mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-12 07:59:01 +02:00
Daniel Bevenius
3bcfeb700f
* 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.
123 lines
3.2 KiB
Bash
Executable File
123 lines
3.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Compile-time profiling using clang -ftime-trace + ClangBuildAnalyzer.
|
|
#
|
|
# Usage:
|
|
# ./scripts/build-profile.sh [--full] [-jN]
|
|
#
|
|
# --full: include Server, Tools, and Tests (default: minimal build)
|
|
# -jN : number of parallel jobs (default: all cores)
|
|
#
|
|
# Requires ClangBuildAnalyzer:
|
|
# macOS: brew install clang-build-analyzer
|
|
# Linux: https://github.com/aras-p/ClangBuildAnalyzer.git
|
|
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
ROOT_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
|
|
|
|
FULL=0
|
|
JOBS="-j$(nproc 2>/dev/null || sysctl -n hw.ncpu)"
|
|
|
|
for arg in "$@"; do
|
|
case "${arg}" in
|
|
--full) FULL=1 ;;
|
|
-j*) JOBS="${arg}" ;;
|
|
*) echo "error: unknown argument: ${arg}" >&2; exit 1 ;;
|
|
esac
|
|
done
|
|
|
|
if [ "${FULL}" -eq 1 ]; then
|
|
BUILD_DIR="${ROOT_DIR}/build-profile-full"
|
|
REPORT="${BUILD_DIR}/profile-report-full.txt"
|
|
else
|
|
BUILD_DIR="${ROOT_DIR}/build-profile-baseline"
|
|
REPORT="${BUILD_DIR}/profile-report.txt"
|
|
fi
|
|
|
|
OUTPUT_BIN="${BUILD_DIR}/clang_analysis.bin"
|
|
|
|
if ! command -v clang++ &>/dev/null; then
|
|
echo "error: clang++ not found" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if ! command -v ClangBuildAnalyzer &>/dev/null; then
|
|
echo "error: ClangBuildAnalyzer not found" >&2
|
|
echo " brew install clangbuildanalyzer (macOS)" >&2
|
|
echo " or: https://github.com/aras-p/ClangBuildAnalyzer/releases" >&2
|
|
exit 1
|
|
fi
|
|
|
|
CLANG_VER=$(clang++ --version | head -1)
|
|
echo "compiler : ${CLANG_VER}"
|
|
echo "build dir: ${BUILD_DIR}"
|
|
echo "output : ${OUTPUT_BIN}"
|
|
echo "jobs : ${JOBS}"
|
|
echo
|
|
|
|
if command -v ccache &>/dev/null; then
|
|
echo "clearing ccache..."
|
|
ccache -C -z
|
|
fi
|
|
|
|
export CCACHE_DISABLE=1
|
|
|
|
cmake --fresh \
|
|
-S "${ROOT_DIR}" \
|
|
-B "${BUILD_DIR}" \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DCMAKE_C_COMPILER=clang \
|
|
-DCMAKE_CXX_COMPILER=clang++ \
|
|
-DCMAKE_C_FLAGS="-ftime-trace" \
|
|
-DCMAKE_CXX_FLAGS="-ftime-trace" \
|
|
-DGGML_CCACHE=OFF \
|
|
-DGGML_OPENMP=ON \
|
|
-DGGML_NATIVE=OFF \
|
|
-DLLAMA_BUILD_TESTS=$([ "${FULL}" -eq 1 ] && echo ON || echo OFF) \
|
|
-DLLAMA_BUILD_EXAMPLES=OFF \
|
|
-DLLAMA_BUILD_TOOLS=$([ "${FULL}" -eq 1 ] && echo ON || echo OFF) \
|
|
-DLLAMA_BUILD_SERVER=$([ "${FULL}" -eq 1 ] && echo ON || echo OFF) \
|
|
-DLLAMA_BUILD_APP=OFF
|
|
|
|
echo
|
|
|
|
echo "Initializing ClangBuildAnalyzer..."
|
|
ClangBuildAnalyzer --start "${BUILD_DIR}"
|
|
echo
|
|
|
|
echo "building..."
|
|
echo
|
|
|
|
START=$(date +%s)
|
|
|
|
cmake --build "${BUILD_DIR}" --clean-first "${JOBS}"
|
|
|
|
END=$(date +%s)
|
|
ELAPSED=$((END - START))
|
|
|
|
echo
|
|
printf "build time: %ds (%dm %ds)\n" "${ELAPSED}" "$((ELAPSED / 60))" "$((ELAPSED % 60))"
|
|
echo
|
|
|
|
echo "Aggregating profile metrics..."
|
|
ClangBuildAnalyzer --stop "${BUILD_DIR}" "${OUTPUT_BIN}" > /dev/null
|
|
|
|
echo
|
|
echo "================================================================================"
|
|
TUS=$(grep -oP "Compilation \(\K[0-9]+" "${REPORT}" 2>/dev/null || echo "?")
|
|
ClangBuildAnalyzer --analyze "${OUTPUT_BIN}" | tee "${REPORT}"
|
|
|
|
echo
|
|
echo "translation units: ${TUS}"
|
|
echo
|
|
echo "largest trace files (top 20 by size):"
|
|
find "${BUILD_DIR}" -name "*.json" ! -name "compile_commands.json" \
|
|
| xargs ls -l 2>/dev/null \
|
|
| awk 'NF>5 {print $5, $NF}' \
|
|
| sort -rn \
|
|
| awk 'NR<=20 {printf "%8.1f KB %s\n", $1/1024, $2}'
|
|
|
|
echo
|
|
echo "ClangBuildAnalyzer report was generated: ${REPORT}"
|