i386: Fix vpblendm{b,w} intrins and insns

For vpblendm{b,w}, they actually do not have constant parameters.
Therefore, there is no need for them been wrapped in __OPTIMIZE__.

Also, we should check TARGET_AVX512VL for 128/256 bit vectors.

gcc/ChangeLog:

	* config/i386/avx512vlbwintrin.h
	(_mm_mask_blend_epi16): Remove __OPTIMIZE__ wrapper.
	(_mm_mask_blend_epi8): Ditto.
	(_mm256_mask_blend_epi16): Ditto.
	(_mm256_mask_blend_epi8): Ditto.
	* config/i386/avx512vlintrin.h
	(_mm256_mask_blend_pd): Ditto.
	(_mm256_mask_blend_ps): Ditto.
	(_mm256_mask_blend_epi64): Ditto.
	(_mm256_mask_blend_epi32): Ditto.
	(_mm_mask_blend_pd): Ditto.
	(_mm_mask_blend_ps): Ditto.
	(_mm_mask_blend_epi64): Ditto.
	(_mm_mask_blend_epi32): Ditto.
	* config/i386/sse.md (VF_AVX512BWHFBF16): Removed.
	(VF_AVX512HFBFVL): Move it before the first usage.
	(<avx512>_blendm<mode>): Change iterator from VF_AVX512BWHFBF16
	to VF_AVX512HFBFVL.

3 files changed, 115 insertions, 178 deletions

diff --git a/gcc/config/i386/avx512vlbwintrin.h b/gcc/config/i386/avx512vlbwintrin.h
index 0232783..9d2aba2 100644
--- a/gcc/config/i386/avx512vlbwintrin.h
+++ b/gcc/config/i386/avx512vlbwintrin.h
@@ -259,6 +259,42 @@ _mm_maskz_loadu_epi8 (__mmask16 __U, void const *__P)
 
 extern __inline __m128i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_epi16 (__mmask8 __U, __m128i __A, __m128i __W)
+{
+  return (__m128i) __builtin_ia32_blendmw_128_mask ((__v8hi) __A,
+						    (__v8hi) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_epi8 (__mmask16 __U, __m128i __A, __m128i __W)
+{
+  return (__m128i) __builtin_ia32_blendmb_128_mask ((__v16qi) __A,
+						    (__v16qi) __W,
+						    (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_epi16 (__mmask16 __U, __m256i __A, __m256i __W)
+{
+  return (__m256i) __builtin_ia32_blendmw_256_mask ((__v16hi) __A,
+						    (__v16hi) __W,
+						    (__mmask16) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_epi8 (__mmask32 __U, __m256i __A, __m256i __W)
+{
+  return (__m256i) __builtin_ia32_blendmb_256_mask ((__v32qi) __A,
+						    (__v32qi) __W,
+						    (__mmask32) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cvtepi16_epi8 (__m256i __A)
 {
 
@@ -1442,42 +1478,6 @@ _mm_maskz_dbsad_epu8 (__mmask8 __U, __m128i __A, __m128i __B,
 						    (__mmask8) __U);
 }
 
-extern __inline __m128i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_epi16 (__mmask8 __U, __m128i __A, __m128i __W)
-{
-  return (__m128i) __builtin_ia32_blendmw_128_mask ((__v8hi) __A,
-						    (__v8hi) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m128i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_epi8 (__mmask16 __U, __m128i __A, __m128i __W)
-{
-  return (__m128i) __builtin_ia32_blendmb_128_mask ((__v16qi) __A,
-						    (__v16qi) __W,
-						    (__mmask16) __U);
-}
-
-extern __inline __m256i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_epi16 (__mmask16 __U, __m256i __A, __m256i __W)
-{
-  return (__m256i) __builtin_ia32_blendmw_256_mask ((__v16hi) __A,
-						    (__v16hi) __W,
-						    (__mmask16) __U);
-}
-
-extern __inline __m256i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_epi8 (__mmask32 __U, __m256i __A, __m256i __W)
-{
-  return (__m256i) __builtin_ia32_blendmb_256_mask ((__v32qi) __A,
-						    (__v32qi) __W,
-						    (__mmask32) __U);
-}
-
 extern __inline __mmask8
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_mask_cmp_epi16_mask (__mmask8 __U, __m128i __X, __m128i __Y,
@@ -1986,26 +1986,6 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B)
                                               (__v8hi)(__m128i)_mm_setzero_si128(), \
                                               (__mmask8)(U)))
 
-#define _mm_mask_blend_epi16(__U, __A, __W)			      \
-  ((__m128i) __builtin_ia32_blendmw_128_mask ((__v8hi) (__A),	      \
-						    (__v8hi) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm_mask_blend_epi8(__U, __A, __W)			      \
-  ((__m128i) __builtin_ia32_blendmb_128_mask ((__v16qi) (__A),	      \
-						    (__v16qi) (__W),  \
-						    (__mmask16) (__U)))
-
-#define _mm256_mask_blend_epi16(__U, __A, __W)			      \
-  ((__m256i) __builtin_ia32_blendmw_256_mask ((__v16hi) (__A),	      \
-						    (__v16hi) (__W),  \
-						    (__mmask16) (__U)))
-
-#define _mm256_mask_blend_epi8(__U, __A, __W)			      \
-  ((__m256i) __builtin_ia32_blendmb_256_mask ((__v32qi) (__A),	      \
-						    (__v32qi) (__W),  \
-						    (__mmask32) (__U)))
-
 #define _mm_cmp_epi16_mask(X, Y, P)				\
   ((__mmask8) __builtin_ia32_cmpw128_mask ((__v8hi)(__m128i)(X),	\
 					    (__v8hi)(__m128i)(Y), (int)(P),\
diff --git a/gcc/config/i386/avx512vlintrin.h b/gcc/config/i386/avx512vlintrin.h
index 758b71a..4a717a7 100644
--- a/gcc/config/i386/avx512vlintrin.h
+++ b/gcc/config/i386/avx512vlintrin.h
@@ -935,6 +935,78 @@ _mm_mask_storeu_epi32 (void *__P, __mmask8 __U, __m128i __A)
 				     (__mmask8) __U);
 }
 
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_pd (__mmask8 __U, __m256d __A, __m256d __W)
+{
+  return (__m256d) __builtin_ia32_blendmpd_256_mask ((__v4df) __A,
+						     (__v4df) __W,
+						     (__mmask8) __U);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_ps (__mmask8 __U, __m256 __A, __m256 __W)
+{
+  return (__m256) __builtin_ia32_blendmps_256_mask ((__v8sf) __A,
+						    (__v8sf) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_epi64 (__mmask8 __U, __m256i __A, __m256i __W)
+{
+  return (__m256i) __builtin_ia32_blendmq_256_mask ((__v4di) __A,
+						    (__v4di) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_blend_epi32 (__mmask8 __U, __m256i __A, __m256i __W)
+{
+  return (__m256i) __builtin_ia32_blendmd_256_mask ((__v8si) __A,
+						    (__v8si) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_pd (__mmask8 __U, __m128d __A, __m128d __W)
+{
+  return (__m128d) __builtin_ia32_blendmpd_128_mask ((__v2df) __A,
+						     (__v2df) __W,
+						     (__mmask8) __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_ps (__mmask8 __U, __m128 __A, __m128 __W)
+{
+  return (__m128) __builtin_ia32_blendmps_128_mask ((__v4sf) __A,
+						    (__v4sf) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_epi64 (__mmask8 __U, __m128i __A, __m128i __W)
+{
+  return (__m128i) __builtin_ia32_blendmq_128_mask ((__v2di) __A,
+						    (__v2di) __W,
+						    (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_blend_epi32 (__mmask8 __U, __m128i __A, __m128i __W)
+{
+  return (__m128i) __builtin_ia32_blendmd_128_mask ((__v4si) __A,
+						    (__v4si) __W,
+						    (__mmask8) __U);
+}
+
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_mask_abs_epi32 (__m256i __W, __mmask8 __U, __m256i __A)
@@ -12262,78 +12334,6 @@ _mm_maskz_permute_ps (__mmask8 __U, __m128 __X, const int __C)
 						 (__mmask8) __U);
 }
 
-extern __inline __m256d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_pd (__mmask8 __U, __m256d __A, __m256d __W)
-{
-  return (__m256d) __builtin_ia32_blendmpd_256_mask ((__v4df) __A,
-						     (__v4df) __W,
-						     (__mmask8) __U);
-}
-
-extern __inline __m256
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_ps (__mmask8 __U, __m256 __A, __m256 __W)
-{
-  return (__m256) __builtin_ia32_blendmps_256_mask ((__v8sf) __A,
-						    (__v8sf) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m256i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_epi64 (__mmask8 __U, __m256i __A, __m256i __W)
-{
-  return (__m256i) __builtin_ia32_blendmq_256_mask ((__v4di) __A,
-						    (__v4di) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m256i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_blend_epi32 (__mmask8 __U, __m256i __A, __m256i __W)
-{
-  return (__m256i) __builtin_ia32_blendmd_256_mask ((__v8si) __A,
-						    (__v8si) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m128d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_pd (__mmask8 __U, __m128d __A, __m128d __W)
-{
-  return (__m128d) __builtin_ia32_blendmpd_128_mask ((__v2df) __A,
-						     (__v2df) __W,
-						     (__mmask8) __U);
-}
-
-extern __inline __m128
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_ps (__mmask8 __U, __m128 __A, __m128 __W)
-{
-  return (__m128) __builtin_ia32_blendmps_128_mask ((__v4sf) __A,
-						    (__v4sf) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m128i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_epi64 (__mmask8 __U, __m128i __A, __m128i __W)
-{
-  return (__m128i) __builtin_ia32_blendmq_128_mask ((__v2di) __A,
-						    (__v2di) __W,
-						    (__mmask8) __U);
-}
-
-extern __inline __m128i
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_blend_epi32 (__mmask8 __U, __m128i __A, __m128i __W)
-{
-  return (__m128i) __builtin_ia32_blendmd_128_mask ((__v4si) __A,
-						    (__v4si) __W,
-						    (__mmask8) __U);
-}
-
 extern __inline __mmask8
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmp_epi64_mask (__m256i __X, __m256i __Y, const int __P)
@@ -13717,46 +13717,6 @@ _mm256_permutex_pd (__m256d __X, const int __M)
 					  (__v4sf)(__m128)_mm_setzero_ps (),	    \
 					  (__mmask8)(U)))
 
-#define _mm256_mask_blend_pd(__U, __A, __W)			      \
-  ((__m256d) __builtin_ia32_blendmpd_256_mask ((__v4df) (__A),	      \
-						     (__v4df) (__W),  \
-						     (__mmask8) (__U)))
-
-#define _mm256_mask_blend_ps(__U, __A, __W)			      \
-  ((__m256) __builtin_ia32_blendmps_256_mask ((__v8sf) (__A),	      \
-						    (__v8sf) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm256_mask_blend_epi64(__U, __A, __W)			      \
-  ((__m256i) __builtin_ia32_blendmq_256_mask ((__v4di) (__A),	      \
-						    (__v4di) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm256_mask_blend_epi32(__U, __A, __W)			      \
-  ((__m256i) __builtin_ia32_blendmd_256_mask ((__v8si) (__A),	      \
-						    (__v8si) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm_mask_blend_pd(__U, __A, __W)			      \
-  ((__m128d) __builtin_ia32_blendmpd_128_mask ((__v2df) (__A),	      \
-						     (__v2df) (__W),  \
-						     (__mmask8) (__U)))
-
-#define _mm_mask_blend_ps(__U, __A, __W)			      \
-  ((__m128) __builtin_ia32_blendmps_128_mask ((__v4sf) (__A),	      \
-						    (__v4sf) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm_mask_blend_epi64(__U, __A, __W)			      \
-  ((__m128i) __builtin_ia32_blendmq_128_mask ((__v2di) (__A),	      \
-						    (__v2di) (__W),   \
-						    (__mmask8) (__U)))
-
-#define _mm_mask_blend_epi32(__U, __A, __W)			      \
-  ((__m128i) __builtin_ia32_blendmd_128_mask ((__v4si) (__A),	      \
-						    (__v4si) (__W),   \
-						    (__mmask8) (__U)))
-
 #define _mm256_cmp_epu32_mask(X, Y, P)					\
   ((__mmask8) __builtin_ia32_ucmpd256_mask ((__v8si)(__m256i)(X),	\
 					    (__v8si)(__m256i)(Y), (int)(P),\
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index b5236ad..ddc9fd2 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -444,8 +444,9 @@
   [(V32HF "TARGET_AVX512FP16") (V16HF "TARGET_AVX512FP16")
    (V8HF "TARGET_AVX512FP16") V32BF V16BF V8BF])
 
-(define_mode_iterator VF_AVX512BWHFBF16
-  [V32HF V16HF V8HF V32BF V16BF V8BF])
+(define_mode_iterator VF_AVX512HFBFVL
+  [V32HF (V16HF "TARGET_AVX512VL") (V8HF "TARGET_AVX512VL")
+   V32BF (V16BF "TARGET_AVX512VL") (V8BF "TARGET_AVX512VL")])
 
 (define_mode_iterator VF_AVX512FP16VL
   [V32HF (V16HF "TARGET_AVX512VL") (V8HF "TARGET_AVX512VL")])
@@ -1585,10 +1586,10 @@
    (set_attr "mode" "<sseinsnmode>")])
 
 (define_insn "<avx512>_blendm<mode>"
-  [(set (match_operand:VF_AVX512BWHFBF16 0 "register_operand" "=v,v")
-	(vec_merge:VF_AVX512BWHFBF16
-	  (match_operand:VF_AVX512BWHFBF16 2 "nonimmediate_operand" "vm,vm")
-	  (match_operand:VF_AVX512BWHFBF16 1 "nonimm_or_0_operand" "0C,v")
+  [(set (match_operand:VF_AVX512HFBFVL 0 "register_operand" "=v,v")
+	(vec_merge:VF_AVX512HFBFVL
+	  (match_operand:VF_AVX512HFBFVL 2 "nonimmediate_operand" "vm,vm")
+	  (match_operand:VF_AVX512HFBFVL 1 "nonimm_or_0_operand" "0C,v")
 	  (match_operand:<avx512fmaskmode> 3 "register_operand" "Yk,Yk")))]
   "TARGET_AVX512BW"
   "@
@@ -4545,10 +4546,6 @@
   DONE;
 })
 
-(define_mode_iterator VF_AVX512HFBFVL
-  [V32HF (V16HF "TARGET_AVX512VL") (V8HF "TARGET_AVX512VL")
-   V32BF (V16BF "TARGET_AVX512VL") (V8BF "TARGET_AVX512VL")])
-
 (define_expand "vcond<mode><sseintvecmodelower>"
   [(set (match_operand:VF_AVX512HFBFVL 0 "register_operand")
 	(if_then_else:VF_AVX512HFBFVL