fixed vreg clearning

rvvector/basic/Makefile

@@ -35,3 +35,8 @@ HEX: ELF
 
 ELF: 
 	$(COMP) $(CC_FLAGS) $(VX_STR) $(VX_VEC) $(VX_FIO) $(NEWLIB) $(VX_INT) $(VX_IO) $(VX_API) $(VX_TEST) $(VX_MAIN).c $(LIBS) -Iinclude  -o $(VX_MAIN).elf
+
+run:
+	../../simX/obj_dir/Vcache_simX -E -a rv32i --core vx_vector_main.hex  -s -b 1> emulator.debug
+
+

rvvector/basic/vx_vec.h

@@ -7,7 +7,7 @@
 extern "C" {
 #endif
 
-void vx_vec_test(int *);
+void vx_vec_test(int n, int* a, int* b, int* c); //vvaddint32 
 
 
 #ifdef __cplusplus

rvvector/basic/vx_vec.s

@@ -1,30 +1,23 @@
 
 
-
 .type vx_vec_test, @function
 .global vx_vec_test
 vx_vec_test:
-	li a1, 7
-	sw a1, 0(a0)
-	ret
-
-
-
-
-# 	slli a0, a0, 2
-# 	add a0, a0, a3
-# 	vmv.v.x vv0, a2
-# 	# vsplat4 vv0, a2
-# stripmine_loop:
-# 	vlb4 vv1, (a1)
-# 	vcmpez4 vp0, vv1
-# 	!vp0 vlw4 vv1, (a3)
-# 	!vp0 vlw4 vv2, (a4)
-# 	!vp0 vfma4 vv1, vv0, vv1, vv2
-# 	!vp0 vsw4 vv1, (a4)
-# 	addi a1, a1, 4
-# 	addi a3, a3, 16
-# 	addi a4, a4, 16
-# 	bleu a3, a0, stripmine_loop
-	# handle edge cases
-	# when (n % 4) != 0 ...
+# vector-vector add routine of 32-bit integers
+# void vvaddint32(size_t n, const int*x, const int*y, int*z)
+# { for (size_t i=0; i<n; i++) { z[i]=x[i]+y[i]; } }
+#
+# a0 = n, a1 = x, a2 = y, a3 = z
+# Non-vector instructions are indented
+    vsetvli t0, a0, e32 # Set vector length based on 32-bit vectors
+    vlw.v v0, (a1)           # Get first vector
+      sub a0, a0, t0         # Decrement number done
+      slli t0, t0, 2         # Multiply number done by 4 bytes
+      add a1, a1, t0         # Bump pointer
+    vlw.v v1, (a2)           # Get second vector
+      add a2, a2, t0         # Bump pointer
+    vadd.vv v2, v0, v1        # Sum vectors
+    vsw.v v2, (a3)           # Store result
+      add a3, a3, t0         # Bump pointer
+      bnez a0, vx_vec_test   # Loop back 
+    ret                    # Finished

rvvector/basic/vx_vector_main.c

@@ -1,32 +1,29 @@
-
 #include "../../runtime/intrinsics/vx_intrinsics.h"
 #include "vx_vec.h"
 
 int main()
 {
-	vx_tmc(1);
-	// int * a = malloc(4);
-	// int * b = malloc(4);
-	// int * c = malloc(4);
+        vx_tmc(1);
+
+        printf("Hello\n");
+
+        int n = 64;
+        int *a = (int*)malloc(sizeof(int) * n); //{1, 1, 1, 1, 1};
+        int *b = (int*)malloc(sizeof(int) * n); //{1, 1, 1, 1, 1};
+        int *c = (int*)malloc(sizeof(int) * n); //{1, 1, 1, 1, 1};
+
+        for(int i = 0; i < n; ++i)
+        {
+           a[i] = b[i] = c[i] = 1;
+        }
+
+        vx_vec_test(n, a, b, c);
+
+        for (int i = 0; i < n; ++i)
+        {
+        	printf("a[%d]=%d, b[%d]=%d, c[%d]=%d\n", i, a[i], i, b[i], i, c[i]);
+        }
 
 
-	int * a = malloc(4);
-	*a = 5;
-	printf("Value of a: %d\n", *a);
-
-	vx_vec_test(a);
-
-	printf("Value of a: %d\n", *a);
-
-
-	// for (int i = 0; i < 4; i++)
-	// {
-	// 	if (c[i] != (a[i] + b[i]))
-	// 	{
-	// 		printf("Fail\n");
-	// 		break;
-	// 	}
-	// }
-
-	vx_tmc(0);
+        vx_tmc(0);
 }

simX/instruction.cpp

@@ -2040,6 +2040,7 @@ void Instruction::executeOn(Warp &c, trace_inst_t * trace_inst) {
 
             Word regNum(0);
 
+            c.vreg.clear();
             for (int j = 0; j < 32; j++)
             {
               c.vreg.push_back(vector<Reg<char*>>());
@@ -2083,9 +2084,11 @@ void Instruction::executeOn(Warp &c, trace_inst_t * trace_inst) {
           }*/
 
           D(3, "Vector Register state after addition:");
-            for(int i=0; i < c.vreg.size(); i++)
-              for(int j=0; j< c.vreg[0].size(); j++)
+            for(int i=0; i < 32; i++)
+            {
+              for(int j=0; j< c.vl; j++)
               {
+                cout << "starting iter" << endl;
                   if (c.vtype.vsew == 8)
                   {
                     uint8_t * ptr_val = (uint8_t *) c.vreg[i][j].val;
@@ -2099,9 +2102,16 @@ void Instruction::executeOn(Warp &c, trace_inst_t * trace_inst) {
                     uint32_t * ptr_val = (uint32_t *) c.vreg[i][j].val;
                     std::cout << "reg[" << i << "][" << j << "] = " << *ptr_val << std::endl;     
                   }
+
+                  cout << "Finished iter" << endl;
               }
-        break;
+            }
+
+            cout << "Finished loop" << endl;
+            break;
         }
+        cout << "hhhhhhhhhhhhhhh" << endl;
+        break;
       }
       break;
       case VS:
@@ -2137,8 +2147,13 @@ void Instruction::executeOn(Warp &c, trace_inst_t * trace_inst) {
         cout << "aERROR: Unsupported instruction: " << *this << "\n" << flush;
         exit(1);
     }
+
+    cout << "outside case" << endl;
+
   }
 
+  std::cout << "finished instruction" << endl;
+
   D(3, "End instruction execute.");
 
   c.activeThreads = nextActiveThreads;