[AArch64][10/10] ARMv8.2-A FP16 lane scalar intrinsics

gcc/
	* config/aarch64/arm_neon.h (vfmah_lane_f16, vfmah_laneq_f16,
	vfmsh_lane_f16, vfmsh_laneq_f16, vmulh_lane_f16, vmulh_laneq_f16,
	vmulxh_lane_f16, vmulxh_laneq_f16): New.

From-SVN: r238725

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index c1da62a..303e4f5 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,11 @@
 2016-07-25  Jiong Wang  <jiong.wang@arm.com>
 
+       * config/aarch64/arm_neon.h (vfmah_lane_f16, vfmah_laneq_f16,
+       vfmsh_lane_f16, vfmsh_laneq_f16, vmulh_lane_f16, vmulh_laneq_f16,
+       vmulxh_lane_f16, vmulxh_laneq_f16): New.
+
+2016-07-25  Jiong Wang  <jiong.wang@arm.com>
+
        * config/aarch64/aarch64-simd-builtins.def: Register new builtins.
        * config/aarch64/aarch64.md (fma, fnma): Support HF.
        * config/aarch64/arm_fp16.h (vfmah_f16, vfmsh_f16): New.

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index fd55558..ab3a00c 100644 (file)
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -26777,6 +26777,20 @@ vfmsq_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
 
 /* ARMv8.2-A FP16 lane vector intrinsics.  */
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vfmah_lane_f16 (float16_t __a, float16_t __b,
+               float16x4_t __c, const int __lane)
+{
+  return vfmah_f16 (__a, __b, __aarch64_vget_lane_any (__c, __lane));
+}
+
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vfmah_laneq_f16 (float16_t __a, float16_t __b,
+                float16x8_t __c, const int __lane)
+{
+  return vfmah_f16 (__a, __b, __aarch64_vget_lane_any (__c, __lane));
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vfma_lane_f16 (float16x4_t __a, float16x4_t __b,
               float16x4_t __c, const int __lane)
@@ -26817,6 +26831,20 @@ vfmaq_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c)
   return vfmaq_f16 (__a, __b, vdupq_n_f16 (__c));
 }
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vfmsh_lane_f16 (float16_t __a, float16_t __b,
+               float16x4_t __c, const int __lane)
+{
+  return vfmsh_f16 (__a, __b, __aarch64_vget_lane_any (__c, __lane));
+}
+
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vfmsh_laneq_f16 (float16_t __a, float16_t __b,
+                float16x8_t __c, const int __lane)
+{
+  return vfmsh_f16 (__a, __b, __aarch64_vget_lane_any (__c, __lane));
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vfms_lane_f16 (float16x4_t __a, float16x4_t __b,
               float16x4_t __c, const int __lane)
@@ -26857,6 +26885,12 @@ vfmsq_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c)
   return vfmsq_f16 (__a, __b, vdupq_n_f16 (__c));
 }
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vmulh_lane_f16 (float16_t __a, float16x4_t __b, const int __lane)
+{
+  return __a * __aarch64_vget_lane_any (__b, __lane);
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vmul_lane_f16 (float16x4_t __a, float16x4_t __b, const int __lane)
 {
@@ -26869,6 +26903,12 @@ vmulq_lane_f16 (float16x8_t __a, float16x4_t __b, const int __lane)
   return vmulq_f16 (__a, vdupq_n_f16 (__aarch64_vget_lane_any (__b, __lane)));
 }
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vmulh_laneq_f16 (float16_t __a, float16x8_t __b, const int __lane)
+{
+  return __a * __aarch64_vget_lane_any (__b, __lane);
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vmul_laneq_f16 (float16x4_t __a, float16x8_t __b, const int __lane)
 {
@@ -26893,6 +26933,12 @@ vmulq_n_f16 (float16x8_t __a, float16_t __b)
   return vmulq_laneq_f16 (__a, vdupq_n_f16 (__b), 0);
 }
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vmulxh_lane_f16 (float16_t __a, float16x4_t __b, const int __lane)
+{
+  return vmulxh_f16 (__a, __aarch64_vget_lane_any (__b, __lane));
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vmulx_lane_f16 (float16x4_t __a, float16x4_t __b, const int __lane)
 {
@@ -26905,6 +26951,12 @@ vmulxq_lane_f16 (float16x8_t __a, float16x4_t __b, const int __lane)
   return vmulxq_f16 (__a, __aarch64_vdupq_lane_f16 (__b, __lane));
 }
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vmulxh_laneq_f16 (float16_t __a, float16x8_t __b, const int __lane)
+{
+  return vmulxh_f16 (__a, __aarch64_vget_lane_any (__b, __lane));
+}
+
 __extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
 vmulx_laneq_f16 (float16x4_t __a, float16x8_t __b, const int __lane)
 {