diff --git a/步骤三.cpp b/步骤三.cpp
new file mode 100644
index 0000000..f7bd261
--- /dev/null
+++ b/步骤三.cpp
@@ -0,0 +1,61 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+
+#define SIZE 1024
+
+// 矩阵乘法函数
+void matmul(float A[SIZE][SIZE], float B[SIZE][SIZE], float C[SIZE][SIZE], int n) {
+    for (int i = 0; i < n; i++) {
+        for (int j = 0; j < n; j++) {
+            C[i][j] = 0; 
+            for (int k = 0; k < n; k++) {
+                C[i][j] += A[i][k] * B[k][j];
+            }
+        }
+    }
+}
+
+int main() {
+    // 矩阵内存分配
+    float *A = (float *)malloc(SIZE * SIZE * sizeof(float));
+    float *B = (float *)malloc(SIZE * SIZE * sizeof(float));
+    float *C = (float *)malloc(SIZE * SIZE * sizeof(float));
+
+    if (A == NULL || B == NULL || C == NULL) {
+        printf("Memory allocation failed!\n");
+        return 1;
+    }
+
+
+    float (*A_matrix)[SIZE] = (float (*)[SIZE])A;
+    float (*B_matrix)[SIZE] = (float (*)[SIZE])B;
+    float (*C_matrix)[SIZE] = (float (*)[SIZE])C;
+
+    // 初始化
+    srand(time(NULL)); 
+    for (int i = 0; i < SIZE; i++) {
+        for (int j = 0; j < SIZE; j++) {
+            A_matrix[i][j] = rand() % 100;
+            B_matrix[i][j] = rand() % 100;
+        }
+    }
+
+    // 计时并输出
+    clock_t start, end;
+    start = clock();
+
+    matmul(*A_matrix, *B_matrix, *C_matrix, SIZE);
+
+    end = clock(); 
+    double time_spent = (double)(end - start) / CLOCKS_PER_SEC; 
+
+    printf("基础矩阵乘法的运行时间为: %lf 秒\n", time_spent);
+
+    
+    free(A);
+    free(B);
+    free(C);
+
+    return 0;
+}
\ No newline at end of file