Merge branch 'nikhil/ftree-mapfix' into 'master'

Clean up fat-tree a bit

See merge request codes/codes!44

src/network-workloads/conf/dual-plane-fattree-tapered.conf

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="198";
+      server="384";
+      modelnet_fattree="24";
+      fattree_switch="6";
+   }
+}
+PARAMS
+{
+   ft_type="0";
+   packet_size="8192";
+   chunk_size="8192";
+   message_size="512";
+   modelnet_scheduler="fcfs";
+   modelnet_order=( "fattree" );
+   num_levels="3";
+   tapering="2";
+   num_rails="2";
+   switch_count="198";
+   switch_radix="36";
+   router_delay="90";
+   soft_delay="200";
+   nic_delay="400";
+   nic_seq_delay="100";
+   num_injection_queues="2";
+   link_bandwidth="11.9";
+   cn_bandwidth="24";
+   vc_size="65536";
+   cn_vc_size="65536";
+   node_copy_queues="4";
+   intra_bandwidth="30";
+   rdma_delay="1000";
+   eager_limit="64000";
+   copy_per_byte="0.01";
+   node_eager_limit="64000";
+   rail_select="adaptive";
+   rail_select_limit="8192";
+   routing="adaptive";
+   routing_folder="taper_routes";
+   dot_file="ftree";
+   dump_topo="0";
+}

src/network-workloads/conf/dual-plane-fattree.conf

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="252";
+      server="288";
+      modelnet_fattree="18";
+      fattree_switch="6";
+   }
+}
+PARAMS
+{
+   ft_type="0";
+   packet_size="8192";
+   chunk_size="8192";
+   message_size="512";
+   modelnet_scheduler="fcfs";
+   modelnet_order=( "fattree" );
+   num_levels="3";
+   tapering="1";
+   num_rails="2";
+   switch_count="252";
+   switch_radix="36";
+   router_delay="90";
+   soft_delay="200";
+   nic_delay="400";
+   nic_seq_delay="100";
+   num_injection_queues="2";
+   link_bandwidth="11.9";
+   cn_bandwidth="24";
+   vc_size="65536";
+   cn_vc_size="65536";
+   node_copy_queues="4";
+   intra_bandwidth="30";
+   rdma_delay="1000";
+   eager_limit="64000";
+   copy_per_byte="0.01";
+   node_eager_limit="64000";
+   rail_select="adaptive";
+   rail_select_limit="8192";
+   routing="adaptive";
+   routing_folder="full_routes";
+   dot_file="ftree";
+   dump_topo="0";
+}

src/network-workloads/conf/tracer-fattree-type2.conf

-LPGROUPS
-{
-   MODELNET_GRP
-   {
-      repetitions="16";
-      server="4";
-      modelnet_fattree="4";
-      fattree_switch="3";
-   }
-}
-PARAMS
-{
-   ft_type="1";
-   packet_size="512";
-   message_size="512";
-   chunk_size="32";
-   modelnet_scheduler="fcfs";
-   #modelnet_scheduler="round-robin";
-   modelnet_order=( "fattree" );
-   num_levels="3";
-   switch_count="16";
-   switch_radix="8";
-   router_delay="60";
-   soft_delay="1000";
-   vc_size="65536";
-   cn_vc_size="65536";
-   link_bandwidth="4.7";
-   cn_bandwidth="5.25";
-}

src/networks/model-net/doc/README.fattree.txt

 *** README file for fattree network model ***
 
-1- Configuring CODES dragonfly network model
-CODES dragonfly network model can be configured using the fattee config file (currently
-located in codes/src/network-workloads/conf). Below is an example config file:
+1- Configuring CODES fat-tree network model
+CODES fat-tree network model can be configured using example config files
+(located in codes/src/network-workloads/conf/*fattree*). Below is the 
+bare-minimum example config file:
 
 MODELNET_GRP
 {
@@ -21,38 +22,46 @@ PARAMS
 	....
 }
 
-The first section, MODELNET_GRP specifies the LP types, number of LPs per type and their
-configuration. In the above case, there are 12 repetitions of 4 server LPs, 4 fat tree
-network node/terminal LPs and 3 fat tree switch LPs. Each repetition represents a leaf
-level switch, nodes connected to it, and higher level switches that may be needed to 
-construct the fat-tree. The 'fattree_switch' parameter indicates there are 3 levels 
-to this fat tree and each repitition will have one switch from each level. This 
-configuration will create a total of (fattree_switch)*repetitions=12*3=36 switch LPs,
-with 'fattree_switch' many switch LPs per level.
+The first section, MODELNET_GRP specifies the LP types, number of LPs per type
+and their configuration. In the above case, there are 12 repetitions each with 4
+server LPs, 4 fat tree network node/terminal LPs and 3 fat tree switch LPs. Each
+repetition represents a leaf level switch, nodes connected to it, and higher
+level switches that may be needed to construct the fat-tree. The
+'fattree_switch' parameter indicates there are 3 levels to this fat tree and
+each repetition will have one switch at each level. This configuration will
+create a total of (fattree_switch)*repetitions=12*3=36 switch LPs, with
+'fattree_switch' many levels.
+
+Typically, for a balanced, single plane fat-tree:
 
 modelnet_fattree = radix of switch/2
 fattree_switch = number of levels in the fattree (2 or 3)
 
 ft_type:
-0: Custom- ("Pruned" Fat Tree)
-1: Standard Full Fat Tree
-
-The Custom- ft_type is simply a pruned standard full fat tree. This layout type starts
-with the standard full fat tree and then removes pods and adjusts L1-L2 switch connections
-as needed to drop the total node/terminal count in the system. This approach still maintains
-full bisection bandwidth. Knowing a full standard fat tree uses k pods of k/2 switches per
-pod (k/2 L1 switches and k/2 L0 switches) and each switch in L0 connects to k/2 terminals,
-then each pod connects to (k/2)*(k/2) terminals. Therefore, the number of pods needed to get
-N-many terminals using the Custom- ft_type is Np = ceil(N/[(k/2)*(k/2)]). So the config file
-should have "repetitions" = "switch_count" = Np*(k/2).
+0: General, possible pruned/multi-railed/tapered, fat-tree
+1: Standard Full Fat Tree (deprecated - use type 0 for this case too)
+2: Multi-nic fat-tree where each NIC is connected to an independent plane
+
+The general- ft_type is simply a pruned standard full fat tree. This layout
+represent a partially filled fat-tree, which is created by removing pods and
+adjusting L1-L2 switch connections as needed to reduce the total node/terminal
+count in the system. This approach still maintains full bisection bandwidth.
+Knowing a full standard fat tree uses k pods of k/2 switches per pod (k/2 L1
+switches and k/2 L0 switches) and each switch in L0 connects to k/2 terminals,
+then each pod connects to (k/2)*(k/2) terminals. Therefore, the number of pods
+needed to get N-many terminals using the Custom- ft_type is Np =
+ceil(N/[(k/2)*(k/2)]). So the config file should have "repetitions" =
+"switch_count" = Np*(k/2).
 
 Supported PARAMS:
 
 packet_size, chunk_size (ideally kept same)
 modelnet_scheduler - NIC message scheduler
-modelnet_order=( "fattree" ); 
-num_levels : number of levels in the fattree (same as fattree_switch)
+modelnet_order="fattree"; 
+message_size="512" ;
+num_levels : number of levels in the fattree (2 or 3)
 tapering : controls division of ports to nodes at leaf level
+num_rails : number of rails/planes in the system (fattree_switch = num_levels * num_rails)
 switch_count : number of leaf level switches (same as repetitions)
 switch_radix : radix of the switches
 router_delay : delay caused by switched in ns
@@ -60,12 +69,22 @@ vc_size : size of switch VCs in bytes
 cn_vc_size : size of VC between NIC and switch in bytes
 link_bandwidth, cn_bandwidth : in GB/s
 routing : {adaptive, static}
+num_injection_queues : number of injection queues in NIC (=num_rails)
+rail_select : {adaptive, static} rail selection scheme for the packets
+rail_select_limit : message size in bytes above which adaptive rail selection algorithm is enabled if chosen
 
 For radix k switches with tapering t, t*k/(t+1) ports are used for connecting
 to nodes, and remaining are connected to next level switches. fmod(k, t+1) has
 to be 0. Default tapering is 1, i.e. full bandwidth. Note that, even when
 tapering is >1, the number of leaf level switches in a Pod are k/2.
 
+If simulation of system with multiple NICs per node is desired (each NIC has 
+its own rail/plane), ft_type = 2 should be selected. In this case, num_rails
+should be set to the number of NICs/rails desired. Also, for this case,
+fattree_switch = num_levels * num_rails
+modelnet_fattree = usual_per_switch_nic * num_rails
+num_injection_queues = 1
+
 2- Static Routing
 If static routing is chosen, two more PARAMS must be provided:
 routing_folder :  folder that contain lft files generated using method described below.

src/networks/model-net/fattree.c

@@ -730,10 +730,12 @@ static void fattree_read_config(const char * anno, fattree_param *p){
   
   int i;
 
-  p->ft_type = 1;
+  p->ft_type = 0;
   configuration_get_value_int(&config, "PARAMS", "ft_type", anno,
       &p->ft_type);
   if(!g_tw_mynode) printf("FT type is %d\n", p->ft_type);
+  if(p->ft_type == 1) printf("Use of FT type 1 is deprecated; please use type 0 for similar functionality\n");
+  if(p->ft_type == 2) printf("You have chosen FT type 2: this is for cases in which different NICs are desired for different rails.\n");
 
   configuration_get_value_int(&config, "PARAMS", "num_levels", anno,
       &p->num_levels);
@@ -866,9 +868,9 @@ static void fattree_read_config(const char * anno, fattree_param *p){
   if(!g_tw_mynode) printf("FT num rails is %d\n", p->num_rails);
   
   if(p->ft_type == 2) {
-    p->ports_per_nic = p->num_rails;
-  } else {
     p->ports_per_nic = 1;
+  } else {
+    p->ports_per_nic = p->num_rails;
   }
 
   p->router_delay = 50;
@@ -1022,7 +1024,7 @@ void ft_terminal_init( ft_terminal_state * s, tw_lp * lp )
    int num_lps = codes_mapping_get_lp_count(lp_group_name, 1, LP_CONFIG_NM,
            s->anno, 0);
 
-   if(s->params->ft_type != 2) {
+   if(s->params->ft_type == 2) {
     num_lps /= s->params->num_rails;
    }
 
@@ -1031,7 +1033,7 @@ void ft_terminal_init( ft_terminal_state * s, tw_lp * lp )
          "%d, not the given value of %d\n", s->params->l0_term_size, num_lps);
    }
   
-   if(s->params->ft_type != 2) {
+   if(s->params->ft_type == 2) {
     s->terminal_id = (mapping_rep_id * num_lps) + (mapping_offset/s->params->num_rails);
     s->rail_id = (mapping_offset % s->params->num_rails);
    } else {
@@ -1040,7 +1042,7 @@ void ft_terminal_init( ft_terminal_state * s, tw_lp * lp )
    }
    s->switch_id = s->terminal_id / s->params->l0_term_size;
    s->switch_lp = (tw_lpid*)malloc(s->params->ports_per_nic * sizeof(tw_lpid));
-   if(s->params->ft_type != 2) {
+   if(s->params->ft_type == 2) {
      codes_mapping_get_lp_id(lp_group_name, "fattree_switch", NULL, 1,
          s->switch_id, 0 + s->params->num_levels * s->rail_id, &s->switch_lp[0]);
    } else {
@@ -1215,7 +1217,7 @@ void switch_init(switch_state * r, tw_lp * lp)
   //if at level 0, first half ports go to terminals
   if(r->switch_level == 0) {
     int term_rails, term_railid;
-    if(p->ft_type != 2) {
+    if(p->ft_type == 2) {
       term_rails = p->num_rails;
       term_railid = r->rail_id;
     } else {
@@ -2672,7 +2674,7 @@ int ft_get_output_port( switch_state * s, tw_bf * bf, fattree_message * msg,
   fattree_param *p = s->params;
 
   int dest_term_local_id = codes_mapping_get_lp_relative_id(msg->dest_terminal_id, 0, 0);
-  if(s->params->ft_type != 2) {
+  if(s->params->ft_type == 2) {
     dest_term_local_id /= s->params->num_rails;
   }
   /* either do static oblivious routing, if set up properly via LFTs */