Fixed most of the cache issues, mat_add left

runtime/mains/simple/Makefile

@@ -1,5 +1,5 @@
 
-COMP     = /opt/riscv-new/drops/bin/riscv32-unknown-elf-gcc
+COMP     = /opt/riscv-new/drops/bin/riscv32-unknown-elf-g++
 CC_FLAGS = -march=rv32im -mabi=ilp32 -O0 -Wl,-Bstatic,-T,../vortex_link.ld -ffreestanding -nostdlib
 
 DMP  = /opt/riscv-new/drops/bin/riscv32-unknown-elf-objdump

runtime/mains/simple/vx_simple_main.c

@@ -52,7 +52,7 @@ int main()
 	// Main is called with all threads active of warp 0
 	vx_tmc(1);
 
-	vx_print_str("Let's start...\n");
+	vx_print_str("Let's start... (This might take a while)\n");
 	unsigned what[36];
 	for (int i = 0; i < 36; i++)
 	{
@@ -98,31 +98,31 @@ int main()
 
 	}
 
-	vx_print_str("vx_spawnWarps mat_add_kernel\n");
+	// vx_print_str("vx_spawnWarps mat_add_kernel\n");
 
-	mat_add_args_t arguments;
-	arguments.x         = x;
-	arguments.y         = y;
-	arguments.z         = z;
-	arguments.numColums = 4;
-	arguments.numRows   = 4;
+	// mat_add_args_t arguments;
+	// arguments.x         = x;
+	// arguments.y         = y;
+	// arguments.z         = z;
+	// arguments.numColums = 4;
+	// arguments.numRows   = 4;
 
 
-	int numWarps   = 4;
-	int numThreads = 4;
+	// int numWarps   = 4;
+	// int numThreads = 4;
 
-	vx_spawnWarps(numWarps, numThreads, mat_add_kernel, &arguments);
+	// vx_spawnWarps(numWarps, numThreads, mat_add_kernel, &arguments);
 
-	for (int i = 0; i < arguments.numRows; i++)
-	{
-		for (int j = 0; j < arguments.numColums; j++)
-		{
-			unsigned index = (i * arguments.numColums) + j;
-			vx_print_hex(z[index]);
-			vx_print_str(" ");
-		}
-		vx_print_str("\n");
-	}
+	// for (int i = 0; i < arguments.numRows; i++)
+	// {
+	// 	for (int j = 0; j < arguments.numColums; j++)
+	// 	{
+	// 		unsigned index = (i * arguments.numColums) + j;
+	// 		vx_print_hex(z[index]);
+	// 		vx_print_str(" ");
+	// 	}
+	// 	vx_print_str("\n");
+	// }
 
 	return 0;
 }