Merge pull request #2399 from martin-frbg/buffersize

Make BUFFER_SIZE configurable at build time

Makefile.rule

@@ -97,6 +97,15 @@ VERSION = 0.3.9.dev
 # they need to wait for the preceding API calls to finish or risk data corruption.
 # NUM_PARALLEL = 2
 
+# When multithreading, OpenBLAS needs to use a memory buffer for communicating
+# and collating results for individual subranges of the original matrix. Since
+# the original GotoBLAS of the early 2000s, the default size of this buffer has
+# been set at a value of 32<<20 (which is 32MB) on x86_64 , twice that on PPC.
+# If you expect to handle large problem sizes (beyond about 30000x30000) uncomment
+# this line and adjust the (32<<n) factor if necessary. Usually an insufficient value
+# manifests itself as a crash in the relevant scal kernel (sscal_k, dscal_k etc) 
+# BUFFERSIZE = 25
+
 # If you don't need to install the static library, please comment this in.
 # NO_STATIC = 1
 

cmake/system.cmake

@@ -289,6 +289,10 @@ set(CCOMMON_OPT "${CCOMMON_OPT} -DMAX_CPU_NUMBER=${NUM_THREADS}")
 
 set(CCOMMON_OPT "${CCOMMON_OPT} -DMAX_PARALLEL_NUMBER=${NUM_PARALLEL}")
 
+if (BUFFERSIZE)
+set(CCOMMON_OPT "${CCOMMON_OPT} -DBUFFERSIZE=${BUFFERSIZE}")
+endif ()
+
 if (USE_SIMPLE_THREADED_LEVEL3)
   set(CCOMMON_OPT "${CCOMMON_OPT} -DUSE_SIMPLE_THREADED_LEVEL3")
 endif ()

common_x86_64.h

@@ -225,7 +225,11 @@ static __inline int blas_quickdivide(unsigned int x, unsigned int y){
 #endif
 #define HUGE_PAGESIZE	( 2 << 20)
 
+#ifndef BUFFERSIZE
 #define BUFFER_SIZE	(32 << 20)
+#else
+#define BUFFER_SIZE	(32 << BUFFERSIZE)
+#endif
 
 #define SEEK_ADDRESS