4 OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version. OpenBLAS is an open source project supported by Lab of Parallel Software and Computational Science, ISCAS <http://www.rdcps.ac.cn>.
6 Please read the documents on OpenBLAS wiki pages <http://github.com/xianyi/OpenBLAS/wiki>.
9 Download from project homepage. http://xianyi.github.com/OpenBLAS/
11 Or, check out codes from git://github.com/xianyi/OpenBLAS.git
13 * type "make" to detect the CPU automatically.
15 * type "make TARGET=xxx" to set target CPU, e.g. "make TARGET=NEHALEM". The full target list is in file TargetList.txt.
18 Please set CC and FC with the cross toolchains. Then, set HOSTCC with your host C compiler. At last, set TARGET explicitly.
22 On X86 box, compile this library for loongson3a CPU.
24 make BINARY=64 CC=mips64el-unknown-linux-gnu-gcc FC=mips64el-unknown-linux-gnu-gfortran HOSTCC=gcc TARGET=LOONGSON3A
30 ### Install to the directory (Optional)
34 make install PREFIX=your_installation_directory
36 The default directory is /opt/OpenBLAS
39 Please read GotoBLAS_01Readme.txt
41 ### Additional support CPU:
44 - **Intel Xeon 56xx (Westmere)**: Used GotoBLAS2 Nehalem codes.
45 - **Intel Sandy Bridge**: Optimized Level-3 BLAS with AVX on x86-64.
46 - **AMD Bobcat**: Used GotoBLAS2 Barcelona codes.
47 - **AMD Bulldozer**: x86-64 S/DGEMM AVX kernels. (Thank Werner Saar)
50 - **ICT Loongson 3A**: Optimized Level-3 BLAS and the part of Level-1,2.
51 - **ICT Loongson 3B**: Experimental
55 - **MingWin/Windows**: Please read <https://github.com/xianyi/OpenBLAS/wiki/How-to-use-OpenBLAS-in-Microsoft-Visual-Studio>.
56 - **Darwin/Mac OS X**: Experimental. Although GotoBLAS2 supports Darwin, we are the beginner on Mac OS X.
57 - **FreeBSD**: Supportted by community. We didn't test the library on this OS.
60 Link with libopenblas.a or -lopenblas for shared library.
62 ### Set the number of threads with environment variables.
66 export OPENBLAS_NUM_THREADS=4
70 export GOTO_NUM_THREADS=4
74 export OMP_NUM_THREADS=4
76 The priorities are OPENBLAS_NUM_THREADS > GOTO_NUM_THREADS > OMP_NUM_THREADS.
78 If you compile this lib with USE_OPENMP=1, you should set OMP_NUM_THREADS environment variable. OpenBLAS ignores OPENBLAS_NUM_THREADS and GOTO_NUM_THREADS with USE_OPENMP=1.
80 ### Set the number of threads on runtime.
82 We provided the below functions to controll the number of threads on runtime.
84 void goto_set_num_threads(int num_threads);
86 void openblas_set_num_threads(int num_threads);
88 If you compile this lib with USE_OPENMP=1, you should use the above functions, too.
91 Please add a issue in https://github.com/xianyi/OpenBLAS/issues
94 OpenBLAS users mailing list: http://list.rdcps.ac.cn/mailman/listinfo/openblas
97 Please see Changelog.txt to obtain the differences between GotoBLAS2 1.13 BSD version.
100 * Please read [Faq](https://github.com/xianyi/OpenBLAS/wiki/Faq) at first.
101 * Please use gcc version 4.6 and above to compile Sandy Bridge AVX kernels on Linux/MingW/BSD.
102 * Please use Clang version 3.1 and above to compile the library on Sandy Bridge microarchitecture. The Clang 3.0 will generate the wrong AVX binary code.
103 * The number of CPUs/Cores should less than or equal to 256.
104 * On Linux, OpenBLAS sets the processor affinity by default. This may cause [the conflict with R parallel](https://stat.ethz.ch/pipermail/r-sig-hpc/2012-April/001348.html). You can build the library with NO_AFFINITY=1.
105 * On Loongson 3A. make test would be failed because of pthread_create error. The error code is EAGAIN. However, it will be OK when you run the same testcase on shell.
107 ## Specification of Git Branches
108 We used the git branching model in this article (http://nvie.com/posts/a-successful-git-branching-model/).
109 Now, there are 4 branches in github.com.
110 * The master branch. This a main branch to reflect a production-ready state.
111 * The develop branch. This a main branch to reflect a state with the latest delivered development changes for the next release.
112 * The loongson3a branch. This is a feature branch. We develop Loongson3A codes on this branch. We will merge this feature to develop branch in future.
113 * The gh-pages branch. This is for web pages