Merge pull request #744 from jeromerobert/bug731

Bug731

CONTRIBUTORS.md

@@ -121,6 +121,11 @@ In chronological order:
   * [2014-10-10] trmm and sgemm kernels (optimized for APM's X-Gene 1).
                  ARMv8 support.
 
+* Jerome Robert <jeromerobert@gmx.com>
+  * [2015-01-01] Speed-up small `ger` and `gemv` using stack allocation (bug #478)
+  * [2015-12-23] `stack_check` in `gemv.c` (bug #722)
+  * [2016-01-19] Disable multi-threading in `ger` and `swap` for small matrices (bug #731)
+
 * Dan Kortschak
   * [2015-01-07] Added test for drotmg bug #484.
 

interface/ger.c

@@ -174,8 +174,11 @@ void CNAME(enum CBLAS_ORDER order,
   STACK_ALLOC(m, FLOAT, buffer);
 
 #ifdef SMPTEST
+  // Threshold chosen so that speed-up is > 1 on a Xeon E5-2630
+  if(1L * m * n > 24L * GEMM_MULTITHREAD_THRESHOLD)
     nthreads = num_cpu_avail(2);
-
+  else
+    nthreads = 1;
 
   if (nthreads == 1) {
 #endif

interface/swap.c

@@ -77,12 +77,13 @@ void CNAME(blasint n, FLOAT *x, blasint incx, FLOAT *y, blasint incy){
   if (incy < 0) y -= (n - 1) * incy;
 
 #ifdef SMP
-  nthreads = num_cpu_avail(1);
 
   //disable multi-thread when incx==0 or incy==0
   //In that case, the threads would be dependent.
-  if (incx == 0 || incy == 0)
+  if (incx == 0 || incy == 0 || n < 2097152 * GEMM_MULTITHREAD_THRESHOLD / sizeof(FLOAT))
     nthreads = 1;
+  else
+    nthreads = num_cpu_avail(1);
 
   if (nthreads == 1) {
 #endif

interface/zger.c

@@ -213,7 +213,11 @@ void CNAME(enum CBLAS_ORDER order,
   buffer = (FLOAT *)blas_memory_alloc(1);
 
 #ifdef SMPTEST
+  // Threshold chosen so that speed-up is > 1 on a Xeon E5-2630
+  if(1L * m * n > 3L * sizeof(FLOAT) * GEMM_MULTITHREAD_THRESHOLD)
     nthreads = num_cpu_avail(2);
+  else
+    nthreads = 1;
 
   if (nthreads == 1) {
 #endif