diff --git a/tensor_t/src/tensor_t/cl_tensor_t.c b/tensor_t/src/tensor_t/cl_tensor_t.c
index a038cac..255b976 100644
--- a/tensor_t/src/tensor_t/cl_tensor_t.c
+++ b/tensor_t/src/tensor_t/cl_tensor_t.c
@@ -3,6 +3,12 @@
 
 #define MAX_SOURCE_SIZE (0x100000)
 
+#define FREE_dM_S_\
+  free_dimension(dM0);\
+  free_dimension(dM1);\
+  free_dimension(dM);\
+  free_dimension(dSub0);\
+  free_dimension(dSub1);\
 
 
 #define SETUP_cl_KERNEL_(type,file_cl_src,func_cl_name)\
@@ -18,7 +24,7 @@
         fprintf(stderr, "Failed to load kernel. \n"); \
         exit(1); \
     } \
-    source_str = (char*)malloc(MAX_SOURCE_SIZE); \
+    source_str = malloc(MAX_SOURCE_SIZE); \
     source_size = fread( source_str, 1, MAX_SOURCE_SIZE, fp); \
     fclose( fp ); \
  \
@@ -85,10 +91,11 @@
       char *log = malloc(sizeof(char)*len);\
       clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, len, log, NULL);\
       printf("Error: Failed to build program executable!\n  %s \n",log);\
+      free(log);\
     }\
     /*/ Create the OpenCL kernel */ \
     /*char func_cl_name[250]; sprintf(func_cl_name,"prodTensorLin_%s", #type);*/ \
-    printf("cl_func_type = %s\n",func_cl_name);  \
+    /*printf("cl_func_type = %s\n",func_cl_name); */ \
     cl_kernel kernel = clCreateKernel(program, func_cl_name, &ret); \
  
 
@@ -194,7 +201,7 @@ void cl_tensorContractnProd_##type(tensor_##type** MM, tensor_##type *M0, tensor
     dimension *dM1 = init_dim(tDk1, contractionNumber);\
     dimension *dM0 = init_dim(tDk0, contractionNumber);\
     dimension *dM;\
-    min_dimension(&dM, dM0, dM1);\
+    min_copy_dimension(&dM, dM0, dM1);\
     \
     dimension *dd;\
     add_dimension(&dd, dSub0, dSub1);\
@@ -230,6 +237,7 @@ void cl_tensorContractnProd_##type(tensor_##type** MM, tensor_##type *M0, tensor
   EXEC_cl_KERNEL(type);\
   READ_BUF_N_CLEANUP(type)\
 \
+  FREE_dM_S_ \
 } \
  \
 \
@@ -283,7 +291,7 @@ void cl2d_tensorContractnProd_##type(tensor_##type **MM, tensor_##type *M0, tens
     dimension *dM1 = init_dim(tDk1, contractionNumber);\
     dimension *dM0 = init_dim(tDk0, contractionNumber);\
     dimension *dM;\
-    min_dimension(&dM, dM0, dM1);\
+    min_copy_dimension(&dM, dM0, dM1);\
     \
     dimension *dd;\
     add_dimension(&dd, dSub0, dSub1);\
@@ -320,7 +328,8 @@ void cl2d_tensorContractnProd_##type(tensor_##type **MM, tensor_##type *M0, tens
   /*printf("EXEC_cl_2d_KERNEL(type,%ld,%ld,%ld,%ld)\n",dSub0->rank,dSub1->rank,div0Wsz,div1Wsz);\
   */EXEC_cl_2d_KERNEL(type,dSub0->rank,dSub1->rank,div0Wsz,div1Wsz);\
   READ_BUF_N_CLEANUP(type)\
-\
+  FREE_dM_S_ \
+  \
 } \
 \
 
diff --git a/tensor_t/src/tensor_t/tensor_t.c b/tensor_t/src/tensor_t/tensor_t.c
index 08f7da8..5fa242b 100644
--- a/tensor_t/src/tensor_t/tensor_t.c
+++ b/tensor_t/src/tensor_t/tensor_t.c
@@ -506,6 +506,7 @@ void tensorProdThrea2d_##type(tensor_##type **MM, tensor_##type *M0, tensor_##ty
   free(thrd);\
   free(arg_th);\
 }  \
+\
 struct arg_ProdContract_##type{\
   type *M0x;\
   type *M1x;\
@@ -603,6 +604,98 @@ void tensorContractnProdThread_##type(tensor_##type** MM, tensor_##type *M0, ten
   free(arg_th);\
   FREE_dM_S_ ; \
 }\
+\
+struct arg_Pro2dContract_##type{\
+  type *M0x;\
+  type *M1x;\
+  type *Mx;\
+  size_t beginRange;\
+  size_t endRange;\
+  size_t dMRank;\
+  size_t dSub0Rank;\
+  size_t dSub1Rank;\
+};\
+void* runPro2dContract_thread_##type(void *arg){\
+  struct arg_Pro2dContract_##type *arg_t = arg;\
+  size_t n0_id, n1_id, l;\
+    for (size_t i = arg_t->beginRange; i < arg_t->endRange; i++) {\
+      for (size_t j = 0; j < arg_t->dSub1Rank; j++) {\
+        if(endian)\
+          l = j + arg_t->dSub1Rank * i;\
+        else\
+          l = j * arg_t->dMRank + i;\
+        arg_t->Mx[l] = 0;\
+        for (size_t k = 0; k < arg_t->dMRank; k++) {\
+          if(endian){\
+            n0_id= i * arg_t->dMRank + k;\
+            n1_id= j + arg_t->dSub1Rank * k;\
+          }\
+          else{\
+            n0_id= i + arg_t->dSub0Rank * k;\
+            n1_id= j * arg_t->dMRank + k;\
+          }\
+            arg_t->Mx[l] += arg_t->M0x[n0_id] * arg_t->M1x[n1_id];\
+        }\
+      }\
+    }\
+}\
+/* M[x0,x1,x3..xn] X M[y0,y1,y3..ym] = M[z0,z1...zp] (deep = l > 0) /exists 1<= l<...<l=n /  xl = y0,x{l+1}=y1, x{n}=yl  et zi=xi i<n-l et zj=y{j-(n-l)} j>=n-l alor p=n+m-2l\
+ M[x0,x1,x3..xl x{l+1}...xn] X M[xn,x{n-1},x{n-2}...xl y{l+1} ..ym] = M[x0,x1..xly{l+1}...y{n+m-2l}] (deep = l > 0)\
+M[[i][j]]=sum_{[k]}M0[[i][k]]*M[[k][j]]*/\
+\
+void tensorContractnPro2dThread_##type(tensor_##type** MM, tensor_##type *M0, tensor_##type *M1, size_t contractionNumber, size_t nbthread) {\
+\
+    size_t len0 = M0->dim->size - contractionNumber;\
+    size_t len1 = M1->dim->size - contractionNumber;\
+\
+    size_t* tsub0 = malloc(sizeof(size_t) *len0);\
+    size_t* tsub1 = malloc(sizeof(size_t) *len1);\
+    size_t* tDk1 = malloc(sizeof(size_t) *contractionNumber);\
+    size_t* tDk0 = malloc(sizeof(size_t) *contractionNumber);\
+    subArray(tsub0, M0->dim->perm, 0, len0, 0);\
+    subArray(tsub1, M1->dim->perm, 0, len1, contractionNumber);\
+    subArray(tDk1, M1->dim->perm, 0, contractionNumber, 0);\
+    subArray(tDk0, M0->dim->perm, 0, contractionNumber, len0);\
+    dimension *dSub0 = init_dim(tsub0, len0);\
+    dimension *dSub1 = init_dim(tsub1, len1);\
+    dimension *dM1 = init_dim(tDk1, contractionNumber);\
+    dimension *dM0 = init_dim(tDk0, contractionNumber);\
+    dimension *dM;\
+    min_copy_dimension(&dM, dM0, dM1);\
+    \
+    dimension *dd;\
+    add_dimension(&dd, dSub0, dSub1);\
+    updateRankDim(dd);\
+    *MM = CREATE_TENSOR_##type(dd);\
+    tensor_##type *M= *MM;\
+\
+\
+    \
+  pthread_t *thrd = malloc(nbthread * sizeof(pthread_t));\
+  struct arg_Pro2dContract_##type **arg_th = malloc( nbthread * sizeof(struct arg_Pro2dContract_##type *));\
+\
+  for(size_t i = 0; i < nbthread; ++i) {\
+    arg_th[i] = malloc(sizeof(struct arg_Pro2dContract_##type));\
+    arg_th[i]->M0x=M0->x;\
+    arg_th[i]->M1x=M1->x;\
+    arg_th[i]->Mx=M->x;\
+    arg_th[i]->beginRange = i*(dSub0->rank)/nbthread ;\
+    arg_th[i]->endRange = (i+1)*(dSub0->rank)/nbthread ;\
+    arg_th[i]->dSub1Rank = dSub1->rank;\
+    arg_th[i]->dSub0Rank = dSub0->rank;\
+    arg_th[i]->dMRank = dM->rank;\
+    pthread_create(&thrd[i], NULL, runPro2dContract_thread_##type, (void*)arg_th[i]);\
+  }\
+\
+  for(size_t i=0; i< nbthread; ++i){\
+    pthread_join(thrd[i], NULL);\
+    free(arg_th[i]);\
+  }\
+\
+  free(thrd);\
+  free(arg_th);\
+  FREE_dM_S_ ; \
+}\
 void tensorContractnProdNotOpt_##type(tensor_##type** MM, tensor_##type *M0, tensor_##type *M1, size_t contractionNumber) {\
    /* if (!checkMatchProdtensor(M0->dim, M1->dim, contractionNumber)) {\
         prsize_tf("Deep = %d\n", contractionNumber);\
diff --git a/tensor_t/src/tensor_t/tensor_t.h b/tensor_t/src/tensor_t/tensor_t.h
index 112d139..0e795a8 100644
--- a/tensor_t/src/tensor_t/tensor_t.h
+++ b/tensor_t/src/tensor_t/tensor_t.h
@@ -29,6 +29,7 @@ void tensorContractnProd_##type(tensor_##type **MM, tensor_##type *M0, tensor_##
 void tensorProdThread_##type(tensor_##type **MM, tensor_##type *M0, tensor_##type *M1,size_t nbthread); \
 void tensorProdThrea2d_##type(tensor_##type **MM, tensor_##type *M0, tensor_##type *M1,size_t nbthread); \
 void tensorContractnProdThread_##type(tensor_##type **MM, tensor_##type *M0, tensor_##type *M1, size_t contractionNumber, size_t nbthread); \
+void tensorContractnPro2dThread_##type(tensor_##type **MM, tensor_##type *M0, tensor_##type *M1, size_t contractionNumber, size_t nbthread); \
 void tensorContractnProdNotOpt_##type(tensor_##type **MM, tensor_##type *M0, tensor_##type *M1, size_t contractionNumber); \
 
 
diff --git a/tensor_t/test/is_good.c b/tensor_t/test/is_good.c
index 3271a98..a497046 100644
--- a/tensor_t/test/is_good.c
+++ b/tensor_t/test/is_good.c
@@ -17,7 +17,7 @@
 //#include "permutation_t/permutation_t.h"
 #include "tensor_t/tensor_t.h"
 
-#define VALGRING_ 1
+#define VALGRIND_ 0
 
 TEST(rank){
   dimension *D=create_dim(4);
@@ -40,7 +40,7 @@ void print_tensor_float(tensor_TYPE_FLOAT *M, char *msg){
   }
   LOG("================= %s ===============\n",msg);
 
-#if VALGRING_
+#if VALGRIND_
   for(size_t i=0; i<M->dim->rank;++i)
       LOG("[%ld]: %f ",i,M->x[i]);
   
@@ -51,7 +51,7 @@ void print_tensor_float(tensor_TYPE_FLOAT *M, char *msg){
 
 void print_tensor_double(tensor_TYPE_DOUBLE *M, char *msg){
   LOG("================= %s ===============\n",msg);
-#if VALGRING_
+#if VALGRIND_
   for(size_t i=0; i<M->dim->rank;++i)
       LOG("[%ld]: %lf ",i,M->x[i]);
   
@@ -262,7 +262,7 @@ TEST(tensorSubtail ){
 TEST(tensorProd ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(2);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -315,7 +315,7 @@ TEST(tensorProd ){
 TEST(tensorContractnProd_TYPE_FLOAT ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -377,7 +377,7 @@ TEST(tensorContractnProd_TYPE_FLOAT ){
 TEST(tensorContractnProd_TYPE_FLOAT2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -438,7 +438,7 @@ TEST(tensorContractnProd_TYPE_FLOAT2 ){
 TEST(tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -499,7 +499,7 @@ TEST(tensorContractnProd_TYPE_DOUBLE2 ){
 TEST(VStensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -555,11 +555,72 @@ TEST(VStensorContractnProd_TYPE_DOUBLE2 ){
   free_tensor_TYPE_DOUBLE(M1);
 
 }
+TEST(Pthread_tensorContractnPro2d_TYPE_DOUBLE2 ){
+  dimension *d0=create_dim(3);
+  dimension *d1=create_dim(3);
+#if VALGRIND_
+  d0->perm[0]=5;
+  d0->perm[1]=2; //3;
+  d0->perm[2]=3;
 
+  d1->perm[0]=2;
+  d1->perm[1]=3;//3;
+  d1->perm[2]=8;
+
+#else
+
+  d0->perm[0]=125;
+  d0->perm[1]=52; //3;
+  d0->perm[2]=63;
+
+  d1->perm[0]=52;
+  d1->perm[1]=63;//3;
+  d1->perm[2]=154;
+#endif
+
+
+  updateRankDim(d0);
+  updateRankDim(d1);
+
+
+  tensor_TYPE_DOUBLE *M0 = CREATE_TENSOR_TYPE_DOUBLE(d0);
+  tensor_TYPE_DOUBLE *M1 = CREATE_TENSOR_TYPE_DOUBLE(d1);
+
+  LOG("M0->dim->rank = %ld\n",M0->dim->rank);
+  LOG("M1->dim->rank = %ld\n",M1->dim->rank);
+  for(size_t i=0; i<M0->dim->rank;++i) M0->x[i]=i*0.1 +1;
+  for(size_t i=0; i<M1->dim->rank;++i) M1->x[i]=i*0.003 + 2;
+
+  //print_tensor_double(M0,"M0");
+  //print_tensor_double(M1,"M1");
+
+  tensor_TYPE_DOUBLE *M;
+  tensor_TYPE_DOUBLE *MnO;
+
+  size_t nbthread = 5;
+
+  tensorContractnProd_TYPE_DOUBLE(&M, M0,M1,2);
+  //print_tensor_double(M,"M");
+  //cl_tensorContractnProd_TYPE_DOUBLE(&MnO, M0,M1,2);
+  tensorContractnPro2dThread_TYPE_DOUBLE(&MnO, M0,M1,2,nbthread);
+
+  //print_tensor_double(MnO,"MnO");
+ 
+  // for(size_t i=0;i<M->dim->rank;++i)
+  //    EXPECT_EQ_TYPE_DOUBLE(M->x[i],MnO->x[i]);
+    
+  EXPECT_ARRAY_EQ_TYPE_DOUBLE(M->x,M->dim->rank,MnO->x,MnO->dim->rank);
+
+  free_tensor_TYPE_DOUBLE(M);
+  free_tensor_TYPE_DOUBLE(MnO);
+  free_tensor_TYPE_DOUBLE(M0);
+  free_tensor_TYPE_DOUBLE(M1);
+
+}
 TEST(Pthread_tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=5;
   d0->perm[1]=2; //3;
   d0->perm[2]=3;
@@ -624,7 +685,7 @@ TEST(tensorProd_vs ){
   dimension *d1=create_dim(2);
 
 
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=2;
   d0->perm[1]=3;
   d0->perm[2]=2;
@@ -676,7 +737,7 @@ TEST(tensorProd_vsThread ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(2);
 
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=2;
   d0->perm[1]=3;
   d0->perm[2]=2;
@@ -734,7 +795,7 @@ TEST(tensorProd_vsThread2d ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(2);
 
-#if VALGRING_
+#if VALGRIND_
   d0->perm[0]=2;
   d0->perm[1]=3;
   d0->perm[2]=2;
diff --git a/tensor_t/test_cl/is_good.c b/tensor_t/test_cl/is_good.c
index 902c7bb..d2cbb5f 100644
--- a/tensor_t/test_cl/is_good.c
+++ b/tensor_t/test_cl/is_good.c
@@ -19,6 +19,7 @@
 #include "tensor_t/cl_tensor_t.h"
 //#include "tools_t/tools_t.h"
 
+#define VALGRIND 1
 
 TEST(rank){
   dimension *D=create_dim(4);
@@ -36,19 +37,22 @@ TEST(rank){
 
 void print_tensor_float(tensor_TYPE_FLOAT *M, char *msg){
   LOG("================= %s ===============\n",msg);
+#if VALGRIND
   for(size_t i=0; i<M->dim->rank;++i)
       LOG("[%ld]: %f ",i,M->x[i]);
-  
     LOG("%s","\n");
+#endif  
 }
 
 
 void print_tensor_double(tensor_TYPE_DOUBLE *M, char *msg){
   LOG("================= %s ===============\n",msg);
+#if VALGRIND
   for(size_t i=0; i<M->dim->rank;++i)
       LOG("[%ld]: %lf ",i,M->x[i]);
   
     LOG("%s","\n");
+#endif  
 }
 
   extern long int PRECISION_TYPE_FLOAT ;
@@ -302,7 +306,17 @@ TEST(cl_tensorContractnProd_TYPE_DOUBLE2 ){
 TEST(tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
+#if VALGRIND
 
+  d0->perm[0]=12;
+  d0->perm[1]=5; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=5;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=14;
+
+#else
   d0->perm[0]=125;
   d0->perm[1]=52; //3;
   d0->perm[2]=63;
@@ -310,7 +324,7 @@ TEST(tensorContractnProd_TYPE_DOUBLE2 ){
   d1->perm[0]=52;
   d1->perm[1]=63;//3;
   d1->perm[2]=54;
-
+#endif
   updateRankDim(d0);
   updateRankDim(d1);
 
@@ -352,6 +366,7 @@ TEST(TensorProdCL){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(2);
 
+ 
   d0->perm[0]=2;
   d0->perm[1]=3;
   d0->perm[2]=2;
@@ -375,6 +390,7 @@ TEST(TensorProdCL){
   print_tensor_float(M1,"M1");
 
 
+
   tensor_TYPE_FLOAT *M; 
   tensor_TYPE_FLOAT *Mn; 
 
@@ -399,7 +415,17 @@ TEST(TensorProdCL){
 TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
+#if VALGRIND
 
+  d0->perm[0]=12;
+  d0->perm[1]=4; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=4;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=16;
+
+#else  
 
   d0->perm[0]=512;
   d0->perm[1]=48; //3;
@@ -408,6 +434,7 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   d1->perm[0]=48;
   d1->perm[1]=64;//3;
   d1->perm[2]=240;
+#endif
 
   updateRankDim(d0);
   updateRankDim(d1);
@@ -457,7 +484,17 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
 TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
+#if VALGRIND
 
+  d0->perm[0]=12;
+  d0->perm[1]=4; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=4;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=16;
+
+#else  
 
   d0->perm[0]=512;
   d0->perm[1]=48; //3;
@@ -466,6 +503,9 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   d1->perm[0]=48;
   d1->perm[1]=64;//3;
   d1->perm[2]=240;
+#endif
+
+
 
   updateRankDim(d0);
   updateRankDim(d1);
@@ -519,7 +559,17 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
 TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
+#if VALGRIND
 
+  d0->perm[0]=12;
+  d0->perm[1]=4; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=4;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=16;
+
+#else  
 
   d0->perm[0]=512;
   d0->perm[1]=48; //3;
@@ -528,6 +578,9 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
   d1->perm[0]=48;
   d1->perm[1]=64;//3;
   d1->perm[2]=240;
+#endif
+
+
 
   updateRankDim(d0);
   updateRankDim(d1);
@@ -578,13 +631,24 @@ TEST(VS_thrd_tensorContractnProd_TYPE_DOUBLE2 ){
 
 
 
-#if 1
 
 
 TEST(VScltensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
 
+#if VALGRIND
+
+  d0->perm[0]=12;
+  d0->perm[1]=4; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=4;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=16;
+
+#else  
+
   d0->perm[0]=512;
   d0->perm[1]=48; //3;
   d0->perm[2]=64;
@@ -592,6 +656,8 @@ TEST(VScltensorContractnProd_TYPE_DOUBLE2 ){
   d1->perm[0]=48;
   d1->perm[1]=64;//3;
   d1->perm[2]=240;
+#endif
+
 
   updateRankDim(d0);
   updateRankDim(d1);
@@ -636,6 +702,27 @@ TEST(VScltensorContractnProd_TYPE_DOUBLE2 ){
 TEST(VScl2dtensorContractnProd_TYPE_DOUBLE2 ){
   dimension *d0=create_dim(3);
   dimension *d1=create_dim(3);
+#if VALGRIND
+
+  d0->perm[0]=12;
+  d0->perm[1]=4; //3;
+  d0->perm[2]=6;
+
+  d1->perm[0]=4;
+  d1->perm[1]=6;//3;
+  d1->perm[2]=16;
+
+#else  
+
+  d0->perm[0]=512;
+  d0->perm[1]=48; //3;
+  d0->perm[2]=64;
+
+  d1->perm[0]=48;
+  d1->perm[1]=64;//3;
+  d1->perm[2]=240;
+#endif
+
 
   d0->perm[0]=512;
   d0->perm[1]=48; //3;
@@ -876,7 +963,6 @@ TEST(tensorProd_vs2d_Endian ){
   free_tensor_TYPE_FLOAT(M1);
 }
 
-#endif
 
 int main(int argc, char **argv){
   
diff --git a/ytest_t/Makefile b/ytest_t/Makefile
index 0587831..b47a7b7 100644
--- a/ytest_t/Makefile
+++ b/ytest_t/Makefile
@@ -40,7 +40,7 @@ $(SUBDIRS):
 		$(MAKE) -C $@ $(MAKECMDGOALS)
 
 update_headers: $(PROJECT_LIB)
-	for file_h in $(SUBDIRS); do cp -r "$$file_h/include" include_ytest/;	done	
+	for file_h in $(SUBDIRS); do cp -r "$$file_h/include/" include_ytest/;	done	
 
 .PHONY: $(TOPTARGETS) $(SUBDIRS)
 
diff --git a/ytest_t/include_ytest/include/fmock/fmock.h b/ytest_t/include_ytest/include/fmock/fmock.h
index 6326ab9..d459ca2 100644
--- a/ytest_t/include_ytest/include/fmock/fmock.h
+++ b/ytest_t/include_ytest/include/fmock/fmock.h
@@ -24,6 +24,7 @@ struct list_current_variable{
  */
 struct func_mock_info_struct{
   long id;
+  bool used;
   char *str_namefunc;
   char *str_conditions;
   char *str_caller;
@@ -74,6 +75,7 @@ extern struct list_base_fmock *g_list_base_fmock;
       (tmp__mock)->call_mock_condition = NULL;\
       /*(tmp__mock)->str_print_current_variables = list_mo_ ## namefunction .str_print_current_variables;*/\
       ((tmp__mock)->info_mock)->expect_call = -1;\
+      ((tmp__mock)->info_mock)->used = true;\
       ((tmp__mock)->info_mock)->call = 0;\
       ((tmp__mock)->info_mock)->failed_call = 0;\
       ((tmp__mock)->info_mock)->str_namefunc = malloc(strlen(#namefunction) + 43 + strlen(#pre_id));\
@@ -101,6 +103,7 @@ extern struct list_base_fmock *g_list_base_fmock;
   } list_mo_ ## namefunction;\
   __attribute__((constructor)) void init_list_m_ ## namefunction(void){\
     list_mo_ ## namefunction.info_mock = malloc(sizeof(struct func_mock_info_struct));\
+    (list_mo_ ## namefunction.info_mock)->used = false;\
     (list_mo_ ## namefunction.info_mock)->times_left = INITSTATE;\
     (list_mo_ ## namefunction.info_mock)->init_times_left = INITSTATE;\
     list_mo_ ## namefunction.str_print_current_variables = NULL;\
@@ -110,12 +113,16 @@ extern struct list_base_fmock *g_list_base_fmock;
   __attribute__((destructor)) void destruct_list_m_  ## namefunction(void){   \
     /*free(list_mo_ ## namefunction.info_mock);*/ \
     struct list_mock_return_ ## namefunction *tmp_nn = list_mo_ ## namefunction.next, *ttmp_nn;\
+    if((list_mo_ ## namefunction.info_mock)->used == false ){\
+      free(list_mo_ ## namefunction.info_mock);\
+    }\
     while(tmp_nn){\
       ttmp_nn = tmp_nn;\
       tmp_nn = tmp_nn->next;\
       /*free(ttmp_nn->info_mock);*/\
       free(ttmp_nn);\
     }\
+    PRINT_DEBUG(" purge list mo_ %s done!\n",#namefunction);\
    \
   }\
     \
@@ -248,6 +255,7 @@ __attribute__((constructor)) void create_str_print_variables ## namefunction(){\
         (tmp_new_mock)->str_print_current_variables = list_mo_ ## namefunction .str_print_current_variables;\
       /*(tmp_new_mock)->info_mock  = malloc(sizeof(struct func_mock_info_struct));*/\
       ((tmp_new_mock)->info_mock)->expect_call = f_expect_call;\
+      ((tmp_new_mock)->info_mock)->used = true;\
       ((tmp_new_mock)->info_mock)->call = 0;\
       ((tmp_new_mock)->info_mock)->failed_call = 0;\
       ((tmp_new_mock)->info_mock)->init_times_left = repeat;\
diff --git a/ytest_t/libytest.so b/ytest_t/libytest.so
index c5c6b5d..24b2d2d 100644
Binary files a/ytest_t/libytest.so and b/ytest_t/libytest.so differ
diff --git a/ytest_t/test/is_good.c b/ytest_t/test/is_good.c
index bad9b2a..9f01353 100644
--- a/ytest_t/test/is_good.c
+++ b/ytest_t/test/is_good.c
@@ -13,11 +13,13 @@
 #include "fmock/fmock.h"
 
 #if 1
+
 TEST(true__){
   PRINTF("another test again false\n");
   bool val_bool = false;
   ASSERT_TRUE(val_bool);
 }
+
 TEST(test)
 {
   PRINTF("test test\n");
@@ -25,6 +27,7 @@ TEST(test)
   ASSERT_FALSE(val_bool);
 
 }
+
 TEST(float_equal){
   PRINTF("another test float\n");
   ASSERT_TRUE(true);
@@ -184,6 +187,8 @@ TEST(mockf1){
 #endif
 
 
+
+
 #if 1
 
 MOCK_FUNC(int, f2_mock,(int a,int b),(a,b))
@@ -349,6 +354,7 @@ TEST(f7_mock_test){
 #endif
 
 
+
 int main(int argc, char **argv){
   
   //run_all_tests();
diff --git a/ytest_t/yfmock/include/fmock/fmock.h b/ytest_t/yfmock/include/fmock/fmock.h
index 6326ab9..d459ca2 100644
--- a/ytest_t/yfmock/include/fmock/fmock.h
+++ b/ytest_t/yfmock/include/fmock/fmock.h
@@ -24,6 +24,7 @@ struct list_current_variable{
  */
 struct func_mock_info_struct{
   long id;
+  bool used;
   char *str_namefunc;
   char *str_conditions;
   char *str_caller;
@@ -74,6 +75,7 @@ extern struct list_base_fmock *g_list_base_fmock;
       (tmp__mock)->call_mock_condition = NULL;\
       /*(tmp__mock)->str_print_current_variables = list_mo_ ## namefunction .str_print_current_variables;*/\
       ((tmp__mock)->info_mock)->expect_call = -1;\
+      ((tmp__mock)->info_mock)->used = true;\
       ((tmp__mock)->info_mock)->call = 0;\
       ((tmp__mock)->info_mock)->failed_call = 0;\
       ((tmp__mock)->info_mock)->str_namefunc = malloc(strlen(#namefunction) + 43 + strlen(#pre_id));\
@@ -101,6 +103,7 @@ extern struct list_base_fmock *g_list_base_fmock;
   } list_mo_ ## namefunction;\
   __attribute__((constructor)) void init_list_m_ ## namefunction(void){\
     list_mo_ ## namefunction.info_mock = malloc(sizeof(struct func_mock_info_struct));\
+    (list_mo_ ## namefunction.info_mock)->used = false;\
     (list_mo_ ## namefunction.info_mock)->times_left = INITSTATE;\
     (list_mo_ ## namefunction.info_mock)->init_times_left = INITSTATE;\
     list_mo_ ## namefunction.str_print_current_variables = NULL;\
@@ -110,12 +113,16 @@ extern struct list_base_fmock *g_list_base_fmock;
   __attribute__((destructor)) void destruct_list_m_  ## namefunction(void){   \
     /*free(list_mo_ ## namefunction.info_mock);*/ \
     struct list_mock_return_ ## namefunction *tmp_nn = list_mo_ ## namefunction.next, *ttmp_nn;\
+    if((list_mo_ ## namefunction.info_mock)->used == false ){\
+      free(list_mo_ ## namefunction.info_mock);\
+    }\
     while(tmp_nn){\
       ttmp_nn = tmp_nn;\
       tmp_nn = tmp_nn->next;\
       /*free(ttmp_nn->info_mock);*/\
       free(ttmp_nn);\
     }\
+    PRINT_DEBUG(" purge list mo_ %s done!\n",#namefunction);\
    \
   }\
     \
@@ -248,6 +255,7 @@ __attribute__((constructor)) void create_str_print_variables ## namefunction(){\
         (tmp_new_mock)->str_print_current_variables = list_mo_ ## namefunction .str_print_current_variables;\
       /*(tmp_new_mock)->info_mock  = malloc(sizeof(struct func_mock_info_struct));*/\
       ((tmp_new_mock)->info_mock)->expect_call = f_expect_call;\
+      ((tmp_new_mock)->info_mock)->used = true;\
       ((tmp_new_mock)->info_mock)->call = 0;\
       ((tmp_new_mock)->info_mock)->failed_call = 0;\
       ((tmp_new_mock)->info_mock)->init_times_left = repeat;\
diff --git a/ytest_t/yfmock/src/fmock/fmock.c b/ytest_t/yfmock/src/fmock/fmock.c
index b58f736..b7326a0 100644
--- a/ytest_t/yfmock/src/fmock/fmock.c
+++ b/ytest_t/yfmock/src/fmock/fmock.c
@@ -34,7 +34,6 @@ pthread_mutex_t mut_g_list_base_fmock;
  * return the numbers of comas (,) +1 in the input string
  */
 
-
 int parse_count_args_(char *input){
   int val=0;
   for(int i = 0; i< strlen(input); ++i){
@@ -90,6 +89,7 @@ void append_variable_current(struct list_current_variable **lcurrent_var, char *
   }
 }
 
+
 void append_fmock_to_listmock(struct func_mock_info_struct **f_mock_list,  struct func_mock_info_struct *f_mock){
   INCREMENT_(count_f_mock_wished);
   if(f_mock->expect_call) {
@@ -140,7 +140,6 @@ __attribute__((constructor))
 
 
 
-
 void clear_fmock_info_list(struct func_mock_info_struct **f_mock_list){
   if(*f_mock_list){
     struct func_mock_info_struct *tmp_fmock_info = *f_mock_list, *ttmp_fmock_info;
@@ -155,7 +154,6 @@ void clear_fmock_info_list(struct func_mock_info_struct **f_mock_list){
     }
     *f_mock_list = NULL;
   }
-
 }
 
 void clear_list_base_fmock(struct list_base_fmock **l_fmock){
@@ -187,6 +185,7 @@ void clear_variable_current(struct list_current_variable **lcurrent_var){
 
 }
 
+/* destructor will be executed in inverse order of call/place in the file */
 __attribute__((destructor))
   void purge_fmock(){
 
@@ -197,11 +196,9 @@ __attribute__((destructor))
   }
 
 
-
 extern bool is_parallel_nb;
 
 
-
 char * number_call_translate(long nb){
   char *ret=malloc(250);
   if(nb>1) sprintf(ret," be called %ld times",nb);
@@ -234,7 +231,6 @@ char * strprint_caller_(char *input){
       PRINTF("\n");\
     }while(0);
 
-
   
 
 __attribute__((destructor))
@@ -256,7 +252,8 @@ __attribute__((destructor))
     char *reader=malloc(w.ws_col+3);
     strcpy(reader,"STAT OF MOCK FUNCTIONS");
 
-    fprintf(F_OUT,"%s\n\n%0*d\n %*s \n%0*d %s\n\n", colors_f[k_YELLOW] ,w.ws_col,0, (int)(w.ws_col+strlen(reader))/2, reader,w.ws_col,0, DEFAULT_K );
+    //fprintf(F_OUT,"%s\n\n%0*d\n %*s \n%0*d %s\n\n", colors_f[k_YELLOW] ,w.ws_col,0, (int)(w.ws_col+strlen(reader))/2, reader,w.ws_col,0, DEFAULT_K );
+    PRINTF("%s\n\n%0*d\n %*s \n%0*d %s\n\n", colors_f[k_YELLOW] ,w.ws_col,0, (int)(w.ws_col+strlen(reader))/2, reader,w.ws_col,0, DEFAULT_K );
 
 
     is_parallel_nb = 0; /* no longer parallel here */
@@ -417,6 +414,5 @@ __attribute__((destructor))
     PRINT_DEBUG("%s\n","pthread_mutex_destroy done!");
     PRINT_DEBUG("%s\n","check mock done!");
 
-
   }
 
diff --git a/ytest_t/yftest/src/ftest/ftest.c b/ytest_t/yftest/src/ftest/ftest.c
index a63302b..2f4e0b0 100644
--- a/ytest_t/yftest/src/ftest/ftest.c
+++ b/ytest_t/yftest/src/ftest/ftest.c
@@ -213,7 +213,11 @@ long int id_of_thread_executed(void){
     if(id_thread_self[i] == id_from_self)
       return i;
   }
-  PRINT_ERROR("something wrong on %s, id_from_self: %ld\n",__func__,id_from_self);
+  /*if(id_thread_self){
+    for(long int i=0; i<= parallel_nb; ++i)
+      PRINT_DEBUG(" id_thread_self[%ld] = %ld \n", i, id_thread_self[i]);
+  }*/
+  PRINT_ERROR("\nsomething wrong on %s, id_from_self: %ld\n",__func__,id_from_self);
   return -1;
 }
 
@@ -1007,10 +1011,10 @@ stat_end_run(size_t ntst, struct timespec start_t){
 bool is_in_array_##type(type *array, type val){\
   bool found = false;\
   for(size_t i = 0; i < cur_array_##type; ++i){\
-    /*char * strarr = type##_TO_STR(array[i]), *strval = type##_TO_STR(val);\
+    char * strarr = type##_TO_STR(array[i]), *strval = type##_TO_STR(val);\
     PRINT_DEBUG("compare |%s| in array and val: |%s|\n",strarr, strval);\
     free(strarr);free(strval);\
-    */PRINT_DEBUG("compare |%s| in array and val: |%s|\n",type##_TO_STR(array[i]), type##_TO_STR(val));\
+    /*PRINT_DEBUG("compare |%s| in array and val: |%s|\n",type##_TO_STR(array[i]), type##_TO_STR(val));*/\
     if(COMPARE_N_##type((void*)(array[i]),(void*)val  ) == 0 ){\
       found = true;\
       break;\
@@ -1024,10 +1028,10 @@ bool is_in_array_##type(type *array, type val){\
 bool is_in_array_##type(type *array, type val){\
   bool found = false;\
   for(size_t i = 0; i < cur_array_##type; ++i){\
-    /*char * strarr = type##_TO_STR(array[i]), *strval = type##_TO_STR(val);\
+    char * strarr = type##_TO_STR(array[i]), *strval = type##_TO_STR(val);\
     PRINT_DEBUG("compare |%s| in array and val: |%s|\n",strarr, strval);\
-    free(strarr);free(strval);*/\
-    PRINT_DEBUG("compare |%s| in array and val: |%s|\n",type##_TO_STR(array[i]), type##_TO_STR(val));\
+    free(strarr);free(strval);\
+    /*PRINT_DEBUG("compare |%s| in array and val: |%s|\n",type##_TO_STR(array[i]), type##_TO_STR(val));*/\
     if(COMPARE_N_##type((void*)(&array[i]),(void*)&val  ) == 0 ){\
       found = true;\
       break;\
@@ -1312,6 +1316,7 @@ init_parallel_test_()
     thread_test_failed_l[i] = NULL;
     count_pass_thread[i] = 0;
     count_fail_thread[i] = 0;
+    id_thread_self[i]=0; /* have to initialize because if some threads not yetr run we have warning with valgrind : non initialize value, beause real value is provide by each thread */
   }
 
   current_fn = f_beging;
@@ -1336,6 +1341,9 @@ final_parallel_test_()
   free(count_pass_thread);
   free(count_fail_thread);
 
+  free(id_thread_self);
+  //id_thread_self = NULL;
+
   for(size_t i=0; i< parallel_nb; ++i)
     clear_all_falied_list(&thread_test_failed_l[i]);
 
@@ -1377,17 +1385,20 @@ final_parallel_test_()
       fclose(f_ou_th[id_thrd]);
     }
   }
-  
+
+  free(f_ou_th); 
+
   if(removelog){
     for(size_t i=0; i<=parallel_nb; ++i){
       remove(log_name_file_thrd[i]);
       PRINT_DEBUG("file log of treard[%ld] removed\n",i);
-      free(log_name_file_thrd[i]);
     }
-    free(log_name_file_thrd);
   }
   
+    for(size_t i=0; i<=parallel_nb; ++i)
+      free(log_name_file_thrd[i]);
 
+    free(log_name_file_thrd);
 }
 
 void run_all_tests_parallel(size_t parallel /*, int max_col*/)