Commit Graph

8 Commits (750d43f7f110c5d18841879c04b346e0a1767d08)

Author SHA1 Message Date
Lucas Hosseini 750d43f7f1
Move source code to faiss/ subdirectory. (#1312)
* Move source code to faiss/ subdirectory.

* Remove stale files.
2020-08-04 17:16:58 +02:00
Lucas Hosseini 3d0ece0cb7
Run time detection of avx2 for conda packages. (#957)
* Build conda CPU packages with run-time detection of AVX2.

* Add cudatoolkit 10.1 to conda list.

* Default to sse4 on x86_64.
2019-09-20 20:17:01 +02:00
Lucas Hosseini 656368b5ed
Dynamically detect avx2 capabilities (#877)
* Install scipy via pip rather than system package manager

* Dynamically detect AVX2 capability

* Simplify build on TravisCI
2019-06-28 13:50:46 +02:00
Lucas Hosseini a8118acbc5
Facebook sync (May 2019) + relicense (#838)
Changelog:

- changed license: BSD+Patents -> MIT
- propagates exceptions raised in sub-indexes of IndexShards and IndexReplicas
- support for searching several inverted lists in parallel (parallel_mode != 0)
- better support for PQ codes where nbit != 8 or 16
- IVFSpectralHash implementation: spectral hash codes inside an IVF
- 6-bit per component scalar quantizer (4 and 8 bit were already supported)
- combinations of inverted lists: HStackInvertedLists and VStackInvertedLists
- configurable number of threads for OnDiskInvertedLists prefetching (including 0=no prefetch)
- more test and demo code compatible with Python 3 (print with parentheses)
- refactored benchmark code: data loading is now in a single file
2019-05-28 16:17:22 +02:00
Lucas Hosseini 7f5b22b0ff
Add conda packages metadata + tests. (#769)
+ Add conda packages metadata (now building Faiss using conda's toolchain);
+ add Dockerfile for building conda packages (for all CUDA versions);
+ add working Dockerfile building faiss on Centos7;
+ simplify GPU build;
+ avoid falling back to CPU-only version (python);
+ simplify TravisCI config;
+ update INSTALL.md;
+ add configure flag for specifying target architectures (--with-cuda-arch);
+ fix Makefile for gpu tests;
+ fix various Makefile issues;
+ remove stale file (gpu/utils/DeviceUtils.cpp).
2019-04-05 11:50:39 +02:00
Marcin Tolysz 4b3210575b Improve arm64 support. (#676)
* Improve Arm64 support.

Make library compile and run on Arm64 8.2 (Nvidia Xavier arm+cuda)
`configure` is regenerated

* remove simd from utils.cpp
2019-02-15 13:13:49 +01:00
Lucas Hosseini 5d29b3624c
Use multi-threaded MKL by default (#509)
* Configure script use threaded MKL instead of sequential.

* Do not link against GNU OpenMP when linking against Intel OpenMP.
2018-07-06 17:26:37 +02:00
Lucas Hosseini cf18101f6d Refactor makefiles and add configure script (#466)
* Refactors Makefiles and add configure script.

* Give MKL higher priority in configure script.

* Clean up Linux example makefile.inc.

* Cleanup makefile.inc examples.

* Fix python clean Makefile target.

* Regen swig wrappers.

* Remove useless CUDAFLAGS variable.

* Fix python linking flags.

* Separate compile and link phase in python makefile.

* Add macro to look for swig.

* Add CUDA check in configure script.

* Cleanup make depend targets.

* Cleanup CUDA flags.

* Fix linking flags.

* Fix python GPU linking.

* Remove useless flags from python gpu module linking.

* Add check for cuda libs.

* Cleanup GPU targets.

* Clean up test target.

* Add cpu/gpu targets to python makefile.

* Clean up tutorial Makefile.

* Remove stale OS var from example makefiles.

* Clean up cuda example flags.
2018-06-02 08:35:30 +02:00