Merge branch 'hls_2018'

Merge hls_2018 to master

hls/auto/auto_compile.c

+#include <stdio.h>
+#include <stdlib.h>
+
+#define STRLEN 65536
+
+int main(void){
+
+   char q[STRLEN], command[STRLEN];
+   char dir[64] = "../lines256_length128";
+
+   FILE *fp;
+   fp = fopen("q.txt", "r");
+   if(fp == NULL){
+      printf("File does not exist.\n");
+      exit(1);
+   }
+
+   int counter = 1;
+   while(1){
+      if(fscanf(fp, "%s", q) == EOF) break;
+      printf("Q. %d\n", counter++);
+      sprintf(command, "./%s/sim.exe %s", dir, q);
+      //printf("(command) %s\n", command);
+      int ret = system(command);
+      printf("ret: %d\n", ret);
+   }
+   fclose(fp);
+   return 0;
+}
+

hls/lines128_length256/main.cpp

@@ -17,6 +17,7 @@
 
 #include "router.hpp"
 
+#define PRINT_SOLUTION
 
 int main(int argc, char *argv[]) {
     using namespace std;
@@ -50,9 +51,11 @@ int main(int argc, char *argv[]) {
         seed = atoi(argv[2]);
     }
 
+#ifdef PRINT_SOLUTION
     int size_x = (boardstr[1] - '0') * 10 + (boardstr[2] - '0');
     int size_y = (boardstr[4] - '0') * 10 + (boardstr[5] - '0');
     int size_z = (boardstr[7] - '0');
+#endif
 
     // ソルバ実行
     ap_int<32> status;
@@ -68,6 +71,7 @@ int main(int argc, char *argv[]) {
     cout << "status = " << (int)status << endl;
     cout << "elapsed = " << ((double)(clock_done - clock_start) / CLOCKS_PER_SEC) << endl << endl;
 
+#ifdef PRINT_SOLUTION
     // 解表示
     cout << "SOLUTION" << endl;
     cout << "========" << endl;
@@ -80,12 +84,13 @@ int main(int argc, char *argv[]) {
                     cout << ",";
                 }
                 int i = ((x * MAX_WIDTH + y) << BITWIDTH_Z) | z;
-                //cout << setfill('0') << setw(2) << right << (unsigned int)(unsigned char)(boardstr[i]);
-                cout << (unsigned int)(unsigned char)(boardstr[i]);
+                cout << setfill('0') << setw(3) << right << (unsigned int)(unsigned char)(boardstr[i]);
+                //cout << (unsigned int)(unsigned char)(boardstr[i]);
             }
             cout << endl;
         }
     }
+#endif
 
     return 0;
 }

hls/lines128_length256/router.cpp

@@ -244,6 +244,7 @@ bool pynqrouter(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *stat
     ap_uint<8> last_target = 255;
 
     // [Step 2] Rip-up 再ルーティング
+    cout << "Rip-up Routing" << endl;
     ROUTING:
     for (ap_uint<16> round = 1; round <= 32768 /* = (2048 * 16) */; round++) {
 #pragma HLS LOOP_TRIPCOUNT min=1 max=4000 avg=50
@@ -284,8 +285,6 @@ bool pynqrouter(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *stat
 #pragma HLS LOOP_TRIPCOUNT min=1 max=255 avg=50
             weights[paths[target][j]] = 1;
         }
-        // 対象ラインのスタートの重みも一旦リセット あとで (*) で戻す
-        weights[starts[target]] = 1;
 
         // (2) 重みを更新
         ap_uint<8> current_round_weight = new_weight(round);
@@ -303,10 +302,18 @@ bool pynqrouter(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *stat
                 }
             }
         }
+        WEIGHT_TERMINAL:
+        for (ap_uint<8> i = 0; i < (ap_uint<8>)(line_num); i++) {
+#pragma HLS LOOP_TRIPCOUNT min=2 max=127 avg=50
+            weights[starts[i]] = MAX_WEIGHT;
+            weights[goals[i]] = MAX_WEIGHT;
+        }
+        // 対象ラインのスタートの重みも一旦リセット あとで (*) で戻す
+        weights[starts[target]] = 1;
 
         // 経路探索
 #ifdef DEBUG_PRINT
-        cout << "LINE #" << (int)(target + 1) << endl;
+        cout << "(round: " << round << ")" << "LINE #" << (int)(target + 1) << endl;
 #endif
         search(&(paths_size[target]), paths[target], starts[target], goals[target], weights);
 
@@ -611,18 +618,18 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
     ap_uint<16> t = prev[goal];
 
 #ifdef DEBUG_PRINT
-    int dbg_start_xy = start >> BITWIDTH_Z;
-    int dbg_start_x = dbg_start_xy / MAX_WIDTH;
-    int dbg_start_y = dbg_start_xy % MAX_WIDTH;
-    int dbg_start_z = start & BITMASK_Z;
-
-    int dbg_goal_xy = goal >> BITWIDTH_Z;
-    int dbg_goal_x = dbg_goal_xy / MAX_WIDTH;
-    int dbg_goal_y = dbg_goal_xy % MAX_WIDTH;
-    int dbg_goal_z = goal & BITMASK_Z;
-
-    cout << "(" << dbg_start_x << ", " << dbg_start_y << ", " << dbg_start_z << ") #" << start << " -> "
-         << "(" << dbg_goal_x  << ", " << dbg_goal_y  << ", " << dbg_goal_z  << ") #" << goal << endl;
+    //int dbg_start_xy = start >> BITWIDTH_Z;
+    //int dbg_start_x = dbg_start_xy / MAX_WIDTH;
+    //int dbg_start_y = dbg_start_xy % MAX_WIDTH;
+    //int dbg_start_z = start & BITMASK_Z;
+
+    //int dbg_goal_xy = goal >> BITWIDTH_Z;
+    //int dbg_goal_x = dbg_goal_xy / MAX_WIDTH;
+    //int dbg_goal_y = dbg_goal_xy % MAX_WIDTH;
+    //int dbg_goal_z = goal & BITMASK_Z;
+
+    //cout << "(" << dbg_start_x << ", " << dbg_start_y << ", " << dbg_start_z << ") #" << start << " -> "
+    //     << "(" << dbg_goal_x  << ", " << dbg_goal_y  << ", " << dbg_goal_z  << ") #" << goal << endl;
 #endif
 
     // バックトラック
@@ -633,11 +640,11 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
 #pragma HLS PIPELINE II=2
 
 #ifdef DEBUG_PRINT
-        int t_xy = prev[t] >> BITWIDTH_Z;
-        int t_x = t_xy / MAX_WIDTH;
-        int t_y = t_xy % MAX_WIDTH;
-        int t_z = prev[t] & BITMASK_Z;
-        cout << "  via " << "(" << t_x << ", " << t_y << ", " << t_z << ") #" << prev[t] << " dist=" << dist[t] << endl;
+        //int t_xy = prev[t] >> BITWIDTH_Z;
+        //int t_x = t_xy / MAX_WIDTH;
+        //int t_y = t_xy % MAX_WIDTH;
+        //int t_z = prev[t] & BITMASK_Z;
+        //cout << "  via " << "(" << t_x << ", " << t_y << ", " << t_z << ") #" << prev[t] << " dist=" << dist[t] << endl;
 #endif
 
         path[p] = t; // 記録
@@ -648,8 +655,8 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
     *path_size = p;
 
 #ifdef DEBUG_PRINT
-    cout << "max_path_len = " << p << endl;
-    cout << "max_pq_len = " << max_pq_len << endl;
+    //cout << "max_path_len = " << p << endl;
+    //cout << "max_pq_len = " << max_pq_len << endl;
 #endif
 
 }
@@ -675,6 +682,7 @@ void pq_push(ap_uint<16> priority, ap_uint<16> data, ap_uint<12> *pq_len, ap_uin
 #pragma HLS INLINE
 
     (*pq_len)++;
+    if ((*pq_len) == 0) { (*pq_len)--; } // Queue is full -> Last element is automatically removed
     ap_uint<12> i = (*pq_len);      // target
     ap_uint<12> p = (*pq_len) >> 1; // i.e., (*pq_len) / 2; // 親
     PQ_PUSH_LOOP:
@@ -707,7 +715,7 @@ void pq_pop(ap_uint<16> *ret_priority, ap_uint<16> *ret_data, ap_uint<12> *pq_le
     ap_uint<16> last_priority = (ap_uint<16>)(pq_nodes[*pq_len] & PQ_PRIORITY_MASK); // 末尾ノードの優先度
 
     PQ_POP_LOOP:
-    while (1) {
+    while (!(i >> 11)) { // (2018.08.25) Loop condition fixed
 #pragma HLS LOOP_TRIPCOUNT min=1 max=8 avg=4
 //#pragma HLS PIPELINE
 //#pragma HLS UNROLL factor=2

hls/lines256_length128/Makefile.cygwin

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -Wl,--stack,16777216 -o $@ $(OBJS)
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls/lines256_length128/main.cpp

@@ -17,6 +17,7 @@
 
 #include "router.hpp"
 
+#define PRINT_SOLUTION
 
 int main(int argc, char *argv[]) {
     using namespace std;
@@ -50,9 +51,11 @@ int main(int argc, char *argv[]) {
         seed = atoi(argv[2]);
     }
 
+#ifdef PRINT_SOLUTION
     int size_x = (boardstr[1] - '0') * 10 + (boardstr[2] - '0');
     int size_y = (boardstr[4] - '0') * 10 + (boardstr[5] - '0');
     int size_z = (boardstr[7] - '0');
+#endif
 
     // ソルバ実行
     ap_int<32> status;
@@ -68,6 +71,7 @@ int main(int argc, char *argv[]) {
     cout << "status = " << (int)status << endl;
     cout << "elapsed = " << ((double)(clock_done - clock_start) / CLOCKS_PER_SEC) << endl << endl;
 
+#ifdef PRINT_SOLUTION
     // 解表示
     cout << "SOLUTION" << endl;
     cout << "========" << endl;
@@ -80,12 +84,13 @@ int main(int argc, char *argv[]) {
                     cout << ",";
                 }
                 int i = ((x * MAX_WIDTH + y) << BITWIDTH_Z) | z;
-                //cout << setfill('0') << setw(2) << right << (unsigned int)(unsigned char)(boardstr[i]);
-                cout << (unsigned int)(unsigned char)(boardstr[i]);
+                cout << setfill('0') << setw(3) << right << (unsigned int)(unsigned char)(boardstr[i]);
+                //cout << (unsigned int)(unsigned char)(boardstr[i]);
             }
             cout << endl;
         }
     }
+#endif
 
     return 0;
 }

hls/lines256_length128/router.cpp

@@ -210,7 +210,6 @@ bool pynqrouter_256x128(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<3
     FIRST_ROUTING:
     for (ap_uint<9> i = 0; i < (ap_uint<9>)(line_num); i++) {
 #pragma HLS LOOP_TRIPCOUNT min=2 max=255 avg=50
-//#pragma HLS LOOP_TRIPCOUNT min=2 max=127 avg=50
 //#pragma HLS PIPELINE
 //#pragma HLS UNROLL factor=2
 
@@ -245,6 +244,7 @@ bool pynqrouter_256x128(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<3
     ap_uint<8> last_target = 255;
 
     // [Step 2] Rip-up 再ルーティング
+	cout << "Rip-up Routing" << endl;
     ROUTING:
     for (ap_uint<16> round = 1; round <= 32768 /* = (2048 * 16) */; round++) {
 #pragma HLS LOOP_TRIPCOUNT min=1 max=4000 avg=50
@@ -285,8 +285,6 @@ bool pynqrouter_256x128(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<3
 #pragma HLS LOOP_TRIPCOUNT min=1 max=255 avg=50
             weights[paths[target][j]] = 1;
         }
-        // 対象ラインのスタートの重みも一旦リセット あとで (*) で戻す
-        weights[starts[target]] = 1;
 
         // (2) 重みを更新
         ap_uint<8> current_round_weight = new_weight(round);
@@ -304,10 +302,18 @@ bool pynqrouter_256x128(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<3
                 }
             }
         }
+		WEIGHT_TERMINAL:
+        for (ap_uint<9> i = 0; i < (ap_uint<9>)(line_num); i++) {
+#pragma HLS LOOP_TRIPCOUNT min=2 max=255 avg=50
+            weights[starts[i]] = MAX_WEIGHT;
+            weights[goals[i]] = MAX_WEIGHT;
+        }
+		// 対象ラインのスタートの重みも一旦リセット あとで (*) で戻す
+        weights[starts[target]] = 1;
 
         // 経路探索
 #ifdef DEBUG_PRINT
-        cout << "LINE #" << (int)(target + 1) << endl;
+        cout << "(round: " << round << ")" << "LINE #" << (int)(target + 1) << endl;
 #endif
         search(&(paths_size[target]), paths[target], starts[target], goals[target], weights);
 
@@ -612,18 +618,18 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
     ap_uint<16> t = prev[goal];
 
 #ifdef DEBUG_PRINT
-    int dbg_start_xy = start >> BITWIDTH_Z;
-    int dbg_start_x = dbg_start_xy / MAX_WIDTH;
-    int dbg_start_y = dbg_start_xy % MAX_WIDTH;
-    int dbg_start_z = start & BITMASK_Z;
-
-    int dbg_goal_xy = goal >> BITWIDTH_Z;
-    int dbg_goal_x = dbg_goal_xy / MAX_WIDTH;
-    int dbg_goal_y = dbg_goal_xy % MAX_WIDTH;
-    int dbg_goal_z = goal & BITMASK_Z;
-
-    cout << "(" << dbg_start_x << ", " << dbg_start_y << ", " << dbg_start_z << ") #" << start << " -> "
-         << "(" << dbg_goal_x  << ", " << dbg_goal_y  << ", " << dbg_goal_z  << ") #" << goal << endl;
+    //int dbg_start_xy = start >> BITWIDTH_Z;
+    //int dbg_start_x = dbg_start_xy / MAX_WIDTH;
+    //int dbg_start_y = dbg_start_xy % MAX_WIDTH;
+    //int dbg_start_z = start & BITMASK_Z;
+
+    //int dbg_goal_xy = goal >> BITWIDTH_Z;
+    //int dbg_goal_x = dbg_goal_xy / MAX_WIDTH;
+    //int dbg_goal_y = dbg_goal_xy % MAX_WIDTH;
+    //int dbg_goal_z = goal & BITMASK_Z;
+
+    //cout << "(" << dbg_start_x << ", " << dbg_start_y << ", " << dbg_start_z << ") #" << start << " -> "
+    //     << "(" << dbg_goal_x  << ", " << dbg_goal_y  << ", " << dbg_goal_z  << ") #" << goal << endl;
 #endif
 
     // バックトラック
@@ -634,11 +640,11 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
 #pragma HLS PIPELINE II=2
 
 #ifdef DEBUG_PRINT
-        int t_xy = prev[t] >> BITWIDTH_Z;
-        int t_x = t_xy / MAX_WIDTH;
-        int t_y = t_xy % MAX_WIDTH;
-        int t_z = prev[t] & BITMASK_Z;
-        cout << "  via " << "(" << t_x << ", " << t_y << ", " << t_z << ") #" << prev[t] << " dist=" << dist[t] << endl;
+        //int t_xy = prev[t] >> BITWIDTH_Z;
+        //int t_x = t_xy / MAX_WIDTH;
+        //int t_y = t_xy % MAX_WIDTH;
+        //int t_z = prev[t] & BITMASK_Z;
+        //cout << "  via " << "(" << t_x << ", " << t_y << ", " << t_z << ") #" << prev[t] << " dist=" << dist[t] << endl;
 #endif
 
         path[p] = t; // 記録
@@ -649,8 +655,8 @@ void search(ap_uint<8> *path_size, ap_uint<16> path[MAX_PATH], ap_uint<16> start
     *path_size = p;
 
 #ifdef DEBUG_PRINT
-    cout << "max_path_len = " << p << endl;
-    cout << "max_pq_len = " << max_pq_len << endl;
+    //cout << "max_path_len = " << p << endl;
+    //cout << "max_pq_len = " << max_pq_len << endl;
 #endif
 
 }
@@ -676,6 +682,7 @@ void pq_push(ap_uint<16> priority, ap_uint<16> data, ap_uint<13> *pq_len, ap_uin
 #pragma HLS INLINE
 
     (*pq_len)++;
+	if ((*pq_len) == 0) { (*pq_len)--; } // Queue is full -> Last element is automatically removed
     ap_uint<13> i = (*pq_len);      // target
     ap_uint<13> p = (*pq_len) >> 1; // i.e., (*pq_len) / 2; // 親
     PQ_PUSH_LOOP:
@@ -708,7 +715,7 @@ void pq_pop(ap_uint<16> *ret_priority, ap_uint<16> *ret_data, ap_uint<13> *pq_le
     ap_uint<16> last_priority = (ap_uint<16>)(pq_nodes[*pq_len] & PQ_PRIORITY_MASK); // 末尾ノードの優先度
 
     PQ_POP_LOOP:
-    while (1) {
+    while (!(i >> 11)) { // (2018.08.25) Loop condition fixed
 #pragma HLS LOOP_TRIPCOUNT min=1 max=8 avg=4
 //#pragma HLS PIPELINE
 //#pragma HLS UNROLL factor=2

hls_2018/README.md

+# pynq-router (sw)
+
+PYNQ-router for Vivado-HLS (2018 ver.)
+
+## Types of router
+
+|Name|Operation name|Description|
+|:---|:---|:---|
+|01|TBD|*Line-number-free* router for "PYNQ-Z1". Priority queue is implemented with circular array(non-parallel)|
+|02|TBD|*Line-number-free* router for "PYNQ-Z1". Priority queue is implemented with circular array(parallel)|
+|03|TBD|*Line-number-free* router for "PYNQ-Z1". Priority queue is implemented with heap(size:$`2^{15}`$)|
+|04|TBD|*Line-number-free* router for "AVNET-Ultra96". Priority queue is implemented with heap(size:$`2^{16}`$)|
+|05|TBD|*Low-memory-usage* router. No BRAMs are used for storing route information of each line.|
+
+## Memo
+
+* Vivado HLS 2018.2
+* Vivado 2018.2
+
+Options:
+* Part: xc7z020clg400-1 (PYNQ-Z1), xczu3eg-sbva484-1-e (AVNET-Ultra96)
+* Clock Period: 10.0 ns
+* Clock Uncertainty: 3.0 ns (--> 3.25 ns)
+* Synthesis strategy: ~~Vivado Synthesis Defaults~~ Flow_PerfOptimized_high
+* Implementation strategy: ~~Vivado Implementation Defaults~~ Performance_ExplorePostRoutePhysOpt
+
+## I/O 
+* Input/Output: boardstr(8bit\*41472), seed(32bit), &status(32bit), return(1bit)
+
+## Results
+|Q|heap(seed:0)|c-array(seed:0)|OR|
+|:---|:---|:---|:---|
+|01|1|1|1|
+|02|1|1|1|
+|03|1|1|1|
+|04|1|1|1|
+|05|1|1|1|
+|06|1|1|1|
+|07|1|1|1|
+|08|0|1|1|
+|09|1|1|1|
+|10|1|1|1|
+|11|1|1|1|
+|12|1|1|1|
+|13|1|1|1|
+|14|0|1|1|
+|15|1|1|1|
+|16|1|1|1|
+|17|0|0|0|
+|18|1|1|1|
+|19|0|0|0|
+|20|1|1|1|
+|21|0|0|0|
+|22|1|1|1|
+|23|1|0|1|
+|24|0|0|0|
+|25|0|0|0|
+|26|1|1|1|
+|27|1|0|1|
+|28|1|1|1|
+|29|0|0|0|
+|30|0|0|0|
+|31|0|0|0|
+|32|1|1|1|
+|33|0|0|0|
+|34|0|0|0|
+|Total|22|22|24|
+

hls_2018/auto/auto_compile.c

+#include <stdio.h>
+#include <stdlib.h>
+
+#define STRLEN 65536
+
+int main(void){
+
+   char q[STRLEN], command[STRLEN];
+   char dir[64] = "../router_01";
+
+   FILE *fp;
+   fp = fopen("q.txt", "r");
+   if(fp == NULL){
+      printf("File does not exist.\n");
+      exit(1);
+   }
+
+   int counter = 1;
+   while(1){
+      if(fscanf(fp, "%s", q) == EOF) break;
+      printf("Q. %d\n", counter++);
+      sprintf(command, "./%s/sim.exe %s", dir, q);
+      //printf("(command) %s\n", command);
+      int ret = system(command);
+      printf("ret: %d\n", ret);
+   }
+   fclose(fp);
+   return 0;
+}
+

hls_2018/router_01/Makefile

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -o $@ $(OBJS)
+
+run:
+	python3 ../NLGenerator.py -x 20 -y 20 -z 6 -l 100;\
+	python3 ./gen_boardstr.py Q-20x20x5_100_10.txt |\
+	./$(TARGET) -
+
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_01/Makefile.cygwin

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -Wl,--stack,33554432 -o $@ $(OBJS)
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_01/main.cpp

+/**
+ * main.cpp
+ *
+ * for Vivado HLS
+ */
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+#ifdef CALCTIME
+#include <stdio.h>
+#include <time.h>
+#endif
+
+#include "router.hpp"
+
+#define PRINT_SOLUTION
+
+
+int main(int argc, char *argv[]) {
+    using namespace std;
+
+    // Test data // 
+    // NL_Q00.txt
+    //char boardstr[BOARDSTR_SIZE] = "X10Y05Z3L0000107041L0004107002L0102102021L0900100003";
+    // NL_Q06.txt
+    char boardstr[BOARDSTR_SIZE] = "X10Y18Z2L0900109002L0901105012L0902103052L0903103062L0904100102L0905106012L0906109022L0717109102L0808109112L0017209172L0401200072L0912208152L0009201092L0709209092L0901206052L0309204092L0701209072L0101201022L0011202152L0016202162";
+    // NL_Q08.txt
+    //char boardstr[BOARDSTR_SIZE] = "X17Y20Z2L0000103022L1603115052L0916107032L0302108012L1104111042L1002100002L0919116162L1616113182L1001115012L0500201182L1603213152L0600210022";
+
+    // Read boardstr from command line
+    if (1 < argc) {
+        // From stdin
+        if(argv[1][0]!='X')
+        {
+            char* c_p=fgets(boardstr, BOARDSTR_SIZE, stdin);
+            int length=strlen(c_p);
+            boardstr[length-1]=0;
+        }
+        else
+        {
+            strcpy(boardstr, argv[1]);
+        }
+    }
+
+    // Seed value
+    int seed = 12345;
+    if (2 < argc) {
+        seed = atoi(argv[2]);
+    }
+
+#ifdef PRINT_SOLUTION
+    int size_x = (boardstr[1] - '0') * 10 + (boardstr[2] - '0');
+    int size_y = (boardstr[4] - '0') * 10 + (boardstr[5] - '0');
+    int size_z = (boardstr[7] - '0');
+#endif
+
+    // Solver
+    ap_int<32> status;
+    clock_t clock_start, clock_done;
+    clock_start = clock();
+    bool result = pynqrouter(boardstr, seed, &status);
+    clock_done = clock();
+    if (result) {
+        cout << endl << "Test Passed!" << endl;
+    } else {
+        cout << endl << "Test Failed!" << endl;
+    }
+    cout << "status = " << (int)status << endl;
+    cout << "elapsed = " << ((double)(clock_done - clock_start) / CLOCKS_PER_SEC) << endl << endl;
+
+#ifdef PRINT_SOLUTION
+    cout << "SOLUTION" << endl;
+    cout << "========" << endl;
+    cout << "SIZE " << size_x << "X" << size_y << "X" << size_z << endl;
+    for (int z = 0; z < size_z; z++) {
+        cout << "LAYER " << (z + 1) << endl;
+        for (int y = 0; y < size_y; y++) {
+            for (int x = 0; x < size_x; x++) {
+                if (x != 0) {
+                    cout << ",";
+                }
+                int i = ((x * MAX_WIDTH + y) << BITWIDTH_Z) | z;
+                cout << setfill('0') << setw(3) << right << (unsigned int)(unsigned char)(boardstr[i]);
+                //cout << (unsigned int)(unsigned char)(boardstr[i]);
+            }
+            cout << endl;
+        }
+    }
+#endif
+
+    return 0;
+}
+

hls_2018/router_01/router.hpp

+/**
+ * router.hpp
+ *
+ * for Vivado HLS
+ */
+
+#ifndef __ROUTER_HPP__
+#define __ROUTER_HPP__
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+//#define DEBUG_PRINT // for debug
+
+#ifdef DEBUG_PRINT
+using namespace std;
+#endif
+
+// Parameters
+#define MAX_WIDTH   72      // Max of X, Y
+#define BITWIDTH_XY 13
+#define BITMASK_XY  65528   // 1111 1111 1111 1000
+#define MAX_LAYER   8       // Max of Z
+#define BITWIDTH_Z  3
+#define BITMASK_Z   7       // 0000 0000 0000 0111
+
+#define MAX_CELLS	41472    // Max #cells (16bit)
+#define MAX_LINES	1024     // Max #lines (10bit)
+#define MAX_PQ		8192     // Queue size (13bit)
+#define MAX_BUFFER	16384    // Line buffer size (14bit)
+#define CELL_BIT	16
+#define LINE_BIT	10
+#define PQ_BIT		13
+#define BUFF_BIT	14
+
+#define PQ_PRIORITY_WIDTH 16
+#define PQ_PRIORITY_MASK  65535       // 0000 0000 0000 0000 1111 1111 1111 1111
+#define PQ_DATA_WIDTH     16
+#define PQ_DATA_MASK      4294901760  // 1111 1111 1111 1111 0000 0000 0000 0000
+
+#define MAX_WEIGHT	255      // Max weight
+#define BOARDSTR_SIZE 41472  // Size of I/O
+
+ap_uint<8> new_weight(ap_uint<16> x);
+bool pynqrouter(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *status);
+
+ap_uint<7> abs_uint7(ap_uint<7> a, ap_uint<7> b);
+ap_uint<3> abs_uint3(ap_uint<3> a, ap_uint<3> b);
+ap_uint<BUFF_BIT> search(ap_uint<BUFF_BIT> idx, ap_uint<CELL_BIT> paths[MAX_BUFFER], ap_uint<CELL_BIT> start, ap_uint<CELL_BIT> goal, ap_uint<8> w[MAX_WEIGHT]);
+void pq_push(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> priority, ap_uint<16> data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+void pq_pop(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> *ret_priority, ap_uint<16> *ret_data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+
+#endif /* __ROUTER_HPP__ */

hls_2018/router_02/Makefile

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -o $@ $(OBJS)
+
+run:
+	python3 ../NLGenerator.py -x 20 -y 20 -z 6 -l 100;\
+	python3 ./gen_boardstr.py Q-20x20x5_100_10.txt |\
+	./$(TARGET) -
+
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_02/Makefile.cygwin

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -Wl,--stack,33554432 -o $@ $(OBJS)
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_02/README.md

+# 並列度の変更 (変更箇所)
+優先度キューに要素を挿入する際，要素の移動を並列して実行できる
+
+コードにいくつかの変更を加えることで並列度を変更可能
+
+## router.hpp
+以下の2箇所を変更する
+* #define PP **32** <-- 並列度
+* #define LOG_PP **5** <-- 並列度のlog2
+
+## router.cpp
+以下の5箇所を変更する
+* (in search func.) #pragma HLS ARRAY_PARTITION variable=pq_nodes cyclic factor=**32** dim=1 <-- 並列度
+* (in pq_push func.) #pragma HLS LOOP_TRIPCOUNT min=0 max=**31** <-- 並列度-1 (計3箇所)
+* (in pq_push func.) #pragma HLS LOOP_TRIPCOUNT min=0 max=**255** <-- キューの最大要素数/並列度-1
+

hls_2018/router_02/main.cpp

+/**
+ * main.cpp
+ *
+ * for Vivado HLS
+ */
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+#ifdef CALCTIME
+#include <stdio.h>
+#include <time.h>
+#endif
+
+#include "router.hpp"
+
+#define PRINT_SOLUTION
+
+
+int main(int argc, char *argv[]) {
+    using namespace std;
+
+    // Test data // 
+    // NL_Q00.txt
+    //char boardstr[BOARDSTR_SIZE] = "X10Y05Z3L0000107041L0004107002L0102102021L0900100003";
+    // NL_Q06.txt
+    char boardstr[BOARDSTR_SIZE] = "X10Y18Z2L0900109002L0901105012L0902103052L0903103062L0904100102L0905106012L0906109022L0717109102L0808109112L0017209172L0401200072L0912208152L0009201092L0709209092L0901206052L0309204092L0701209072L0101201022L0011202152L0016202162";
+    // NL_Q08.txt
+    //char boardstr[BOARDSTR_SIZE] = "X17Y20Z2L0000103022L1603115052L0916107032L0302108012L1104111042L1002100002L0919116162L1616113182L1001115012L0500201182L1603213152L0600210022";
+
+    // Read boardstr from command line
+    if (1 < argc) {
+        // From stdin
+        if(argv[1][0]!='X')
+        {
+            char* c_p=fgets(boardstr, BOARDSTR_SIZE, stdin);
+            int length=strlen(c_p);
+            boardstr[length-1]=0;
+        }
+        else
+        {
+            strcpy(boardstr, argv[1]);
+        }
+    }
+
+    // Seed value
+    int seed = 12345;
+    if (2 < argc) {
+        seed = atoi(argv[2]);
+    }
+
+#ifdef PRINT_SOLUTION
+    int size_x = (boardstr[1] - '0') * 10 + (boardstr[2] - '0');
+    int size_y = (boardstr[4] - '0') * 10 + (boardstr[5] - '0');
+    int size_z = (boardstr[7] - '0');
+#endif
+
+    // Solver
+    ap_int<32> status;
+    clock_t clock_start, clock_done;
+    clock_start = clock();
+    bool result = pynqrouter(boardstr, seed, &status);
+    clock_done = clock();
+    if (result) {
+        cout << endl << "Test Passed!" << endl;
+    } else {
+        cout << endl << "Test Failed!" << endl;
+    }
+    cout << "status = " << (int)status << endl;
+    cout << "elapsed = " << ((double)(clock_done - clock_start) / CLOCKS_PER_SEC) << endl << endl;
+
+#ifdef PRINT_SOLUTION
+    cout << "SOLUTION" << endl;
+    cout << "========" << endl;
+    cout << "SIZE " << size_x << "X" << size_y << "X" << size_z << endl;
+    for (int z = 0; z < size_z; z++) {
+        cout << "LAYER " << (z + 1) << endl;
+        for (int y = 0; y < size_y; y++) {
+            for (int x = 0; x < size_x; x++) {
+                if (x != 0) {
+                    cout << ",";
+                }
+                int i = ((x * MAX_WIDTH + y) << BITWIDTH_Z) | z;
+                cout << setfill('0') << setw(3) << right << (unsigned int)(unsigned char)(boardstr[i]);
+                //cout << (unsigned int)(unsigned char)(boardstr[i]);
+            }
+            cout << endl;
+        }
+    }
+#endif
+
+    return 0;
+}
+

hls_2018/router_02/router.hpp

+/**
+ * router.hpp
+ *
+ * for Vivado HLS
+ */
+
+#ifndef __ROUTER_HPP__
+#define __ROUTER_HPP__
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+//#define DEBUG_PRINT // for debug
+
+#ifdef DEBUG_PRINT
+using namespace std;
+#endif
+
+// Parameters
+#define MAX_WIDTH   72      // Max of X, Y
+#define BITWIDTH_XY 13
+#define BITMASK_XY  65528   // 1111 1111 1111 1000
+#define MAX_LAYER   8       // Max of Z
+#define BITWIDTH_Z  3
+#define BITMASK_Z   7       // 0000 0000 0000 0111
+
+#define MAX_CELLS	41472    // Max #cells (16bit)
+#define MAX_LINES	1024     // Max #lines (10bit)
+#define MAX_PQ		8192     // Queue size (13bit)
+#define MAX_BUFFER	16384    // Line buffer size (14bit)
+#define CELL_BIT	16
+#define LINE_BIT	10
+#define PQ_BIT		13
+#define BUFF_BIT	14
+
+#define PQ_PRIORITY_WIDTH 16
+#define PQ_PRIORITY_MASK  65535       // 0000 0000 0000 0000 1111 1111 1111 1111
+#define PQ_DATA_WIDTH     16
+#define PQ_DATA_MASK      4294901760  // 1111 1111 1111 1111 0000 0000 0000 0000
+
+#define MAX_WEIGHT	255      // Max weight
+#define BOARDSTR_SIZE 41472  // Size of I/O
+
+#define PP 32		// Parameter for Parallel shifting in queue push
+#define LOG_PP 5	// LOG_PP is log2(PP)
+
+ap_uint<8> new_weight(ap_uint<16> x);
+bool pynqrouter(char boardstr[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *status);
+
+ap_uint<7> abs_uint7(ap_uint<7> a, ap_uint<7> b);
+ap_uint<3> abs_uint3(ap_uint<3> a, ap_uint<3> b);
+ap_uint<BUFF_BIT> search(ap_uint<BUFF_BIT> idx, ap_uint<CELL_BIT> paths[MAX_BUFFER], ap_uint<CELL_BIT> start, ap_uint<CELL_BIT> goal, ap_uint<8> w[MAX_WEIGHT]);
+void pq_push(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> priority, ap_uint<16> data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+void pq_pop(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> *ret_priority, ap_uint<16> *ret_data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+
+#endif /* __ROUTER_HPP__ */

hls_2018/router_02_boardstr/Makefile

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -o $@ $(OBJS)
+
+run:
+	python3 ../NLGenerator.py -x 20 -y 20 -z 6 -l 100;\
+	python3 ./gen_boardstr.py Q-20x20x5_100_10.txt |\
+	./$(TARGET) -
+
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_02_boardstr/Makefile.cygwin

+TARGET = sim
+OBJS = $(CPPS:.cpp=.o)
+CPPS = $(wildcard *.cpp)
+CXX = g++
+CXXFLAGS = -O3 -Wall -Wno-unknown-pragmas -Wno-unused-label -DSOFTWARE -DCALCTIME
+
+all: $(TARGET)
+
+$(TARGET): $(OBJS)
+	$(CXX) -O3 -Wl,--stack,33554432 -o $@ $(OBJS)
+
+clean:
+	rm *.o
+	rm $(TARGET)

hls_2018/router_02_boardstr/README.md

+# 並列度の変更 (変更箇所)
+優先度キューに要素を挿入する際，要素の移動を並列して実行できる
+
+コードにいくつかの変更を加えることで並列度を変更可能
+
+## router.hpp
+以下の2箇所を変更する
+* #define PP **32** <-- 並列度
+* #define LOG_PP **5** <-- 並列度のlog2
+
+## router.cpp
+以下の5箇所を変更する
+* (in search func.) #pragma HLS ARRAY_PARTITION variable=pq_nodes cyclic factor=**32** dim=1 <-- 並列度
+* (in pq_push func.) #pragma HLS LOOP_TRIPCOUNT min=0 max=**31** <-- 並列度-1 (計3箇所)
+* (in pq_push func.) #pragma HLS LOOP_TRIPCOUNT min=0 max=**255** <-- キューの最大要素数/並列度-1
+

hls_2018/router_02_boardstr/main.cpp

+/**
+ * main.cpp
+ *
+ * for Vivado HLS
+ */
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+#ifdef CALCTIME
+#include <stdio.h>
+#include <time.h>
+#endif
+
+#include "router.hpp"
+
+#define PRINT_SOLUTION
+
+
+int main(int argc, char *argv[]) {
+    using namespace std;
+
+    // Test data // 
+    // NL_Q00.txt
+    //char boardstr[BOARDSTR_SIZE] = "X10Y05Z3L0000107041L0004107002L0102102021L0900100003";
+    // NL_Q06.txt
+    char boardstr[BOARDSTR_SIZE] = "X10Y18Z2L0900109002L0901105012L0902103052L0903103062L0904100102L0905106012L0906109022L0717109102L0808109112L0017209172L0401200072L0912208152L0009201092L0709209092L0901206052L0309204092L0701209072L0101201022L0011202152L0016202162";
+    // NL_Q08.txt
+    //char boardstr[BOARDSTR_SIZE] = "X17Y20Z2L0000103022L1603115052L0916107032L0302108012L1104111042L1002100002L0919116162L1616113182L1001115012L0500201182L1603213152L0600210022";
+    char boardstr_high[BOARDSTR_SIZE] = {};
+
+    // Read boardstr from command line
+    if (1 < argc) {
+        // From stdin
+        if(argv[1][0]!='X')
+        {
+            char* c_p=fgets(boardstr, BOARDSTR_SIZE, stdin);
+            int length=strlen(c_p);
+            boardstr[length-1]=0;
+        }
+        else
+        {
+            strcpy(boardstr, argv[1]);
+        }
+    }
+
+    // Seed value
+    int seed = 12345;
+    if (2 < argc) {
+        seed = atoi(argv[2]);
+    }
+
+#ifdef PRINT_SOLUTION
+    int size_x = (boardstr[1] - '0') * 10 + (boardstr[2] - '0');
+    int size_y = (boardstr[4] - '0') * 10 + (boardstr[5] - '0');
+    int size_z = (boardstr[7] - '0');
+#endif
+
+    // Solver
+    ap_int<32> status;
+    clock_t clock_start, clock_done;
+    clock_start = clock();
+    bool result = pynqrouter(boardstr, boardstr_high, seed, &status);
+    clock_done = clock();
+    if (result) {
+        cout << endl << "Test Passed!" << endl;
+    } else {
+        cout << endl << "Test Failed!" << endl;
+    }
+    cout << "status = " << (int)status << endl;
+    cout << "elapsed = " << ((double)(clock_done - clock_start) / CLOCKS_PER_SEC) << endl << endl;
+
+#ifdef PRINT_SOLUTION
+    cout << "SOLUTION" << endl;
+    cout << "========" << endl;
+    cout << "SIZE " << size_x << "X" << size_y << "X" << size_z << endl;
+    for (int z = 0; z < size_z; z++) {
+        cout << "LAYER " << (z + 1) << endl;
+        for (int y = 0; y < size_y; y++) {
+            for (int x = 0; x < size_x; x++) {
+                if (x != 0) {
+                    cout << ",";
+                }
+                int i = ((x * MAX_WIDTH + y) << BITWIDTH_Z) | z;
+                unsigned int num = (unsigned char)(boardstr[i]) + ((unsigned char)(boardstr_high[i]) << 8);
+                cout << setfill('0') << setw(3) << right << num;
+                //cout << num;
+            }
+            cout << endl;
+        }
+    }
+#endif
+
+    return 0;
+}
+

hls_2018/router_02_boardstr/router.hpp

+/**
+ * router.hpp
+ *
+ * for Vivado HLS
+ */
+
+#ifndef __ROUTER_HPP__
+#define __ROUTER_HPP__
+
+#ifdef SOFTWARE
+#include "ap_int.h"
+#else
+#include <ap_int.h>
+#endif
+
+//#define DEBUG_PRINT // for debug
+
+#ifdef DEBUG_PRINT
+using namespace std;
+#endif
+
+// Parameters
+#define MAX_WIDTH   72      // Max of X, Y
+#define BITWIDTH_XY 13
+#define BITMASK_XY  65528   // 1111 1111 1111 1000
+#define MAX_LAYER   8       // Max of Z
+#define BITWIDTH_Z  3
+#define BITMASK_Z   7       // 0000 0000 0000 0111
+
+#define MAX_CELLS	41472    // Max #cells (16bit)
+#define MAX_LINES	1024     // Max #lines (10bit)
+#define MAX_PQ		8192     // Queue size (13bit)
+#define MAX_BUFFER	16384    // Line buffer size (14bit)
+#define CELL_BIT	16
+#define LINE_BIT	10
+#define PQ_BIT		13
+#define BUFF_BIT	14
+
+#define PQ_PRIORITY_WIDTH 16
+#define PQ_PRIORITY_MASK  65535       // 0000 0000 0000 0000 1111 1111 1111 1111
+#define PQ_DATA_WIDTH     16
+#define PQ_DATA_MASK      4294901760  // 1111 1111 1111 1111 0000 0000 0000 0000
+
+#define MAX_WEIGHT	255      // Max weight
+#define BOARDSTR_SIZE 41472      // Size of I/O
+
+#define PP 32		// Parameter for Parallel shifting in queue push
+#define LOG_PP 5	// LOG_PP is log2(PP)
+
+ap_uint<8> new_weight(ap_uint<16> x);
+bool pynqrouter(char boardstr[BOARDSTR_SIZE], char boardstr_high[BOARDSTR_SIZE], ap_uint<32> seed, ap_int<32> *status);
+
+ap_uint<7> abs_uint7(ap_uint<7> a, ap_uint<7> b);
+ap_uint<3> abs_uint3(ap_uint<3> a, ap_uint<3> b);
+ap_uint<BUFF_BIT> search(ap_uint<BUFF_BIT> idx, ap_uint<BUFF_BIT> *n_idx, ap_uint<CELL_BIT> paths[MAX_BUFFER], ap_uint<CELL_BIT> start, ap_uint<CELL_BIT> goal, ap_uint<8> w[MAX_WEIGHT]);
+void pq_push(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> priority, ap_uint<16> data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+void pq_pop(ap_uint<32> pq_nodes[MAX_PQ], ap_uint<16> *ret_priority, ap_uint<16> *ret_data, ap_uint<PQ_BIT> *top, ap_uint<PQ_BIT> *bottom, bool *is_empty);
+
+#endif /* __ROUTER_HPP__ */