Reduce the BLAS3 heap allocation threshold to 32 and mark it as configurable

diff --git a/Makefile.rule b/Makefile.rule
index 4d6f2d3..635e02c 100644 (file)
--- a/Makefile.rule
+++ b/Makefile.rule
@@ -279,7 +279,22 @@ COMMON_PROF = -pg
 
 # If you want to enable the experimental BFLOAT16 support
 # BUILD_HALF = 1
-#
+
+
+# Set the thread number threshold beyond which the job array for the threaded level3 BLAS
+# will be allocated on the heap rather than the stack. (This array alone requires 
+# NUM_THREADS*NUM_THREADS*128 bytes of memory so should not pose a problem at low cpu
+# counts, but obviously it is not the only item that ends up on the stack.
+# The default value of 32 ensures that the overall requirement is compatible
+# with the default 1MB stacksize imposed by having the Java VM loaded without use
+# of its -Xss parameter.
+# The value of 160 formerly used from about version 0.2.7 until 0.3.10 is easily compatible
+# with the common Linux stacksize of 8MB but will cause crashes with unwary use of the java
+# VM e.g. in Octave or with the java-based libhdfs in numpy or scipy code
+# BLAS3_MEM_ALLOC_THRESHOLD = 160
+
+
+
 # the below is not yet configurable, use cmake if you need to build only select types
 BUILD_SINGLE = 1
 BUILD_DOUBLE = 1

diff --git a/common.h b/common.h
index ac12dd6..ab28726 100644 (file)
--- a/common.h
+++ b/common.h
@@ -402,7 +402,7 @@ please https://github.com/xianyi/OpenBLAS/issues/246
 #endif
 
 #ifndef BLAS3_MEM_ALLOC_THRESHOLD
-#define BLAS3_MEM_ALLOC_THRESHOLD 160
+#define BLAS3_MEM_ALLOC_THRESHOLD 32 
 #endif
 
 #ifdef QUAD_PRECISION