Merge pull request #19 from xianyi/develop

rebase

CMakeLists.txt

@@ -6,7 +6,7 @@ cmake_minimum_required(VERSION 2.8.5)
 project(OpenBLAS C ASM)
 set(OpenBLAS_MAJOR_VERSION 0)
 set(OpenBLAS_MINOR_VERSION 3)
-set(OpenBLAS_PATCH_VERSION 13.dev)
+set(OpenBLAS_PATCH_VERSION 14.dev)
 set(OpenBLAS_VERSION "${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.${OpenBLAS_PATCH_VERSION}")
 
 # Adhere to GNU filesystem layout conventions

Changelog.txt

@@ -1,4 +1,52 @@
 OpenBLAS ChangeLog
+====================================================================
+Version 0.3.14
+ 17-Mar-2021
+ 
+ common:
+	* Fixed a race condition on thread shutdown in non-OpenMP builds
+	* Fixed custom BUFFERSIZE option getting ignored in gmake builds
+	* Fixed CMAKE compilation of the TRMM kernels for GENERIC platforms
+	* Added CBLAS interfaces for CROTG, ZROTG, CSROT and ZDROT
+	* Improved performance of OMATCOPY_RT across all platforms
+	* Changed perl scripts to use env instead of a hardcoded /usr/bin/perl
+	* Fixed potential misreading of the GCC compiler version in the build scripts
+	* Fixed convergence problems in LAPACK complex GGEV/GGES (Reference-LAPACK #477)
+	* Reduced the stacksize requirements for running the LAPACK testsuite (Reference-LAPACK #335)
+
+ RISCV:
+ 	* Fixed compilation on RISCV (missing entry in getarch)
+	
+ POWER:
+ 	* Fixed compilation for DYNAMIC_ARCH with clang and with old gcc versions
+	* Added support for compilation on FreeBSD/ppc64le
+ 	* Added optimized POWER10 kernels for SSCAL, DSCAL, CSCAL, ZSCAL
+	* Added optimized POWER10 kernels for SROT, DROT, CDOT, SASUM, DASUM
+	* Improved SSWAP, DSWAP, CSWAP, ZSWAP performance on POWER10
+	* Improved SCOPY and CCOPY performance on POWER10
+	* Improved SGEMM and DGEMM performance on POWER10
+	* Added support for compilation with the NVIDIA HPC compiler
+
+ x86_64:
+	* Added an optimized bfloat16 GEMM kernel for Cooperlake
+	* Added CPUID autodetection for Intel Rocket Lake and Tiger Lake cpus
+	* Improved the performance of SASUM,DASUM,SROT,DROT on AMD Ryzen cpus
+	* Added support for compilation with the NAG Fortran compiler
+	* Fixed recognition of the AMD AOCC compiler
+	* Fixed compilation for DYNAMIC_ARCH with clang on Windows
+	* Added support for running the BLAS/CBLAS tests on Windows
+	* Fixed signatures of the tls callback functions for Windows x64
+	* Fixed various issues with fma intrinsics support handling 
+
+ ARM:
+	* Added support for embedded Cortex M targets via a new option EMBEDDED
+
+ ARMV8:
+ 	* Fixed the THUNDERX2T99 and NEOVERSEN1 DNRM2/ZNRM2 kernels for inputs with Inf
+	* Added support for the DYNAMIC_LIST option
+	* Added support for compilation with the NVIDIA HPC compiler
+ 	* Added support for compiling with the NAG Fortran compiler
+
 ====================================================================
 Version 0.3.13
  12-Dec-2020

Makefile.rule

@@ -3,7 +3,7 @@
 #
 
 # This library's version
-VERSION = 0.3.13.dev
+VERSION = 0.3.14.dev
 
 # If you set the suffix, the library name will be libopenblas_$(LIBNAMESUFFIX).a
 # and libopenblas_$(LIBNAMESUFFIX).so. Meanwhile, the soname in shared library

param.h

@@ -72,6 +72,14 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #ifndef PARAM_H
 #define PARAM_H
 
+#define LONGCAST (BLASLONG)
+#if defined(__BYTE_ORDER__)
+#if __GNUC__ < 9
+#undef LONGCAST
+#define LONGCAST
+#endif
+#endif
+
 #define SBGEMM_DEFAULT_UNROLL_N 4
 #define SBGEMM_DEFAULT_UNROLL_M 8
 #define SBGEMM_DEFAULT_UNROLL_MN 32
@@ -2088,7 +2096,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #ifdef PPCG4
 #define GEMM_DEFAULT_OFFSET_A    0
 #define GEMM_DEFAULT_OFFSET_B 1024
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SGEMM_DEFAULT_UNROLL_M 16
 #define SGEMM_DEFAULT_UNROLL_N 4
@@ -2119,7 +2127,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A 2688
 #define GEMM_DEFAULT_OFFSET_B 3072
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x03fffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x03fffUL
 
 #if defined(__BYTE_ORDER__)&&(__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
 #define SGEMM_DEFAULT_UNROLL_M 4
@@ -2168,7 +2176,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A (32 * 0)
 #define GEMM_DEFAULT_OFFSET_B (32 * 0)
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SGEMM_DEFAULT_UNROLL_M 4
 #define SGEMM_DEFAULT_UNROLL_N 4
@@ -2204,7 +2212,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A (32 * 0)
 #define GEMM_DEFAULT_OFFSET_B (32 * 0)
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SGEMM_DEFAULT_UNROLL_M 8
 #define SGEMM_DEFAULT_UNROLL_N 4
@@ -2239,7 +2247,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #if defined(POWER3) || defined(POWER4) || defined(POWER5)
 #define GEMM_DEFAULT_OFFSET_A 0
 #define GEMM_DEFAULT_OFFSET_B 2048
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SGEMM_DEFAULT_UNROLL_M 4
 #define SGEMM_DEFAULT_UNROLL_N 4
@@ -2312,7 +2320,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A  384
 #define GEMM_DEFAULT_OFFSET_B 1024
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x03fffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x03fffUL
 
 #define SGEMM_DEFAULT_UNROLL_M 4
 #define SGEMM_DEFAULT_UNROLL_N 4
@@ -2345,7 +2353,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #define GEMM_DEFAULT_OFFSET_A 0 
 #define GEMM_DEFAULT_OFFSET_B 65536
 
-#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 #if defined(__32BIT__)
 #warning using BINARY32==POWER6
 #define SGEMM_DEFAULT_UNROLL_M 4
@@ -2398,7 +2406,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A 0 
 #define GEMM_DEFAULT_OFFSET_B 65536
-#define GEMM_DEFAULT_ALIGN 0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SWITCH_RATIO            16
 #define GEMM_PREFERED_SIZE      16
@@ -2437,7 +2445,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define GEMM_DEFAULT_OFFSET_A 0
 #define GEMM_DEFAULT_OFFSET_B 65536
-#define GEMM_DEFAULT_ALIGN 0x0ffffUL
+#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL
 
 #define SWITCH_RATIO            16
 #define GEMM_PREFERED_SIZE      16