diff --git a/volk/apps/volk_profile.cc b/volk/apps/volk_profile.cc
index bd36d6d..893c0da 100644
--- a/volk/apps/volk_profile.cc
+++ b/volk/apps/volk_profile.cc
@@ -13,7 +13,10 @@ extern "C" {
 int main(int argc, char *argv[]) {
 
     std::vector<std::string> results;
-    
+
+    VOLK_PROFILE(volk_32fc_32f_multiply_32fc_a, 1e-4, 0, 2046, 1, &results);
+
+    /*    
     //VOLK_PROFILE(volk_16i_x5_add_quad_16i_x4_a, 1e-4, 2046, 10000, &results);
     //VOLK_PROFILE(volk_16i_branch_4_state_8_a, 1e-4, 2046, 10000, &results);
     VOLK_PROFILE(volk_16ic_s32f_deinterleave_real_32f_a, 1e-5, 32768.0, 204600, 10000, &results);
@@ -117,7 +120,7 @@ int main(int argc, char *argv[]) {
     VOLK_PROFILE(volk_32fc_s32fc_multiply_32fc_u, 1e-4, 0, 204600, 1000, &results);
     VOLK_PROFILE(volk_32f_s32f_multiply_32f_a, 1e-4, 1.0, 204600, 10000, &results);
     VOLK_PROFILE(volk_32f_s32f_multiply_32f_u, 1e-4, 0, 204600, 1000, &results);
-
+    */
 
     char path[256];
     get_config_path(path);
diff --git a/volk/include/volk/volk_32fc_32f_multiply_32fc_a.h b/volk/include/volk/volk_32fc_32f_multiply_32fc_a.h
index b7350b9..cb1ef8e 100644
--- a/volk/include/volk/volk_32fc_32f_multiply_32fc_a.h
+++ b/volk/include/volk/volk_32fc_32f_multiply_32fc_a.h
@@ -72,6 +72,7 @@ static inline void volk_32fc_32f_multiply_32fc_a_generic(lv_32fc_t* cVector, con
   
   for(number = 0; number < num_points; number++){
     *cPtr++ = (*aPtr++) * (*bPtr++);
+    printf("%lu %lu %lu %u \n",sizeof(*aPtr),sizeof(*bPtr),sizeof(*cPtr),number);
   }
 }
 #endif /* LV_HAVE_GENERIC */
diff --git a/volk/lib/qa_utils.cc b/volk/lib/qa_utils.cc
index bb37801..d08ae98 100644
--- a/volk/lib/qa_utils.cc
+++ b/volk/lib/qa_utils.cc
@@ -293,8 +293,12 @@ bool run_volk_tests(struct volk_func_desc desc,
     //for(int i=0; i<outputsig.size(); i++) std::cout << "Output: " << outputsig[i].str << std::endl;
     std::vector<void *> inbuffs;
     BOOST_FOREACH(volk_type_t sig, inputsig) {
-        if(!sig.is_scalar) //we don't make buffers for scalars
+        if(!sig.is_scalar) {//we don't make buffers for scalars
           inbuffs.push_back(mem_pool.get_new(vlen*sig.size*(sig.is_complex ? 2 : 1)));
+	  std::cout << "in signature: " << sig.str << " vlen: " << vlen << " size: " << sig.size
+		    << " is_complex: " << sig.is_complex << " buf size: "
+		    << (vlen*sig.size*(sig.is_complex ? 2 : 1)) << std::endl;
+	}
     }
     for(size_t i=0; i<inbuffs.size(); i++) {
         load_random_data(inbuffs[i], inputsig[i], vlen);
@@ -306,6 +310,10 @@ bool run_volk_tests(struct volk_func_desc desc,
         std::vector<void *> arch_buffs;
         for(size_t j=0; j<outputsig.size(); j++) {
             arch_buffs.push_back(mem_pool.get_new(vlen*outputsig[j].size*(outputsig[j].is_complex ? 2 : 1)));
+	    std::cout << "out signature: " << outputsig[j].str << " vlen: " << vlen
+		      << " size: " << outputsig[j].size
+		      << " is_complex: " << outputsig[j].is_complex << " buf size: "
+		      << (vlen*outputsig[j].size*(outputsig[j].is_complex ? 2 : 1)) << std::endl;
         }
         for(size_t j=0; j<inputsig.size(); j++) {
             arch_buffs.push_back(inbuffs[j]);