mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-12 02:13:36 +00:00
Evandabest
66cea52433
Summary: ## Summary Adds a new Metal compute backend so FAISS can run GPU-accelerated similarity search on Apple Silicon (M1/M2/M3/M4/M5). This is just an initial pr, it introduces the build system integration, core Metal infrastructure, and a working `IndexFlat` with L2 and inner product search. I have some follow up prs with more functionality that I plan to submit. Addresses https://github.com/facebookresearch/faiss/issues/2386 — FAISS currently has no GPU acceleration path on Apple Silicon, forcing CPU-only execution. This Metal backend enables GPU-accelerated search on M-series chips, with follow-up PRs adding IVF indexes, Python bindings, and kernel optimizations. All Metal code lives in a new `faiss/gpu_metal/` directory, keeping `faiss/gpu/` (CUDA/ROCm) completely untouched. The backend is opt-in via `cmake -DFAISS_ENABLE_METAL=ON -DFAISS_ENABLE_GPU=OFF`. ### What's included - **Build system**: New `FAISS_ENABLE_METAL` CMake option. When enabled, requires Apple platform, links Metal/MetalKit/MPS/Foundation frameworks, and builds `libfaiss_metal.a`. Three small additions to root `CMakeLists.txt`. - **MetalResources**: Owns `MTLDevice`, `MTLCommandQueue`, and buffer allocation/deallocation. Mirrors `GpuResources` roles. - **MetalIndex**: Base class for Metal-backed indexes (mirrors `GpuIndex`). Single-device only (device 0). - **MetalIndexFlat**: Flat index storing vectors in an `MTLBuffer`. Supports `add`, `add_with_ids`, `reset`, `search` for both `METRIC_L2` and `METRIC_INNER_PRODUCT`. - **MSL compute kernels**: `l2_squared_matrix`, `ip_matrix` (distance computation), and `topk` (sorted insertion, k ≤ 256). Embedded as a compile-time string in `MetalFlatKernels.mm`. - **Backend abstraction**: `get_num_gpus()`, `index_cpu_to_metal_gpu()`, `index_metal_gpu_to_cpu()`, `StandardMetalResources`, and a `GpuIndexFlat` typedef for API parity. - **Tests**: 8 gtest cases in `TestMetalIndexFlat.mm` — L2/IP search correctness vs CPU `IndexFlat`, `add_with_ids`, reset, empty search, `get_num_gpus`, and CPU↔Metal cloning in both directions. All tests skip gracefully if no Metal device is available. - Python/SWIG bindings ### Planned follow up prs - Larger k support (tiling, heap-based top-k) - IVFFlat, IVFPQ, IVFSQ, BinaryFlat - Kernel optimizations (fused distance+top-k, GEMM-tiled distance, simdgroup/threadgroup parallel selection) ### Build and test ```bash mkdir -p build_metal && cd build_metal cmake .. -DFAISS_ENABLE_METAL=ON -DFAISS_ENABLE_GPU=OFF \ -DBUILD_TESTING=ON -DFAISS_ENABLE_PYTHON=OFF \ -DCMAKE_PREFIX_PATH="/opt/homebrew/opt/libomp;/opt/homebrew" cmake --build . --target faiss_metal TestMetalIndexFlat ctest -R TestMetalIndexFlat ``` > The `mkdir -p` avoids the error if the directory exists, and `-DFAISS_ENABLE_PYTHON=OFF` skips the Python dependency that isn't needed for this PR. Pull Request resolved: https://github.com/facebookresearch/faiss/pull/5144 Reviewed By: alibeklfc Differential Revision: D102284936 Pulled By: mnorris11 fbshipit-source-id: 812fc6ceae251b7b33d25f6861fc37b8d7b475c1
35 lines
493 B
Plaintext
35 lines
493 B
Plaintext
*.swp
|
|
*.swo
|
|
*.o
|
|
*.a
|
|
*.dSYM
|
|
*.so
|
|
*.dylib
|
|
*.pyc
|
|
*~
|
|
/build/
|
|
/build_metal/
|
|
/config.*
|
|
/aclocal.m4
|
|
/autom4te.cache/
|
|
/makefile.inc
|
|
/bin/
|
|
/c_api/bin/
|
|
/c_api/gpu/bin/
|
|
/tests/test
|
|
/tests/gtest/
|
|
faiss/python/swigfaiss_avx2.swig
|
|
faiss/python/swigfaiss_avx512.swig
|
|
faiss/python/swigfaiss_avx512_spr.swig
|
|
faiss/python/swigfaiss_sve.swig
|
|
|
|
# Local intermediate build artifacts (CUDA 13.2 scripts)
|
|
/_build/
|
|
/_build_python_*/
|
|
/_libfaiss_stage/
|
|
/build_output/
|
|
|
|
# Python package build outputs
|
|
/dist/
|
|
/*.egg-info/
|