| /external/mesa3d/src/gallium/drivers/nouveau/ci/ |
| D | nouveau-nv49-fails.txt | 777 deqp-gles2@performance@compiler@cache@lighting@point_8_lights_fragment,Fail
778 deqp-gles2@performance@compiler@valid_shader@lighting@point_8_lights_fragment,Fail
779 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@fragment@highp_float,Fail
780 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@fragment@lowp_float,Fail
781 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@fragment@mediump_float,Fail
782 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@vertex@highp_float,Fail
783 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@vertex@lowp_float,Fail
784 deqp-gles2@performance@shader@operator@angle_and_trigonometry@acos@vertex@mediump_float,Fail
785 deqp-gles2@performance@shader@operator@angle_and_trigonometry@asin@fragment@highp_float,Fail
786 deqp-gles2@performance@shader@operator@angle_and_trigonometry@asin@fragment@lowp_float,Fail
[all …]
|
| /external/deqp/android/cts/main/vk-main-2024-03-01/shader-object/ |
| D | performance.txt | 1 dEQP-VK.shader_object.performance.binary_bind_shaders
2 dEQP-VK.shader_object.performance.binary_memcpy
3 dEQP-VK.shader_object.performance.binary_shader_create
4 dEQP-VK.shader_object.performance.dispatch
5 dEQP-VK.shader_object.performance.dispatch_base
6 dEQP-VK.shader_object.performance.dispatch_indirect
7 dEQP-VK.shader_object.performance.draw_binary_shaders
8 dEQP-VK.shader_object.performance.draw_dynamic_pipeline
9 dEQP-VK.shader_object.performance.draw_indexed_binary_shaders
10 dEQP-VK.shader_object.performance.draw_indexed_dynamic_pipeline
[all …]
|
| /external/sdv/vsomeip/third_party/boost/spirit/doc/karma/ |
| D | numeric_performance.qbk | 9 [section:numeric_performance Performance of Numeric Generators]
11 [section:int_performance Comparing the performance of a single int_ generator]
13 These performance measurements are centered around default formatting of a
18 For the full source code of the performance test please see here:
25 Code used to measure the performance for `ltoa`:
29 Code used to measure the performance for standard C++ iostreams:
33 Code used to measure the performance for __boost_format__:
37 Code used to measure the performance for __karma__ using a plain character buffer:
41 The following table shows the overall performance results collected
47 [table Performance comparison for a single int (all times in [s], `1e7` iterations)
[all …]
|
| /external/coreboot/src/vendorcode/intel/edk2/edk2-stable202302/MdePkg/Include/Library/ |
| D | PerformanceLib.h | 13 /// Performance library propery mask bits
57 Creates a record for the beginning of a performance measurement.
87 Fills in the end time of a performance measurement.
119 Attempts to retrieve a performance measurement log entry from the performance measurement log.
123 Attempts to retrieve the performance log entry specified by LogEntryKey. If LogEntryKey is
124 zero on entry, then an attempt is made to retrieve the first entry from the performance log,
125 and the key for the second entry in the log is returned. If the performance log is empty,
126 then no entry is retrieved and zero is returned. If LogEntryKey is not zero, then the performance
129 …trieved and an implementation specific non-zero key value that specifies the end of the performance
131 is retrieved and zero is returned. In the cases where a performance log entry can be returned,
[all …]
|
| D | TimerLib.h | 2 Provides calibrated delay and performance counter services.
45 Retrieves the current value of a 64-bit free running performance counter.
48 performance counter counts by a larger increment, then the counter values
52 @return The current value of the free running performance counter.
62 Retrieves the 64-bit frequency in Hz and the range of performance counter
65 If StartValue is not NULL, then the value that the performance counter starts
67 EndValue is not NULL, then the value that the performance counter end with
69 frequency of the performance counter in Hz is always returned. If StartValue
70 is less than EndValue, then the performance counter counts up. If StartValue
71 is greater than EndValue, then the performance counter counts down. For
[all …]
|
| /external/perfetto/docs/contributing/ |
| D | perfetto-in-the-press.md | 7 - [Performance: Perfetto Traceviewer - MAD Skills](https://www.youtube.com/watch?v=phhLFicMacY)
8 "On this episode of the MAD Skills series on Performance, Android Performance Engineer Carmen Jacks…
9 - [Performance and optimisation on the Meta Quest Platform](https://m.facebook.com/RealityLabs/vide…
10 - [Performance testing through proportional traces
11 ](https://www.jviotti.com/2022/09/07/performance-testing-through-proportional-traces.html)
12 …Performance](https://www.twoscomplement.org/podcast/performance.mp3) An episode of the [Twoscomple…
15 difficult to find the root cause of performance problems. By leveraging traces,
20 to performance tests and finally in production."
21 …performance](https://devblogs.microsoft.com/performance-diagnostics/perfetto-tooling-for-analyzing…
|
| /external/coreboot/src/vendorcode/intel/edk2/UDK2017/MdePkg/Include/Library/ |
| D | PerformanceLib.h | 19 /// Performance library propery mask bits
24 Creates a record for the beginning of a performance measurement.
54 Fills in the end time of a performance measurement.
86 Attempts to retrieve a performance measurement log entry from the performance measurement log.
90 Attempts to retrieve the performance log entry specified by LogEntryKey. If LogEntryKey is
91 zero on entry, then an attempt is made to retrieve the first entry from the performance log,
92 and the key for the second entry in the log is returned. If the performance log is empty,
93 then no entry is retrieved and zero is returned. If LogEntryKey is not zero, then the performance
96 …trieved and an implementation specific non-zero key value that specifies the end of the performance
98 is retrieved and zero is returned. In the cases where a performance log entry can be returned,
[all …]
|
| D | TimerLib.h | 2 Provides calibrated delay and performance counter services.
51 Retrieves the current value of a 64-bit free running performance counter.
54 performance counter counts by a larger increment, then the counter values
58 @return The current value of the free running performance counter.
68 Retrieves the 64-bit frequency in Hz and the range of performance counter
71 If StartValue is not NULL, then the value that the performance counter starts
73 EndValue is not NULL, then the value that the performance counter end with
75 frequency of the performance counter in Hz is always returned. If StartValue
76 is less than EndValue, then the performance counter counts up. If StartValue
77 is greater than EndValue, then the performance counter counts down. For
[all …]
|
| /external/squashfs-tools/RELEASE-READMEs/ |
| D | PERFORMANCE.README | 1 GENERAL INFORMATION ON PERFORMANCE TESTS
4 The following performance tests were based on two file sets: the
7 The Ubuntu liveCD filesystem was used to test filesystem performance
9 CRAMFS filesystem performance could not be tested for this filesystem
11 CRAMFS performance against Squashfs, the liveCD filesystem from
20 1. Ubuntu liveCD performance tests
28 1.1 Performance tests from CDROM
30 1.1.1 Directory Lookup performance
40 1.1.2 Sequential I/O performance
50 1.1.3 Random I/O performance
[all …]
|
| /external/coreboot/src/vendorcode/intel/edk2/edk2-stable202005/MdePkg/Include/Library/ |
| D | TimerLib.h | 2 Provides calibrated delay and performance counter services.
45 Retrieves the current value of a 64-bit free running performance counter.
48 performance counter counts by a larger increment, then the counter values
52 @return The current value of the free running performance counter.
62 Retrieves the 64-bit frequency in Hz and the range of performance counter
65 If StartValue is not NULL, then the value that the performance counter starts
67 EndValue is not NULL, then the value that the performance counter end with
69 frequency of the performance counter in Hz is always returned. If StartValue
70 is less than EndValue, then the performance counter counts up. If StartValue
71 is greater than EndValue, then the performance counter counts down. For
[all …]
|
| D | PerformanceLib.h | 13 /// Performance library propery mask bits
57 Creates a record for the beginning of a performance measurement.
87 Fills in the end time of a performance measurement.
119 Attempts to retrieve a performance measurement log entry from the performance measurement log.
123 Attempts to retrieve the performance log entry specified by LogEntryKey. If LogEntryKey is
124 zero on entry, then an attempt is made to retrieve the first entry from the performance log,
125 and the key for the second entry in the log is returned. If the performance log is empty,
126 then no entry is retrieved and zero is returned. If LogEntryKey is not zero, then the performance
129 …trieved and an implementation specific non-zero key value that specifies the end of the performance
131 is retrieved and zero is returned. In the cases where a performance log entry can be returned,
[all …]
|
| /external/coreboot/src/vendorcode/intel/edk2/edk2-stable202111/MdePkg/Include/Library/ |
| D | TimerLib.h | 2 Provides calibrated delay and performance counter services.
45 Retrieves the current value of a 64-bit free running performance counter.
48 performance counter counts by a larger increment, then the counter values
52 @return The current value of the free running performance counter.
62 Retrieves the 64-bit frequency in Hz and the range of performance counter
65 If StartValue is not NULL, then the value that the performance counter starts
67 EndValue is not NULL, then the value that the performance counter end with
69 frequency of the performance counter in Hz is always returned. If StartValue
70 is less than EndValue, then the performance counter counts up. If StartValue
71 is greater than EndValue, then the performance counter counts down. For
[all …]
|
| D | PerformanceLib.h | 13 /// Performance library propery mask bits
57 Creates a record for the beginning of a performance measurement.
87 Fills in the end time of a performance measurement.
119 Attempts to retrieve a performance measurement log entry from the performance measurement log.
123 Attempts to retrieve the performance log entry specified by LogEntryKey. If LogEntryKey is
124 zero on entry, then an attempt is made to retrieve the first entry from the performance log,
125 and the key for the second entry in the log is returned. If the performance log is empty,
126 then no entry is retrieved and zero is returned. If LogEntryKey is not zero, then the performance
129 …trieved and an implementation specific non-zero key value that specifies the end of the performance
131 is retrieved and zero is returned. In the cases where a performance log entry can be returned,
[all …]
|
| /external/executorch/extension/benchmark/ |
| D | README.md | 3 …performance of models on Android and iOS devices. It supports various backend delegates and device…
13 …ing performance offline. [Android App](android/benchmark/) | [iOS App](apple/Benchmark/). Popular …
15 - **Performance Monitoring**: Stores results in a database with a dashboard for tracking performanc…
22 The ExecuTorch Benchmark Dashboard tracks performance metrics for various models across different b…
25 - Analyze performance differences between backend delegates (e.g., XNNPACK, CoreML, QNN, MPS) for t…
26 - Compare performance across different models.
27 - Track performance changes over time and across different commits.
31 - Observe performance trends over time to identify improvements or regressions.
34 - View detailed performance data through charts and graphs.
42 …laborate with the ExecuTorch team to debug performance issues and advance state-of-the-art (SOTA) …
[all …]
|
| /external/pytorch/benchmarks/dynamo/ |
| D | README.md | 21 ## GPU Performance Dashboard
24 Performance Dashboard](https://hud.pytorch.org/benchmark/compilers),
28 workflow generates the data in the performance dashboard. If you have the needed permissions, you …
39 An entry such as `2.38x → 2.41x` means that the performance improved
40 from `2.38x` in the base to `2.41x` in the new commit. All performance
44 ## CPU Performance Dashboard
46 The [TorchInductor CPU Performance
53 the performance dashboards can be found
62 - `--accuracy` or `--performance`: selects between checking correctness and measuring speedup (both…
81 As an example, the commands to run first line of the dashboard (performance only) would be:
[all …]
|
| /external/apache-xml/test/tests/contrib/xsltc/mk/ |
| D | mk028.xml | 4 <performance>
7 ever heard ... a singer to watch out for</quote>. </performance>
8 <performance>Other highlights include a
11 <role>Judas</role>,</performance> <performance>an acclaimed performance of
13 </performance> <performance>
16 by <artist>Stephen Layton</artist>, broadcast on Radio Three.</performance>
|
| D | mk029.xml | 4 <performance>
7 ever heard ... a singer to watch out for</quote>. </performance>
8 <performance>Other highlights include a
11 <role>Judas</role>,</performance> <performance>an acclaimed performance of
13 </performance> <performance>
16 by <artist>Stephen Layton</artist>, broadcast on Radio Three.</performance>
|
| /external/expat/testdata/largefiles/ |
| D | README.txt | 2 benchmark various aspects of Expat's performance.
12 - purpose: mostly for performance testing with the benchmark utility
18 - purpose: mostly for performance testing with the benchmark utility
24 - purpose: mostly for performance testing with the benchmark utility
30 - purpose: mostly for performance testing with the benchmark
37 - purpose: performance/regression test
42 - purpose: performance/regression test
47 - purpose: performance/regression test
52 - purpose: performance/regression test
57 - purpose: performance/regression test
|
| /external/mesa3d/src/intel/compiler/elk/ |
| D | elk_ir_performance.h | 33 * Various estimates of the performance of a shader based on static
36 struct performance { struct
37 performance(const elk_fs_visitor *v);
38 performance(const vec4_visitor *v);
39 ~performance();
72 * performance doesn't scale without limits as a function of its thread argument
79 performance(const performance &perf); argument
80 performance &
81 operator=(performance u); argument
|
| /external/tensorflow/tensorflow/lite/g3doc/examples/build/ |
| D | index.md | 51 For more information building effective, compatible, high performance models
53 [Performance best practices](../../performance/best_practices).
77 Whether you are looking to benchmark performance for a
94 Once you've developed your model, you should evaluate its performance and test
103 * [Benchmarking tools](https://www.tensorflow.org/lite/performance/measurement)
106 for important performance metrics.
112 model performance well and uses less compute resources. Machine learning model
113 performance is usually a balance between size and speed of inference vs
116 [model optimization] (https://www.tensorflow.org/lite/performance/model_optimization)
133 [performance best practices guide](https://www.tensorflow.org/lite/performance/best_practices)
[all …]
|
| /external/cronet/tot/third_party/icu/source/test/perf/ |
| D | README | 7 README for ICU4C Performance Test
10 The performance tests in ICU4C compares various aspects of ICU against previous versions of ICU,
12 performance tests are driven by a perl-based script which calls the underlying C program and
26 Running Performance Test:
33 3) Build the ICU performance tests either through Visual Studios or with the Makefile.
34 (The location of the performance test is: icu/source/test/perf)
39 b) Path to the performance test data
57 Note: After building the performance tests, it is a good idea to execute each C program to ensure t…
59 Note: To run the actual performance test, you will need to setup Perl with the following modules:
62 …s take a while depending on the machine it is running on so a script to run each performance test's
|
| /external/icu/icu4c/source/test/perf/ |
| D | README | 7 README for ICU4C Performance Test
10 The performance tests in ICU4C compares various aspects of ICU against previous versions of ICU,
12 performance tests are driven by a perl-based script which calls the underlying C program and
26 Running Performance Test:
33 3) Build the ICU performance tests either through Visual Studios or with the Makefile.
34 (The location of the performance test is: icu/source/test/perf)
39 b) Path to the performance test data
57 Note: After building the performance tests, it is a good idea to execute each C program to ensure t…
59 Note: To run the actual performance test, you will need to setup Perl with the following modules:
62 …s take a while depending on the machine it is running on so a script to run each performance test's
|
| /external/cronet/stable/third_party/icu/source/test/perf/ |
| D | README | 7 README for ICU4C Performance Test
10 The performance tests in ICU4C compares various aspects of ICU against previous versions of ICU,
12 performance tests are driven by a perl-based script which calls the underlying C program and
26 Running Performance Test:
33 3) Build the ICU performance tests either through Visual Studios or with the Makefile.
34 (The location of the performance test is: icu/source/test/perf)
39 b) Path to the performance test data
57 Note: After building the performance tests, it is a good idea to execute each C program to ensure t…
59 Note: To run the actual performance test, you will need to setup Perl with the following modules:
62 …s take a while depending on the machine it is running on so a script to run each performance test's
|
| /external/pytorch/docs/source/ |
| D | torch.compiler_performance_dashboard.rst | 1 PyTorch 2.0 Performance Dashboard
6 PyTorch 2.0's performance is tracked nightly on this `dashboard <https://hud.pytorch.org/benchmark/…
7 The performance collection runs on 12 GCP A100 nodes every night. Each node contains a 40GB A100 Nv…
16 training performance trend in the past 7 days for ``TorchBench``. Droplists on the top of that page…
18 performance metrics reported there: ``Geometric mean speedup``, ``Mean compilation time``, and
21 the PyTorch eager performance, and the larger the better. Each individual performance number on tho…
30 performance with AMP precision on the three benchmark suites. We also measure different settings of…
33 Can I check if my PR affects TorchInductor's performance on the dashboard before merging?
40 on the performance dashboard UI. Be aware that this is an expensive CI run. With the limited
43 How can I run any performance test locally?
[all …]
|
| /external/mesa3d/src/intel/compiler/ |
| D | brw_ir_performance.h | 33 * Various estimates of the performance of a shader based on static
36 struct performance { struct
37 performance(const fs_visitor *v);
38 ~performance();
71 * performance doesn't scale without limits as a function of its thread argument
78 performance(const performance &perf); argument
79 performance &
80 operator=(performance u); argument
|