diff mbox series

[47/62] AVX512FP16: Add scalar fma instructions.

Message ID 20210701061648.9447-48-hongtao.liu@intel.com
State New
Headers show
Series Support all AVX512FP16 intrinsics. | expand

Commit Message

liuhongt July 1, 2021, 6:16 a.m. UTC
Add vfmadd[132,213,231]sh/vfnmadd[132,213,231]sh/
vfmsub[132,213,231]sh/vfnmsub[132,213,231]sh.

gcc/ChangeLog:

	* config/i386/avx512fp16intrin.h (_mm_fmadd_sh):
	New intrinsic.
	(_mm_mask_fmadd_sh): Likewise.
	(_mm_mask3_fmadd_sh): Likewise.
	(_mm_maskz_fmadd_sh): Likewise.
	(_mm_fmadd_round_sh): Likewise.
	(_mm_mask_fmadd_round_sh): Likewise.
	(_mm_mask3_fmadd_round_sh): Likewise.
	(_mm_maskz_fmadd_round_sh): Likewise.
	(_mm_fnmadd_sh): Likewise.
	(_mm_mask_fnmadd_sh): Likewise.
	(_mm_mask3_fnmadd_sh): Likewise.
	(_mm_maskz_fnmadd_sh): Likewise.
	(_mm_fnmadd_round_sh): Likewise.
	(_mm_mask_fnmadd_round_sh): Likewise.
	(_mm_mask3_fnmadd_round_sh): Likewise.
	(_mm_maskz_fnmadd_round_sh): Likewise.
	(_mm_fmsub_sh): Likewise.
	(_mm_mask_fmsub_sh): Likewise.
	(_mm_mask3_fmsub_sh): Likewise.
	(_mm_maskz_fmsub_sh): Likewise.
	(_mm_fmsub_round_sh): Likewise.
	(_mm_mask_fmsub_round_sh): Likewise.
	(_mm_mask3_fmsub_round_sh): Likewise.
	(_mm_maskz_fmsub_round_sh): Likewise.
	(_mm_fnmsub_sh): Likewise.
	(_mm_mask_fnmsub_sh): Likewise.
	(_mm_mask3_fnmsub_sh): Likewise.
	(_mm_maskz_fnmsub_sh): Likewise.
	(_mm_fnmsub_round_sh): Likewise.
	(_mm_mask_fnmsub_round_sh): Likewise.
	(_mm_mask3_fnmsub_round_sh): Likewise.
	(_mm_maskz_fnmsub_round_sh): Likewise.
	* config/i386/i386-builtin-types.def
	(V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT): New builtin type.
	* config/i386/i386-builtin.def: Add new builtins.
	* config/i386/i386-expand.c: Handle new builtin type.
	* config/i386/sse.md (fmai_vmfmadd_<mode><round_name>):
	Ajdust to support FP16.
	(fmai_vmfmsub_<mode><round_name>): Ditto.
	(fmai_vmfnmadd_<mode><round_name>): Ditto.
	(fmai_vmfnmsub_<mode><round_name>): Ditto.
	(*fmai_fmadd_<mode>): Ditto.
	(*fmai_fmsub_<mode>): Ditto.
	(*fmai_fnmadd_<mode><round_name>): Ditto.
	(*fmai_fnmsub_<mode><round_name>): Ditto.
	(avx512f_vmfmadd_<mode>_mask<round_name>): Ditto.
	(avx512f_vmfmadd_<mode>_mask3<round_name>): Ditto.
	(avx512f_vmfmadd_<mode>_maskz<round_expand_name>): Ditto.
	(avx512f_vmfmadd_<mode>_maskz_1<round_name>): Ditto.
	(*avx512f_vmfmsub_<mode>_mask<round_name>): Ditto.
	(avx512f_vmfmsub_<mode>_mask3<round_name>): Ditto.
	(*avx512f_vmfmsub_<mode>_maskz_1<round_name>): Ditto.
	(*avx512f_vmfnmsub_<mode>_mask<round_name>): Ditto.
	(*avx512f_vmfnmsub_<mode>_mask3<round_name>): Ditto.
	(*avx512f_vmfnmsub_<mode>_mask<round_name>): Ditto.
	(*avx512f_vmfnmadd_<mode>_mask<round_name>): Renamed to ...
	(avx512f_vmfnmadd_<mode>_mask<round_name>) ... this, and
	adjust to support FP16.
	(avx512f_vmfnmadd_<mode>_mask3<round_name>): Ditto.
	(avx512f_vmfnmadd_<mode>_maskz_1<round_name>): Ditto.
	(avx512f_vmfnmadd_<mode>_maskz<round_expand_name>): New
	expander.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx-1.c: Add test for new builtins.
	* gcc.target/i386/sse-13.c: Ditto.
	* gcc.target/i386/sse-23.c: Ditto.
	* gcc.target/i386/sse-14.c: Add test for new intrinsics.
	* gcc.target/i386/sse-22.c: Ditto.
---
 gcc/config/i386/avx512fp16intrin.h     | 412 +++++++++++++++++++++++++
 gcc/config/i386/i386-builtin-types.def |   1 +
 gcc/config/i386/i386-builtin.def       |   7 +
 gcc/config/i386/i386-expand.c          |   1 +
 gcc/config/i386/sse.md                 | 340 ++++++++++----------
 gcc/testsuite/gcc.target/i386/avx-1.c  |  12 +
 gcc/testsuite/gcc.target/i386/sse-13.c |  12 +
 gcc/testsuite/gcc.target/i386/sse-14.c |  16 +
 gcc/testsuite/gcc.target/i386/sse-22.c |  16 +
 gcc/testsuite/gcc.target/i386/sse-23.c |  12 +
 10 files changed, 666 insertions(+), 163 deletions(-)
diff mbox series

Patch

diff --git a/gcc/config/i386/avx512fp16intrin.h b/gcc/config/i386/avx512fp16intrin.h
index f246bab5159..5c85ec15b22 100644
--- a/gcc/config/i386/avx512fp16intrin.h
+++ b/gcc/config/i386/avx512fp16intrin.h
@@ -5697,6 +5697,418 @@  _mm512_maskz_fnmsub_round_ph (__mmask32 __U, __m512h __A, __m512h __B,
 
 #endif /* __OPTIMIZE__ */
 
+/* Intrinsics vfmadd[132,213,231]sh.  */
+extern __inline __m128h
+  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fmadd_sh (__m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask  ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) -1,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmadd_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  (__v8hf) __B,
+						  (__mmask8) __U,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_sh (__mmask8 __U, __m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+
+#ifdef __OPTIMIZE__
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fmadd_round_sh (__m128h __W, __m128h __A, __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  (__v8hf) __B,
+						  (__mmask8) -1,
+						  __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmadd_round_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B,
+			 const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  (__v8hf) __B,
+						  (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmadd_round_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U,
+			  const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmadd_round_sh (__mmask8 __U, __m128h __W, __m128h __A,
+			  __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+#else
+#define _mm_fmadd_round_sh(A, B, C, R)					\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), (B), (C), (-1), (R)))
+#define _mm_mask_fmadd_round_sh(A, U, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), (B), (C), (U), (R)))
+#define _mm_mask3_fmadd_round_sh(A, B, C, U, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask3 ((A), (B), (C), (U), (R)))
+#define _mm_maskz_fmadd_round_sh(U, A, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_maskz ((A), (B), (C), (U), (R)))
+
+#endif /* __OPTIMIZE__ */
+
+/* Intrinsics vfnmadd[132,213,231]sh.  */
+extern __inline __m128h
+  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fnmadd_sh (__m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) -1,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  (__v8hf) __B,
+						  (__mmask8) __U,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_sh (__mmask8 __U, __m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+
+#ifdef __OPTIMIZE__
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fnmadd_round_sh (__m128h __W, __m128h __A, __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) -1,
+						   __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmadd_round_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B,
+			 const int __R)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  (__v8hf) __B,
+						  (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmadd_round_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U,
+			  const int __R)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmadd_round_sh (__mmask8 __U, __m128h __W, __m128h __A,
+			  __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfnmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+#else
+#define _mm_fnmadd_round_sh(A, B, C, R)					\
+  ((__m128h) __builtin_ia32_vfnmaddsh3_mask ((A), (B), (C), (-1), (R)))
+#define _mm_mask_fnmadd_round_sh(A, U, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfnmaddsh3_mask ((A), (B), (C), (U), (R)))
+#define _mm_mask3_fnmadd_round_sh(A, B, C, U, R)				\
+  ((__m128h) __builtin_ia32_vfnmaddsh3_mask3 ((A), (B), (C), (U), (R)))
+#define _mm_maskz_fnmadd_round_sh(U, A, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfnmaddsh3_maskz ((A), (B), (C), (U), (R)))
+
+#endif /* __OPTIMIZE__ */
+
+/* Intrinsics vfmsub[132,213,231]sh.  */
+extern __inline __m128h
+  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fmsub_sh (__m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) -1,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) __U,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U)
+{
+  return (__m128h) __builtin_ia32_vfmsubsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_sh (__mmask8 __U, __m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   -(__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+
+#ifdef __OPTIMIZE__
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fmsub_round_sh (__m128h __W, __m128h __A, __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) -1,
+						  __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fmsub_round_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B,
+			 const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  (__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fmsub_round_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U,
+			  const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmsubsh3_mask3 ((__v8hf) __W,
+						   (__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fmsub_round_sh (__mmask8 __U, __m128h __W, __m128h __A,
+			  __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   (__v8hf) __A,
+						   -(__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+#else
+#define _mm_fmsub_round_sh(A, B, C, R)					\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), (B), -(C), (-1), (R)))
+#define _mm_mask_fmsub_round_sh(A, U, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), (B), -(C), (U), (R)))
+#define _mm_mask3_fmsub_round_sh(A, B, C, U, R)				\
+  ((__m128h) __builtin_ia32_vfmsubsh3_mask3 ((A), (B), (C), (U), (R)))
+#define _mm_maskz_fmsub_round_sh(U, A, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_maskz ((A), (B), -(C), (U), (R)))
+
+#endif /* __OPTIMIZE__ */
+
+/* Intrinsics vfnmsub[132,213,231]sh.  */
+extern __inline __m128h
+  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fnmsub_sh (__m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  -(__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) -1,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  -(__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) __U,
+						  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U)
+{
+  return (__m128h) __builtin_ia32_vfmsubsh3_mask3 ((__v8hf) __W,
+						   -(__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_sh (__mmask8 __U, __m128h __W, __m128h __A, __m128h __B)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   -(__v8hf) __A,
+						   -(__v8hf) __B,
+						   (__mmask8) __U,
+						   _MM_FROUND_CUR_DIRECTION);
+}
+
+
+#ifdef __OPTIMIZE__
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fnmsub_round_sh (__m128h __W, __m128h __A, __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  -(__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) -1,
+						  __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fnmsub_round_sh (__m128h __W, __mmask8 __U, __m128h __A, __m128h __B,
+			 const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_mask ((__v8hf) __W,
+						  -(__v8hf) __A,
+						  -(__v8hf) __B,
+						  (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask3_fnmsub_round_sh (__m128h __W, __m128h __A, __m128h __B, __mmask8 __U,
+			  const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmsubsh3_mask3 ((__v8hf) __W,
+						   -(__v8hf) __A,
+						   (__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fnmsub_round_sh (__mmask8 __U, __m128h __W, __m128h __A,
+			  __m128h __B, const int __R)
+{
+  return (__m128h) __builtin_ia32_vfmaddsh3_maskz ((__v8hf) __W,
+						   -(__v8hf) __A,
+						   -(__v8hf) __B,
+						   (__mmask8) __U, __R);
+}
+
+#else
+#define _mm_fnmsub_round_sh(A, B, C, R)					\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), -(B), -(C), (-1), (R)))
+#define _mm_mask_fnmsub_round_sh(A, U, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_mask ((A), -(B), -(C), (U), (R)))
+#define _mm_mask3_fnmsub_round_sh(A, B, C, U, R)				\
+  ((__m128h) __builtin_ia32_vfmsubsh3_mask3 ((A), -(B), (C), (U), (R)))
+#define _mm_maskz_fnmsub_round_sh(U, A, B, C, R)				\
+  ((__m128h) __builtin_ia32_vfmaddsh3_maskz ((A), -(B), -(C), (U), (R)))
+
+#endif /* __OPTIMIZE__ */
+
 #ifdef __DISABLE_AVX512FP16__
 #undef __DISABLE_AVX512FP16__
 #pragma GCC pop_options
diff --git a/gcc/config/i386/i386-builtin-types.def b/gcc/config/i386/i386-builtin-types.def
index 0cdbf1bc0c0..22b924bf98d 100644
--- a/gcc/config/i386/i386-builtin-types.def
+++ b/gcc/config/i386/i386-builtin-types.def
@@ -1342,6 +1342,7 @@  DEF_FUNCTION_TYPE (V8HF, V8HF, V8HF, INT)
 DEF_FUNCTION_TYPE (V8HF, V8HF, INT, V8HF, UQI)
 DEF_FUNCTION_TYPE (UQI, V8HF, V8HF, INT, UQI)
 DEF_FUNCTION_TYPE (V8HF, V8HF, V8HF, V8HF, UQI)
+DEF_FUNCTION_TYPE (V8HF, V8HF, V8HF, V8HF, INT)
 DEF_FUNCTION_TYPE (UQI, V8HF, V8HF, INT, UQI, INT)
 DEF_FUNCTION_TYPE (V8DI, V8HF, V8DI, UQI, INT)
 DEF_FUNCTION_TYPE (V8DF, V8HF, V8DF, UQI, INT)
diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index cf0259843cc..f446a6ce5d3 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -3194,6 +3194,13 @@  BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_fmsub_v32hf_maskz_round
 BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_fnmsub_v32hf_mask_round, "__builtin_ia32_vfnmsubph512_mask", IX86_BUILTIN_VFNMSUBPH512_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
 BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_fnmsub_v32hf_mask3_round, "__builtin_ia32_vfnmsubph512_mask3", IX86_BUILTIN_VFNMSUBPH512_MASK3, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
 BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_fnmsub_v32hf_maskz_round, "__builtin_ia32_vfnmsubph512_maskz", IX86_BUILTIN_VFNMSUBPH512_MASKZ, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfmadd_v8hf_mask_round, "__builtin_ia32_vfmaddsh3_mask", IX86_BUILTIN_VFMADDSH3_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfmadd_v8hf_mask3_round, "__builtin_ia32_vfmaddsh3_mask3", IX86_BUILTIN_VFMADDSH3_MASK3, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfmadd_v8hf_maskz_round, "__builtin_ia32_vfmaddsh3_maskz", IX86_BUILTIN_VFMADDSH3_MASKZ, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfnmadd_v8hf_mask_round, "__builtin_ia32_vfnmaddsh3_mask", IX86_BUILTIN_VFNMADDSH3_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfnmadd_v8hf_mask3_round, "__builtin_ia32_vfnmaddsh3_mask3", IX86_BUILTIN_VFNMADDSH3_MASK3, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfnmadd_v8hf_maskz_round, "__builtin_ia32_vfnmaddsh3_maskz", IX86_BUILTIN_VFNMADDSH3_MASKZ, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmfmsub_v8hf_mask3_round, "__builtin_ia32_vfmsubsh3_mask3", IX86_BUILTIN_VFMSUBSH3_MASK3, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
 
 BDESC_END (ROUND_ARGS, MULTI_ARG)
 
diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 006f4bec8db..f6de05c769a 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -10558,6 +10558,7 @@  ix86_expand_round_builtin (const struct builtin_description *d,
     case V8HF_FTYPE_V8DI_V8HF_UQI_INT:
     case V8HF_FTYPE_V8DF_V8HF_UQI_INT:
     case V16HF_FTYPE_V16SF_V16HF_UHI_INT:
+    case V8HF_FTYPE_V8HF_V8HF_V8HF_INT:
       nargs = 4;
       break;
     case V4SF_FTYPE_V4SF_V4SF_INT_INT:
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index cbf1e75c0b2..31f8fc68c65 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -5049,60 +5049,60 @@  (define_insn "<avx512>_fmsubadd_<mode>_mask3<round_name>"
 ;; high-order elements from the destination register.
 
 (define_expand "fmai_vmfmadd_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand")
-	(vec_merge:VF_128
-	  (fma:VF_128
-	    (match_operand:VF_128 1 "register_operand")
-	    (match_operand:VF_128 2 "<round_nimm_scalar_predicate>")
-	    (match_operand:VF_128 3 "<round_nimm_scalar_predicate>"))
+  [(set (match_operand:VFH_128 0 "register_operand")
+	(vec_merge:VFH_128
+	  (fma:VFH_128
+	    (match_operand:VFH_128 1 "register_operand")
+	    (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>")
+	    (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>"))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA")
 
 (define_expand "fmai_vmfmsub_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand")
-	(vec_merge:VF_128
-	  (fma:VF_128
-	    (match_operand:VF_128 1 "register_operand")
-	    (match_operand:VF_128 2 "<round_nimm_scalar_predicate>")
-	    (neg:VF_128
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>")))
+  [(set (match_operand:VFH_128 0 "register_operand")
+	(vec_merge:VFH_128
+	  (fma:VFH_128
+	    (match_operand:VFH_128 1 "register_operand")
+	    (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>")
+	    (neg:VFH_128
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>")))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA")
 
 (define_expand "fmai_vmfnmadd_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand")
-	(vec_merge:VF_128
-	  (fma:VF_128
-	    (neg:VF_128
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>"))
-	    (match_operand:VF_128 1 "register_operand")
-	    (match_operand:VF_128 3 "<round_nimm_scalar_predicate>"))
+  [(set (match_operand:VFH_128 0 "register_operand")
+	(vec_merge:VFH_128
+	  (fma:VFH_128
+	    (neg:VFH_128
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>"))
+	    (match_operand:VFH_128 1 "register_operand")
+	    (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>"))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA")
 
 (define_expand "fmai_vmfnmsub_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand")
-	(vec_merge:VF_128
-	  (fma:VF_128
-	    (neg:VF_128
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>"))
-	    (match_operand:VF_128 1 "register_operand")
-	    (neg:VF_128
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>")))
+  [(set (match_operand:VFH_128 0 "register_operand")
+	(vec_merge:VFH_128
+	  (fma:VFH_128
+	    (neg:VFH_128
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>"))
+	    (match_operand:VFH_128 1 "register_operand")
+	    (neg:VFH_128
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>")))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA")
 
 (define_insn "*fmai_fmadd_<mode>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-        (vec_merge:VF_128
-	  (fma:VF_128
-	    (match_operand:VF_128 1 "register_operand" "0,0")
-	    (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>, v")
-	    (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+        (vec_merge:VFH_128
+	  (fma:VFH_128
+	    (match_operand:VFH_128 1 "register_operand" "0,0")
+	    (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>, v")
+	    (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA || TARGET_AVX512F"
@@ -5113,13 +5113,13 @@  (define_insn "*fmai_fmadd_<mode>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*fmai_fmsub_<mode>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-        (vec_merge:VF_128
-	  (fma:VF_128
-	    (match_operand:VF_128   1 "register_operand" "0,0")
-	    (match_operand:VF_128   2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
-	    (neg:VF_128
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+        (vec_merge:VFH_128
+	  (fma:VFH_128
+	    (match_operand:VFH_128   1 "register_operand" "0,0")
+	    (match_operand:VFH_128   2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
+	    (neg:VFH_128
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA || TARGET_AVX512F"
@@ -5130,13 +5130,13 @@  (define_insn "*fmai_fmsub_<mode>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*fmai_fnmadd_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-        (vec_merge:VF_128
-	  (fma:VF_128
-	    (neg:VF_128
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	    (match_operand:VF_128   1 "register_operand" "0,0")
-	    (match_operand:VF_128   3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+        (vec_merge:VFH_128
+	  (fma:VFH_128
+	    (neg:VFH_128
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	    (match_operand:VFH_128   1 "register_operand" "0,0")
+	    (match_operand:VFH_128   3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA || TARGET_AVX512F"
@@ -5147,14 +5147,14 @@  (define_insn "*fmai_fnmadd_<mode><round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*fmai_fnmsub_<mode><round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-        (vec_merge:VF_128
-	  (fma:VF_128
-	    (neg:VF_128
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	    (match_operand:VF_128   1 "register_operand" "0,0")
-	    (neg:VF_128
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+        (vec_merge:VFH_128
+	  (fma:VFH_128
+	    (neg:VFH_128
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	    (match_operand:VFH_128   1 "register_operand" "0,0")
+	    (neg:VFH_128
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_FMA || TARGET_AVX512F"
@@ -5165,13 +5165,13 @@  (define_insn "*fmai_fnmsub_<mode><round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "avx512f_vmfmadd_<mode>_mask<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
 	    (match_dup 1)
 	    (match_operand:QI 4 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
@@ -5184,13 +5184,13 @@  (define_insn "avx512f_vmfmadd_<mode>_mask<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "avx512f_vmfmadd_<mode>_mask3<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "<round_nimm_scalar_predicate>" "%v")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>")
-	      (match_operand:VF_128 3 "register_operand" "0"))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "<round_nimm_scalar_predicate>" "%v")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>")
+	      (match_operand:VFH_128 3 "register_operand" "0"))
 	    (match_dup 3)
 	    (match_operand:QI 4 "register_operand" "Yk"))
 	  (match_dup 3)
@@ -5201,10 +5201,10 @@  (define_insn "avx512f_vmfmadd_<mode>_mask3<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_expand "avx512f_vmfmadd_<mode>_maskz<round_expand_name>"
-  [(match_operand:VF_128 0 "register_operand")
-   (match_operand:VF_128 1 "<round_expand_nimm_predicate>")
-   (match_operand:VF_128 2 "<round_expand_nimm_predicate>")
-   (match_operand:VF_128 3 "<round_expand_nimm_predicate>")
+  [(match_operand:VFH_128 0 "register_operand")
+   (match_operand:VFH_128 1 "<round_expand_nimm_predicate>")
+   (match_operand:VFH_128 2 "<round_expand_nimm_predicate>")
+   (match_operand:VFH_128 3 "<round_expand_nimm_predicate>")
    (match_operand:QI 4 "register_operand")]
   "TARGET_AVX512F"
 {
@@ -5215,14 +5215,14 @@  (define_expand "avx512f_vmfmadd_<mode>_maskz<round_expand_name>"
 })
 
 (define_insn "avx512f_vmfmadd_<mode>_maskz_1<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
-	    (match_operand:VF_128 4 "const0_operand" "C,C")
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+	    (match_operand:VFH_128 4 "const0_operand" "C,C")
 	    (match_operand:QI 5 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
 	  (const_int 1)))]
@@ -5234,14 +5234,14 @@  (define_insn "avx512f_vmfmadd_<mode>_maskz_1<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*avx512f_vmfmsub_<mode>_mask<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
 	    (match_dup 1)
 	    (match_operand:QI 4 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
@@ -5254,14 +5254,14 @@  (define_insn "*avx512f_vmfmsub_<mode>_mask<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "avx512f_vmfmsub_<mode>_mask3<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "<round_nimm_scalar_predicate>" "%v")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "register_operand" "0")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "<round_nimm_scalar_predicate>" "%v")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "register_operand" "0")))
 	    (match_dup 3)
 	    (match_operand:QI 4 "register_operand" "Yk"))
 	  (match_dup 3)
@@ -5272,15 +5272,15 @@  (define_insn "avx512f_vmfmsub_<mode>_mask3<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*avx512f_vmfmsub_<mode>_maskz_1<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
-	    (match_operand:VF_128 4 "const0_operand" "C,C")
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+	    (match_operand:VFH_128 4 "const0_operand" "C,C")
 	    (match_operand:QI 5 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
 	  (const_int 1)))]
@@ -5291,15 +5291,15 @@  (define_insn "*avx512f_vmfmsub_<mode>_maskz_1<round_name>"
   [(set_attr "type" "ssemuladd")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*avx512f_vmfnmadd_<mode>_mask<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+(define_insn "avx512f_vmfnmadd_<mode>_mask<round_name>"
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
 	    (match_dup 1)
 	    (match_operand:QI 4 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
@@ -5311,15 +5311,15 @@  (define_insn "*avx512f_vmfnmadd_<mode>_mask<round_name>"
   [(set_attr "type" "ssemuladd")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*avx512f_vmfnmadd_<mode>_mask3<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>"))
-	      (match_operand:VF_128 1 "<round_nimm_scalar_predicate>" "%v")
-	      (match_operand:VF_128 3 "register_operand" "0"))
+(define_insn "avx512f_vmfnmadd_<mode>_mask3<round_name>"
+  [(set (match_operand:VFH_128 0 "register_operand" "=v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>"))
+	      (match_operand:VFH_128 1 "<round_nimm_scalar_predicate>" "%v")
+	      (match_operand:VFH_128 3 "register_operand" "0"))
 	    (match_dup 3)
 	    (match_operand:QI 4 "register_operand" "Yk"))
 	  (match_dup 3)
@@ -5329,16 +5329,30 @@  (define_insn "*avx512f_vmfnmadd_<mode>_mask3<round_name>"
   [(set_attr "type" "ssemuladd")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*avx512f_vmfnmadd_<mode>_maskz_1<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
-	    (match_operand:VF_128 4 "const0_operand" "C,C")
+(define_expand "avx512f_vmfnmadd_<mode>_maskz<round_expand_name>"
+  [(match_operand:VFH_128 0 "register_operand")
+   (match_operand:VFH_128 1 "<round_expand_nimm_predicate>")
+   (match_operand:VFH_128 2 "<round_expand_nimm_predicate>")
+   (match_operand:VFH_128 3 "<round_expand_nimm_predicate>")
+   (match_operand:QI 4 "register_operand")]
+  "TARGET_AVX512F"
+{
+  emit_insn (gen_avx512f_vmfnmadd_<mode>_maskz_1<round_expand_name> (
+    operands[0], operands[1], operands[2], operands[3],
+    CONST0_RTX (<MODE>mode), operands[4]<round_expand_operand>));
+  DONE;
+})
+
+(define_insn "avx512f_vmfnmadd_<mode>_maskz_1<round_name>"
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>"))
+	    (match_operand:VFH_128 4 "const0_operand" "C,C")
 	    (match_operand:QI 5 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
 	  (const_int 1)))]
@@ -5350,15 +5364,15 @@  (define_insn "*avx512f_vmfnmadd_<mode>_maskz_1<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*avx512f_vmfnmsub_<mode>_mask<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
 	    (match_dup 1)
 	    (match_operand:QI 4 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
@@ -5371,15 +5385,15 @@  (define_insn "*avx512f_vmfnmsub_<mode>_mask<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*avx512f_vmfnmsub_<mode>_mask3<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>"))
-	      (match_operand:VF_128 1 "<round_nimm_scalar_predicate>" "%v")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "register_operand" "0")))
+  [(set (match_operand:VFH_128 0 "register_operand" "=v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>"))
+	      (match_operand:VFH_128 1 "<round_nimm_scalar_predicate>" "%v")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "register_operand" "0")))
 	    (match_dup 3)
 	    (match_operand:QI 4 "register_operand" "Yk"))
 	  (match_dup 3)
@@ -5390,16 +5404,16 @@  (define_insn "*avx512f_vmfnmsub_<mode>_mask3<round_name>"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*avx512f_vmfnmsub_<mode>_maskz_1<round_name>"
-  [(set (match_operand:VF_128 0 "register_operand" "=v,v")
-	(vec_merge:VF_128
-	  (vec_merge:VF_128
-	    (fma:VF_128
-	      (neg:VF_128
-		(match_operand:VF_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
-	      (match_operand:VF_128 1 "register_operand" "0,0")
-	      (neg:VF_128
-		(match_operand:VF_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
-	    (match_operand:VF_128 4 "const0_operand" "C,C")
+  [(set (match_operand:VFH_128 0 "register_operand" "=v,v")
+	(vec_merge:VFH_128
+	  (vec_merge:VFH_128
+	    (fma:VFH_128
+	      (neg:VFH_128
+		(match_operand:VFH_128 2 "<round_nimm_scalar_predicate>" "<round_constraint>,v"))
+	      (match_operand:VFH_128 1 "register_operand" "0,0")
+	      (neg:VFH_128
+		(match_operand:VFH_128 3 "<round_nimm_scalar_predicate>" "v,<round_constraint>")))
+	    (match_operand:VFH_128 4 "const0_operand" "C,C")
 	    (match_operand:QI 5 "register_operand" "Yk,Yk"))
 	  (match_dup 1)
 	  (const_int 1)))]
diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c b/gcc/testsuite/gcc.target/i386/avx-1.c
index d2ab16538d8..6c2d1dc3df4 100644
--- a/gcc/testsuite/gcc.target/i386/avx-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx-1.c
@@ -775,6 +775,18 @@ 
 #define __builtin_ia32_vfnmsubph512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, 8)
 
 /* avx512fp16vlintrin.h */
 #define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c b/gcc/testsuite/gcc.target/i386/sse-13.c
index 49c72f6fcef..f16be008909 100644
--- a/gcc/testsuite/gcc.target/i386/sse-13.c
+++ b/gcc/testsuite/gcc.target/i386/sse-13.c
@@ -792,6 +792,18 @@ 
 #define __builtin_ia32_vfnmsubph512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, 8)
 
 /* avx512fp16vlintrin.h */
 #define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c b/gcc/testsuite/gcc.target/i386/sse-14.c
index 9151e50afd2..01ac4e04173 100644
--- a/gcc/testsuite/gcc.target/i386/sse-14.c
+++ b/gcc/testsuite/gcc.target/i386/sse-14.c
@@ -842,6 +842,10 @@  test_3 (_mm512_fmadd_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fnmadd_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fmsub_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fnmsub_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
+test_3 (_mm_fmadd_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fnmadd_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fmsub_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fnmsub_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
 test_3x (_mm512_mask_cmp_round_ph_mask, __mmask32, __mmask32, __m512h, __m512h, 1, 8)
 test_3x (_mm_mask_cmp_round_sh_mask, __mmask8, __mmask8, __m128h, __m128h, 1, 8)
 test_3x (_mm512_mask_reduce_round_ph, __m512h, __m512h, __mmask32, __m512h, 123, 8)
@@ -892,6 +896,18 @@  test_4 (_mm512_maskz_fmsub_round_ph, __m512h, __mmask32, __m512h, __m512h, __m51
 test_4 (_mm512_mask_fnmsub_round_ph, __m512h, __m512h, __mmask32, __m512h, __m512h, 9)
 test_4 (_mm512_mask3_fnmsub_round_ph, __m512h, __m512h, __m512h, __m512h, __mmask32, 9)
 test_4 (_mm512_maskz_fnmsub_round_ph, __m512h, __mmask32, __m512h, __m512h, __m512h, 9)
+test_4 (_mm_mask_fmadd_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fmadd_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fmadd_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fnmadd_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fnmadd_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fnmadd_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fmsub_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fmsub_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fmsub_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fnmsub_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fnmsub_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fnmsub_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
 test_4x (_mm_mask_reduce_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 123, 8)
 test_4x (_mm_mask_roundscale_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 123, 8)
 test_4x (_mm_mask_getmant_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 1, 1)
diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c
index 892b6334ae2..79e3f35ab86 100644
--- a/gcc/testsuite/gcc.target/i386/sse-22.c
+++ b/gcc/testsuite/gcc.target/i386/sse-22.c
@@ -945,6 +945,10 @@  test_3 (_mm512_fmadd_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fnmadd_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fmsub_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
 test_3 (_mm512_fnmsub_round_ph, __m512h, __m512h, __m512h, __m512h, 9)
+test_3 (_mm_fmadd_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fnmadd_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fmsub_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
+test_3 (_mm_fnmsub_round_sh, __m128h, __m128h, __m128h, __m128h, 9)
 test_3x (_mm512_mask_cmp_round_ph_mask, __mmask32, __mmask32, __m512h, __m512h, 1, 8)
 test_3x (_mm_mask_cmp_round_sh_mask, __mmask8, __mmask8, __m128h, __m128h, 1, 8)
 test_3x (_mm512_mask_reduce_round_ph, __m512h, __m512h, __mmask32, __m512h, 123, 8)
@@ -994,6 +998,18 @@  test_4 (_mm512_maskz_fmsub_round_ph, __m512h, __mmask32, __m512h, __m512h, __m51
 test_4 (_mm512_mask_fnmsub_round_ph, __m512h, __m512h, __mmask32, __m512h, __m512h, 9)
 test_4 (_mm512_mask3_fnmsub_round_ph, __m512h, __m512h, __m512h, __m512h, __mmask32, 9)
 test_4 (_mm512_maskz_fnmsub_round_ph, __m512h, __mmask32, __m512h, __m512h, __m512h, 9)
+test_4 (_mm_mask_fmadd_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fmadd_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fmadd_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fnmadd_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fnmadd_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fnmadd_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fmsub_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fmsub_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fmsub_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
+test_4 (_mm_mask_fnmsub_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 9)
+test_4 (_mm_mask3_fnmsub_round_sh, __m128h, __m128h, __m128h, __m128h, __mmask8, 9)
+test_4 (_mm_maskz_fnmsub_round_sh, __m128h, __mmask8, __m128h, __m128h, __m128h, 9)
 test_4x (_mm_mask_reduce_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 123, 8)
 test_4x (_mm_mask_roundscale_round_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 123, 8)
 test_4x (_mm_mask_getmant_sh, __m128h, __m128h, __mmask8, __m128h, __m128h, 1, 1)
diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c
index 447b83829f3..caf14408b91 100644
--- a/gcc/testsuite/gcc.target/i386/sse-23.c
+++ b/gcc/testsuite/gcc.target/i386/sse-23.c
@@ -793,6 +793,18 @@ 
 #define __builtin_ia32_vfnmsubph512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubph512_mask3(A, B, C, D, 8)
 #define __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubph512_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmaddsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfmsubsh3_maskz(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_mask3(A, B, C, D, 8)
+#define __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, E) __builtin_ia32_vfnmsubsh3_maskz(A, B, C, D, 8)
 
 /* avx512fp16vlintrin.h */
 #define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)