Initial commit

This commit is contained in:
yichuan520030910320
2025-06-30 09:05:05 +00:00
commit 46f6cc100b
1231 changed files with 278432 additions and 0 deletions

View File

@@ -0,0 +1,39 @@
name: 'DiskANN Build Bootstrap'
description: 'Prepares DiskANN build environment and executes build'
runs:
using: "composite"
steps:
# ------------ Linux Build ---------------
- name: Prepare and Execute Build
if: ${{ runner.os == 'Linux' }}
run: |
sudo scripts/dev/install-dev-deps-ubuntu.bash
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DUNIT_TEST=True
cmake --build build -- -j
cmake --install build --prefix="dist"
shell: bash
# ------------ End Linux Build ---------------
# ------------ Windows Build ---------------
- name: Add VisualStudio command line tools into path
if: runner.os == 'Windows'
uses: ilammy/msvc-dev-cmd@v1
- name: Run configure and build for Windows
if: runner.os == 'Windows'
run: |
mkdir build && cd build && cmake .. -DUNIT_TEST=True && msbuild diskann.sln /m /nologo /t:Build /p:Configuration="Release" /property:Platform="x64" -consoleloggerparameters:"ErrorsOnly;Summary"
cd ..
mkdir dist
mklink /j .\dist\bin .\x64\Release\
shell: cmd
# ------------ End Windows Build ---------------
# ------------ Windows Build With EXEC_ENV_OLS and USE_BING_INFRA ---------------
- name: Add VisualStudio command line tools into path
if: runner.os == 'Windows'
uses: ilammy/msvc-dev-cmd@v1
- name: Run configure and build for Windows with Bing feature flags
if: runner.os == 'Windows'
run: |
mkdir build_bing && cd build_bing && cmake .. -DEXEC_ENV_OLS=1 -DUSE_BING_INFRA=1 -DUNIT_TEST=True && msbuild diskann.sln /m /nologo /t:Build /p:Configuration="Release" /property:Platform="x64" -consoleloggerparameters:"ErrorsOnly;Summary"
cd ..
shell: cmd
# ------------ End Windows Build ---------------

View File

@@ -0,0 +1,13 @@
name: 'Checking code formatting...'
description: 'Ensures code complies with code formatting rules'
runs:
using: "composite"
steps:
- name: Checking code formatting...
run: |
sudo apt install clang-format
find include -name '*.h' -type f -print0 | xargs -0 -P 16 /usr/bin/clang-format --Werror --dry-run
find src -name '*.cpp' -type f -print0 | xargs -0 -P 16 /usr/bin/clang-format --Werror --dry-run
find apps -name '*.cpp' -type f -print0 | xargs -0 -P 16 /usr/bin/clang-format --Werror --dry-run
find python -name '*.cpp' -type f -print0 | xargs -0 -P 16 /usr/bin/clang-format --Werror --dry-run
shell: bash

View File

@@ -0,0 +1,28 @@
name: 'Generating Random Data (Basic)'
description: 'Generates the random data files used in acceptance tests'
runs:
using: "composite"
steps:
- name: Generate Random Data (Basic)
run: |
mkdir data
echo "Generating random 1020,1024,1536D float and 4096 int8 vectors for index"
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1020D_5K_norm1.0.bin -D 1020 -N 5000 --norm 1.0
#dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1024D_5K_norm1.0.bin -D 1024 -N 5000 --norm 1.0
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1536D_5K_norm1.0.bin -D 1536 -N 5000 --norm 1.0
dist/bin/rand_data_gen --data_type int8 --output_file data/rand_int8_4096D_5K_norm1.0.bin -D 4096 -N 5000 --norm 1.0
echo "Generating random 1020,1024,1536D float and 4096D int8 avectors for query"
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1020D_1K_norm1.0.bin -D 1020 -N 1000 --norm 1.0
#dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1024D_1K_norm1.0.bin -D 1024 -N 1000 --norm 1.0
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_1536D_1K_norm1.0.bin -D 1536 -N 1000 --norm 1.0
dist/bin/rand_data_gen --data_type int8 --output_file data/rand_int8_4096D_1K_norm1.0.bin -D 4096 -N 1000 --norm 1.0
echo "Computing ground truth for 1020,1024,1536D float and 4096D int8 avectors for query"
dist/bin/compute_groundtruth --data_type float --dist_fn l2 --base_file data/rand_float_1020D_5K_norm1.0.bin --query_file data/rand_float_1020D_1K_norm1.0.bin --gt_file data/l2_rand_float_1020D_5K_norm1.0_1020D_1K_norm1.0_gt100 --K 100
#dist/bin/compute_groundtruth --data_type float --dist_fn l2 --base_file data/rand_float_1024D_5K_norm1.0.bin --query_file data/rand_float_1024D_1K_norm1.0.bin --gt_file data/l2_rand_float_1024D_5K_norm1.0_1024D_1K_norm1.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type float --dist_fn l2 --base_file data/rand_float_1536D_5K_norm1.0.bin --query_file data/rand_float_1536D_1K_norm1.0.bin --gt_file data/l2_rand_float_1536D_5K_norm1.0_1536D_1K_norm1.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type int8 --dist_fn l2 --base_file data/rand_int8_4096D_5K_norm1.0.bin --query_file data/rand_int8_4096D_1K_norm1.0.bin --gt_file data/l2_rand_int8_4096D_5K_norm1.0_4096D_1K_norm1.0_gt100 --K 100
shell: bash

View File

@@ -0,0 +1,38 @@
name: 'Generating Random Data (Basic)'
description: 'Generates the random data files used in acceptance tests'
runs:
using: "composite"
steps:
- name: Generate Random Data (Basic)
run: |
mkdir data
echo "Generating random vectors for index"
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_10D_10K_norm1.0.bin -D 10 -N 10000 --norm 1.0
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_10D_10K_unnorm.bin -D 10 -N 10000 --rand_scaling 2.0
dist/bin/rand_data_gen --data_type int8 --output_file data/rand_int8_10D_10K_norm50.0.bin -D 10 -N 10000 --norm 50.0
dist/bin/rand_data_gen --data_type uint8 --output_file data/rand_uint8_10D_10K_norm50.0.bin -D 10 -N 10000 --norm 50.0
echo "Generating random vectors for query"
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_10D_1K_norm1.0.bin -D 10 -N 1000 --norm 1.0
dist/bin/rand_data_gen --data_type float --output_file data/rand_float_10D_1K_unnorm.bin -D 10 -N 1000 --rand_scaling 2.0
dist/bin/rand_data_gen --data_type int8 --output_file data/rand_int8_10D_1K_norm50.0.bin -D 10 -N 1000 --norm 50.0
dist/bin/rand_data_gen --data_type uint8 --output_file data/rand_uint8_10D_1K_norm50.0.bin -D 10 -N 1000 --norm 50.0
echo "Computing ground truth for floats across l2, mips, and cosine distance functions"
dist/bin/compute_groundtruth --data_type float --dist_fn l2 --base_file data/rand_float_10D_10K_norm1.0.bin --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/l2_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type float --dist_fn mips --base_file data/rand_float_10D_10K_norm1.0.bin --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/mips_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type float --dist_fn cosine --base_file data/rand_float_10D_10K_norm1.0.bin --query_file data/rand_float_10D_1K_norm1.0.bin --gt_file data/cosine_rand_float_10D_10K_norm1.0_10D_1K_norm1.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type float --dist_fn cosine --base_file data/rand_float_10D_10K_unnorm.bin --query_file data/rand_float_10D_1K_unnorm.bin --gt_file data/cosine_rand_float_10D_10K_unnorm_10D_1K_unnorm_gt100 --K 100
echo "Computing ground truth for int8s across l2, mips, and cosine distance functions"
dist/bin/compute_groundtruth --data_type int8 --dist_fn l2 --base_file data/rand_int8_10D_10K_norm50.0.bin --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/l2_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type int8 --dist_fn mips --base_file data/rand_int8_10D_10K_norm50.0.bin --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/mips_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type int8 --dist_fn cosine --base_file data/rand_int8_10D_10K_norm50.0.bin --query_file data/rand_int8_10D_1K_norm50.0.bin --gt_file data/cosine_rand_int8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
echo "Computing ground truth for uint8s across l2, mips, and cosine distance functions"
dist/bin/compute_groundtruth --data_type uint8 --dist_fn l2 --base_file data/rand_uint8_10D_10K_norm50.0.bin --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/l2_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type uint8 --dist_fn mips --base_file data/rand_uint8_10D_10K_norm50.0.bin --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/mips_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
dist/bin/compute_groundtruth --data_type uint8 --dist_fn cosine --base_file data/rand_uint8_10D_10K_norm50.0.bin --query_file data/rand_uint8_10D_1K_norm50.0.bin --gt_file data/cosine_rand_uint8_10D_10K_norm50.0_10D_1K_norm50.0_gt100 --K 100
shell: bash

View File

@@ -0,0 +1,22 @@
name: Build Python Wheel
description: Builds a python wheel with cibuildwheel
inputs:
cibw-identifier:
description: "CI build wheel identifier to build"
required: true
runs:
using: "composite"
steps:
- uses: actions/setup-python@v3
- name: Install cibuildwheel
run: python -m pip install cibuildwheel==2.11.3
shell: bash
- name: Building Python ${{inputs.cibw-identifier}} Wheel
run: python -m cibuildwheel --output-dir dist
env:
CIBW_BUILD: ${{inputs.cibw-identifier}}
shell: bash
- uses: actions/upload-artifact@v3
with:
name: wheels
path: ./dist/*.whl