[GCC][PATCH] arm: Fix MVE intrinsics polymorphic variants wrongly generating __ARM_undef type (pr96795).

Hello,

This patch fixes (PR96795) MVE intrinsic polymorphic variants vaddq, vaddq_m, vaddq_x, vcmpeqq_m,
vcmpeqq, vcmpgeq_m, vcmpgeq, vcmpgtq_m, vcmpgtq, vcmpleq_m, vcmpleq, vcmpltq_m, vcmpltq,
vcmpneq_m, vcmpneq, vfmaq_m, vfmaq, vfmasq_m, vfmasq, vmaxnmavq, vmaxnmavq_p, vmaxnmvq,
vmaxnmvq_p, vminnmavq, vminnmavq_p, vminnmvq, vminnmvq_p, vmulq_m, vmulq, vmulq_x, vsetq_lane,
vsubq_m, vsubq and vsubq_x which are incorrectly generating __ARM_undef and mismatching the passed
floating point scalar arguments.

Bootstrapped on arm-none-linux-gnueabihf and regression tested on arm-none-eabi and found no regressions.

Ok for master? Ok for GCC-10 branch?

Regards,
Srinath.

gcc/ChangeLog:

2020-09-30  Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

	PR target/96795
	* config/arm/arm_mve.h (__ARM_mve_coerce2): Define.
	(__arm_vaddq): Correct the scalar argument.
	(__arm_vaddq_m): Likewise.
	(__arm_vaddq_x): Likewise.
	(__arm_vcmpeqq_m): Likewise.
	(__arm_vcmpeqq): Likewise.
	(__arm_vcmpgeq_m): Likewise.
	(__arm_vcmpgeq): Likewise.
	(__arm_vcmpgtq_m): Likewise.
	(__arm_vcmpgtq): Likewise.
	(__arm_vcmpleq_m): Likewise.
	(__arm_vcmpleq): Likewise.
	(__arm_vcmpltq_m): Likewise.
	(__arm_vcmpltq): Likewise.
	(__arm_vcmpneq_m): Likewise.
	(__arm_vcmpneq): Likewise.
	(__arm_vfmaq_m): Likewise.
	(__arm_vfmaq): Likewise.
	(__arm_vfmasq_m): Likewise.
	(__arm_vfmasq): Likewise.
	(__arm_vmaxnmavq): Likewise.
	(__arm_vmaxnmavq_p): Likewise.
	(__arm_vmaxnmvq): Likewise.
	(__arm_vmaxnmvq_p): Likewise.
	(__arm_vminnmavq): Likewise.
	(__arm_vminnmavq_p): Likewise.
	(__arm_vminnmvq): Likewise.
	(__arm_vminnmvq_p): Likewise.
	(__arm_vmulq_m): Likewise.
	(__arm_vmulq): Likewise.
	(__arm_vmulq_x): Likewise.
	(__arm_vsetq_lane): Likewise.
	(__arm_vsubq_m): Likewise.
	(__arm_vsubq): Likewise.
	(__arm_vsubq_x): Likewise.

gcc/testsuite/ChangeLog:

	PR target/96795
	* gcc.target/arm/mve/intrinsics/mve_fp_vaddq_n.c: New Test.
	* gcc.target/arm/mve/intrinsics/mve_vaddq_n.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_x_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_x_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpleq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpleq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmaq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmaq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmaq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmaq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmasq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmasq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmasq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vfmasq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_p_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_p_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_p_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_p_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_x_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_x_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsetq_lane_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsetq_lane_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_m_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_m_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_n_f32-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_x_n_f16-1.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_x_n_f32-1.c: Likewise.

69 files changed, 959 insertions, 82 deletions

diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index a801705..99cff41 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -35651,6 +35651,7 @@ enum {
 	short: __ARM_mve_type_int_n, \
 	int: __ARM_mve_type_int_n, \
 	long: __ARM_mve_type_int_n, \
+	double: __ARM_mve_type_fp_n, \
 	long long: __ARM_mve_type_int_n, \
 	unsigned char: __ARM_mve_type_int_n, \
 	unsigned short: __ARM_mve_type_int_n, \
@@ -35723,6 +35724,8 @@ extern void *__ARM_undef;
     _Generic(param, type: param, default: *(type *)__ARM_undef)
 #define __ARM_mve_coerce1(param, type) \
     _Generic(param, type: param, const type: param, default: *(type *)__ARM_undef)
+#define __ARM_mve_coerce2(param, type) \
+    _Generic(param, type: param, float16_t: param, float32_t: param, default: *(type *)__ARM_undef)
 
 #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point.  */
 
@@ -35939,14 +35942,14 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vaddq_f16 (__ARM_mve_coerce(p0, float16x8_t), __ARM_mve_coerce(p1, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vaddq_f32 (__ARM_mve_coerce(p0, float32x4_t), __ARM_mve_coerce(p1, float32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)));})
 
 #define __arm_vandq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -35997,8 +36000,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vmulq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmulq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -36029,8 +36032,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpeqq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpeqq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpeqq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -36069,8 +36072,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpeqq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpeqq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2));})
 
 #define __arm_vcmpgtq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36083,8 +36086,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgtq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgtq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)));})
 
 #define __arm_vcmpleq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36097,8 +36100,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vcmpleq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpleq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpleq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)));})
 
 #define __arm_vcmpltq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36111,8 +36114,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpltq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpltq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)));})
 
 #define __arm_vcmpneq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36123,8 +36126,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vcmpneq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpneq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpneq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpneq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpneq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpneq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -36179,8 +36182,8 @@ extern void *__ARM_undef;
 #define __arm_vmaxnmavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vmaxnmq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36191,14 +36194,14 @@ extern void *__ARM_undef;
 #define __arm_vmaxnmvq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vmaxnmvq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vminnmaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -36209,8 +36212,8 @@ extern void *__ARM_undef;
 #define __arm_vminnmavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vbrsrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -36232,8 +36235,8 @@ extern void *__ARM_undef;
 #define __arm_vsubq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
@@ -36252,8 +36255,8 @@ extern void *__ARM_undef;
 #define __arm_vminnmvq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vshlq_r(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -37011,8 +37014,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgtq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgtq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgtq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
@@ -37027,8 +37030,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vcmpleq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpleq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpleq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2));})
 
 #define __arm_vcmpltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37041,8 +37044,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vcmpltq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpltq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpltq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2));})
 
 #define __arm_vcmpneq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37061,8 +37064,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vcmpneq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpneq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpneq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2));})
 
 #define __arm_vcvtbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37116,8 +37119,8 @@ extern void *__ARM_undef;
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double)), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
 
@@ -37132,8 +37135,8 @@ extern void *__ARM_undef;
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t)));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double)));})
 
 #define __arm_vmaxnmaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37156,14 +37159,14 @@ extern void *__ARM_undef;
 #define __arm_vmaxnmavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_p_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_p_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vmaxnmvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_p_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_p_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vminnmaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37174,14 +37177,14 @@ extern void *__ARM_undef;
 #define __arm_vminnmavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_p_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_p_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vminnmvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_p_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_p_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vrndnq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37248,8 +37251,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double)));})
 
 #define __arm_vrshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37353,8 +37356,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce2(__p1, double), p2), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpgeq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce2(__p1, double), p2), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
@@ -37389,8 +37392,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int), p3), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vandq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37531,15 +37534,15 @@ extern void *__ARM_undef;
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmaq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vfmasq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vfmsq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37580,8 +37583,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vmulq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmulq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -37614,8 +37617,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vsubq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vsubq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vsubq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vorrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -38113,8 +38116,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vaddq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vaddq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vandq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
@@ -38248,8 +38251,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmulq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmulq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vnegq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
@@ -38337,8 +38340,8 @@ extern void *__ARM_undef;
   _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vsubq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vsubq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(__p2, double), p3), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(__p2, double), p3));})
 
 #define __arm_vcmulq_rot90_x(p1,p2,p3)  ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
@@ -38370,8 +38373,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
   int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
   int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint64x2_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce2(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #else /* MVE Integer.  */
 
@@ -38895,12 +38898,12 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int)));})
 
 #define __arm_vandq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_fp_vaddq_n.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_fp_vaddq_n.c
new file mode 100644
index 0000000..714fbf9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_fp_vaddq_n.c
@@ -0,0 +1,47 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include <arm_mve.h>
+int8x16_t foo (int8x16_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+int16x8_t foo1 (int16x8_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+int32x4_t foo2 (int32x4_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint8x16_t foo3 (uint8x16_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint16x8_t foo4 (uint16x8_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint32x4_t foo5 (uint32x4_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+float16x8_t foo6 (float16x8_t a)
+{
+  return vaddq (a, (float16_t)23.6);
+}
+float32x4_t foo7 (float32x4_t a)
+{
+  return vaddq (a, (float32_t)23.46);
+}
+float16x8_t foo8 (float16x8_t a)
+{
+  return vaddq (a, 23.6);
+}
+float32x4_t foo9 (float32x4_t a)
+{
+  return vaddq (a, 23.46);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_vaddq_n.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_vaddq_n.c
new file mode 100644
index 0000000..baa7fab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_vaddq_n.c
@@ -0,0 +1,31 @@
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include <arm_mve.h>
+int8x16_t foo (int8x16_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+int16x8_t foo1 (int16x8_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+int32x4_t foo2 (int32x4_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint8x16_t foo3 (uint8x16_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint16x8_t foo4 (uint16x8_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+uint32x4_t foo5 (uint32x4_t a, int16_t b)
+{
+  return vaddq (a, (b<<3));
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f16-1.c
new file mode 100644
index 0000000..8348098
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t inactive, float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vaddq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f32-1.c
new file mode 100644
index 0000000..c34cc98
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t inactive, float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vaddq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f16-1.c
new file mode 100644
index 0000000..3bb0167
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vaddq_x (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f32-1.c
new file mode 100644
index 0000000..66dedc7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vaddq_x_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vaddq_x (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f16-1.c
new file mode 100644
index 0000000..909ca93
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpeqq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f32-1.c
new file mode 100644
index 0000000..8f993af
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpeqq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16-1.c
new file mode 100644
index 0000000..223cffc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpeqq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32-1.c
new file mode 100644
index 0000000..81669bd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpeqq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f16-1.c
new file mode 100644
index 0000000..4a4e4b3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpgeq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f32-1.c
new file mode 100644
index 0000000..c406a63
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpgeq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f16-1.c
new file mode 100644
index 0000000..a65ed44
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpgeq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f32-1.c
new file mode 100644
index 0000000..2e2fc01
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpgeq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16-1.c
new file mode 100644
index 0000000..08c91a7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpgtq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32-1.c
new file mode 100644
index 0000000..0b74482
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpgtq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16-1.c
new file mode 100644
index 0000000..3b2faea
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpgtq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32-1.c
new file mode 100644
index 0000000..16862e0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpgtq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16-1.c
new file mode 100644
index 0000000..50e53bd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpleq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32-1.c
new file mode 100644
index 0000000..b16da27
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpleq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16-1.c
new file mode 100644
index 0000000..4a4b973
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpleq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32-1.c
new file mode 100644
index 0000000..8d8f105
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpleq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16-1.c
new file mode 100644
index 0000000..62ab53f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpltq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32-1.c
new file mode 100644
index 0000000..55886fc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpltq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f16-1.c
new file mode 100644
index 0000000..cd95dae
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpltq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f32-1.c
new file mode 100644
index 0000000..db76687
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpltq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16-1.c
new file mode 100644
index 0000000..30618e8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vcmpneq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32-1.c
new file mode 100644
index 0000000..4ecfda6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vcmpneq_m (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16-1.c
new file mode 100644
index 0000000..75a0090
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vcmpneq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32-1.c
new file mode 100644
index 0000000..11ae14c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+mve_pred16_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vcmpneq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f16-1.c
new file mode 100644
index 0000000..e47ae6d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16x8_t b, float16_t c, mve_pred16_t p)
+{
+  return vfmaq_m (a, b, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f32-1.c
new file mode 100644
index 0000000..78c39f0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32x4_t b, float32_t c, mve_pred16_t p)
+{
+  return vfmaq_m (a, b, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f16-1.c
new file mode 100644
index 0000000..f7867f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16x8_t b, float16_t c)
+{
+  return vfmaq (a, b, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f32-1.c
new file mode 100644
index 0000000..f0bc45b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmaq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32x4_t b, float32_t c)
+{
+  return vfmaq (a, b, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f16-1.c
new file mode 100644
index 0000000..4750e10
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16x8_t b, float16_t c, mve_pred16_t p)
+{
+  return vfmasq_m (a, b, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f32-1.c
new file mode 100644
index 0000000..4a37971
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32x4_t b, float32_t c, mve_pred16_t p)
+{
+  return vfmasq_m (a, b, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f16-1.c
new file mode 100644
index 0000000..db82451
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16x8_t b, float16_t c)
+{
+  return vfmasq (a, b, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f32-1.c
new file mode 100644
index 0000000..12b1410
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vfmasq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32x4_t b, float32_t c)
+{
+  return vfmasq (a, b, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f16-1.c
new file mode 100644
index 0000000..7c2349d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b)
+{
+  return vmaxnmavq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f32-1.c
new file mode 100644
index 0000000..0deef7948
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b)
+{
+  return vmaxnmavq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f16-1.c
new file mode 100644
index 0000000..56a7ac0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b, mve_pred16_t p)
+{
+  return vmaxnmavq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f32-1.c
new file mode 100644
index 0000000..36c10a9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b, mve_pred16_t p)
+{
+  return vmaxnmavq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f16-1.c
new file mode 100644
index 0000000..f60641f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b)
+{
+  return vmaxnmvq (23.35, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f32-1.c
new file mode 100644
index 0000000..f8c9f44
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b)
+{
+  return vmaxnmvq (34.56, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f16-1.c
new file mode 100644
index 0000000..96820ec
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b, mve_pred16_t p)
+{
+  return vmaxnmvq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f32-1.c
new file mode 100644
index 0000000..826ee8f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b, mve_pred16_t p)
+{
+  return vmaxnmvq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f16-1.c
new file mode 100644
index 0000000..37d5136
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b)
+{
+  return vminnmavq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f32-1.c
new file mode 100644
index 0000000..78978d0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b)
+{
+  return vminnmavq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f16-1.c
new file mode 100644
index 0000000..7170b74
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b, mve_pred16_t p)
+{
+  return vminnmavq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f32-1.c
new file mode 100644
index 0000000..0955905
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmavq_p_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b, mve_pred16_t p)
+{
+  return vminnmavq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f16-1.c
new file mode 100644
index 0000000..132d1a1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b)
+{
+  return vminnmvq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f32-1.c
new file mode 100644
index 0000000..7490907
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b)
+{
+  return vminnmvq (a, b);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f16-1.c
new file mode 100644
index 0000000..c88c3b7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16_t
+foo1 (float16_t a, float16x8_t b, mve_pred16_t p)
+{
+  return vminnmvq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f32-1.c
new file mode 100644
index 0000000..e4db972
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vminnmvq_p_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32_t
+foo1 (float32_t a, float32x4_t b, mve_pred16_t p)
+{
+  return vminnmvq_p (a, b, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f16-1.c
new file mode 100644
index 0000000..c8222c5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t inactive, float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vmulq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f32-1.c
new file mode 100644
index 0000000..2fae3a7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t inactive, float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vmulq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f16-1.c
new file mode 100644
index 0000000..cef311d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vmulq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f32-1.c
new file mode 100644
index 0000000..d6d4b9a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vmulq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f16-1.c
new file mode 100644
index 0000000..ea4cab0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vmulq_x (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f32-1.c
new file mode 100644
index 0000000..a7a54c7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmulq_x_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vmulq_x (a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f16-1.c
new file mode 100644
index 0000000..608dd30
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f16-1.c
@@ -0,0 +1,13 @@
+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=soft" } {""} } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo (float16_t a, float16x8_t b)
+{
+  return vsetq_lane (23.26, b, 0);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f32-1.c
new file mode 100644
index 0000000..c5f5db7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsetq_lane_f32-1.c
@@ -0,0 +1,13 @@
+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=soft" } {""} } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo (float32_t a, float32x4_t b)
+{
+    return vsetq_lane (23.34, b, 0);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f16-1.c
new file mode 100644
index 0000000..f3e1961
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t inactive, float16x8_t a, float16_t b, mve_pred16_t p)
+{
+  return vsubq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f32-1.c
new file mode 100644
index 0000000..4b5cd90
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_m_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t inactive, float32x4_t a, float32_t b, mve_pred16_t p)
+{
+  return vsubq_m (inactive, a, 23.23, p);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f16-1.c
new file mode 100644
index 0000000..f883254
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f16-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo1 (float16x8_t a, float16_t b)
+{
+  return vsubq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f32-1.c
new file mode 100644
index 0000000..88d9675
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_n_f32-1.c
@@ -0,0 +1,12 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo1 (float32x4_t a, float32_t b)
+{
+  return vsubq (a, 23.23);
+}
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f16-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f16-1.c
new file mode 100644
index 0000000..b3a67bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f16-1.c
@@ -0,0 +1,13 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float16x8_t
+foo (float16x8_t a, float16_t b, mve_pred16_t p)
+{
+    return vsubq_x_n_f16 (a, 23.23, p);
+}
+
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f32-1.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f32-1.c
new file mode 100644
index 0000000..dcb2425
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vsubq_x_n_f32-1.c
@@ -0,0 +1,13 @@
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+float32x4_t
+foo (float32x4_t a, float32_t b, mve_pred16_t p)
+{
+    return vsubq_x_n_f32 (a, 23.23, p);
+}
+
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */