feat(nr_dlsch): option to provide the number of symbols per thread

* Add option `--L1s.L1_num_tx_sym_per_thread` for the softmodems and `-Y` for `nr_dlsim`
  to provide the number of symbols processed per thread.
  It defaults to 0 which makes that every symbols are processed in one thread.
* The last symbol processing task is processed in the L1 TX thread.

executables/nr-gnb.c

@@ -307,9 +307,6 @@ void init_gNB_Tpool(int inst)
   PHY_VARS_gNB *gNB;
   gNB = RC.gNB[inst];
   gNB_L1_proc_t *proc = &gNB->proc;
-  // PUSCH symbols per thread need to be calculated by how many threads we have
-  gNB->num_pusch_symbols_per_thread = 1;
-  gNB->num_pdsch_symbols_per_thread = 1;
   // ULSCH decoding threadpool
   initTpool(get_softmodem_params()->threadPoolConfig, &gNB->threadPool, cpumeas(CPUMEAS_GETSTATE));
 

openair1/PHY/NR_TRANSPORT/nr_dlsch.c

@@ -669,9 +669,15 @@ static int do_one_dlsch(unsigned char *input_ptr, PHY_VARS_gNB *gNB, NR_gNB_DLSC
 
   // spawn symbol threads
 
-  int nb_tasks = rel15->NrOfSymbols / gNB->num_pdsch_symbols_per_thread;
-  if ((rel15->NrOfSymbols % gNB->num_pdsch_symbols_per_thread) > 0)
+  int nb_tasks = 1;
+  int num_pdsch_symbols_per_task = rel15->NrOfSymbols;
+  if (gNB->num_pdsch_symbols_per_thread > 0) {
+    // symbol processing in thread pool enabled
+    num_pdsch_symbols_per_task = gNB->num_pdsch_symbols_per_thread;
+    nb_tasks = rel15->NrOfSymbols / num_pdsch_symbols_per_task;
+    if ((rel15->NrOfSymbols % num_pdsch_symbols_per_task) > 0)
       nb_tasks++;
+  }
   pdschSymbolProc_t arr[nb_tasks];
   task_ans_t ans;
   init_task_ans(&ans, nb_tasks);
@@ -679,7 +685,7 @@ static int do_one_dlsch(unsigned char *input_ptr, PHY_VARS_gNB *gNB, NR_gNB_DLSC
   unsigned int re_beginning_of_symbol = 0;
   int res = 0;
   for (int l_symbol = rel15->StartSymbolIndex; l_symbol < rel15->StartSymbolIndex + rel15->NrOfSymbols;
-       l_symbol += gNB->num_pdsch_symbols_per_thread) {
+       l_symbol += num_pdsch_symbols_per_task) {
     pdschSymbolProc_t *rdata = &arr[sz_arr];
     rdata->ans = &ans;
     ++sz_arr;
@@ -690,8 +696,8 @@ static int do_one_dlsch(unsigned char *input_ptr, PHY_VARS_gNB *gNB, NR_gNB_DLSC
     rdata->slot = slot;
     rdata->startSymbol = l_symbol;
     res = rel15->NrOfSymbols - (l_symbol - rel15->StartSymbolIndex);
-    if (res >= gNB->num_pdsch_symbols_per_thread)
-      rdata->numSymbols = gNB->num_pdsch_symbols_per_thread;
+    if (res >= num_pdsch_symbols_per_task)
+      rdata->numSymbols = num_pdsch_symbols_per_task;
     else
       rdata->numSymbols = res;
     rdata->layerSz2 = layerSz2;
@@ -711,8 +717,12 @@ static int do_one_dlsch(unsigned char *input_ptr, PHY_VARS_gNB *gNB, NR_gNB_DLSC
     reset_meas(&rdata->dlsch_precoding_stats);
     for (int l = 0; l < rel15->nrOfLayers; l++)
       rdata->tx_layers[l] = tx_layers[l];
+    if (l_symbol < rel15->StartSymbolIndex + rel15->NrOfSymbols - num_pdsch_symbols_per_task) {
       task_t t = {.func = &nr_pdsch_symbol_processing, .args = rdata};
       pushTpool(&gNB->threadPool, t);
+    } else {
+      nr_pdsch_symbol_processing(rdata);
+    }
   }
   join_task_ans(&ans);
   for (int i = 0; i < nb_tasks; i++) {

openair1/SIMULATION/NR_PHY/dlsim.c

@@ -382,6 +382,8 @@ int main(int argc, char **argv)
   uint8_t  dlsch_threads = 0;
   int chest_type[2] = {0};
   uint8_t  max_ldpc_iterations = 5;
+  // number of PDSCH symbols per thread = 0 means do not use thread pool
+  int num_pdsch_symbols_per_thread = 0;
   if ((uniqCfg = load_configmodule(argc, argv, CONFIG_ENABLECMDLINEONLY)) == 0) {
     exit_fun("[NR_DLSIM] Error, configuration module init failed\n");
   }
@@ -583,6 +585,10 @@ int main(int argc, char **argv)
       gNBthreads[sizeof(gNBthreads)-1]=0;
       break;
 
+    case 'Y':
+      num_pdsch_symbols_per_thread = atoi(optarg);
+      break;
+
     case 'Z' :
       filename_csv = strdup(optarg);
       AssertFatal(filename_csv != NULL, "strdup() error: errno %d\n", errno);
@@ -657,6 +663,7 @@ int main(int argc, char **argv)
       printf("-T Enable PTRS, arguments list L_PTRS{0,1,2} K_PTRS{2,4}, e.g. -T 2 0 2 \n");
       printf("-U Change DMRS Config, arguments list DMRS TYPE{0=A,1=B} DMRS AddPos{0:2} DMRS ConfType{1:2}, e.g. -U 3 0 2 1 \n");
       printf("-X gNB thread pool configuration, n => no threads\n");
+      printf("-Y Number of symbols processed per PDSCH generation thread\n");
       printf("-Z Output filename (.csv format) for stats\n");
       exit (-1);
       break;
@@ -715,7 +722,7 @@ int main(int argc, char **argv)
 
   AssertFatal((gNB->if_inst = NR_IF_Module_init(0)) != NULL, "Cannot register interface");
   gNB->if_inst->NR_PHY_config_req = nr_phy_config_request;
-  gNB->num_pdsch_symbols_per_thread = 1;
+  gNB->num_pdsch_symbols_per_thread = num_pdsch_symbols_per_thread;
 
   NR_ServingCellConfigCommon_t *scc = calloc(1,sizeof(*scc));;
   prepare_scc(scc);

openair2/GNB_APP/L1_nr_paramdef.h

@@ -28,6 +28,10 @@
 #define L1_MAX_LDPC_ITERATIONS               "max_ldpc_iterations"
 #define L1_RX_THREAD_CORE                    "L1_rx_thread_core"
 #define L1_TX_THREAD_CORE                    "L1_tx_thread_core"
+#define L1_NUM_RX_SYM_PER_THREAD             "L1_num_rx_sym_per_thread"
+#define HLP_L1_NUM_RX_SYM_PER_THREAD         "number of symbols processed per PUSCH generation thread"
+#define L1_NUM_TX_SYM_PER_THREAD             "L1_num_tx_sym_per_thread"
+#define HLP_L1_NUM_TX_SYM_PER_THREAD         "number of symbols processed per PDSCH generation thread"
 #define HLP_TP_SIZ "thread_pool_size paramter removed, please use --thread-pool"
 #define L1_TX_AMP_BACKOFF_dB                 "tx_amp_backoff_dB"
 #define HLP_L1TX_BO "Backoff from full-scale output at the L1 entity(frequency domain), ex. 12 would corresponding to 14-bit input level (6 dB/bit). Default 36 dBFS for OAI RU entity"
@@ -58,6 +62,8 @@
   {L1_MAX_LDPC_ITERATIONS,               NULL,       0,         .uptr=NULL,           .defintval=8,               TYPE_UINT,     0},         \
   {L1_RX_THREAD_CORE,                    NULL,       0,         .iptr=NULL,           .defintval=-1,              TYPE_INT,      0},         \
   {L1_TX_THREAD_CORE,                    NULL,       0,         .iptr=NULL,           .defintval=-1,              TYPE_INT,      0},         \
+  {L1_NUM_RX_SYM_PER_THREAD,             HLP_L1_NUM_RX_SYM_PER_THREAD, 0, .iptr=NULL, .defintval=1,               TYPE_INT,      0},         \
+  {L1_NUM_TX_SYM_PER_THREAD,             HLP_L1_NUM_TX_SYM_PER_THREAD, 0, .iptr=NULL, .defintval=0,               TYPE_INT,      0},         \
   {L1_TX_AMP_BACKOFF_dB,                 HLP_L1TX_BO,0,         .uptr=NULL,           .defintval=36,              TYPE_UINT,     0},         \
   {L1_PHASE_COMP,                        HLP_L1_PHASE_COMP,PARAMFLAG_BOOL, .uptr=NULL,.defintval=1,               TYPE_UINT,     0},         \
   {L1_NUM_ANTENNAS_PER_THREAD,           HLP_NUM_ARX,0,         .uptr=NULL,           .defintval=1,               TYPE_UINT,     0},         \

openair2/GNB_APP/gnb_config.c

@@ -841,6 +841,9 @@ void RCconfig_NR_L1(void)
       gNB->L1_rx_thread_core = *gpd(params, np, L1_RX_THREAD_CORE)->iptr;
       gNB->L1_tx_thread_core = *gpd(params, np, L1_TX_THREAD_CORE)->iptr;
       LOG_I(NR_PHY, "thread cores for L1_RX %d L1_TX %d\n", gNB->L1_rx_thread_core, gNB->L1_tx_thread_core);
+      // PUSCH symbols per thread need to be calculated by how many threads we have
+      gNB->num_pusch_symbols_per_thread = *gpd(params, np, L1_NUM_RX_SYM_PER_THREAD)->iptr;
+      gNB->num_pdsch_symbols_per_thread = *gpd(params, np, L1_NUM_TX_SYM_PER_THREAD)->iptr;
       gNB->TX_AMP = min(32767.0 / pow(10.0, .05 * (double)(*gpd(params, np, L1_TX_AMP_BACKOFF_dB)->uptr)), INT16_MAX);
       LOG_I(NR_PHY, "TX_AMP = %d (-%d dBFS)\n", gNB->TX_AMP, *gpd(params, np, L1_TX_AMP_BACKOFF_dB)->uptr);
       AssertFatal(gNB->TX_AMP > 300, "TX_AMP is too small, must be larger than 300 (is %d)\n", gNB->TX_AMP);