Skip to content

GitLab

Commit 8274da0d authored by Neil McGlohon's avatar Neil McGlohon
Browse files

Add DFDally work into its own model for merging

parent 312fb670
Hide whitespace changes
Inline Side-by-side
Showing with 5965 additions and 1 deletion
codes/model-net-lp.h
View file @ 8274da0d
......@@ -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
View file @ 8274da0d
......@@ -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 0 → 100644
View file @ 8274da0d
/*
* 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
*/
src/Makefile.subdir
View file @ 8274da0d
......@@ -94,6 +94,8 @@ nobase_include_HEADERS = \
codes/net/common-net.h \
codes/net/dragonfly.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 \
......@@ -162,6 +164,7 @@ 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 \
......@@ -196,6 +199,7 @@ 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 = \
......@@ -210,6 +214,7 @@ 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 0 → 100644
View file @ 8274da0d
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
{
adaptive_threshold="131072";
num_qos_levels="2";
qos_bandwidth="30,70";
minimal-bias="1";
df-dally-vc = "1";
# 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";
}
src/network-workloads/model-net-synthetic-dally-dfly.c 0 → 100644
View file @ 8274da0d
/*
* 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"
static int net_id = 0;
static int traffic = 1;
static double arrival_time = 1000.0;
static int PAYLOAD_SZ = 2048;
/* whether to pull instead of push */
static int num_servers_per_rep = 0;
static int num_routers_per_grp = 0;
static int num_nodes_per_grp = 0;
static int num_nodes_per_cn = 0;
static int num_groups = 0;
static unsigned long long num_nodes = 0;
static char lp_io_dir[256] = {'\0'};
static lp_io_handle io_handle;
static unsigned int lp_io_use_suffix = 0;
static int do_lp_io = 0;
static int num_msgs = 20;
static tw_stime sampling_interval = 800000;
static tw_stime sampling_end_time = 1600000;
typedef struct svr_msg svr_msg;
typedef struct svr_state svr_state;
/* global variables for codes mapping */
static char group_name[MAX_NAME_LENGTH];
static char lp_type_name[MAX_NAME_LENGTH];
static int group_index, lp_type_index, rep_id, offset;
/* type of events */
enum svr_event
{
KICKOFF, /* kickoff event */
REMOTE, /* remote event */
LOCAL /* local event */
};
/* type of synthetic traffic */
enum TRAFFIC
{
UNIFORM = 1, /* sends message to a randomly selected node */
RAND_PERM = 2,
NEAREST_GROUP = 3, /* sends message to the node connected to the neighboring router */
NEAREST_NEIGHBOR = 4, /* sends message to the next node (potentially connected to the same router) */
RANDOM_OTHER_GROUP = 5
};
struct svr_state
{
int msg_sent_count; /* requests sent */
int msg_recvd_count; /* requests recvd */
int local_recvd_count; /* number of local messages received */
tw_stime start_ts; /* time that we started sending requests */
tw_stime end_ts; /* time that we ended sending requests */
int dest_id;
};
struct svr_msg
{
enum svr_event svr_event_type;
tw_lpid src; /* source of this request or ack */
int incremented_flag; /* helper for reverse computation */
model_net_event_return event_rc;
};
static void svr_init(
svr_state * ns,
tw_lp * lp);
static void svr_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp);
static void svr_rev_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp);
static void svr_finalize(
svr_state * ns,
tw_lp * lp);
tw_lptype svr_lp = {
(init_f) svr_init,
(pre_run_f) NULL,
(event_f) svr_event,
(revent_f) svr_rev_event,
(commit_f) NULL,
(final_f) svr_finalize,
(map_f) codes_mapping,
sizeof(svr_state),
};
// /* setup for the ROSS event tracing
// */
// void dally_svr_event_collect(svr_msg *m, tw_lp *lp, char *buffer, int *collect_flag)
// {
// (void)lp;
// (void)collect_flag;
// int type = (int) m->svr_event_type;
// memcpy(buffer, &type, sizeof(type));
// }
// /* can add in any model level data to be collected along with simulation engine data
// * in the ROSS instrumentation. Will need to update the last field in
// * svr_model_types[0] for the size of the data to save in each function call
// */
// void dally_svr_model_stat_collect(svr_state *s, tw_lp *lp, char *buffer)
// {
// (void)s;
// (void)lp;
// (void)buffer;
// return;
// }
// st_model_types dally_svr_model_types[] = {
// {(ev_trace_f) dally_svr_event_collect,
// sizeof(int),
// (model_stat_f) dally_svr_model_stat_collect,
// 0,
// NULL,
// NULL,
// 0},
// {NULL, 0, NULL, 0, NULL, NULL, 0}
// };
// static const st_model_types *dally_svr_get_model_stat_types(void)
// {
// return(&dally_svr_model_types[0]);
// }
// void dally_svr_register_model_types()
// {
// st_model_type_register("nw-lp", dally_svr_get_model_stat_types());
// }
const tw_optdef app_opt [] =
{
TWOPT_GROUP("Model net synthetic traffic " ),
TWOPT_UINT("traffic", traffic, "UNIFORM RANDOM=1, NEAREST NEIGHBOR=2 "),
TWOPT_UINT("num_messages", num_msgs, "Number of messages to be generated per terminal "),
TWOPT_UINT("payload_sz",PAYLOAD_SZ, "size of the message being sent "),
TWOPT_STIME("sampling-interval", sampling_interval, "the sampling interval "),
TWOPT_STIME("sampling-end-time", sampling_end_time, "sampling end time "),
TWOPT_STIME("arrival_time", arrival_time, "INTER-ARRIVAL TIME"),
TWOPT_CHAR("lp-io-dir", lp_io_dir, "Where to place io output (unspecified -> no output"),
TWOPT_UINT("lp-io-use-suffix", lp_io_use_suffix, "Whether to append uniq suffix to lp-io directory (default 0)"),
TWOPT_END()
};
const tw_lptype* svr_get_lp_type()
{
return(&svr_lp);
}
static void svr_add_lp_type()
{
lp_type_register("nw-lp", svr_get_lp_type());
}
static void issue_event(
svr_state * ns,
tw_lp * lp)
{
(void)ns;
tw_event *e;
svr_msg *m;
tw_stime kickoff_time;
/* each server sends a dummy event to itself that will kick off the real
* simulation
*/
/* skew each kickoff event slightly to help avoid event ties later on */
kickoff_time = 1.1 * g_tw_lookahead + tw_rand_exponential(lp->rng, arrival_time);
e = tw_event_new(lp->gid, kickoff_time, lp);
m = tw_event_data(e);
m->svr_event_type = KICKOFF;
tw_event_send(e);
}
static void svr_init(
svr_state * ns,
tw_lp * lp)
{
ns->start_ts = 0.0;
ns->dest_id = -1;
issue_event(ns, lp);
return;
}
static void handle_kickoff_rev_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
if(m->incremented_flag)
return;
if(b->c1)
tw_rand_reverse_unif(lp->rng);
if(b->c8)
tw_rand_reverse_unif(lp->rng);
if(traffic == RANDOM_OTHER_GROUP) {
tw_rand_reverse_unif(lp->rng);
tw_rand_reverse_unif(lp->rng);
}
model_net_event_rc2(lp, &m->event_rc);
ns->msg_sent_count--;
tw_rand_reverse_unif(lp->rng);
}
static void handle_kickoff_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
if(ns->msg_sent_count >= num_msgs)
{
m->incremented_flag = 1;
return;
}
m->incremented_flag = 0;
char anno[MAX_NAME_LENGTH];
tw_lpid local_dest = -1, global_dest = -1;
svr_msg * m_local = malloc(sizeof(svr_msg));
svr_msg * m_remote = malloc(sizeof(svr_msg));
m_local->svr_event_type = LOCAL;
m_local->src = lp->gid;
memcpy(m_remote, m_local, sizeof(svr_msg));
m_remote->svr_event_type = REMOTE;
assert(net_id == DRAGONFLY || net_id == DRAGONFLY_DALLY); /* only supported for dragonfly model right now. */
ns->start_ts = tw_now(lp);
codes_mapping_get_lp_info(lp->gid, group_name, &group_index, lp_type_name, &lp_type_index, anno, &rep_id, &offset);
int local_id = codes_mapping_get_lp_relative_id(lp->gid, 0, 0);
/* in case of uniform random traffic, send to a random destination. */
if(traffic == UNIFORM)
{
b->c1 = 1;
local_dest = tw_rand_integer(lp->rng, 0, num_nodes - 1);
}
else if(traffic == NEAREST_GROUP)
{
local_dest = (local_id + num_nodes_per_grp) % num_nodes;
//printf("\n LP %ld sending to %ld num nodes %d ", local_id, local_dest, num_nodes);
}
else if(traffic == NEAREST_NEIGHBOR)
{
local_dest = (local_id + 1) % num_nodes;
// printf("\n LP %ld sending to %ld num nodes %d ", rep_id * 2 + offset, local_dest, num_nodes);
}
else if(traffic == RAND_PERM)
{
if(ns->dest_id == -1)
{
b->c8 = 1;
ns->dest_id = tw_rand_integer(lp->rng, 0, num_nodes - 1);
local_dest = ns->dest_id;
}
else
{
local_dest = ns->dest_id;
}
}
else if(traffic == RANDOM_OTHER_GROUP)
{
int my_group_id = local_id / num_nodes_per_grp;
int other_groups[num_groups-1];
int added =0;
for(int i = 0; i < num_groups; i++)
{
if(i != my_group_id) {
other_groups[added] = i;
added++;
}
}
int rand_group = other_groups[tw_rand_integer(lp->rng,0,added -1)];
int rand_node_intra_id = tw_rand_integer(lp->rng, 0, num_nodes_per_grp-1);
local_dest = (rand_group * num_nodes_per_grp) + rand_node_intra_id;
printf("\n LP %ld sending to %ld num nodes %d ", local_id, local_dest, num_nodes);
}
assert(local_dest < num_nodes);
// codes_mapping_get_lp_id(group_name, lp_type_name, anno, 1, local_dest / num_servers_per_rep, local_dest % num_servers_per_rep, &global_dest);
global_dest = codes_mapping_get_lpid_from_relative(local_dest, group_name, lp_type_name, NULL, 0);
ns->msg_sent_count++;
m->event_rc = model_net_event(net_id, "test", global_dest, PAYLOAD_SZ, 0.0, sizeof(svr_msg), (const void*)m_remote, sizeof(svr_msg), (const void*)m_local, lp);
issue_event(ns, lp);
return;
}
static void handle_remote_rev_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
(void)b;
(void)m;
(void)lp;
ns->msg_recvd_count--;
}
static void handle_remote_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
(void)b;
(void)m;
(void)lp;
ns->msg_recvd_count++;
}
static void handle_local_rev_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
(void)b;
(void)m;
(void)lp;
ns->local_recvd_count--;
}
static void handle_local_event(
svr_state * ns,
tw_bf * b,
svr_msg * m,
tw_lp * lp)
{
(void)b;
(void)m;
(void)lp;
ns->local_recvd_count++;
}