Merge branch 'qos-dev-merge-resolved' into 'master'

DFP QoS work and DFDally Custom Standalone model

See merge request !64

codes/model-net-lp.h

@@ -24,6 +24,7 @@ extern "C" {
 #include "net/dragonfly.h"
 #include "net/dragonfly-custom.h"
 #include "net/dragonfly-plus.h"
+#include "net/dragonfly-dally.h"
 #include "net/slimfly.h"
 #include "net/fattree.h"
 #include "net/loggp.h"
@@ -133,6 +134,7 @@ typedef struct model_net_wrap_msg {
         terminal_message        m_dfly;  // dragonfly
         terminal_custom_message        m_custom_dfly;  // dragonfly-custom
         terminal_plus_message        m_dfly_plus;  // dragonfly plus
+        terminal_dally_message        m_dally_dfly;  // dragonfly dally
         slim_terminal_message   m_slim;  // slimfly
 	fattree_message		m_fat;   // fattree
         loggp_message           m_loggp; // loggp

codes/model-net.h

@@ -76,6 +76,8 @@ typedef struct mn_stats mn_stats;
     X(EXPRESS_MESH_ROUTER, "modelnet_express_mesh_router", "express_mesh_router", &express_mesh_router_method)\
     X(DRAGONFLY_PLUS, "modelnet_dragonfly_plus", "dragonfly_plus", &dragonfly_plus_method)\
     X(DRAGONFLY_PLUS_ROUTER, "modelnet_dragonfly_plus_router", "dragonfly_plus_router", &dragonfly_plus_router_method)\
+    X(DRAGONFLY_DALLY, "modelnet_dragonfly_dally", "dragonfly_dally", &dragonfly_dally_method)\
+    X(DRAGONFLY_DALLY_ROUTER, "modelnet_dragonfly_dally_router", "dragonfly_dally_router", &dragonfly_dally_router_method)\
     X(MAX_NETS,  NULL,                 NULL,        NULL)
 
 #define X(a,b,c,d) a,

codes/net/dragonfly-dally.h

+/*
+ * Copyright (C) 2014 University of Chicago.
+ * See COPYRIGHT notice in top-level directory.
+ *
+ */
+
+#ifndef DRAGONFLY_DALLY_H
+#define DRAGONFLY_DALLY_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <ross.h>
+
+typedef struct terminal_dally_message terminal_dally_message;
+
+/* this message is used for both dragonfly compute nodes and routers */
+struct terminal_dally_message
+{
+  /* magic number */
+  int magic;
+  /* flit travel start time*/
+  tw_stime travel_start_time;
+ /* packet ID of the flit  */
+  unsigned long long packet_ID;
+  /* event type of the flit */
+  short  type;
+  /* category: comes from codes */
+  char category[CATEGORY_NAME_MAX];
+  /* store category hash in the event */
+  uint32_t category_hash;
+  /* final destination LP ID, this comes from codes can be a server or any other LP type*/
+  tw_lpid final_dest_gid;
+  /*sending LP ID from CODES, can be a server or any other LP type */
+  tw_lpid sender_lp;
+  tw_lpid sender_mn_lp; // source modelnet id
+ /* destination terminal ID of the dragonfly */
+  tw_lpid dest_terminal_id;
+  /* source terminal ID of the dragonfly */
+  unsigned int src_terminal_id;
+  /* message originating router id. MM: Can we calculate it through
+   * sender_mn_lp??*/
+  unsigned int origin_router_id;
+
+  /* number of hops traversed by the packet */
+  short my_N_hop;
+  short my_l_hop, my_g_hop;
+  short saved_channel;
+  short saved_vc;
+
+  int next_stop;
+
+  short nonmin_done;
+  /* Intermediate LP ID from which this message is coming */
+  unsigned int intm_lp_id;
+  /* last hop of the message, can be a terminal, local router or global router */
+  short last_hop;
+   /* For routing */
+  int intm_rtr_id;
+  int saved_src_dest;
+  int saved_src_chan;
+
+   uint32_t chunk_id;
+   uint32_t packet_size;
+   uint32_t message_id;
+   uint32_t total_size;
+
+   int remote_event_size_bytes;
+   int local_event_size_bytes;
+
+  // For buffer message
+   short vc_index;
+   int output_chan;
+   model_net_event_return event_rc;
+   int is_pull;
+   uint32_t pull_size;
+   int path_type;
+
+   /* for reverse computation */   
+   short num_rngs;
+   short num_cll;
+
+   int qos_index;
+   short last_saved_qos;
+   short qos_reset1;
+   short qos_reset2;
+
+   tw_stime saved_available_time;
+   tw_stime saved_avg_time;
+   tw_stime saved_rcv_time;
+   tw_stime saved_busy_time; 
+   tw_stime saved_total_time;
+   tw_stime saved_sample_time;
+   tw_stime msg_start_time;
+   tw_stime saved_busy_time_ross;
+   tw_stime saved_fin_chunks_ross;
+};
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* end of include guard: DRAGONFLY_H */
+
+/*
+ * Local variables:
+ *  c-indent-level: 4
+ *  c-basic-offset: 4
+ * End:
+ *
+ * vim: ft=c ts=8 sts=4 sw=4 expandtab
+ */

codes/net/dragonfly-plus.h

@@ -83,6 +83,21 @@ struct terminal_plus_message
    int is_pull;
    uint32_t pull_size;
 
+   /* for counting reverse calls */
+   short num_rngs;
+   short num_cll;
+
+   /* qos related attributes */   
+   short last_saved_qos;
+   short qos_reset1;
+   short qos_reset2;
+
+   /* new qos rc - These are calloced in forward events, free'd in RC or commit_f */
+   /* note: dynamic memory here is OK since it's only accessed by the LP that alloced it in the first place. */
+   short rc_is_qos_set;
+   unsigned long long * rc_qos_data;
+   int * rc_qos_status;
+
    /* for reverse computation */
    int path_type;
    tw_stime saved_available_time;

configure.ac

@@ -230,4 +230,7 @@ AC_CONFIG_FILES([Makefile])
 
 AC_OUTPUT([maint/codes.pc])
 AC_OUTPUT([src/network-workloads/conf/dragonfly-custom/modelnet-test-dragonfly-1728-nodes.conf])
+AC_OUTPUT([src/network-workloads/conf/dragonfly-plus/modelnet-test-dragonfly-plus.conf])
+AC_OUTPUT([src/network-workloads/conf/dragonfly-dally/modelnet-test-dragonfly-dally.conf])
+
 

scripts/allocation_gen/config_alloc-upd.conf

-CONT
-3456
+rand
+1024
 2
 1
-1024 128
+512 512

scripts/allocation_gen/config_alloc.conf

-CONT
-3456
-1024 128
+rand
+1008
+512 496

src/Makefile.subdir

@@ -94,8 +94,9 @@ nobase_include_HEADERS = \
 	codes/connection-manager.h	\
 	codes/net/common-net.h \
 	codes/net/dragonfly.h \
-	codes/net/dragonfly-plus.h	\
 	codes/net/dragonfly-custom.h \
+	codes/net/dragonfly-dally.h \
+	codes/net/dragonfly-plus.h \
 	codes/net/slimfly.h \
 	codes/net/fattree.h \
 	codes/net/loggp.h \
@@ -164,6 +165,7 @@ src_libcodes_la_SOURCES =  \
 	src/networks/model-net/dragonfly.c \
 	src/networks/model-net/dragonfly-custom.C \
 	src/networks/model-net/dragonfly-plus.C \
+	src/networks/model-net/dragonfly-dally.C \
 	src/networks/model-net/slimfly.c \
 	src/networks/model-net/fattree.c \
 	src/networks/model-net/loggp.c \
@@ -198,6 +200,7 @@ bin_PROGRAMS += src/network-workloads/model-net-synthetic-custom-dfly
 bin_PROGRAMS += src/network-workloads/model-net-synthetic-slimfly
 bin_PROGRAMS += src/network-workloads/model-net-synthetic-fattree
 bin_PROGRAMS += src/network-workloads/model-net-synthetic-dfly-plus
+bin_PROGRAMS += src/network-workloads/model-net-synthetic-dally-dfly
 
 
 src_workload_codes_workload_dump_SOURCES = \
@@ -212,6 +215,7 @@ src_network_workloads_model_net_mpi_replay_CFLAGS = $(AM_CFLAGS)
 src_network_workloads_model_net_synthetic_SOURCES = src/network-workloads/model-net-synthetic.c
 src_network_workloads_model_net_synthetic_custom_dfly_SOURCES = src/network-workloads/model-net-synthetic-custom-dfly.c
 src_network_workloads_model_net_synthetic_dfly_plus_SOURCES = src/network-workloads/model-net-synthetic-dfly-plus.c
+src_network_workloads_model_net_synthetic_dally_dfly_SOURCES = src/network-workloads/model-net-synthetic-dally-dfly.c
 src_networks_model_net_topology_test_SOURCES = src/networks/model-net/topology-test.c
 
 #bin_PROGRAMS += src/network-workload/codes-nw-test

src/network-workloads/conf/dragonfly-dally/dfdally_8k.conf

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="1040";
+# name of this lp changes according to the model
+      nw-lp="8";
+# these lp names will be the same for dragonfly-custom model
+      modelnet_dragonfly_dally="8";
+      modelnet_dragonfly_dally_router="1";
+   }
+}
+PARAMS
+{
+# packet size in the network
+   packet_size="4096";
+   modelnet_order=( "dragonfly_dally","dragonfly_dally_router" );
+   # scheduler options
+   modelnet_scheduler="fcfs";
+# chunk size in the network (when chunk size = packet size, packets will not be
+# divided into chunks)
+   chunk_size="4096";
+   # modelnet_scheduler="round-robin";
+
+   num_router_rows="1";
+   # intra-group columns for routers
+   num_router_cols="16";
+   # number of groups in the network
+   num_groups="65";
+# buffer size in bytes for local virtual channels
+   local_vc_size="16384";
+#buffer size in bytes for global virtual channels
+   global_vc_size="16384";
+#buffer size in bytes for compute node virtual channels
+   cn_vc_size="32768";
+#bandwidth in GiB/s for local channels
+   local_bandwidth="2.0";
+# bandwidth in GiB/s for global channels
+   global_bandwidth="2.0";
+# bandwidth in GiB/s for compute node-router channels
+   cn_bandwidth="2.0";
+# Number of row channels
+   num_row_chans="1";
+# Number of column channels
+   num_col_chans="1";
+# ROSS message size
+   message_size="656";
+# number of compute nodes connected to router, dictated by dragonfly config
+# file
+   num_cns_per_router="8";
+# number of global channels per router
+   num_global_channels="8";
+# network config file for intra-group connections
+   intra-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_intra";
+# network config file for inter-group connections
+   inter-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_inter";
+# routing protocol to be used
+   routing="prog-adaptive";
+   adaptive_threshold="131072";
+   minimal-bias="1";
+   df-dally-vc = "1";
+}

src/network-workloads/conf/dragonfly-dally/modelnet-test-dragonfly-dally.conf

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="1040";
+# name of this lp changes according to the model
+      nw-lp="8";
+# these lp names will be the same for dragonfly-custom model
+      modelnet_dragonfly_dally="8";
+      modelnet_dragonfly_dally_router="1";
+   }
+}
+PARAMS
+{
+# packet size in the network
+   packet_size="4096";
+   modelnet_order=( "dragonfly_dally","dragonfly_dally_router" );
+   # scheduler options
+   modelnet_scheduler="fcfs";
+# chunk size in the network (when chunk size = packet size, packets will not be
+# divided into chunks)
+   chunk_size="4096";
+   # modelnet_scheduler="round-robin";
+
+   num_router_rows="1";
+   # intra-group columns for routers
+   num_router_cols="16";
+   # number of groups in the network
+   num_groups="65";
+# buffer size in bytes for local virtual channels
+   local_vc_size="16384";
+#buffer size in bytes for global virtual channels
+   global_vc_size="16384";
+#buffer size in bytes for compute node virtual channels
+   cn_vc_size="32768";
+#bandwidth in GiB/s for local channels
+   local_bandwidth="2.0";
+# bandwidth in GiB/s for global channels
+   global_bandwidth="2.0";
+# bandwidth in GiB/s for compute node-router channels
+   cn_bandwidth="2.0";
+# Number of row channels
+   num_row_chans="1";
+# Number of column channels
+   num_col_chans="1";
+# ROSS message size
+   message_size="656";
+# number of compute nodes connected to router, dictated by dragonfly config
+# file
+   num_cns_per_router="8";
+# number of global channels per router
+   num_global_channels="8";
+# network config file for intra-group connections
+   intra-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_intra";
+# network config file for inter-group connections
+   inter-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_inter";
+# routing protocol to be used
+   routing="prog-adaptive";
+   adaptive_threshold="131072";
+   minimal-bias="1";
+   df-dally-vc = "1";
+}

src/network-workloads/conf/dragonfly-dally/modelnet-test-dragonfly-dally.conf.in

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="1040";
+# name of this lp changes according to the model
+      nw-lp="8";
+# these lp names will be the same for dragonfly-custom model
+      modelnet_dragonfly_dally="8";
+      modelnet_dragonfly_dally_router="1";
+   }
+}
+PARAMS
+{
+# packet size in the network
+   packet_size="4096";
+   modelnet_order=( "dragonfly_dally","dragonfly_dally_router" );
+   # scheduler options
+   modelnet_scheduler="fcfs";
+# chunk size in the network (when chunk size = packet size, packets will not be
+# divided into chunks)
+   chunk_size="4096";
+   # modelnet_scheduler="round-robin";
+
+   num_router_rows="1";
+   # intra-group columns for routers
+   num_router_cols="16";
+   # number of groups in the network
+   num_groups="65";
+# buffer size in bytes for local virtual channels
+   local_vc_size="16384";
+#buffer size in bytes for global virtual channels
+   global_vc_size="16384";
+#buffer size in bytes for compute node virtual channels
+   cn_vc_size="32768";
+#bandwidth in GiB/s for local channels
+   local_bandwidth="2.0";
+# bandwidth in GiB/s for global channels
+   global_bandwidth="2.0";
+# bandwidth in GiB/s for compute node-router channels
+   cn_bandwidth="2.0";
+# Number of row channels
+   num_row_chans="1";
+# Number of column channels
+   num_col_chans="1";
+# ROSS message size
+   message_size="656";
+# number of compute nodes connected to router, dictated by dragonfly config
+# file
+   num_cns_per_router="8";
+# number of global channels per router
+   num_global_channels="8";
+# network config file for intra-group connections
+   intra-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_intra";
+# network config file for inter-group connections
+   inter-group-connections="../src/network-workloads/conf/dragonfly-dally/dfdally_8k_inter";
+# routing protocol to be used
+   routing="prog-adaptive";
+   adaptive_threshold="131072";
+   minimal-bias="1";
+   df-dally-vc = "1";
+}

src/network-workloads/conf/dragonfly-plus/dfp_8k.conf

@@ -47,9 +47,9 @@ PARAMS
 # number of global channels per router
    num_global_connections="16";
 # network config file for intra-group connections
-   intra-group-connections="/gpfs/u/home/SPNR/SPNRmcgl/barn/dfp-df-comparisons/experiments/network_configs/dfp_8k_intra";
+   intra-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_intra";
 # network config file for inter-group connections
-   inter-group-connections="/gpfs/u/home/SPNR/SPNRmcgl/barn/dfp-df-comparisons/experiments/network_configs/dfp_8k_inter";
+   inter-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_inter";
 # routing protocol to be used - 'minimal', 'non-minimal-spine', 'non-minimal-leaf', 'prog-adaptive'
    routing="prog-adaptive";
 # route scoring protocol to be used - options are 'alpha', 'beta', or 'delta' - 'gamma' has been deprecated

src/network-workloads/conf/dragonfly-plus/modelnet-test-dragonfly-plus.conf

@@ -2,61 +2,59 @@ LPGROUPS
 {
    MODELNET_GRP
    {
-      repetitions="12";
+      repetitions="1056";
 # name of this lp changes according to the model
-      nw-lp="4";
+      nw-lp="8";
 # these lp names will be the same for dragonfly-custom model
-      modelnet_dragonfly_plus="4";
-      modelnet_dragonfly_plus_router="2";
+      modelnet_dragonfly_plus="8";
+      modelnet_dragonfly_plus_router="1";
    }
 }
 PARAMS
 {
 # packet size in the network
-   packet_size="1024";
+   packet_size="4096";
+# order of LPs, mapping for modelnet grp
    modelnet_order=( "dragonfly_plus","dragonfly_plus_router" );
-   # scheduler options
+# scheduler options
    modelnet_scheduler="fcfs";
-# chunk size in the network (when chunk size = packet size, packets will not be
-# divided into chunks)
-   chunk_size="1024";
-   # modelnet_scheduler="round-robin";
-   # number of routers within each group
-   # each router row corresponds to a chassis in Cray systems
-   num_router_spine="4";
-   # each router column corresponds to a slot in a chassis
-   num_router_leaf="4";
-   # number of links connecting between group levels per router
+# chunk size in the network (when chunk size = packet size, packets will not be divided into chunks)
+   chunk_size="4096";
+# number of spine routers per group
+   num_router_spine="16";
+# number of leaf routers per group
+   num_router_leaf="16";
+# number of links connecting between group levels per router
    num_level_chans="1";
-   # number of groups in the network
-   num_groups="3";
-
-# predefined threshold (T) deciding when to reassign packet to a lower priority queue
-   queue_threshold="50";
-
+# number of groups in the network
+   num_groups="33";
 # buffer size in bytes for local virtual channels
-   local_vc_size="8192";
-#buffer size in bytes for global virtual channels
-   global_vc_size="16384";
-#buffer size in bytes for compute node virtual channels
-   cn_vc_size="8192";
-#bandwidth in GiB/s for local channels
-   local_bandwidth="5.25";
+   local_vc_size="32768";
+# buffer size in bytes for global virtual channels
+   global_vc_size="32768";
+# buffer size in bytes for compute node virtual channels
+   cn_vc_size="32768";
+# bandwidth in GiB/s for local channels
+   local_bandwidth="25.0";
 # bandwidth in GiB/s for global channels
-   global_bandwidth="1.5";
+   global_bandwidth="25.0";
 # bandwidth in GiB/s for compute node-router channels
-   cn_bandwidth="8.0";
+   cn_bandwidth="25.0";
 # ROSS message size
-   message_size="608";
-# number of compute nodes connected to router, dictated by dragonfly config
-# file
-   num_cns_per_router="4";
+   message_size="640";
+# number of compute nodes connected to router, dictated by dragonfly config file
+   num_cns_per_router="16";
 # number of global channels per router
-   num_global_connections="4";
+   num_global_connections="16";
 # network config file for intra-group connections
-   intra-group-connections="../src/network-workloads/conf/dragonfly-plus/neil-intra";
+   intra-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_intra";
 # network config file for inter-group connections
-   inter-group-connections="../src/network-workloads/conf/dragonfly-plus/neil-inter";
-# routing protocol to be used
-   routing="minimal";
+   inter-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_inter";
+# routing protocol to be used - 'minimal', 'non-minimal-spine', 'non-minimal-leaf', 'prog-adaptive'
+   routing="prog-adaptive";
+# route scoring protocol to be used - options are 'alpha', 'beta', or 'delta' - 'gamma' has been deprecated
+   route_scoring_metric="delta";
+# minimal route threshold before considering non-minimal paths
+   adaptive_threshold="131072"; #1/16 of 32768
 }
+

src/network-workloads/conf/dragonfly-plus/modelnet-test-dragonfly-plus.conf.in

+LPGROUPS
+{
+   MODELNET_GRP
+   {
+      repetitions="1056";
+# name of this lp changes according to the model
+      nw-lp="8";
+# these lp names will be the same for dragonfly-custom model
+      modelnet_dragonfly_plus="8";
+      modelnet_dragonfly_plus_router="1";
+   }
+}
+PARAMS
+{
+# packet size in the network
+   packet_size="4096";
+# order of LPs, mapping for modelnet grp
+   modelnet_order=( "dragonfly_plus","dragonfly_plus_router" );
+# scheduler options
+   modelnet_scheduler="fcfs";
+# chunk size in the network (when chunk size = packet size, packets will not be divided into chunks)
+   chunk_size="4096";
+# number of spine routers per group
+   num_router_spine="16";
+# number of leaf routers per group
+   num_router_leaf="16";
+# number of links connecting between group levels per router
+   num_level_chans="1";
+# number of groups in the network
+   num_groups="33";
+# buffer size in bytes for local virtual channels
+   local_vc_size="32768";
+# buffer size in bytes for global virtual channels
+   global_vc_size="32768";
+# buffer size in bytes for compute node virtual channels
+   cn_vc_size="32768";
+# bandwidth in GiB/s for local channels
+   local_bandwidth="25.0";
+# bandwidth in GiB/s for global channels
+   global_bandwidth="25.0";
+# bandwidth in GiB/s for compute node-router channels
+   cn_bandwidth="25.0";
+# ROSS message size
+   message_size="640";
+# number of compute nodes connected to router, dictated by dragonfly config file
+   num_cns_per_router="16";
+# number of global channels per router
+   num_global_connections="16";
+# network config file for intra-group connections
+   intra-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_intra";
+# network config file for inter-group connections
+   inter-group-connections="../src/network-workloads/conf/dragonfly-plus/dfp_8k_inter";
+# routing protocol to be used - 'minimal', 'non-minimal-spine', 'non-minimal-leaf', 'prog-adaptive'
+   routing="prog-adaptive";
+# route scoring protocol to be used - options are 'alpha', 'beta', or 'delta' - 'gamma' has been deprecated
+   route_scoring_metric="delta";
+# minimal route threshold before considering non-minimal paths
+   adaptive_threshold="131072"; #1/16 of 32768
+}
+

src/network-workloads/model-net-synthetic-dally-dfly.c

+/*
+ * Copyright (C) 2015 University of Chicago.
+ * See COPYRIGHT notice in top-level directory.
+ *
+ */
+
+/*
+* The test program generates some synthetic traffic patterns for the model-net network models.
+* currently it only support the dragonfly network model uniform random and nearest neighbor traffic patterns.
+*/
+
+#include "codes/model-net.h"
+#include "codes/lp-io.h"
+#include "codes/codes.h"
+#include "codes/codes_mapping.h"
+#include "codes/configuration.h"
+#include "codes/lp-type-lookup.h"
+
+