Found via `codespell -q 3 -w -L ith,als,dum,nd,amin,nto,wis,ba -S ./relapack,./kernel,./lapack-netlib`
* ARMV8 builds with the BINARY=32 option are now automatically handled as ARMV7
IBM Z:
- * optimized microkernels for single precicion BLAS1/2 functions have been added
+ * optimized microkernels for single precision BLAS1/2 functions have been added
for both Z13 and Z14
====================================================================
s/d/c/zaxpby, s/d/c/zimatcopy, s/d/c/zomatcopy.
* Added OPENBLAS_CORETYPE environment for dynamic_arch. (a86d34)
* Added NO_AVX2 flag for old binutils. (#401)
- * Support outputing the CPU corename on runtime.(#407)
- * Patched LAPACK to fix bug 114, 117, 118.
+ * Support outputting the CPU corename on runtime.(#407)
+ * Patched LAPACK to fix bug 114, 117, 118.
(http://www.netlib.org/lapack/bug_list.html)
* Disabled ?gemm3m for a work-around fix. (#400)
x86/x86-64:
13-Jan-2013
common:
* Update LAPACK to 3.5.0 version
- * Fixed compatiable issues with Clang and Pathscale compilers.
+ * Fixed compatible issues with Clang and Pathscale compilers.
x86/x86-64:
* Optimization on Intel Haswell.
26-Nov-2012
common:
* Added NO_SHARED flag to disable generating the shared library.
- * Compile LAPACKE with ILP64 modle when INTERFACE64=1 (#158)
+ * Compile LAPACKE with ILP64 model when INTERFACE64=1 (#158)
* Export LAPACK 3.4.2 symbols in shared library. (#147)
* Only detect the number of physical CPU cores on Mac OSX. (#157)
* Fixed NetBSD build. (#155)
* Fixed #28 a wrong result of dsdot on x86_64.
* Fixed #32 a SEGFAULT bug of zdotc with gcc-4.6.
* Fixed #33 ztrmm bug on Nehalem.
- * Work-around #27 the low performance axpy issue with small imput size & multithreads.
+ * Work-around #27 the low performance axpy issue with small input size & multithreads.
MIPS64:
* Fixed #28 a wrong result of dsdot on Loongson3A/MIPS64.
* Imported GotoBLAS2 1.13 BSD version
x86/x86_64:
- * On x86 32bits, fixed a bug in zdot_sse2.S line 191. This would casue
+ * On x86 32bits, fixed a bug in zdot_sse2.S line 191. This would cause
zdotu & zdotc failures. Instead, work-around it. (Refs issue #8 #9 on github)
* Modified ?axpy functions to return same netlib BLAS results
when incx==0 or incy==0 (Refs issue #7 on github)
# time out to improve performance. This number should be from 4 to 30
# which corresponds to (1 << n) cycles. For example, if you set to 26,
# thread will be running for (1 << 26) cycles(about 25ms on 3.0GHz
-# system). Also you can control this mumber by THREAD_TIMEOUT
+# system). Also you can control this number by THREAD_TIMEOUT
# CCOMMON_OPT += -DTHREAD_TIMEOUT=26
-# Using special device driver for mapping physically contigous memory
+# Using special device driver for mapping physically contiguous memory
# to the user space. If bigphysarea is enabled, it will use it.
# DEVICEDRIVER_ALLOCATION = 1
# If you need to synchronize FP CSR between threads (for x86/x86_64 only).
# CONSISTENT_FPCSR = 1
-# If any gemm arguement m, n or k is less or equal this threshold, gemm will be execute
+# If any gemm argument m, n or k is less or equal this threshold, gemm will be execute
# with single thread. (Actually in recent versions this is a factor proportional to the
# number of floating point operations necessary for the given problem size, no longer
# an individual dimension). You can use this setting to avoid the overhead of multi-
#### PPC/PPC64
-- **POWER8**: Optmized Level-3 BLAS and some Level-1, only with `USE_OPENMP=1`
+- **POWER8**: Optimized Level-3 BLAS and some Level-1, only with `USE_OPENMP=1`
#### IBM zEnterprise System
# helper functions for the kernel CMakeLists.txt
-# Set the default filenames for L1 objects. Most of these will be overriden by the appropriate KERNEL file.
+# Set the default filenames for L1 objects. Most of these will be overridden by the appropriate KERNEL file.
macro(SetDefaultL1)
set(SAMAXKERNEL amax.S)
set(DAMAXKERNEL amax.S)
set(KERNELDIR "${PROJECT_SOURCE_DIR}/kernel/${ARCH}")
-# TODO: nead to convert these Makefiles
+# TODO: need to convert these Makefiles
# include ${PROJECT_SOURCE_DIR}/cmake/${ARCH}.cmake
if (${CORE} STREQUAL "PPC440")
set(CODES_OUT ${CODES_OUT} PARENT_SCOPE)
endfunction ()
-# generates object files for each of the sources, using the BLAS naming scheme to pass the funciton name as a preprocessor definition
+# generates object files for each of the sources, using the BLAS naming scheme to pass the function name as a preprocessor definition
# @param sources_in the source files to build from
# @param defines_in (optional) preprocessor definitions that will be applied to all objects
# @param name_in (optional) if this is set this name will be used instead of the filename. Use a * to indicate where the float character should go, if no star the character will be prepended.
* SIZE must be carefully chosen to be:
* - as small as possible to maximize the number of stack allocation
* - large enough to support all architectures and kernel
- * Chosing a too small SIZE will lead to a stack smashing.
+ * Choosing a SIZE too small will lead to a stack smashing.
*/
#define STACK_ALLOC(SIZE, TYPE, BUFFER) \
/* make it volatile because some function (ex: dgemv_n.S) */ \
#endif
#if defined(PILEDRIVER) || defined(BULLDOZER) || defined(STEAMROLLER) || defined(EXCAVATOR)
-//Enable some optimazation for barcelona.
+//Enable some optimization for barcelona.
#define BARCELONA_OPTIMIZATION
#endif
#ifdef ASSEMBLER
#if defined(PILEDRIVER) || defined(BULLDOZER) || defined(STEAMROLLER) || defined(EXCAVATOR)
-//Enable some optimazation for barcelona.
+//Enable some optimization for barcelona.
#define BARCELONA_OPTIMIZATION
#endif
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
/* equal to "OMP_NUM_THREADS - 1" and thread only wakes up when */
/* jobs is queued. */
-/* We need this grobal for cheking if initialization is finished. */
+/* We need this global for checking if initialization is finished. */
int blas_server_avail __attribute__((aligned(ATTRIBUTE_SIZE))) = 0;
/* Local Variables */
#ifdef MONITOR
-/* Monitor is a function to see thread's status for every seconds. */
-/* Usually it turns off and it's for debugging. */
+/* Monitor is a function to see thread's status for every second. */
+/* Usually it turns off and it's for debugging. */
static pthread_t monitor_thread;
static int main_status[MAX_CPU_NUMBER];
/* This is a thread implementation for Win32 lazy implementation */
-/* Thread server common infomation */
+/* Thread server common information */
typedef struct{
CRITICAL_SECTION lock;
HANDLE filled;
} blas_pool_t;
-/* We need this global for cheking if initialization is finished. */
+/* We need this global for checking if initialization is finished. */
int blas_server_avail = 0;
/* Local Variables */
int mynode = 1;
- /* if number of threads is larger than inital condition */
+ /* if number of threads is larger than initial condition */
if (pos < 0) {
sched_setaffinity(0, sizeof(cpu_orig_mask), &cpu_orig_mask[0]);
return 0;
#ifdef ALLOC_DEVICEDRIVER
if ((*func == alloc_devicedirver) && (map_address == (void *)-1)) {
- fprintf(stderr, "OpenBLAS Warning ... Physically contigous allocation was failed.\n");
+ fprintf(stderr, "OpenBLAS Warning ... Physically contiguous allocation was failed.\n");
}
#endif
$openmp = "-openmp";
}
- # for embeded underscore name, e.g. zho_ge, it may append 2 underscores.
+ # for embedded underscore name, e.g. zho_ge, it may append 2 underscores.
$data = `$compiler -O2 -S ftest3.f > /dev/null 2>&1 && cat ftest3.s && rm -f ftest3.s`;
if ($data =~ / zho_ge__/) {
$need2bu = 1;
axpby.c
)
-# TODO: USE_NETLIB_GEMV shoudl switch gemv.c to netlib/*gemv.f
+# TODO: USE_NETLIB_GEMV should switch gemv.c to netlib/*gemv.f
# these all have 'z' sources for complex versions
set(BLAS2_SOURCES
gemv.c ger.c
//disable multi-thread when incx==0 or incy==0
//In that case, the threads would be dependent.
//
- //Temporarily work-around the low performance issue with small imput size &
+ //Temporarily work-around the low performance issue with small input size &
//multithreads.
if (incx == 0 || incy == 0 || n <= MULTI_THREAD_MINIMAL)
nthreads = 1;
//disable multi-thread when incx==0 or incy==0
//In that case, the threads would be dependent.
//
- //Temporarily work-around the low performance issue with small imput size &
+ //Temporarily work-around the low performance issue with small input size &
//multithreads.
if (incx == 0 || incy == 0 || n <= MULTI_THREAD_MINIMAL)
nthreads = 1;
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
* ( 1 + ( n - 1 )*abs( INCX ) ).
* Before entry, the incremented array X must contain the n
* element vector x. On exit, X is overwritten with the
-* tranformed vector x.
+* transformed vector x.
*
* INCX - INTEGER.
* On entry, INCX specifies the increment for the elements of
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*
SUBROUTINE STEST1(SCOMP1,STRUE1,SSIZE,SFAC)
* ************************* STEST1 *****************************
*
-* THIS IS AN INTERFACE SUBROUTINE TO ACCOMODATE THE FORTRAN
+* THIS IS AN INTERFACE SUBROUTINE TO ACCOMMODATE THE FORTRAN
* REQUIREMENT THAT WHEN A DUMMY ARGUMENT IS AN ARRAY, THE
* ACTUAL ARGUMENT MUST ALSO BE AN ARRAY OR AN ARRAY ELEMENT.
*