From 0f986a34882a58d050e9e9c30b9c9cba529de923 Mon Sep 17 00:00:00 2001
From: Ryan Oldenburg <ryan@guzba.com>
Date: Sat, 23 Jul 2022 00:11:40 -0500
Subject: [PATCH] 1.1.8 more neon

---
 nimsimd.nimble       |  2 +-
 src/nimsimd/neon.nim | 25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/nimsimd.nimble b/nimsimd.nimble
index 5c028e3..028ee95 100644
--- a/nimsimd.nimble
+++ b/nimsimd.nimble
@@ -1,4 +1,4 @@
-version     = "1.1.7"
+version     = "1.1.8"
 author      = "Ryan Oldenburg"
 description = "Pleasant Nim bindings for SIMD instruction sets."
 license     = "MIT"
diff --git a/src/nimsimd/neon.nim b/src/nimsimd/neon.nim
index 07cb4f3..35f5ea3 100644
--- a/src/nimsimd/neon.nim
+++ b/src/nimsimd/neon.nim
@@ -35,11 +35,21 @@ func vmovq_n_u16*(a: uint16): uint16x8
 func vmovq_n_u32*(a: uint32): uint32x4
 func vmovq_n_u64*(a: uint64): uint64x2
 
+func vmov_n_u8*(a: uint8): uint8x8
+func vmov_n_u16*(a: uint16): uint16x4
+func vmov_n_u32*(a: uint32): uint32x2
+func vmov_n_u64*(a: uint64): uint64x1
+
 func vld1q_u8*(p: pointer): uint8x16
 func vld1q_u16*(p: pointer): uint16x8
 func vld1q_u32*(p: pointer): uint32x4
 func vld1q_u64*(p: pointer): uint64x2
 
+func vld1_u8*(p: pointer): uint8x8
+func vld1_u16*(p: pointer): uint16x4
+func vld1_u32*(p: pointer): uint32x2
+func vld1_u64*(p: pointer): uint64x1
+
 func vceqq_u8*(a, b: uint8x16): uint8x16
 func vceqq_u16*(a, b: uint16x8): uint16x8
 func vceqq_u32*(a, b: uint32x4): uint32x4
@@ -64,6 +74,11 @@ func vst1q_u16*(p: pointer, v: uint16x8)
 func vst1q_u32*(p: pointer, v: uint32x4)
 func vst1q_u64*(p: pointer, v: uint64x2)
 
+func vst1_u8*(p: pointer, v: uint8x8)
+func vst1_u16*(p: pointer, v: uint16x4)
+func vst1_u32*(p: pointer, v: uint32x2)
+func vst1_u64*(p: pointer, v: uint64x1)
+
 func vandq_u8*(a, b: uint8x16): uint8x16
 func vandq_u16*(a, b: uint16x8): uint16x8
 func vandq_u32*(a, b: uint32x4): uint32x4
@@ -151,4 +166,14 @@ func vcombine_u16*(a, b: uint16x4): uint16x8
 func vcombine_u32*(a, b: uint32x2): uint32x4
 func vcombine_u64*(a, b: uint64x1): uint64x2
 
+func vbicq_u8*(a, b: uint8x16): uint8x16
+func vbicq_u16*(a, b: uint16x8): uint16x8
+func vbicq_u32*(a, b: uint32x4): uint32x4
+func vbicq_u64*(a, b: uint64x2): uint64x2
+
+func vsubq_u8*(a, b: uint8x16): uint8x16
+func vsubq_u16*(a, b: uint16x8): uint16x8
+func vsubq_u32*(a, b: uint32x4): uint32x4
+func vsubq_u64*(a, b: uint64x2): uint64x2
+
 {.pop.}