Move all instructions to main.py

code/vfclass_d.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 2;i++) {
+    dst.dword[i] = fp_classify(a.fp64[i]);
+}

code/vfclass_s.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 4;i++) {
+    dst.word[i] = fp_classify(a.fp32[i]);
+}

code/vfmadd_d.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 2;i++) {
+    dst.fp64[i] = a.fp64[i] * b.fp64[i] + c.fp64[i];
+}

code/vfmadd_s.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 4;i++) {
+    dst.fp32[i] = a.fp32[i] * b.fp32[i] + c.fp32[i];
+}

code/vfmsub_d.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 2;i++) {
+    dst.fp64[i] = a.fp64[i] * b.fp64[i] - c.fp64[i];
+}

code/vfmsub_s.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 4;i++) {
+    dst.fp32[i] = a.fp32[i] * b.fp32[i] - c.fp32[i];
+}

code/vfnmadd_d.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 2;i++) {
+    dst.fp64[i] = (a.fp64[i] * b.fp64[i] + c.fp64[i]);
+}

code/vfnmadd_s.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 4;i++) {
+    dst.fp32[i] = -(a.fp32[i] * b.fp32[i] + c.fp32[i]);
+}

code/vfnmsub_d.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 2;i++) {
+    dst.fp64[i] = -(a.fp64[i] * b.fp64[i] - c.fp64[i]);
+}

code/vfnmsub_s.h

@@ -0,0 +1,3 @@
+for (int i = 0;i < 4;i++) {
+    dst.fp32[i] = -(a.fp32[i] * b.fp32[i] - c.fp32[i]);
+}

docs/lsx/bitwise_operations.md

@@ -1,46 +1,8 @@
 # Bitwise Operations
 
-## __m128i __lsx_vbitsel_v (__m128i a, __m128i b, __m128i c)
+{{ vbitsel_v() }}
 
-### Synopsis
-
-```c++
-__m128i __lsx_vbitsel_v (__m128i a, __m128i b, __m128i c)
-#include <lsxintrin.h>
-Instruction: vbitsel.v vr, vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Compute bitwise selection: for each bit position, if the bit in `c` equals to one, copy the bit from `b` to `dst`, otherwise copy from `a`.
-
-### Operation
-
-```c++
-{% include 'vbitsel_v.h' %}
-```
-
-## __m128i __lsx_vbitseli_b (__m128i a, __m128i b, imm0_255 imm)
-
-### Synopsis
-
-```c++
-__m128i __lsx_vbitseli_b (__m128i a, __m128i b, imm0_255 imm)
-#include <lsxintrin.h>
-Instruction: vbitseli.b vr, vr, imm
-CPU Flags: LSX
-```
-
-### Description
-
-Compute bitwise selection: for each bit position, if the bit in `a` equals to one, copy the bit from `imm` to `dst`, otherwise copy from `b`.
-
-### Operation
-
-```c++
-{% include 'vbitseli_b.h' %}
-```
+{{ vbitseli_b() }}
 
 {{ vbitclr('b') }}
 {{ vbitclr('h') }}

docs/lsx/float_conversion.md

@@ -1,132 +1,14 @@
 # Floating Point Conversion
 
-## __m128d __lsx_vfcvth_d_s (__m128 a)
+{{ vfcvth_d_s() }}
+{{ vfcvtl_d_s() }}
 
-### Synopsis
+{{ vfcvt_s_d() }}
 
-```c++
-__m128d __lsx_vfcvth_d_s (__m128 a)
-#include <lsxintrin.h>
-Instruction: vfcvth.d.s vr, vr
-CPU Flags: LSX
-```
+{{ vfcvth_s_h() }}
+{{ vfcvtl_s_h() }}
 
-### Description
-
-Convert single precision floating point elements in higher half of `a` to double precision.
-
-### Operation
-
-```c++
-{% include('vfcvth_d_s.h') %}
-```
-
-## __m128d __lsx_vfcvtl_d_s (__m128 a)
-
-### Synopsis
-
-```c++
-__m128d __lsx_vfcvtl_d_s (__m128 a)
-#include <lsxintrin.h>
-Instruction: vfcvtl.d.s vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Convert single precision floating point elements in lower half of `a` to double precision.
-
-### Operation
-
-```c++
-{% include('vfcvtl_d_s.h') %}
-```
-
-
-## __m128 __lsx_vfcvt_s_d (__m128d a, __m128d b)
-
-### Synopsis
-
-```c++
-__m128 __lsx_vfcvt_s_d (__m128a, __m128d b)
-#include <lsxintrin.h>
-Instruction: vfcvt.s.d vr, vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Convert double precision floating point elements in `a` and `b` to double precision.
-
-### Operation
-
-```c++
-{% include('vfcvt_s_d.h') %}
-```
-
-## __m128 __lsx_vfcvth_s_h (__m128i a)
-
-### Synopsis
-
-```c++
-__m128 __lsx_vfcvth_s_h (__m128i a)
-#include <lsxintrin.h>
-Instruction: vfcvth.s.h vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Convert half precision floating point elements in higher half of `a` to single precision.
-
-### Operation
-
-```c++
-{% include('vfcvth_s_h.h') %}
-```
-
-## __m128 __lsx_vfcvtl_s_h (__m128i a)
-
-### Synopsis
-
-```c++
-__m128 __lsx_vfcvtl_s_h (__m128i a)
-#include <lsxintrin.h>
-Instruction: vfcvtl.s.h vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Convert half precision floating point elements in lower half of `a` to single precision.
-
-### Operation
-
-```c++
-{% include('vfcvtl_s_h.h') %}
-```
-
-
-## __m128i __lsx_vfcvt_h_s (__m128 a, __m128 b)
-
-### Synopsis
-
-```c++
-__m128i __lsx_vfcvt_h_s (__m128, __m128 b)
-#include <lsxintrin.h>
-Instruction: vfcvt.h.s vr, vr, vr
-CPU Flags: LSX
-```
-
-### Description
-
-Convert single precision floating point elements in `a` and `b` to half precision.
-
-### Operation
-
-```c++
-{% include('vfcvt_h_s.h') %}
-```
+{{ vfcvt_h_s() }}
 
 {{ vffint_d_w('h') }}
 {{ vffint_d_w('l') }}

docs/lsx/float_misc.md

@@ -1,51 +1,7 @@
 # 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]);
-}
-```
-
+{{ vclass_d() }}
+{{ vclass_s() }}
 
 {{ vfrint('', 's') }}
 {{ vfrint('', 'd') }}