Misc. typo fixes

Found via `codespell -q 3 -w -L ith,als,dum,nd,amin,nto,wis,ba -S ./relapack,./kernel,./lapack-netlib`

Changelog.txt

@@ -74,7 +74,7 @@ ARMv8:
 	* 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
 
 ====================================================================
@@ -588,7 +588,7 @@ common:
 	  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)
+	* 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)
@@ -628,7 +628,7 @@ Version 0.2.9.rc1
 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.
@@ -705,7 +705,7 @@ Version 0.2.5
 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)
@@ -896,7 +896,7 @@ x86/x86_64:
 	* 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.
@@ -919,7 +919,7 @@ common:
 	* 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)

Makefile.rule

@@ -181,17 +181,17 @@ NO_AFFINITY = 1
 # 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-

README.md

@@ -133,7 +133,7 @@ Please read `GotoBLAS_01Readme.txt`.
 
 #### 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
 

cmake/kernel.cmake

@@ -1,7 +1,7 @@
 # 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)

cmake/system.cmake

@@ -283,7 +283,7 @@ endif ()
 
 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")

cmake/utils.cmake

@@ -89,7 +89,7 @@ function(AllCombinations list_in absent_codes_in)
   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.

common_stackalloc.h

@@ -45,7 +45,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  * 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) */                 \

common_x86.h

@@ -214,7 +214,7 @@ static __inline int blas_quickdivide(unsigned int x, unsigned int y){
 #endif
 
 #if defined(PILEDRIVER) || defined(BULLDOZER) || defined(STEAMROLLER) || defined(EXCAVATOR)
-//Enable some optimazation for barcelona.
+//Enable some optimization for barcelona.
 #define BARCELONA_OPTIMIZATION
 #endif
 

common_x86_64.h

@@ -276,7 +276,7 @@ static __inline int blas_quickdivide(unsigned int x, unsigned int y){
 #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
 

ctest/c_cblat1.f

@@ -577,7 +577,7 @@
       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.
 *

ctest/c_dblat1.f

@@ -653,7 +653,7 @@
       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.
 *

ctest/c_sblat1.f

@@ -653,7 +653,7 @@
       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.
 *

ctest/c_zblat1.f

@@ -577,7 +577,7 @@
       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.
 *

driver/others/blas_server.c

@@ -109,7 +109,7 @@ extern unsigned int openblas_thread_timeout();
 /* 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 */
@@ -150,7 +150,7 @@ static unsigned int thread_timeout = (1U << (THREAD_TIMEOUT));
 
 #ifdef MONITOR
 
-/* Monitor is a function to see thread's status for every seconds. */
+/* 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;

driver/others/blas_server_win32.c

@@ -50,7 +50,7 @@
 
 /* This is a thread implementation for Win32 lazy implementation */
 
-/* Thread server common infomation */
+/* Thread server common information */
 typedef struct{
   CRITICAL_SECTION lock;
   HANDLE filled;
@@ -61,7 +61,7 @@ typedef struct{
 
 } 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 */

driver/others/init.c

@@ -765,7 +765,7 @@ int gotoblas_set_affinity(int pos) {
 
   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;

driver/others/memory.c

@@ -2751,7 +2751,7 @@ void *blas_memory_alloc(int procpos){
 
 #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
 

f_check

@@ -125,7 +125,7 @@ if ($compiler eq "") {
 	    $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;

interface/CMakeLists.txt

@@ -24,7 +24,7 @@ set(BLAS1_MANGLED_SOURCES
   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

interface/axpy.c

@@ -91,7 +91,7 @@ void CNAME(blasint n, FLOAT alpha, FLOAT *x, blasint incx, FLOAT *y, blasint inc
   //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;

interface/zaxpy.c

@@ -99,7 +99,7 @@ void CNAME(blasint n, FLOAT *ALPHA, FLOAT *x, blasint incx, FLOAT *y, blasint in
   //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;

reference/ctbmvf.f

@@ -117,7 +117,7 @@
 *           ( 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

reference/ctpmvf.f

@@ -77,7 +77,7 @@
 *           ( 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

reference/ctrmvf.f

@@ -80,7 +80,7 @@
 *           ( 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

reference/dtbmvf.f

@@ -117,7 +117,7 @@
 *           ( 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

reference/dtpmvf.f

@@ -77,7 +77,7 @@
 *           ( 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

reference/dtrmvf.f

@@ -80,7 +80,7 @@
 *           ( 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

reference/stbmvf.f

@@ -117,7 +117,7 @@
 *           ( 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

reference/stpmvf.f

@@ -77,7 +77,7 @@
 *           ( 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

reference/strmvf.f

@@ -80,7 +80,7 @@
 *           ( 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

reference/ztbmvf.f

@@ -117,7 +117,7 @@
 *           ( 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

reference/ztpmvf.f

@@ -77,7 +77,7 @@
 *           ( 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

reference/ztrmvf.f

@@ -80,7 +80,7 @@
 *           ( 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

test/cblat1.f

@@ -576,7 +576,7 @@
       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.
 *

test/dblat1.f

@@ -991,7 +991,7 @@
       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.
 *

test/sblat1.f

@@ -946,7 +946,7 @@
       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.
 *

test/zblat1.f

@@ -576,7 +576,7 @@
       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.
 *