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 ### Intall 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.
48 * ICT Loongson 3A. Optimized Level-3 BLAS and the part of Level-1,2.
49 * ICT Loongson 3B (Experimental)
52 Link with libopenblas.a or -lopenblas for shared library.
54 ### Set the number of threads with environment variables.
58 export OPENBLAS_NUM_THREADS=4
62 export GOTO_NUM_THREADS=4
66 export OMP_NUM_THREADS=4
68 The priorities are OPENBLAS_NUM_THREADS > GOTO_NUM_THREADS > OMP_NUM_THREADS.
70 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.
72 ### Set the number of threads with calling functions.
76 void goto_set_num_threads(int num_threads);
78 void openblas_set_num_threads(int num_threads);
80 If you compile this lib with USE_OPENMP=1, you should use the above functions, too.
83 Please add a issue in https://github.com/xianyi/OpenBLAS/issues
86 OpenBLAS users mailing list: http://list.rdcps.ac.cn/mailman/listinfo/openblas
89 Please see Changelog.txt to obtain the differences between GotoBLAS2 1.13 BSD version.
92 * Please use gcc version 4.6 and above to compile Sandy Bridge AVX kernels on Linux/MingW/BSD.
93 * 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.
94 * The number of CPUs/Cores should less than or equal to 256.
95 * 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.
97 ## Specification of Git Branches
98 We used the git branching model in this article (http://nvie.com/posts/a-successful-git-branching-model/).
99 Now, there are 4 branches in github.com.
100 * The master branch. This a main branch to reflect a production-ready state.
101 * The develop branch. This a main branch to reflect a state with the latest delivered development changes for the next release.
102 * 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.
103 * The gh-pages branch. This is for web pages