Files
llama.cpp/scripts/build-profile.ps1
T
Daniel Bevenius 3bcfeb700f cmake : add PCH and unity build to improve build times (#28091)
* scripts : add initial profiling script (wip)

* src : add precompile headers (PCH) for models.h

* common : add common.h as PCH

* ggml : add PCH for ggml-impl.h

* mtmd : use PCH for models.h

* scripts : add script to build with Server/Tools/Tests

* server : add PCH for common.h

* docs: add profiling progress notes (wip)

* ggml : add exclude for GCC + SVE on ARM

Refs: https://github.com/ggml-org/llama.cpp/actions/runs/33393906061/job/99493756214?pr=28091

* ggml : attempt to fix use of std::hardware_destructive_inference_size

Refs: https://github.com/ggml-org/llama.cpp/actions/runs/33396221677/job/99501265689?pr=28091

* squash! ggml : attempt to fix use of std::hardware_destructive_inference_size

Add a version check for GCC 12 to conditionally apply the `-Winterference-size`
pragma.

* editorconfig : exclude profiling reports dir

This directory will not be included in the merge later and this commit
can be ignore at that point. Just fixing to keep CI happy.

* ggml : skip PCH for gcc on non-x86 architectures

* tests : add PCH for peg-parser/tests.h

There are 7 peg-parser tests that can share one PCH instead of then each
parsing the full tests.h.

* common : add PCH for chat.h

* docs : update linux build profiling full results

Just updating after a number of PCH additions. These are not exact
figures and will vary a bit from run to run, but they give a general idea
of the performance impact of PCH.

* cmake : introduce unity build for models

This commit introduces a unity build for the models to improve
compilation time.

The improvements were roughly the following:
```console
+------------------------+-----+------------+------------+------------+
| Build                  | TUs | Frontend   | Backend    | Total      |
+------------------------+-----+------------+------------+------------+
| Full,    master        | 396 |   811.0 s  |   692.2 s  | 1,503.2 s  |
| Full,    with PCH      | 405 |   380.0 s  |   664.7 s  | 1,044.7 s  |
| Full,    with PCH + UB | 264 |   357.7 s  |   635.7 s  |   993.4 s  |
+------------------------+-----+------------+------------+------------+

TU   = Translation Unit.
Full = includes Server, Tools, and Tests.
PCH  = precompiled headers.
UB   = unity build for models.
```

* docs : update linux profiling table with unitiy build results

* docs : update mac profiling results to include unity build [no ci]

* docs: remove profiling reports

* scripts : merge build profile scripts into one script

I was lazy before and just copied the first script to enable Tests,
Server, and Tools. This now merges them into a single script.

* Revert "editorconfig : exclude profiling reports dir" [no ci]

This reverts commit 2922a12118.

* src : rename ggml_view_2d_slice to gemma3n_view_2d_slice

This is to be consistent with the rename in gemma4.cpp which was
required to avoid a name clash.

* cmake : add build profile script for windows [no ci]

This commit adds a port of the scripts/build-profile.sh script to
windows powershell.

This was developed on Windows on ARM but should work on X64 as well but
needs to be tested there as well.
2026-09-11 13:01:29 +02:00

137 lines
3.7 KiB
PowerShell

# Compile-time profiling using clang -ftime-trace + ClangBuildAnalyzer.
#
# Usage:
# .\scripts\build-profile.ps1 [-Full] [-Jobs N]
#
# -Full : include Server, Tools, and Tests (default: minimal build)
# -Jobs : number of parallel jobs (default: all cores)
#
# Requires ClangBuildAnalyzer:
# https://github.com/aras-p/ClangBuildAnalyzer
param(
[switch]$Full,
[int]$Jobs = [Environment]::ProcessorCount
)
$ErrorActionPreference = "Stop"
$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$RootDir = Split-Path -Parent $ScriptDir
if ($Full) {
$BuildDir = Join-Path $RootDir "build-profile-full"
$Report = Join-Path $BuildDir "profile-report-full.txt"
} else {
$BuildDir = Join-Path $RootDir "build-profile-baseline"
$Report = Join-Path $BuildDir "profile-report.txt"
}
$OutputBin = Join-Path $BuildDir "clang_analysis.bin"
if (-not (Get-Command clang++ -ErrorAction SilentlyContinue)) {
Write-Error "clang++ not found"
exit 1
}
if (-not (Get-Command ninja -ErrorAction SilentlyContinue)) {
Write-Error "ninja not found (required so cmake does not fall back to the Visual Studio/MSVC generator)"
exit 1
}
if (-not (Get-Command ClangBuildAnalyzer -ErrorAction SilentlyContinue)) {
Write-Error "ClangBuildAnalyzer not found`n https://github.com/aras-p/ClangBuildAnalyzer/releases"
exit 1
}
$ClangVer = (clang++ --version | Select-Object -First 1)
Write-Host "compiler : $ClangVer"
Write-Host "build dir: $BuildDir"
Write-Host "output : $OutputBin"
Write-Host "jobs : $Jobs"
Write-Host ""
if (Get-Command ccache -ErrorAction SilentlyContinue) {
Write-Host "clearing ccache..."
ccache -C -z
}
$env:CCACHE_DISABLE = "1"
$TestsFlag = if ($Full) { "ON" } else { "OFF" }
$ToolsFlag = if ($Full) { "ON" } else { "OFF" }
$ServerFlag = if ($Full) { "ON" } else { "OFF" }
cmake --fresh `
-S $RootDir `
-B $BuildDir `
-G "Ninja" `
-DCMAKE_BUILD_TYPE=Release `
-DCMAKE_C_COMPILER=clang `
-DCMAKE_CXX_COMPILER=clang++ `
-DCMAKE_C_FLAGS="-ftime-trace" `
-DCMAKE_CXX_FLAGS="-ftime-trace" `
-DGGML_CCACHE=OFF `
-DGGML_OPENMP=ON `
-DGGML_NATIVE=OFF `
"-DLLAMA_BUILD_TESTS=$TestsFlag" `
-DLLAMA_BUILD_EXAMPLES=OFF `
"-DLLAMA_BUILD_TOOLS=$ToolsFlag" `
"-DLLAMA_BUILD_SERVER=$ServerFlag" `
-DLLAMA_BUILD_APP=OFF
if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
$StrayTrace = Join-Path $RootDir "-.json"
if (Test-Path $StrayTrace) {
Remove-Item $StrayTrace -Force
}
Write-Host ""
Write-Host "Initializing ClangBuildAnalyzer..."
ClangBuildAnalyzer --start $BuildDir
Write-Host ""
Write-Host "building..."
Write-Host ""
$StartTime = Get-Date
cmake --build $BuildDir --clean-first -j $Jobs
if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
$Elapsed = (Get-Date) - $StartTime
Write-Host ""
Write-Host ("build time: {0}s ({1}m {2}s)" -f [int]$Elapsed.TotalSeconds, [int]$Elapsed.TotalMinutes, $Elapsed.Seconds)
Write-Host ""
Write-Host "Aggregating profile metrics..."
ClangBuildAnalyzer --stop $BuildDir $OutputBin | Out-Null
Write-Host ""
Write-Host ("=" * 80)
$TUs = "?"
if (Test-Path $Report) {
$Match = Select-String -Path $Report -Pattern "Compilation \((\d+)" | Select-Object -First 1
if ($Match) { $TUs = $Match.Matches[0].Groups[1].Value }
}
ClangBuildAnalyzer --analyze $OutputBin | Tee-Object -FilePath $Report
Write-Host ""
Write-Host "translation units: $TUs"
Write-Host ""
Write-Host "largest trace files (top 20 by size):"
Get-ChildItem -Path $BuildDir -Recurse -Filter "*.json" |
Where-Object { $_.Name -ne "compile_commands.json" } |
Sort-Object Length -Descending |
Select-Object -First 20 |
ForEach-Object { "{0,8:F1} KB {1}" -f ($_.Length / 1024), $_.FullName }
Write-Host ""
Write-Host "ClangBuildAnalyzer report was generated: $Report"