mirror of
https://github.com/bytecodealliance/wasm-micro-runtime.git
synced 2025-12-11 10:02:51 +00:00
8d88471c46
LLVM PGO (Profile-Guided Optimization) allows the compiler to better optimize code
for how it actually runs. This PR implements the AOT static PGO, and is tested on
Linux x86-64 and x86-32. The basic steps are:
1. Use `wamrc --enable-llvm-pgo -o <aot_file_of_pgo> <wasm_file>`
to generate an instrumented aot file.
2. Compile iwasm with `cmake -DWAMR_BUILD_STATIC_PGO=1` and run
`iwasm --gen-prof-file=<raw_profile_file> <aot_file_of_pgo>`
to generate the raw profile file.
3. Run `llvm-profdata merge -output=<profile_file> <raw_profile_file>`
to merge the raw profile file into the profile file.
4. Run `wamrc --use-prof-file=<profile_file> -o <aot_file> <wasm_file>`
to generate the optimized aot file.
5. Run the optimized aot_file: `iwasm <aot_file>`.
The test scripts are also added for each benchmark, run `test_pgo.sh` under
each benchmark's folder to test the AOT static pgo.
24 lines
1.3 KiB
Markdown
24 lines
1.3 KiB
Markdown
# Introduction
|
|
|
|
[Sightglass](https://github.com/bytecodealliance/sightglass) is a benchmarking suite and tooling to test WebAssembly applications.
|
|
|
|
**Source**: https://github.com/bytecodealliance/sightglass
|
|
|
|
# Building
|
|
|
|
Please build iwasm and wamrc, refer to:
|
|
- [Build iwasm on Linux](../../../doc/build_wamr.md#linux), or [Build iwasm on MacOS](../../../doc/build_wamr.md#macos)
|
|
- [Build wamrc AOT compiler](../../../README.md#build-wamrc-aot-compiler)
|
|
|
|
And install WASI SDK, please download the [wasi-sdk release](https://github.com/CraneStation/wasi-sdk/releases) and extract the archive to default path `/opt/wasi-sdk`.
|
|
|
|
And then run `./build.sh` to build the source code, the folder `out` will be created and files will be generated under it.
|
|
|
|
# Running
|
|
|
|
Run `./run_aot.sh` to test the benchmark, the native mode and iwasm aot mode will be tested for each workload, and the file `report.txt` will be generated.
|
|
|
|
Run `./run_interp.sh` to test the benchmark, the native mode and iwasm interpreter mode will be tested for each workload, and the file `report.txt` will be generated.
|
|
|
|
Run `./test_pgo.sh` to test the benchmark with AOT static PGO (Profile-Guided Optimization) enabled, please refer [here](../README.md#install-llvm-profdata) to install tool `llvm-profdata` and build `iwasm` with `cmake -DWAMR_BUILD_STATIC_PGO=1`.
|