner/work/Qcodes/Qcodes/docs/examples/example_output/benchmarking.db
---------------------------------------------------------------------------------------------------------------

Now we can create a dataset. Note two things:

- if we don't specfiy a exp_id, but we have an experiment in the experiment container the dataset will go into that one.
- dataset can be created from the experiment object

dataSet = new_data_set("benchmark_data", exp_id=exp.exp_id)
exp

benchmarking#the sample is a lie#1@/home/runner/work/Qcodes/Qcodes/docs/examples/example_output/benchmarking.db
---------------------------------------------------------------------------------------------------------------
1-benchmark_data-1-None-0

In this benchmark we will assueme that we are doing a 2D loop and investigate the performance implications of writing to the dataset

x_shape = 100
y_shape = 100

Baseline: Generate data

%%time
for x in range(x_shape):
    for y in range(y_shape):
        z = np.random.random_sample(1)

CPU times: user 8.2 ms, sys: 3.03 ms, total: 11.2 ms
Wall time: 11.1 ms

and store in memory

x_data = np.zeros((x_shape, y_shape))
y_data = np.zeros((x_shape, y_shape))
z_data = np.zeros((x_shape, y_shape))

%%time
for x in range(x_shape):
    for y in range(y_shape):
        x_data[x, y] = x
        y_data[x, y] = y
        z_data[x, y] = np.random.random_sample()

CPU times: user 8.2 ms, sys: 24 μs, total: 8.22 ms
Wall time: 8.36 ms

Add to dataset inside double loop

double_dataset = new_data_set(
    "doubledata",
    exp_id=exp.exp_id,
    specs=[
        ParamSpec("x", "numeric"),
        ParamSpec("y", "numeric"),
        ParamSpec("z", "numeric"),
    ],
)
double_dataset.mark_started()

Note that this is so slow that we are only doing a 10th of the computation

%%time
for x in range(x_shape // 10):
    for y in range(y_shape):
        double_dataset.add_results([{"x": x, "y": y, "z": np.random.random_sample()}])

CPU times: user 171 ms, sys: 72.9 ms, total: 243 ms
Wall time: 554 ms

Add the data in outer loop and store as np array

single_dataset = new_data_set(
    "singledata",
    exp_id=exp.exp_id,
    specs=[ParamSpec("x", "array"), ParamSpec("y", "array"), ParamSpec("z", "array")],
)
single_dataset.mark_started()
x_data = np.zeros(y_shape)
y_data = np.zeros(y_shape)
z_data = np.zeros(y_shape)

%%time
for x in range(x_shape):
    for y in range(y_shape):
        x_data[y] = x
        y_data[y] = y
        z_data[y] = np.random.random_sample(1)
    single_dataset.add_results([{"x": x_data, "y": y_data, "z": z_data}])

CPU times: user 50.9 ms, sys: 4.77 ms, total: 55.7 ms
Wall time: 98.3 ms

<timed exec>:5: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)

Save once after loop

zero_dataset = new_data_set(
    "zerodata",
    exp_id=exp.exp_id,
    specs=[ParamSpec("x", "array"), ParamSpec("y", "array"), ParamSpec("z", "array")],
)
zero_dataset.mark_started()
x_data = np.zeros((x_shape, y_shape))
y_data = np.zeros((x_shape, y_shape))
z_data = np.zeros((x_shape, y_shape))

%%time
for x in range(x_shape):
    for y in range(y_shape):
        x_data[x, y] = x
        y_data[x, y] = y
        z_data[x, y] = np.random.random_sample(1)
zero_dataset.add_results([{"x": x_data, "y": y_data, "z": z_data}])

CPU times: user 38.9 ms, sys: 829 μs, total: 39.7 ms
Wall time: 39.7 ms

<timed exec>:5: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)

Array parameter

array1D_dataset = new_data_set(
    "array1Ddata",
    exp_id=exp.exp_id,
    specs=[ParamSpec("x", "array"), ParamSpec("y", "array"), ParamSpec("z", "array")],
)
array1D_dataset.mark_started()
y_setpoints = np.arange(y_shape)

%%timeit
for x in range(x_shape):
    x_data[x, :] = x
    array1D_dataset.add_results(
        [{"x": x_data[x, :], "y": y_setpoints, "z": np.random.random_sample(y_shape)}]
    )

39.2 ms ± 1.75 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

x_data = np.zeros((x_shape, y_shape))
y_data = np.zeros((x_shape, y_shape))
z_data = np.zeros((x_shape, y_shape))
y_setpoints = np.arange(y_shape)

array0D_dataset = new_data_set(
    "array0Ddata",
    exp_id=exp.exp_id,
    specs=[ParamSpec("x", "array"), ParamSpec("y", "array"), ParamSpec("z", "array")],
)
array0D_dataset.mark_started()

%%timeit
for x in range(x_shape):
    x_data[x, :] = x
    y_data[x, :] = y_setpoints
    z_data[x, :] = np.random.random_sample(y_shape)
array0D_dataset.add_results([{"x": x_data, "y": y_data, "z": z_data}])

1.87 ms ± 51.2 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)

Insert many

data = []
for i in range(100):
    for j in range(100):
        data.append({"x": i, "y": j, "z": np.random.random_sample()})

many_Data = new_data_set(
    "many_data",
    exp_id=exp.exp_id,
    specs=[
        ParamSpec("x", "numeric"),
        ParamSpec("y", "numeric"),
        ParamSpec("z", "numeric"),
    ],
)
many_Data.mark_started()

%%timeit
many_Data.add_results(data)

18.4 ms ± 179 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)