diff --git a/README.md b/README.md
index d301a3b4..1fd4f2db 100644
--- a/README.md
+++ b/README.md
@@ -188,8 +188,6 @@ Vector Multiplication High
 
 ### vsignconv.b/h/w/d
 
-### vfadd.s/d
-
 ### vfsub.s/d
 
 ### vfmul.s/d
@@ -260,8 +258,6 @@ Vector Multiplication High
 
 ### vflogb.s/d
 
-### vfclass.s/d
-
 ### vfsqrt.s/d
 
 ### vfrecip.s/d
diff --git a/docs/lsx/float_comparison.md b/docs/lsx/float_comparison.md
index 729728cb..34fc55e9 100644
--- a/docs/lsx/float_comparison.md
+++ b/docs/lsx/float_comparison.md
@@ -1,4 +1,4 @@
-# Float Comparison
+# Floating Point Comparison
 
 ## __m128i __lsx_vfcmp_cond_s (__m128 a, __m128 b)
 
diff --git a/docs/lsx/float_computation.md b/docs/lsx/float_computation.md
new file mode 100644
index 00000000..61b35b1b
--- /dev/null
+++ b/docs/lsx/float_computation.md
@@ -0,0 +1,47 @@
+# Floating Point Computation
+
+## __m128d __lsx_vfadd_d (__m128d a, __m128d b)
+
+### Synopsis
+
+```c++
+__m128d __lsx_vfadd_d (__m128d a, __m128d b)
+#include <lsxintrin.h>
+Instruction: vfadd.d vr, vr, vr
+CPU Flags: LSX
+```
+
+### Description
+
+Add double precision floating point elements in `a` to `b` and store the result in `dst`.
+
+### Operation
+
+```c++
+for (int i = 0;i < 2;i++) {
+    dst.fp64[i] = a.fp64[i] + b.fp64[i];
+}
+```
+
+## __m128 __lsx_vfadd_s (__m128 a, __m128 b)
+
+### Synopsis
+
+```c++
+__m128d __lsx_vfadd_s (__m128d a, __m128d b)
+#include <lsxintrin.h>
+Instruction: vfadd.s vr, vr, vr
+CPU Flags: LSX
+```
+
+### Description
+
+Add single precision floating point elements in `a` to `b` and store the result in `dst`.
+
+### Operation
+
+```c++
+for (int i = 0;i < 4;i++) {
+    dst.fp32[i] = a.fp32[i] + b.fp32[i];
+}
+```
diff --git a/docs/lsx/float_misc.md b/docs/lsx/float_misc.md
new file mode 100644
index 00000000..d6b8c38c
--- /dev/null
+++ b/docs/lsx/float_misc.md
@@ -0,0 +1,47 @@
+# Floatint Point Misc
+
+## __m128i __lsx_vfclass_d (__m128d a)
+
+### Synopsis
+
+```c++
+__m128i __lsx_vfclass_d (__m128d a)
+#include <lsxintrin.h>
+Instruction: vfclass.d vr, vr
+CPU Flags: LSX
+```
+
+### Description
+
+Classifiy each double precision floating point elements in `a`.
+
+### Operation
+
+```c++
+for (int i = 0;i < 2;i++) {
+    dst.dword[i] = fp_classify(a.fp64[i]);
+}
+```
+
+## __m128i __lsx_vfclass_s (__m128 a)
+
+### Synopsis
+
+```c++
+__m128i __lsx_vfclass_s (__m128d a)
+#include <lsxintrin.h>
+Instruction: vfclass.s vr, vr
+CPU Flags: LSX
+```
+
+### Description
+
+Classifiy each single precision floating point elements in `a`.
+
+### Operation
+
+```c++
+for (int i = 0;i < 4;i++) {
+    dst.word[i] = fp_classify(a.fp32[i]);
+}
+```