Skip to content

Commit 1c9a333

Browse files
gfursingfursin
committed
Version 5.0.15
1 parent 726643a commit 1c9a333

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

80 files changed

+17100
-2
lines changed

‎LICENSE.md

Lines changed: 177 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,177 @@
1+
2+
Apache License
3+
Version 2.0, January 2004
4+
http://www.apache.org/licenses/
5+
6+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7+
8+
1. Definitions.
9+
10+
"License" shall mean the terms and conditions for use, reproduction,
11+
and distribution as defined by Sections 1 through 9 of this document.
12+
13+
"Licensor" shall mean the copyright owner or entity authorized by
14+
the copyright owner that is granting the License.
15+
16+
"Legal Entity" shall mean the union of the acting entity and all
17+
other entities that control, are controlled by, or are under common
18+
control with that entity. For the purposes of this definition,
19+
"control" means (i) the power, direct or indirect, to cause the
20+
direction or management of such entity, whether by contract or
21+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
22+
outstanding shares, or (iii) beneficial ownership of such entity.
23+
24+
"You" (or "Your") shall mean an individual or Legal Entity
25+
exercising permissions granted by this License.
26+
27+
"Source" form shall mean the preferred form for making modifications,
28+
including but not limited to software source code, documentation
29+
source, and configuration files.
30+
31+
"Object" form shall mean any form resulting from mechanical
32+
transformation or translation of a Source form, including but
33+
not limited to compiled object code, generated documentation,
34+
and conversions to other media types.
35+
36+
"Work" shall mean the work of authorship, whether in Source or
37+
Object form, made available under the License, as indicated by a
38+
copyright notice that is included in or attached to the work
39+
(an example is provided in the Appendix below).
40+
41+
"Derivative Works" shall mean any work, whether in Source or Object
42+
form, that is based on (or derived from) the Work and for which the
43+
editorial revisions, annotations, elaborations, or other modifications
44+
represent, as a whole, an original work of authorship. For the purposes
45+
of this License, Derivative Works shall not include works that remain
46+
separable from, or merely link (or bind by name) to the interfaces of,
47+
the Work and Derivative Works thereof.
48+
49+
"Contribution" shall mean any work of authorship, including
50+
the original version of the Work and any modifications or additions
51+
to that Work or Derivative Works thereof, that is intentionally
52+
submitted to Licensor for inclusion in the Work by the copyright owner
53+
or by an individual or Legal Entity authorized to submit on behalf of
54+
the copyright owner. For the purposes of this definition, "submitted"
55+
means any form of electronic, verbal, or written communication sent
56+
to the Licensor or its representatives, including but not limited to
57+
communication on electronic mailing lists, source code control systems,
58+
and issue tracking systems that are managed by, or on behalf of, the
59+
Licensor for the purpose of discussing and improving the Work, but
60+
excluding communication that is conspicuously marked or otherwise
61+
designated in writing by the copyright owner as "Not a Contribution."
62+
63+
"Contributor" shall mean Licensor and any individual or Legal Entity
64+
on behalf of whom a Contribution has been received by Licensor and
65+
subsequently incorporated within the Work.
66+
67+
2. Grant of Copyright License. Subject to the terms and conditions of
68+
this License, each Contributor hereby grants to You a perpetual,
69+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70+
copyright license to reproduce, prepare Derivative Works of,
71+
publicly display, publicly perform, sublicense, and distribute the
72+
Work and such Derivative Works in Source or Object form.
73+
74+
3. Grant of Patent License. Subject to the terms and conditions of
75+
this License, each Contributor hereby grants to You a perpetual,
76+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77+
(except as stated in this section) patent license to make, have made,
78+
use, offer to sell, sell, import, and otherwise transfer the Work,
79+
where such license applies only to those patent claims licensable
80+
by such Contributor that are necessarily infringed by their
81+
Contribution(s) alone or by combination of their Contribution(s)
82+
with the Work to which such Contribution(s) was submitted. If You
83+
institute patent litigation against any entity (including a
84+
cross-claim or counterclaim in a lawsuit) alleging that the Work
85+
or a Contribution incorporated within the Work constitutes direct
86+
or contributory patent infringement, then any patent licenses
87+
granted to You under this License for that Work shall terminate
88+
as of the date such litigation is filed.
89+
90+
4. Redistribution. You may reproduce and distribute copies of the
91+
Work or Derivative Works thereof in any medium, with or without
92+
modifications, and in Source or Object form, provided that You
93+
meet the following conditions:
94+
95+
(a) You must give any other recipients of the Work or
96+
Derivative Works a copy of this License; and
97+
98+
(b) You must cause any modified files to carry prominent notices
99+
stating that You changed the files; and
100+
101+
(c) You must retain, in the Source form of any Derivative Works
102+
that You distribute, all copyright, patent, trademark, and
103+
attribution notices from the Source form of the Work,
104+
excluding those notices that do not pertain to any part of
105+
the Derivative Works; and
106+
107+
(d) If the Work includes a "NOTICE" text file as part of its
108+
distribution, then any Derivative Works that You distribute must
109+
include a readable copy of the attribution notices contained
110+
within such NOTICE file, excluding those notices that do not
111+
pertain to any part of the Derivative Works, in at least one
112+
of the following places: within a NOTICE text file distributed
113+
as part of the Derivative Works; within the Source form or
114+
documentation, if provided along with the Derivative Works; or,
115+
within a display generated by the Derivative Works, if and
116+
wherever such third-party notices normally appear. The contents
117+
of the NOTICE file are for informational purposes only and
118+
do not modify the License. You may add Your own attribution
119+
notices within Derivative Works that You distribute, alongside
120+
or as an addendum to the NOTICE text from the Work, provided
121+
that such additional attribution notices cannot be construed
122+
as modifying the License.
123+
124+
You may add Your own copyright statement to Your modifications and
125+
may provide additional or different license terms and conditions
126+
for use, reproduction, or distribution of Your modifications, or
127+
for any such Derivative Works as a whole, provided Your use,
128+
reproduction, and distribution of the Work otherwise complies with
129+
the conditions stated in this License.
130+
131+
5. Submission of Contributions. Unless You explicitly state otherwise,
132+
any Contribution intentionally submitted for inclusion in the Work
133+
by You to the Licensor shall be under the terms and conditions of
134+
this License, without any additional terms or conditions.
135+
Notwithstanding the above, nothing herein shall supersede or modify
136+
the terms of any separate license agreement you may have executed
137+
with Licensor regarding such Contributions.
138+
139+
6. Trademarks. This License does not grant permission to use the trade
140+
names, trademarks, service marks, or product names of the Licensor,
141+
except as required for reasonable and customary use in describing the
142+
origin of the Work and reproducing the content of the NOTICE file.
143+
144+
7. Disclaimer of Warranty. Unless required by applicable law or
145+
agreed to in writing, Licensor provides the Work (and each
146+
Contributor provides its Contributions) on an "AS IS" BASIS,
147+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148+
implied, including, without limitation, any warranties or conditions
149+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150+
PARTICULAR PURPOSE. You are solely responsible for determining the
151+
appropriateness of using or redistributing the Work and assume any
152+
risks associated with Your exercise of permissions under this License.
153+
154+
8. Limitation of Liability. In no event and under no legal theory,
155+
whether in tort (including negligence), contract, or otherwise,
156+
unless required by applicable law (such as deliberate and grossly
157+
negligent acts) or agreed to in writing, shall any Contributor be
158+
liable to You for damages, including any direct, indirect, special,
159+
incidental, or consequential damages of any character arising as a
160+
result of this License or out of the use or inability to use the
161+
Work (including but not limited to damages for loss of goodwill,
162+
work stoppage, computer failure or malfunction, or any and all
163+
other commercial damages or losses), even if such Contributor
164+
has been advised of the possibility of such damages.
165+
166+
9. Accepting Warranty or Additional Liability. While redistributing
167+
the Work or Derivative Works thereof, You may choose to offer,
168+
and charge a fee for, acceptance of support, warranty, indemnity,
169+
or other liability obligations and/or rights consistent with this
170+
License. However, in accepting such obligations, You may act only
171+
on Your own behalf and on Your sole responsibility, not on behalf
172+
of any other Contributor, and only if You agree to indemnify,
173+
defend, and hold each Contributor harmless for any liability
174+
incurred by, or claims asserted against, such Contributor by reason
175+
of your accepting any such warranty or additional liability.
176+
177+
END OF TERMS AND CONDITIONS

‎README.md

Lines changed: 174 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,174 @@
1-
# mlperf-loadgen
2-
Minimal copy of the MLPerf loadgen
1+
*This is a minimal copy of the MLPerf loadgen tool,
2+
extracted from the [inference repository](https://github.com/mlcommons/inference)
3+
to reduce size.*
4+
5+
# Overview {#mainpage}
6+
7+
## Introduction
8+
9+
* The LoadGen is a *reusable* module that *efficiently* and *fairly* measures
10+
the performance of inference systems.
11+
* It generates traffic for scenarios as formulated by a diverse set of experts
12+
in the [MLCommons working group](https://mlcommons.org/).
13+
* The scenarios emulate the workloads seen in mobile devices,
14+
autonomous vehicles, robotics, and cloud-based setups.
15+
* Although the LoadGen is not model or dataset aware, its strength is in its
16+
reusability with logic that is.
17+
18+
## Integration Example and Flow
19+
The following is an diagram of how the LoadGen can be integrated into an
20+
inference system, resembling how some of the MLPerf reference models are
21+
implemented.
22+
<div style="display:flex; flex-flow:row wrap; justify-content: space-evenly;">
23+
<img src="https://raw.githubusercontent.com/mlcommons/inference/master/loadgen/loadgen_integration_diagram.svg" width="500px" style="padding: 20px">
24+
<ol style="padding: 20px">
25+
<li>Benchmark knows the model, dataset, and preprocessing.</li>
26+
<li>Benchmark hands dataset sample IDs to LoadGen.</li>
27+
<li>LoadGen starts generating queries of sample IDs.</li>
28+
<li>Benchmark creates requests to backend.</li>
29+
<li>Result is post processed and forwarded to LoadGen.</li>
30+
<li>LoadGen outputs logs for analysis.<br>
31+
</ol>
32+
</div>
33+
34+
## Useful Links
35+
* [FAQ](README_FAQ.md)
36+
* [LoadGen Build Instructions](README_BUILD.md)
37+
* [LoadGen API](loadgen.h)
38+
* [Test Settings](test_settings.h) -
39+
A good description of available scenarios, modes, and knobs.
40+
* [MLPerf Inference Code](https://github.com/mlcommons/inference) -
41+
Includes source for the LoadGen and reference models that use the LoadGen.
42+
* [MLPerf Inference Rules](https://github.com/mlcommons/inference_policies) -
43+
Any mismatch with this is a bug in the LoadGen.
44+
45+
## Scope of the LoadGen's Responsibilities
46+
47+
### In Scope
48+
* **Provide a reusable** C++ library with python bindings.
49+
* **Implement** the traffic patterns of the MLPerf Inference scenarios and
50+
modes.
51+
* **Record** all traffic generated and received for later analysis and
52+
verification.
53+
* **Summarize** the results and whether performance constraints were met.
54+
* **Target high-performance** systems with efficient multi-thread friendly
55+
logging utilities.
56+
* **Generate trust** via a shared, well-tested, and community-hardened
57+
code base.
58+
59+
### Out of Scope
60+
The LoadGen is:
61+
* **NOT** aware of the ML model it is running against.
62+
* **NOT** aware of the data formats of the model's inputs and outputs.
63+
* **NOT** aware of how to score the accuracy of a model's outputs.
64+
* **NOT** aware of MLPerf rules regarding scenario-specific constraints.
65+
66+
Limitting the scope of the LoadGen in this way keeps it reusable across
67+
different models and datasets without modification. Using composition and
68+
dependency injection, the user can define their own model, datasets, and
69+
metrics.
70+
71+
Additionally, not hardcoding MLPerf-specific test constraints, like test
72+
duration and performance targets, allows users to use the LoadGen unmodified
73+
for custom testing and continuous integration purposes.
74+
75+
## Submission Considerations
76+
77+
### Upstream all local modifications
78+
* As a rule, no local modifications to the LoadGen's C++ library are allowed
79+
for submission.
80+
* Please upstream early and often to keep the playing field level.
81+
82+
### Choose your TestSettings carefully!
83+
* Since the LoadGen is oblivious to the model, it can't enforce the MLPerf
84+
requirements for submission. *e.g.:* target percentiles and latencies.
85+
* For verification, the values in TestSettings are logged.
86+
* To help make sure your settings are spec compliant, use
87+
TestSettings::FromConfig in conjunction with the relevant config file provided
88+
with the reference models.
89+
90+
## Responsibilities of a LoadGen User
91+
92+
### Implement the Interfaces
93+
* Implement the SystemUnderTest and QuerySampleLibrary interfaces and pass
94+
them to the StartTest function.
95+
* Call QuerySampleComplete for every sample received by
96+
SystemUnderTest::IssueQuery.
97+
98+
### Assess Accuracy
99+
* Process the *mlperf_log_accuracy.json* output by the LoadGen to determine
100+
the accuracy of your system.
101+
* For the official models, Python scripts will be provided by the MLPerf model
102+
owners for you to do this automatically.
103+
104+
For templates of how to do the above in detail, refer to code for the demos,
105+
tests, and reference models.
106+
107+
108+
## LoadGen over the Network
109+
110+
For reference, on a high level a submission looks like this:
111+
112+
<div align="center" style="display:flex; flex-flow:row wrap; justify-content: space-evenly;">
113+
<img src="https://raw.githubusercontent.com/mlcommons/inference/master/loadgen/diagram_submission.png" width="300px" style="padding: 20px">
114+
</div>
115+
116+
The LoadGen implementation is common to all submissions, while the QSL (“Query Sample Library”) and SUT (“System Under Test”) are implemented by submitters. QSL is responsible for loading the data and includes untimed preprocessing.
117+
118+
A submission over the network introduces a new component “QDL” (query dispatch library) that is added to the system as presented in the following diagram:
119+
120+
<div align="center" style="display:flex; flex-flow:row wrap; justify-content: space-evenly;">
121+
<img src="https://raw.githubusercontent.com/mlcommons/inference/master/loadgen/diagram_network_submission.png" width="300px" style="padding: 20px">
122+
</div>
123+
124+
QDL is a proxy for a load-balancer, that dispatches queries to SUT over a physical network, receives the responses and passes them back to LoadGen. It is implemented by the submitter. The interface of the QDL is the same as the API to SUT.
125+
126+
In scenarios using QDL, data may be compressed in QSL at the choice of the submitter in order to reduce network transmission time. Decompression is part of the timed processing in SUT. A set of approved standard compression schemes will be specified for each benchmark; additional compression schemes must be approved in advance by the Working Group.
127+
128+
All communication between LoadGen/QSL and SUT is via QDL, and all communication between QDL and SUT must pass over a physical network.
129+
130+
QDL implements the protocol to transmit queries over the network and receive responses. It also implements decompression of any response returned by the SUT, where compression of responses is allowed. Performing any part of the timed preprocessing or inference in QDL is specifically disallowed. Currently no batching is allowed in QDL, although this may be revisited in future.
131+
132+
The MLperf over the Network will run in Server mode and Offline mode. All LoadGen modes are expected to work as is with insignificant changes. These include running the test in performance mode, accuracy mode, find peak performance mode and compliance mode. The same applies for power measurements.
133+
134+
### QDL details
135+
The Query Dispatch Library is implemented by the submitter and interfaces with LoadGen using the same SUT API. All MLPerf Inference SUTs implement the `mlperf::SystemUnderTest` class which is defined in system_under_test.h. The QDL implements `mlperf::QueryDispatchLibrary` class which inherits the `mlperf::SystemUnderTest` class and has the same API and support all existing `mlperf::SystemUnderTest` methods. It has a separate header file query_dispatch_library.h. Using sut with `mlperf::SystemUnderTest` class in LoadGen StartTest is natively upcasting `mlperf::QueryDispatchLibrary` class.
136+
137+
#### QDL Query issue and response over the network
138+
139+
The QDL gets the queries from the LoadGen through
140+
```CPP
141+
void IssueQuery(const std::vector<QuerySample>& samples)
142+
```
143+
144+
The QDL dispatches the queries to the SUT over the physical media. The exact method and implementation for it are submitter specific and would not be specified at MLCommons. Submitter implementation includes all methods required to serialize the query, load balance, drive it to the Operating system and network interface card and send to the SUT.
145+
146+
The QDL receives the query responses over the network from the SUT. The exact method and implementation for it are submitter specific and would not be specified at MLCommons. The submitter implementation includes all methods required to receive the network data from the Network Interface card, go through the Operating system, deserialize the query response, and provide it back to the LoadGen through query completion by:
147+
148+
```CPP
149+
struct QuerySampleResponse {
150+
ResponseId id;
151+
uintptr_t data;
152+
size_t size;
153+
};
154+
void QuerySamplesComplete(QuerySampleResponse* responses,
155+
size_t response_count);
156+
157+
```
158+
159+
#### QDL Additional Methods
160+
161+
In addition to that the QDL needs to implement the following methods that are provided by the SUT interface to the LoadGen:
162+
```CPP
163+
const std::string& Name();
164+
```
165+
The `Name` function returns a known string for over the Network SUTs to identify it as over the network benchmark.
166+
```CPP
167+
void FlushQueries();
168+
```
169+
170+
It is not specified here how the QDL would query and configure the SUT to execute the above methods. The QDL responds to the LoadGen after receiving its own response from the SUT.
171+
172+
### Example
173+
174+
Refer to [LON demo](demos/lon) for a reference example illustrating usage of Loadgen over the network.

‎inference/loadgen/.clang-format

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
BasedOnStyle: Google
2+
Standard: Cpp11

0 commit comments

Comments
 (0)