diff --git a/ex3/code/main.cpp b/ex3/code/main.cpp
index 9f91412..f6d50a5 100644
--- a/ex3/code/main.cpp
+++ b/ex3/code/main.cpp
@@ -1,14 +1,17 @@
+// Compile with "make" / "make run" or
+// g++ *.cpp -O3 -ffast-math -lopenblas -llapacke -o main
+
 
 #include "task_3.h"
 #include "task_4+6.h"
 #include "task_5.h"
 #include "task_7.h"
 #include "timing.h"
+#include <cblas.h>               // cBLAS Library
+#include <lapacke.h>
 
 #include <iomanip>
 #include <iostream>
-#include <cblas.h>               // cBLAS Library
-#include <lapacke.h>
 
 void task_1() {
     printf("\n\n-------------- Task 1 --------------\n\n");
@@ -23,12 +26,12 @@ void task_1() {
     // Memory per array = 610.4 MiB (= 0.6 GiB).
     // Total memory required = 1831.1 MiB (= 1.8 GiB).
     // Each kernel will be executed 20 times.
-    //  The *best* time for each kernel (excluding the first iteration)
-    //  will be used to compute the reported bandwidth.
+    //     The *best* time for each kernel (excluding the first iteration)
+    //     will be used to compute the reported bandwidth.
     // -------------------------------------------------------------
     // Your clock granularity/precision appears to be 1 microseconds.
     // Each test below will take on the order of 116886 microseconds.
-    //    (= 116886 clock ticks)
+    //     (= 116886 clock ticks)
     // Increase the size of the arrays if this shows that
     // you are not getting at least 20 clock ticks per test.
     // -------------------------------------------------------------
@@ -46,25 +49,25 @@ void task_1() {
     // -------------------------------------------------------------
     // ./flops.exe
 
-    //    FLOPS C Program (Double Precision), V2.0 18 Dec 1992
+    //     FLOPS C Program (Double Precision), V2.0 18 Dec 1992
 
-    //    Module     Error        RunTime      MFLOPS
+    //     Module     Error        RunTime      MFLOPS
     //                             (usec)
-    //      1      4.0146e-13      0.0024   5827.9076
-    //      2     -1.4166e-13      0.0007  10037.8942
-    //      3      4.7184e-14      0.0039   4371.9185
-    //      4     -1.2557e-13      0.0034   4355.5711
-    //      5     -1.3800e-13      0.0066   4415.6439
-    //      6      3.2380e-13      0.0065   4441.6299
-    //      7     -8.4583e-11      0.0053   2277.1707
-    //      8      3.4867e-13      0.0069   4367.6094
+    //         1      4.0146e-13      0.0024   5827.9076
+    //         2     -1.4166e-13      0.0007  10037.8942
+    //         3      4.7184e-14      0.0039   4371.9185
+    //         4     -1.2557e-13      0.0034   4355.5711
+    //         5     -1.3800e-13      0.0066   4415.6439
+    //         6      3.2380e-13      0.0065   4441.6299
+    //         7     -8.4583e-11      0.0053   2277.1707
+    //         8      3.4867e-13      0.0069   4367.6094
 
-    //    Iterations      =  512000000
-    //    NullTime (usec) =     0.0000
-    //    MFLOPS(1)       =  7050.6178
-    //    MFLOPS(2)       =  3461.6233
-    //    MFLOPS(3)       =  4175.0442
-    //    MFLOPS(4)       =  4389.7311
+    //     Iterations      =  512000000
+    //     NullTime (usec) =     0.0000
+    //     MFLOPS(1)       =  7050.6178
+    //     MFLOPS(2)       =  3461.6233
+    //     MFLOPS(3)       =  4175.0442
+    //     MFLOPS(4)       =  4389.7311
 }
 
 void task_2() {
@@ -231,7 +234,7 @@ void task_7() {
     // #################################
     // Benchmark
 
-    cout << fixed << setprecision(4);  // 4 digits after decimal
+    cout << fixed << setprecision(4);
     size_t NLOOPS = 1000;
     cout << "N    = " << "  | 1      | 2      | 4      | 8      | 16     | 32 " << endl;
     cout <<       "---------|--------|--------|--------|--------|--------|-------" << endl;
@@ -248,9 +251,6 @@ void task_7() {
         cout << endl;
     }
     printf("\nFor fixed n, the solution time per rhs does not slow down consistently and scales very well.\nIts faster than expected.");
-
-
-
 }
 
 int main() {
diff --git a/ex3/code/task_3.cpp b/ex3/code/task_3.cpp
index 22a0482..57c5561 100644
--- a/ex3/code/task_3.cpp
+++ b/ex3/code/task_3.cpp
@@ -1,7 +1,6 @@
 #include "task_3.h"
 #include <vector>
 #include <cassert>
-#include <iostream>
 #include <cmath>
 using namespace std;
 
diff --git a/ex3/code/task_4+6.cpp b/ex3/code/task_4+6.cpp
index bcde52c..51359f9 100644
--- a/ex3/code/task_4+6.cpp
+++ b/ex3/code/task_4+6.cpp
@@ -1,9 +1,9 @@
 #include "task_3.h"
 #include "task_4+6.h"
 #include "timing.h"
+#include <cblas.h>               // cBLAS Library
 #include <vector>
 #include <iostream>
-#include <cblas.h>               // cBLAS Library
 using namespace std;
 
 void print_performance(double sec, size_t memory, size_t flops, unsigned int size) {
diff --git a/ex3/code/task_5.h b/ex3/code/task_5.h
index 24609ba..b8f970b 100644
--- a/ex3/code/task_5.h
+++ b/ex3/code/task_5.h
@@ -1,5 +1,4 @@
 #pragma once
-
 #include <vector>
 using namespace std;
 
diff --git a/ex3/code/task_7.cpp b/ex3/code/task_7.cpp
index 1121ec7..86b523d 100644
--- a/ex3/code/task_7.cpp
+++ b/ex3/code/task_7.cpp
@@ -1,9 +1,8 @@
 #include "task_7.h"
-
-#include <iostream>
-#include <vector>
-#include <cmath>
 #include <lapacke.h>
+#include <vector>
+#include <iostream>
+#include <cmath>
 using namespace std;
 
 tuple<vector<double>, vector<double>> init_M(size_t N, size_t Nrhs) {