Added sse files to implement sse assembly instructions in inline code

CMakeLists.txt

@@ -10,6 +10,7 @@ add_executable(cpplab main.cpp)
 
 add_executable(
     sse 
+    src/core/cpu/sse.cpp
     src/core/cpu/naive.cpp
     src/core/cpu/avx2.cpp
     sse.cpp

src/core/cpu/sse.cpp

@@ -0,0 +1,13 @@
+#include "sse.hpp"
+#include <iostream>
+
+//X86 Assembly to add two 128 bit numbers
+void core::cpu::SSE::sum_128(int *a,int *b) {
+    asm(
+        "movdqa %0, %%xmm1\n"
+        "paddw %1, %%xmm1\n"
+        "movdqa %%xmm1, %0"
+        : "=m"(*a)
+        : "m"(*b)
+    );
+}

src/core/cpu/sse.hpp

@@ -0,0 +1,17 @@
+#ifndef CORE_CPU_SSE_H
+#define CORE_CPU_SSE_H
+
+using namespace std;
+/**
+ * This will define a set of functions 
+ */
+namespace core {
+    namespace cpu {
+        class SSE {
+            public:
+                static void sum_128(int *a,int *b);
+        };
+    };
+};
+
+#endif

sse.cpp

@@ -3,19 +3,22 @@
 #include <iomanip>
 
 #include "src/core/cpu/naive.hpp"
+#include "src/core/cpu/sse.hpp"
 
 using namespace core::cpu;
 
 int main(int argc, char** argcv){
-    int v1_128[Naive::LEN_128] = { 0x100, 0x2,0x3,0x4 };
+    int v1_128[Naive::LEN_128] = { 0x1, 0x2,0x3,0x4 };
-    int v2_128[Naive::LEN_128] = { 0x10, 0x2,0x3,0x4 };
+    int v2_128[Naive::LEN_128] = { 0x1, 0x2,0x3,0x4 };
 
     Naive::print(v1_128,Naive::LEN_128);
     Naive::print(v2_128,Naive::LEN_128);
 
     Naive::sum_128_long(v1_128,v2_128);
+    SSE::sum_128(v1_128,v2_128);
 
     Naive::print(v1_128,Naive::LEN_128);
     Naive::print(v2_128,Naive::LEN_128);
+    
 
 }