diff --git a/doc/SW-archi-graph.md b/doc/SW-archi-graph.md
index 8a14c38cfa..e8b0cdc0d7 100644
--- a/doc/SW-archi-graph.md
+++ b/doc/SW-archi-graph.md
@@ -4,7 +4,7 @@ flowchart TB
     feprx --> half-slot --> end_feprx
     feprx --> second-thread -- block_end_feprx --> end_feprx>feprx]
     end_feprx --> rx_nr_prach_ru
-rx_nr_prach_ru -- block_queue --> resp_L1>resp L1]
+rx_nr_prach_ru -- block_queue_singleton --> resp_L1>resp L1]
 resp_L1 -- async launch --> rx_func
 resp_L1 -- immediate return --> RFin
 
@@ -29,24 +29,35 @@ rx_func_implem[rx_func]
       handle_nr_rach
       --> handle_nr_uci
       --> handle_nr_ulsch
-      --> gNB_dlsch_ulsch_scheduler
-      --> NR_Schedule_response
+      subgraph gNB_dlsch_ulsch_scheduler
+          run_pdcp
+          --> nr_rrc_trigger
+          --> schedule_xxxx
+      end
+      handle_nr_ulsch --> gNB_dlsch_ulsch_scheduler
+      subgraph NR_Schedule_response
+         L1_tx_free3>L1_tx_free]
+         --> handle_dl_fapi
+         --> sendTxFilled((L1_tx_filled))
+         --> handle_ul_nfapi
+       
+      end
+      gNB_dlsch_ulsch_scheduler --> NR_Schedule_response
     end 
     rx_func_implem --> rxfuncbeg
     rxfuncbeg --> phy_procedures_gNB_uespec_RX
 phy_procedures_gNB_uespec_RX --> NR_UL_indication
--- block_queue --> L1_tx_free2>L1 tx free]
+-- block_queue_block_PNF_monolithic --> L1_tx_free2>L1 tx filled]
 -- async launch --> tx_func
 L1_tx_free2 -- send_msg --> rsp((resp_L1))
 end 
 rx_func --> rxfunc
 
 
-subgraph tx
+subgraph tx_func
     direction LR
-    subgraph tx_func2
-       phy_procedures_gNB_TX
-       --> dcitop[nr_generate dci top]
+    subgraph phy_procedures_gNB_TX
+       dcitop[nr_generate dci top]
        --> nr_generate_csi_rs
        --> apply_nr_rotation
        -- send_msg --> end_tx_func((L1_tx_out))
@@ -59,6 +70,6 @@ subgraph tx
         ru_tx_func --> feptx_prec
         --> feptx_ofdm
     end 
-    tx_func2 --> tx_reorder_thread
 end
+
 ```
diff --git a/executables/nr-gnb.c b/executables/nr-gnb.c
index 60239576e4..ff018b5452 100644
--- a/executables/nr-gnb.c
+++ b/executables/nr-gnb.c
@@ -303,8 +303,8 @@ void rx_func(void *param) {
 }
 static void dump_L1_meas_stats(PHY_VARS_gNB *gNB, RU_t *ru, char *output) {
   int stroff = 0;
-  stroff += print_meas_log(gNB->phy_proc_tx_0, "L1 Tx processing thread 0", NULL, NULL, output);
-  stroff += print_meas_log(gNB->phy_proc_tx_1, "L1 Tx processing thread 1", NULL, NULL, output+stroff);
+  stroff += print_meas_log(gNB->phy_proc_tx[0], "L1 Tx processing thread 0", NULL, NULL, output);
+  stroff += print_meas_log(gNB->phy_proc_tx[1], "L1 Tx processing thread 1", NULL, NULL, output+stroff);
   stroff += print_meas_log(&gNB->dlsch_encoding_stats, "DLSCH encoding", NULL, NULL, output+stroff);
   stroff += print_meas_log(&gNB->phy_proc_rx, "L1 Rx processing", NULL, NULL, output+stroff);
   stroff += print_meas_log(&gNB->ul_indication_stats, "UL Indication", NULL, NULL, output+stroff);
@@ -339,8 +339,8 @@ void *nrL1_stats_thread(void *param) {
   fd=fopen("nrL1_stats.log","w");
   AssertFatal(fd!=NULL,"Cannot open nrL1_stats.log\n");
 
-  reset_meas(gNB->phy_proc_tx_0);
-  reset_meas(gNB->phy_proc_tx_1);
+  reset_meas(gNB->phy_proc_tx[0]);
+  reset_meas(gNB->phy_proc_tx[1]);
   reset_meas(&gNB->dlsch_encoding_stats);
   reset_meas(&gNB->phy_proc_rx);
   reset_meas(&gNB->ul_indication_stats);
@@ -444,22 +444,17 @@ void init_gNB_Tpool(int inst) {
   initNotifiedFIFO(gNB->L1_tx_free);
   initNotifiedFIFO(gNB->L1_tx_filled);
   initNotifiedFIFO(gNB->L1_tx_out);
+  
   // we create 2 threads for L1 tx processing
-  notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t),0,gNB->L1_tx_out,tx_func);
-  processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
-  init_DLSCH_struct(gNB, msgDataTx);
-  memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
-  reset_meas(&msgDataTx->phy_proc_tx);
-  gNB->phy_proc_tx_0 = &msgDataTx->phy_proc_tx;
-  pushNotifiedFIFO(gNB->L1_tx_free,msgL1Tx); // to unblock the process in the beginning
-
-  msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t),0,gNB->L1_tx_out,tx_func);
-  msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
-  init_DLSCH_struct(gNB, msgDataTx);
-  memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
-  reset_meas(&msgDataTx->phy_proc_tx);
-  gNB->phy_proc_tx_1 = &msgDataTx->phy_proc_tx;
-  pushNotifiedFIFO(gNB->L1_tx_free,msgL1Tx); // to unblock the process in the beginning
+  for (int i=0; i < 2; i++) {
+    notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t),0,gNB->L1_tx_out,tx_func);
+    processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
+    init_DLSCH_struct(gNB, msgDataTx);
+    memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
+    reset_meas(&msgDataTx->phy_proc_tx);
+    gNB->phy_proc_tx[i] = &msgDataTx->phy_proc_tx;
+    pushNotifiedFIFO(gNB->L1_tx_free,msgL1Tx); // to unblock the process in the beginning
+  }
 
   threadCreate(&proc->L1_stats_thread,nrL1_stats_thread,(void*)gNB,"L1_stats",-1,OAI_PRIORITY_RT_LOW);
   threadCreate(&proc->pthread_tx_reorder, tx_reorder_thread, (void *)gNB, "thread_tx_reorder", -1, OAI_PRIORITY_RT_MAX);
diff --git a/nfapi/open-nFAPI/nfapi/public_inc/fapi_nr_ue_interface.h b/nfapi/open-nFAPI/nfapi/public_inc/fapi_nr_ue_interface.h
index 0e923931ad..798141f9ca 100644
--- a/nfapi/open-nFAPI/nfapi/public_inc/fapi_nr_ue_interface.h
+++ b/nfapi/open-nFAPI/nfapi/public_inc/fapi_nr_ue_interface.h
@@ -346,8 +346,8 @@ typedef struct {
 } fapi_nr_ul_config_request_pdu_t;
 
 typedef struct {
-  uint16_t sfn;
-  uint16_t slot;
+  //uint16_t sfn;
+  //uint16_t slot;
   uint8_t number_pdus;
   fapi_nr_ul_config_request_pdu_t ul_config_list[FAPI_NR_UL_CONFIG_LIST_NUM];
   pthread_mutex_t mutex_ul_config;
diff --git a/openair1/PHY/defs_gNB.h b/openair1/PHY/defs_gNB.h
index 6202cc72cd..a259a0a008 100644
--- a/openair1/PHY/defs_gNB.h
+++ b/openair1/PHY/defs_gNB.h
@@ -860,8 +860,7 @@ typedef struct PHY_VARS_gNB_s {
   /*
   time_stats_t phy_proc;
   */
-  time_stats_t *phy_proc_tx_0;
-  time_stats_t *phy_proc_tx_1;
+  time_stats_t *phy_proc_tx[2];
   time_stats_t phy_proc_rx;
   time_stats_t rx_prach;
   /*
diff --git a/openair1/SCHED_NR_UE/fapi_nr_ue_l1.c b/openair1/SCHED_NR_UE/fapi_nr_ue_l1.c
index 7cf22db1a9..1df5c84efa 100644
--- a/openair1/SCHED_NR_UE/fapi_nr_ue_l1.c
+++ b/openair1/SCHED_NR_UE/fapi_nr_ue_l1.c
@@ -235,8 +235,8 @@ int8_t nr_ue_scheduled_response(nr_scheduled_response_t *scheduled_response){
       }
       if (scheduled_response->tx_request)
         scheduled_response->tx_request->number_of_pdus = 0;
-      ul_config->sfn = 0;
-      ul_config->slot = 0;
+      //ul_config->sfn = 0;
+      //ul_config->slot = 0;
       ul_config->number_pdus = 0;
       memset(ul_config->ul_config_list, 0, sizeof(ul_config->ul_config_list));
       pthread_mutex_unlock(&ul_config->mutex_ul_config);
diff --git a/openair1/SIMULATION/NR_PHY/dlsim.c b/openair1/SIMULATION/NR_PHY/dlsim.c
index 50e21ac02b..df07d8b7d3 100644
--- a/openair1/SIMULATION/NR_PHY/dlsim.c
+++ b/openair1/SIMULATION/NR_PHY/dlsim.c
@@ -978,7 +978,7 @@ int main(int argc, char **argv)
   msgDataTx->frame = frame;
   memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
   reset_meas(&msgDataTx->phy_proc_tx);
-  gNB->phy_proc_tx_0 = &msgDataTx->phy_proc_tx;
+  gNB->phy_proc_tx[0] = &msgDataTx->phy_proc_tx;
   pushTpool(gNB->threadPool,msgL1Tx);
 
   for (SNR = snr0; SNR < snr1; SNR += .2) {
@@ -1294,7 +1294,7 @@ int main(int argc, char **argv)
 	     msgDataTx->dlsch[0][0]->harq_process.pdsch_pdu.pdsch_pdu_rel15.TBSize[0]<<3,
 	     msgDataTx->dlsch[0][0]->harq_process.K,
 	     msgDataTx->dlsch[0][0]->harq_process.K/((msgDataTx->dlsch[0][0]->harq_process.pdsch_pdu.pdsch_pdu_rel15.TBSize[0]<<3)>3824?22:10));
-      printDistribution(gNB->phy_proc_tx_0,table_tx,"PHY proc tx");
+      printDistribution(gNB->phy_proc_tx[0],table_tx,"PHY proc tx");
       printStatIndent2(&gNB->dlsch_encoding_stats,"DLSCH encoding time");
       printStatIndent3(&gNB->dlsch_segmentation_stats,"DLSCH segmentation time");
       printStatIndent3(&gNB->tinput,"DLSCH LDPC input processing time");
diff --git a/openair1/SIMULATION/NR_PHY/ulsim.c b/openair1/SIMULATION/NR_PHY/ulsim.c
index a7075eb218..2237f2db2b 100644
--- a/openair1/SIMULATION/NR_PHY/ulsim.c
+++ b/openair1/SIMULATION/NR_PHY/ulsim.c
@@ -670,7 +670,7 @@ int main(int argc, char **argv)
   notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t),0,gNB->resp_L1_tx,NULL);
   processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
   msgDataTx->slot = -1;
-  gNB->phy_proc_tx_0 = &msgDataTx->phy_proc_tx;
+  gNB->phy_proc_tx[0] = &msgDataTx->phy_proc_tx;
   pushNotifiedFIFO(gNB->resp_L1_tx,msgL1Tx); // to unblock the process in the beginning
   //gNB_config = &gNB->gNB_config;
 
diff --git a/openair2/LAYER2/NR_MAC_UE/nr_ue_scheduler.c b/openair2/LAYER2/NR_MAC_UE/nr_ue_scheduler.c
index 911d051ed5..9a880ecbd8 100644
--- a/openair2/LAYER2/NR_MAC_UE/nr_ue_scheduler.c
+++ b/openair2/LAYER2/NR_MAC_UE/nr_ue_scheduler.c
@@ -61,11 +61,11 @@ static ssb_list_info_t ssb_list;
 
 void fill_ul_config(fapi_nr_ul_config_request_t *ul_config, frame_t frame_tx, int slot_tx, uint8_t pdu_type){
   ul_config->ul_config_list[ul_config->number_pdus].pdu_type = pdu_type;
-  ul_config->slot = slot_tx;
-  ul_config->sfn = frame_tx;
+  //ul_config->slot = slot_tx;
+  //ul_config->sfn = frame_tx;
   ul_config->number_pdus++;
 
-  LOG_D(NR_MAC, "In %s: Set config request for UL transmission in [%d.%d], number of UL PDUs: %d\n", __FUNCTION__, ul_config->sfn, ul_config->slot, ul_config->number_pdus);
+  LOG_D(NR_MAC, "In %s: Set config request for UL transmission in [%d.%d], number of UL PDUs: %d\n", __FUNCTION__, frame_tx,  slot_tx, ul_config->number_pdus);
 
 }
 
@@ -947,15 +947,15 @@ NR_UE_L2_STATE_t nr_ue_scheduler(nr_downlink_indication_t *dl_info, nr_uplink_in
     // AND if a UL grant (UL DCI or Msg3) has been received (as indicated by num_pdus)
     if (ul_config){
       pthread_mutex_lock(&ul_config->mutex_ul_config);
-      if ((ul_info->slot_tx == ul_config->slot && ul_info->frame_tx == ul_config->sfn) && ul_config->number_pdus > 0){
+      if (/*(ul_info->slot_tx == ul_config->slot && ul_info->frame_tx == ul_config->sfn) && */ ul_config->number_pdus > 0){
 
-        LOG_D(NR_MAC, "In %s:[%d.%d]: number of UL PDUs: %d with UL transmission in [%d.%d]\n", __FUNCTION__, frame_tx, slot_tx, ul_config->number_pdus, ul_config->sfn, ul_config->slot);
+        LOG_D(NR_MAC, "In %s:[%d.%d]: number of UL PDUs: %d with UL transmission\n", __FUNCTION__, frame_tx, slot_tx, ul_config->number_pdus);
 
         uint8_t ulsch_input_buffer_array[NFAPI_MAX_NUM_UL_PDU][MAX_ULSCH_PAYLOAD_BYTES];
         nr_scheduled_response_t scheduled_response;
         fapi_nr_tx_request_t tx_req;
-        tx_req.slot = slot_tx;
-        tx_req.sfn = frame_tx;
+        //tx_req.slot = slot_tx;
+        //tx_req.sfn = frame_tx;
         tx_req.number_of_pdus = 0;
 
         for (int j = 0; j < ul_config->number_pdus; j++) {