From 6d594a8b898b58e08a660278b43944611407eecd Mon Sep 17 00:00:00 2001
From: Jiajie Chen <c@jia.je>
Date: Mon, 11 Dec 2023 22:54:11 +0800
Subject: [PATCH] Document more instructions

---
 README.md | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index a9cb8bde..13d3946b 100644
--- a/README.md
+++ b/README.md
@@ -8,19 +8,31 @@ GCC Intrinsic: <https://gcc.gnu.org/onlinedocs/gcc/LoongArch-SX-Vector-Intrinsic
 
 ### vfmadd.s/d
 
-Vector Fused Multiply Add Single/Double Precision
+Vector Fused Multiply Add (`a * b + c`) Single/Double Precision
+
+- Single Precision: `__m128 __lsx_vfmadd_s (__m128 a, __m128 b, __m128 c)`
+- Double Precision: `__m128d __lsx_vfmadd_d (__m128d a, __m128d b, __m128d c)`
 
 ### vfmsub.s/d
 
-Vector Fused Multiply Subtract Single/Double Precision
+Vector Fused Multiply Subtract (`a * b - c`) Single/Double Precision
+
+- Single Precision: `__m128 __lsx_vfmsub_s (__m128 a, __m128 b, __m128 c)`
+- Double Precision: `__m128d __lsx_vfmsub_d (__m128d a, __m128d b, __m128d c)`
+
+### vfnmadd.s/d
 
-### vnfmadd.s/d
+Vector Fused Negative Multiply Add (`- a * b - c`) Single/Double Precision
 
-Vector Negative Fused Multiply Add Single/Double Precision
+- Single Precision: `__m128 __lsx_vfnmadd_s (__m128 a, __m128 b, __m128 c)`
+- Double Precision: `__m128d __lsx_vfnmadd_d (__m128d a, __m128d b, __m128d c)`
 
-### vnfmsub.s/d
+### vfnmsub.s/d
 
-Vector Negative Fused Multiply Subtract Single/Double Precision
+Vector Fused Negative Multiply Subtract (`- a * b + c`) Single/Double Precision
+
+- Single Precision: `__m128 __lsx_vfnmsub_s (__m128 a, __m128 b, __m128 c)`
+- Double Precision: `__m128d __lsx_vfnmsub_d (__m128d a, __m128d b, __m128d c)`
 
 ### vfcmp.cond.s/d
 
@@ -30,12 +42,16 @@ Vector Float Compare
 
 ### vbitsel.v
 
-Vector Bit Selection
+Vector Bit Selection: For each bit, `c ? b : a`
+
+`__m128i __lsx_vbitsel_v (__m128i a, __m128i b, __m128i c)`
 
 ### vshuf.b
 
 Vector Shuffle
 
+`__m128i __lsx_vshuf_b (__m128i a, __m128i b, __m128i c)`
+
 ### vld
 
 Vector Load