Mercurial > hg > CbC > CbC_llvm

comparison libc/utils/benchmarks/README.md @ 173:0572611fdcc8 llvm10 llvm12

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
reorgnization done
author Shinji KONO <kono@ie.u-ryukyu.ac.jp>
date Mon, 25 May 2020 11:55:54 +0900
parents 1d019706d866
children
comparison
equal deleted inserted replaced
172:9fbae9c8bf63 173:0572611fdcc8
16 16
17 ```shell 17 ```shell
18 apt-get install python3-pip 18 apt-get install python3-pip
19 pip3 install matplotlib scipy numpy 19 pip3 install matplotlib scipy numpy
20 ``` 20 ```
21 You may need `python3-gtk` or similar package for displaying benchmark results.
21 22
22 To get good reproducibility it is important to make sure that the system runs in 23 To get good reproducibility it is important to make sure that the system runs in
23 `performance` mode. This is achieved by running: 24 `performance` mode. This is achieved by running:
24 25
25 ```shell 26 ```shell
35 ```shell 36 ```shell
36 cd llvm-project 37 cd llvm-project
37 cmake -B/tmp/build -Sllvm -DLLVM_ENABLE_PROJECTS=libc -DCMAKE_BUILD_TYPE=Release 38 cmake -B/tmp/build -Sllvm -DLLVM_ENABLE_PROJECTS=libc -DCMAKE_BUILD_TYPE=Release
38 make -C /tmp/build -j display-libc-memcpy-benchmark-small 39 make -C /tmp/build -j display-libc-memcpy-benchmark-small
39 ``` 40 ```
41
42 The display target will attempt to open a window on the machine where you're
43 running the benchmark. If this may not work for you then you may want `render`
44 or `run` instead as detailed below.
45
46 ## Benchmarking targets
47
48 The benchmarking process occurs in two steps:
49
50 1. Benchmark the functions and produce a `json` file
51 2. Display (or renders) the `json` file
52
53 Targets are of the form `<action>-libc-<function>-benchmark-<configuration>`
54
55 - `action` is one of :
56 - `run`, runs the benchmark and writes the `json` file
57 - `display`, displays the graph on screen
58 - `render`, renders the graph on disk as a `png` file
59 - `function` is one of : `memcpy`, `memcmp`, `memset`
60 - `configuration` is one of : `small`, `big`
40 61
41 ## Benchmarking regimes 62 ## Benchmarking regimes
42 63
43 Using a profiler to observe size distributions for calls into libc functions, it 64 Using a profiler to observe size distributions for calls into libc functions, it
44 was found most operations act on a small number of bytes. 65 was found most operations act on a small number of bytes.
60 - Caching effects can show up here which prevents comparing different hosts 81 - Caching effects can show up here which prevents comparing different hosts
61 82
62 _<sup>1</sup> - The size refers to the size of the buffers to compare and not 83 _<sup>1</sup> - The size refers to the size of the buffers to compare and not
63 the number of bytes until the first difference._ 84 the number of bytes until the first difference._
64 85
65 ## Benchmarking targets
66
67 The benchmarking process occurs in two steps:
68
69 1. Benchmark the functions and produce a `json` file
70 2. Display (or renders) the `json` file
71
72 Targets are of the form `<action>-libc-<function>-benchmark-<configuration>`
73
74 - `action` is one of :
75 - `run`, runs the benchmark and writes the `json` file
76 - `display`, displays the graph on screen
77 - `render`, renders the graph on disk as a `png` file
78 - `function` is one of : `memcpy`, `memcmp`, `memset`
79 - `configuration` is one of : `small`, `big`
80
81 ## Superposing curves 86 ## Superposing curves
82 87
83 It is possible to **merge** several `json` files into a single graph. This is 88 It is possible to **merge** several `json` files into a single graph. This is
84 useful to **compare** implementations. 89 useful to **compare** implementations.
85 90