* config/i386/avx512bitalgintrin.h (_mm512_mask_bitshuffle_epi64_mask):

	Use __mmask64 type instead of __mmask8 for __M argument.
	* config/i386/avx512fintrin.h (_mm512_mask_xor_epi64,
	_mm512_maskz_xor_epi64): Use __mmask8 type instead of __mmask16 for
	__U argument.
	(_mm512_mask_cmpneq_epi64_mask): Use __mmask8 type instead of
	__mmask16 for __M argument.
	(_mm512_maskz_insertf32x4, _mm512_maskz_inserti32x4,
	_mm512_mask_insertf32x4, _mm512_mask_inserti32x4): Cast last argument
	to __mmask16 instead of __mmask8.
	* config/i386/avx512vlintrin.h (_mm_mask_add_ps, _mm_maskz_add_ps,
	_mm256_mask_add_ps, _mm256_maskz_add_ps, _mm_mask_sub_ps,
	_mm_maskz_sub_ps, _mm256_mask_sub_ps, _mm256_maskz_sub_ps,
	_mm256_maskz_cvtepi32_ps, _mm_maskz_cvtepi32_ps): Use __mmask8 type
	instead of __mmask16 for __U argument.
	* config/i386/avx512vlbwintrin.h (_mm_mask_cmp_epi8_mask): Use
	__mmask16 instead of __mmask8 for __U argument.
	(_mm256_mask_cmp_epi8_mask): Use __mmask32 instead of __mmask16 for
	__U argument.
	(_mm256_cmp_epi8_mask): Use __mmask32 return type instead of
	__mmask16.
	(_mm_mask_cmp_epu8_mask): Use __mmask16 instead of __mmask8 for __U
	argument.
	(_mm256_mask_cmp_epu8_mask): Use __mmask32 instead of __mmask16 for
	__U argument.
	(_mm256_cmp_epu8_mask): Use __mmask32 return type instead of
	__mmask16.
	(_mm_mask_cmp_epi16_mask): Cast last argument to __mmask8 instead
	of __mmask16.
	(_mm256_mask_cvtepi8_epi16): Use __mmask16 instead of __mmask32 for
	__U argument.
	(_mm_mask_cvtepi8_epi16): Use __mmask8 instead of __mmask32 for
	__U argument.
	(_mm256_mask_cvtepu8_epi16): Use __mmask16 instead of __mmask32 for
	__U argument.
	(_mm_mask_cvtepu8_epi16): Use __mmask8 instead of __mmask32 for
	__U argument.
	(_mm256_mask_cmpneq_epu8_mask, _mm256_mask_cmplt_epu8_mask,
	_mm256_mask_cmpge_epu8_mask, _mm256_mask_cmple_epu8_mask): Change
	return type as well as __M argument type and all casts from __mmask8
	to __mmask32.
	(_mm256_mask_cmpneq_epu16_mask, _mm256_mask_cmplt_epu16_mask,
	_mm256_mask_cmpge_epu16_mask, _mm256_mask_cmple_epu16_mask): Change
	return type as well as __M argument type and all casts from __mmask8
	to __mmask16.
	(_mm256_mask_cmpneq_epi8_mask, _mm256_mask_cmplt_epi8_mask,
	_mm256_mask_cmpge_epi8_mask, _mm256_mask_cmple_epi8_mask): Change
	return type as well as __M argument type and all casts from __mmask8
	to __mmask32.
	(_mm256_mask_cmpneq_epi16_mask, _mm256_mask_cmplt_epi16_mask,
	_mm256_mask_cmpge_epi16_mask, _mm256_mask_cmple_epi16_mask): Change
	return type as well as __M argument type and all casts from __mmask8
	to __mmask16.
	* config/i386/avx512vbmi2vlintrin.h (_mm_mask_shrdi_epi32,
	_mm_mask_shldi_epi32): Cast last argument to __mmask8 instead of
	__mmask16.

	* gcc.target/i386/avx512bw-vpcmpb-2.c (CMP): Use SIZE macro instead
	of hardcoding size.  Cast (rel) to MASK_TYPE.
	* gcc.target/i386/avx512bw-vpcmpub-2.c (CMP): Likewise.
	* gcc.target/i386/avx512f-vinserti32x4-3.c: New test.
	* gcc.target/i386/avx512f-vinsertf32x4-3.c: New test.
	* gcc.target/i386/avx512vl-vpcmpnequb-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpgeub-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpleb-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpgeb-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpltb-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpltub-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpleub-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpneqb-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpnequw-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpgeuw-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmplew-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpgew-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpltw-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpltuw-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpleuw-2.c: New test.
	* gcc.target/i386/avx512vl-vpcmpneqw-2.c: New test.

2018-07-11  Grazvydas Ignotas  <notasas@gmail.com>

	* config/i386/avx512bwintrin.h: (_mm512_mask_cmp_epi8_mask,
	_mm512_mask_cmp_epu8_mask): Use __mmask64 type instead of __mmask32
	for __U argument.

	* gcc.target/i386/avx512bw-vpcmpb-2.c (SIZE): Define to
	(AVX512F_LEN / 8) instead of (AVX512F_LEN / 16).
	* gcc.target/i386/avx512bw-vpcmpub-2.c (SIZE): Likewise.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/branches/gcc-8-branch@262567 138bc75d-0d04-0410-961f-82ee72b054a4

28 files changed, 596 insertions, 139 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index b75cb76afa2..d62451fd2e3 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,68 @@
+2018-07-11  Jakub Jelinek  <jakub@redhat.com>
+
+	* config/i386/avx512bitalgintrin.h (_mm512_mask_bitshuffle_epi64_mask):
+	Use __mmask64 type instead of __mmask8 for __M argument.
+	* config/i386/avx512fintrin.h (_mm512_mask_xor_epi64,
+	_mm512_maskz_xor_epi64): Use __mmask8 type instead of __mmask16 for
+	__U argument.
+	(_mm512_mask_cmpneq_epi64_mask): Use __mmask8 type instead of
+	__mmask16 for __M argument.
+	(_mm512_maskz_insertf32x4, _mm512_maskz_inserti32x4,
+	_mm512_mask_insertf32x4, _mm512_mask_inserti32x4): Cast last argument
+	to __mmask16 instead of __mmask8.
+	* config/i386/avx512vlintrin.h (_mm_mask_add_ps, _mm_maskz_add_ps,
+	_mm256_mask_add_ps, _mm256_maskz_add_ps, _mm_mask_sub_ps,
+	_mm_maskz_sub_ps, _mm256_mask_sub_ps, _mm256_maskz_sub_ps,
+	_mm256_maskz_cvtepi32_ps, _mm_maskz_cvtepi32_ps): Use __mmask8 type
+	instead of __mmask16 for __U argument.
+	* config/i386/avx512vlbwintrin.h (_mm_mask_cmp_epi8_mask): Use
+	__mmask16 instead of __mmask8 for __U argument.
+	(_mm256_mask_cmp_epi8_mask): Use __mmask32 instead of __mmask16 for
+	__U argument.
+	(_mm256_cmp_epi8_mask): Use __mmask32 return type instead of
+	__mmask16.
+	(_mm_mask_cmp_epu8_mask): Use __mmask16 instead of __mmask8 for __U
+	argument.
+	(_mm256_mask_cmp_epu8_mask): Use __mmask32 instead of __mmask16 for
+	__U argument.
+	(_mm256_cmp_epu8_mask): Use __mmask32 return type instead of
+	__mmask16.
+	(_mm_mask_cmp_epi16_mask): Cast last argument to __mmask8 instead
+	of __mmask16.
+	(_mm256_mask_cvtepi8_epi16): Use __mmask16 instead of __mmask32 for
+	__U argument.
+	(_mm_mask_cvtepi8_epi16): Use __mmask8 instead of __mmask32 for
+	__U argument.
+	(_mm256_mask_cvtepu8_epi16): Use __mmask16 instead of __mmask32 for
+	__U argument.
+	(_mm_mask_cvtepu8_epi16): Use __mmask8 instead of __mmask32 for
+	__U argument.
+	(_mm256_mask_cmpneq_epu8_mask, _mm256_mask_cmplt_epu8_mask,
+	_mm256_mask_cmpge_epu8_mask, _mm256_mask_cmple_epu8_mask): Change
+	return type as well as __M argument type and all casts from __mmask8
+	to __mmask32.
+	(_mm256_mask_cmpneq_epu16_mask, _mm256_mask_cmplt_epu16_mask,
+	_mm256_mask_cmpge_epu16_mask, _mm256_mask_cmple_epu16_mask): Change
+	return type as well as __M argument type and all casts from __mmask8
+	to __mmask16.
+	(_mm256_mask_cmpneq_epi8_mask, _mm256_mask_cmplt_epi8_mask,
+	_mm256_mask_cmpge_epi8_mask, _mm256_mask_cmple_epi8_mask): Change
+	return type as well as __M argument type and all casts from __mmask8
+	to __mmask32.
+	(_mm256_mask_cmpneq_epi16_mask, _mm256_mask_cmplt_epi16_mask,
+	_mm256_mask_cmpge_epi16_mask, _mm256_mask_cmple_epi16_mask): Change
+	return type as well as __M argument type and all casts from __mmask8
+	to __mmask16.
+	* config/i386/avx512vbmi2vlintrin.h (_mm_mask_shrdi_epi32,
+	_mm_mask_shldi_epi32): Cast last argument to __mmask8 instead of
+	__mmask16.
+
+2018-07-11  Grazvydas Ignotas  <notasas@gmail.com>
+
+	* config/i386/avx512bwintrin.h: (_mm512_mask_cmp_epi8_mask,
+	_mm512_mask_cmp_epu8_mask): Use __mmask64 type instead of __mmask32
+	for __U argument.
+
 2018-07-05  Martin Sebor  <msebor@redhat.com>
 
 	PR c++/86400
diff --git a/gcc/config/i386/avx512bitalgintrin.h b/gcc/config/i386/avx512bitalgintrin.h
index 54f03eec3e9..3a7414adb69 100644
--- a/gcc/config/i386/avx512bitalgintrin.h
+++ b/gcc/config/i386/avx512bitalgintrin.h
@@ -107,7 +107,7 @@ _mm512_bitshuffle_epi64_mask (__m512i __A, __m512i __B)
 
 extern __inline __mmask64
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_bitshuffle_epi64_mask (__mmask8 __M, __m512i __A, __m512i __B)
+_mm512_mask_bitshuffle_epi64_mask (__mmask64 __M, __m512i __A, __m512i __B)
 {
   return (__mmask64) __builtin_ia32_vpshufbitqmb512_mask ((__v64qi) __A,
 						 (__v64qi) __B,
diff --git a/gcc/config/i386/avx512bwintrin.h b/gcc/config/i386/avx512bwintrin.h
index bd389fa9581..24ad5f1e2af 100644
--- a/gcc/config/i386/avx512bwintrin.h
+++ b/gcc/config/i386/avx512bwintrin.h
@@ -3043,7 +3043,7 @@ _mm512_cmp_epi16_mask (__m512i __X, __m512i __Y, const int __P)
 
 extern __inline __mmask64
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmp_epi8_mask (__mmask32 __U, __m512i __X, __m512i __Y,
+_mm512_mask_cmp_epi8_mask (__mmask64 __U, __m512i __X, __m512i __Y,
 			   const int __P)
 {
   return (__mmask64) __builtin_ia32_cmpb512_mask ((__v64qi) __X,
@@ -3081,7 +3081,7 @@ _mm512_cmp_epu16_mask (__m512i __X, __m512i __Y, const int __P)
 
 extern __inline __mmask64
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmp_epu8_mask (__mmask32 __U, __m512i __X, __m512i __Y,
+_mm512_mask_cmp_epu8_mask (__mmask64 __U, __m512i __X, __m512i __Y,
 			   const int __P)
 {
   return (__mmask64) __builtin_ia32_ucmpb512_mask ((__v64qi) __X,
diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
index ba65acadf8d..363194ff3fc 100644
--- a/gcc/config/i386/avx512fintrin.h
+++ b/gcc/config/i386/avx512fintrin.h
@@ -7306,7 +7306,7 @@ _mm512_xor_epi64 (__m512i __A, __m512i __B)
 
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+_mm512_mask_xor_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
 {
   return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
 						 (__v8di) __B,
@@ -7316,7 +7316,7 @@ _mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
 
 extern __inline __m512i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_maskz_xor_epi64 (__mmask16 __U, __m512i __A, __m512i __B)
+_mm512_maskz_xor_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
 {
   return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
 						 (__v8di) __B,
@@ -9544,7 +9544,7 @@ _mm512_cmpneq_epu32_mask (__m512i __X, __m512i __Y)
 
 extern __inline __mmask8
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmpneq_epi64_mask (__mmask16 __M, __m512i __X, __m512i __Y)
+_mm512_mask_cmpneq_epi64_mask (__mmask8 __M, __m512i __X, __m512i __Y)
 {
   return (__mmask8) __builtin_ia32_cmpq512_mask ((__v8di) __X,
 						    (__v8di) __Y, 4,
@@ -10806,22 +10806,22 @@ _mm512_mask_insertf32x4 (__m512 __A, __mmask16 __B, __m512 __C,
 #define _mm512_maskz_insertf32x4(A, X, Y, C)                            \
   ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X),     \
     (__v4sf)(__m128) (Y), (int) (C), (__v16sf)_mm512_setzero_ps(),      \
-    (__mmask8)(A)))
+    (__mmask16)(A)))
 
 #define _mm512_maskz_inserti32x4(A, X, Y, C)                            \
   ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X),   \
     (__v4si)(__m128i) (Y), (int) (C), (__v16si)_mm512_setzero_si512 (),     \
-    (__mmask8)(A)))
+    (__mmask16)(A)))
 
 #define _mm512_mask_insertf32x4(A, B, X, Y, C)                          \
   ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X),     \
     (__v4sf)(__m128) (Y), (int) (C), (__v16sf)(__m512) (A),             \
-					     (__mmask8)(B)))
+					     (__mmask16)(B)))
 
 #define _mm512_mask_inserti32x4(A, B, X, Y, C)                          \
   ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X),   \
     (__v4si)(__m128i) (Y), (int) (C), (__v16si)(__m512i) (A),           \
-					      (__mmask8)(B)))
+					      (__mmask16)(B)))
 #endif
 
 extern __inline __m512i
diff --git a/gcc/config/i386/avx512vbmi2vlintrin.h b/gcc/config/i386/avx512vbmi2vlintrin.h
index b6a3cfd8030..b089d3381fe 100644
--- a/gcc/config/i386/avx512vbmi2vlintrin.h
+++ b/gcc/config/i386/avx512vbmi2vlintrin.h
@@ -541,7 +541,7 @@ _mm_shldi_epi64 (__m128i __A, __m128i __B, int __C)
 	(__v4si)(__m128i)(B),(int)(C))
 #define _mm_mask_shrdi_epi32(A, B, C, D, E) \
   ((__m128i) __builtin_ia32_vpshrd_v4si_mask ((__v4si)(__m128i)(C), \
-	(__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask16)(B))
+	(__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask8)(B))
 #define _mm_maskz_shrdi_epi32(A, B, C, D) \
   ((__m128i) __builtin_ia32_vpshrd_v4si_mask ((__v4si)(__m128i)(B), \
 	(__v4si)(__m128i)(C),(int)(D), \
@@ -601,7 +601,7 @@ _mm_shldi_epi64 (__m128i __A, __m128i __B, int __C)
 	(__v4si)(__m128i)(B),(int)(C))
 #define _mm_mask_shldi_epi32(A, B, C, D, E) \
   ((__m128i) __builtin_ia32_vpshld_v4si_mask ((__v4si)(__m128i)(C), \
-	(__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask16)(B))
+	(__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask8)(B))
 #define _mm_maskz_shldi_epi32(A, B, C, D) \
   ((__m128i) __builtin_ia32_vpshld_v4si_mask ((__v4si)(__m128i)(B), \
 	(__v4si)(__m128i)(C),(int)(D), \
diff --git a/gcc/config/i386/avx512vlbwintrin.h b/gcc/config/i386/avx512vlbwintrin.h
index c14a86a9590..02afce15686 100644
--- a/gcc/config/i386/avx512vlbwintrin.h
+++ b/gcc/config/i386/avx512vlbwintrin.h
@@ -1467,7 +1467,7 @@ _mm256_cmp_epi16_mask (__m256i __X, __m256i __Y, const int __P)
 
 extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_epi8_mask (__mmask8 __U, __m128i __X, __m128i __Y,
+_mm_mask_cmp_epi8_mask (__mmask16 __U, __m128i __X, __m128i __Y,
 			const int __P)
 {
   return (__mmask16) __builtin_ia32_cmpb128_mask ((__v16qi) __X,
@@ -1486,7 +1486,7 @@ _mm_cmp_epi8_mask (__m128i __X, __m128i __Y, const int __P)
 
 extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmp_epi8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
+_mm256_mask_cmp_epi8_mask (__mmask32 __U, __m256i __X, __m256i __Y,
 			   const int __P)
 {
   return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
@@ -1494,7 +1494,7 @@ _mm256_mask_cmp_epi8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
 						  (__mmask32) __U);
 }
 
-extern __inline __mmask16
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmp_epi8_mask (__m256i __X, __m256i __Y, const int __P)
 {
@@ -1543,7 +1543,7 @@ _mm256_cmp_epu16_mask (__m256i __X, __m256i __Y, const int __P)
 
 extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_epu8_mask (__mmask8 __U, __m128i __X, __m128i __Y,
+_mm_mask_cmp_epu8_mask (__mmask16 __U, __m128i __X, __m128i __Y,
 			const int __P)
 {
   return (__mmask16) __builtin_ia32_ucmpb128_mask ((__v16qi) __X,
@@ -1562,7 +1562,7 @@ _mm_cmp_epu8_mask (__m128i __X, __m128i __Y, const int __P)
 
 extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmp_epu8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
+_mm256_mask_cmp_epu8_mask (__mmask32 __U, __m256i __X, __m256i __Y,
 			   const int __P)
 {
   return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
@@ -1570,7 +1570,7 @@ _mm256_mask_cmp_epu8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
 						   (__mmask32) __U);
 }
 
-extern __inline __mmask16
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmp_epu8_mask (__m256i __X, __m256i __Y, const int __P)
 {
@@ -1998,7 +1998,7 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m128i __A, int __B)
 #define _mm_mask_cmp_epi16_mask(M, X, Y, P)				\
   ((__mmask8) __builtin_ia32_cmpw128_mask ((__v8hi)(__m128i)(X),	\
 					    (__v8hi)(__m128i)(Y), (int)(P),\
-					    (__mmask16)(M)))
+					    (__mmask8)(M)))
 
 #define _mm_mask_cmp_epi8_mask(M, X, Y, P)				\
   ((__mmask16) __builtin_ia32_cmpb128_mask ((__v16qi)(__m128i)(X),	\
@@ -2430,7 +2430,7 @@ _mm_maskz_mullo_epi16 (__mmask8 __U, __m128i __A, __m128i __B)
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cvtepi8_epi16 (__m256i __W, __mmask32 __U, __m128i __A)
+_mm256_mask_cvtepi8_epi16 (__m256i __W, __mmask16 __U, __m128i __A)
 {
   return (__m256i) __builtin_ia32_pmovsxbw256_mask ((__v16qi) __A,
 						    (__v16hi) __W,
@@ -2449,7 +2449,7 @@ _mm256_maskz_cvtepi8_epi16 (__mmask16 __U, __m128i __A)
 
 extern __inline __m128i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cvtepi8_epi16 (__m128i __W, __mmask32 __U, __m128i __A)
+_mm_mask_cvtepi8_epi16 (__m128i __W, __mmask8 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_pmovsxbw128_mask ((__v16qi) __A,
 						    (__v8hi) __W,
@@ -2468,7 +2468,7 @@ _mm_maskz_cvtepi8_epi16 (__mmask8 __U, __m128i __A)
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cvtepu8_epi16 (__m256i __W, __mmask32 __U, __m128i __A)
+_mm256_mask_cvtepu8_epi16 (__m256i __W, __mmask16 __U, __m128i __A)
 {
   return (__m256i) __builtin_ia32_pmovzxbw256_mask ((__v16qi) __A,
 						    (__v16hi) __W,
@@ -2487,7 +2487,7 @@ _mm256_maskz_cvtepu8_epi16 (__mmask16 __U, __m128i __A)
 
 extern __inline __m128i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cvtepu8_epi16 (__m128i __W, __mmask32 __U, __m128i __A)
+_mm_mask_cvtepu8_epi16 (__m128i __W, __mmask8 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_pmovzxbw128_mask ((__v16qi) __A,
 						    (__v8hi) __W,
@@ -4541,148 +4541,148 @@ _mm_mask_cmple_epi16_mask (__mmask8 __M, __m128i __X, __m128i __Y)
 						 (__mmask8) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
-						  (__v32qi) __Y, 4,
-						  (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+						   (__v32qi) __Y, 4,
+						   (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
-						  (__v32qi) __Y, 1,
-						  (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+						   (__v32qi) __Y, 1,
+						   (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
-						  (__v32qi) __Y, 5,
-						  (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+						   (__v32qi) __Y, 5,
+						   (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
-						  (__v32qi) __Y, 2,
-						  (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+						   (__v32qi) __Y, 2,
+						   (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
-						  (__v16hi) __Y, 4,
-						  (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+						   (__v16hi) __Y, 4,
+						   (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
-						  (__v16hi) __Y, 1,
-						  (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+						   (__v16hi) __Y, 1,
+						   (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
-						  (__v16hi) __Y, 5,
-						  (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+						   (__v16hi) __Y, 5,
+						   (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
-						  (__v16hi) __Y, 2,
-						  (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+						   (__v16hi) __Y, 2,
+						   (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
-						 (__v32qi) __Y, 4,
-						 (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+						  (__v32qi) __Y, 4,
+						  (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
-						 (__v32qi) __Y, 1,
-						 (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+						  (__v32qi) __Y, 1,
+						  (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
-						 (__v32qi) __Y, 5,
-						 (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+						  (__v32qi) __Y, 5,
+						  (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask32
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
-						 (__v32qi) __Y, 2,
-						 (__mmask8) __M);
+  return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+						  (__v32qi) __Y, 2,
+						  (__mmask32) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
-						 (__v16hi) __Y, 4,
-						 (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+						  (__v16hi) __Y, 4,
+						  (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
-						 (__v16hi) __Y, 1,
-						 (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+						  (__v16hi) __Y, 1,
+						  (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
-						 (__v16hi) __Y, 5,
-						 (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+						  (__v16hi) __Y, 5,
+						  (__mmask16) __M);
 }
 
-extern __inline __mmask8
+extern __inline __mmask16
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
 {
-  return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
-						 (__v16hi) __Y, 2,
-						 (__mmask8) __M);
+  return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+						  (__v16hi) __Y, 2,
+						  (__mmask16) __M);
 }
 
 #ifdef __DISABLE_AVX512VLBW__
diff --git a/gcc/config/i386/avx512vlintrin.h b/gcc/config/i386/avx512vlintrin.h
index 4dfe12fdeb0..68b5537845b 100644
--- a/gcc/config/i386/avx512vlintrin.h
+++ b/gcc/config/i386/avx512vlintrin.h
@@ -466,7 +466,7 @@ _mm256_maskz_add_pd (__mmask8 __U, __m256d __A, __m256d __B)
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_add_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
+_mm_mask_add_ps (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
 {
   return (__m128) __builtin_ia32_addps128_mask ((__v4sf) __A,
 						(__v4sf) __B,
@@ -476,7 +476,7 @@ _mm_mask_add_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_add_ps (__mmask16 __U, __m128 __A, __m128 __B)
+_mm_maskz_add_ps (__mmask8 __U, __m128 __A, __m128 __B)
 {
   return (__m128) __builtin_ia32_addps128_mask ((__v4sf) __A,
 						(__v4sf) __B,
@@ -487,7 +487,7 @@ _mm_maskz_add_ps (__mmask16 __U, __m128 __A, __m128 __B)
 
 extern __inline __m256
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_add_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
+_mm256_mask_add_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B)
 {
   return (__m256) __builtin_ia32_addps256_mask ((__v8sf) __A,
 						(__v8sf) __B,
@@ -497,7 +497,7 @@ _mm256_mask_add_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
 
 extern __inline __m256
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_add_ps (__mmask16 __U, __m256 __A, __m256 __B)
+_mm256_maskz_add_ps (__mmask8 __U, __m256 __A, __m256 __B)
 {
   return (__m256) __builtin_ia32_addps256_mask ((__v8sf) __A,
 						(__v8sf) __B,
@@ -551,7 +551,7 @@ _mm256_maskz_sub_pd (__mmask8 __U, __m256d __A, __m256d __B)
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_sub_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
+_mm_mask_sub_ps (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
 {
   return (__m128) __builtin_ia32_subps128_mask ((__v4sf) __A,
 						(__v4sf) __B,
@@ -561,7 +561,7 @@ _mm_mask_sub_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_sub_ps (__mmask16 __U, __m128 __A, __m128 __B)
+_mm_maskz_sub_ps (__mmask8 __U, __m128 __A, __m128 __B)
 {
   return (__m128) __builtin_ia32_subps128_mask ((__v4sf) __A,
 						(__v4sf) __B,
@@ -572,7 +572,7 @@ _mm_maskz_sub_ps (__mmask16 __U, __m128 __A, __m128 __B)
 
 extern __inline __m256
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_sub_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
+_mm256_mask_sub_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B)
 {
   return (__m256) __builtin_ia32_subps256_mask ((__v8sf) __A,
 						(__v8sf) __B,
@@ -582,7 +582,7 @@ _mm256_mask_sub_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
 
 extern __inline __m256
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_sub_ps (__mmask16 __U, __m256 __A, __m256 __B)
+_mm256_maskz_sub_ps (__mmask8 __U, __m256 __A, __m256 __B)
 {
   return (__m256) __builtin_ia32_subps256_mask ((__v8sf) __A,
 						(__v8sf) __B,
@@ -1320,7 +1320,7 @@ _mm256_mask_cvtepi32_ps (__m256 __W, __mmask8 __U, __m256i __A)
 
 extern __inline __m256
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_cvtepi32_ps (__mmask16 __U, __m256i __A)
+_mm256_maskz_cvtepi32_ps (__mmask8 __U, __m256i __A)
 {
   return (__m256) __builtin_ia32_cvtdq2ps256_mask ((__v8si) __A,
 						   (__v8sf)
@@ -1339,7 +1339,7 @@ _mm_mask_cvtepi32_ps (__m128 __W, __mmask8 __U, __m128i __A)
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_cvtepi32_ps (__mmask16 __U, __m128i __A)
+_mm_maskz_cvtepi32_ps (__mmask8 __U, __m128i __A)
 {
   return (__m128) __builtin_ia32_cvtdq2ps128_mask ((__v4si) __A,
 						   (__v4sf)
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 3fb9d2234c4..c83833af06f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,33 @@
+2018-07-11  Jakub Jelinek  <jakub@redhat.com>
+
+	* gcc.target/i386/avx512bw-vpcmpb-2.c (CMP): Use SIZE macro instead
+	of hardcoding size.  Cast (rel) to MASK_TYPE.
+	* gcc.target/i386/avx512bw-vpcmpub-2.c (CMP): Likewise.
+	* gcc.target/i386/avx512f-vinserti32x4-3.c: New test.
+	* gcc.target/i386/avx512f-vinsertf32x4-3.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpnequb-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpgeub-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpleb-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpgeb-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpltb-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpltub-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpleub-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpneqb-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpnequw-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpgeuw-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmplew-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpgew-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpltw-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpltuw-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpleuw-2.c: New test.
+	* gcc.target/i386/avx512vl-vpcmpneqw-2.c: New test.
+
+2018-07-11  Grazvydas Ignotas  <notasas@gmail.com>
+
+	* gcc.target/i386/avx512bw-vpcmpb-2.c (SIZE): Define to
+	(AVX512F_LEN / 8) instead of (AVX512F_LEN / 16).
+	* gcc.target/i386/avx512bw-vpcmpub-2.c (SIZE): Likewise.
+
 2018-07-10  Jakub Jelinek  <jakub@redhat.com>
 
 	PR sanitizer/86406
diff --git a/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpb-2.c b/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpb-2.c
index b6f56777dbb..024c4a620f7 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpb-2.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpb-2.c
@@ -6,17 +6,15 @@
 #include "avx512f-helper.h"
 
 #include <math.h>
-#define SIZE (AVX512F_LEN / 16)
+#define SIZE (AVX512F_LEN / 8)
 #include "avx512f-mask-type.h"
 
 #if AVX512F_LEN == 512
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 64; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm512_loadu_si512 (s1);		\
     source2.x = _mm512_loadu_si512 (s2);		\
     dst1 = _mm512_cmp_epi8_mask (source1.x, source2.x, imm);\
@@ -29,10 +27,8 @@
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 32; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm256_loadu_si256 ((__m256i*)s1);	\
     source2.x = _mm256_loadu_si256 ((__m256i*)s2);	\
     dst1 = _mm256_cmp_epi8_mask (source1.x, source2.x, imm);\
@@ -45,10 +41,8 @@
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 16; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm_loadu_si128 ((__m128i*)s1);		\
     source2.x = _mm_loadu_si128 ((__m128i*)s2);		\
     dst1 = _mm_cmp_epi8_mask (source1.x, source2.x, imm);\
diff --git a/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpub-2.c b/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpub-2.c
index 8fdc9f2a1d8..2d592a6e6ed 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpub-2.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bw-vpcmpub-2.c
@@ -6,17 +6,15 @@
 #include "avx512f-helper.h"
 
 #include <math.h>
-#define SIZE (AVX512F_LEN / 16)
+#define SIZE (AVX512F_LEN / 8)
 #include "avx512f-mask-type.h"
 
 #if AVX512F_LEN == 512
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 64; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm512_loadu_si512 (s1);		\
     source2.x = _mm512_loadu_si512 (s2);		\
     dst1 = _mm512_cmp_epu8_mask (source1.x, source2.x, imm);\
@@ -29,10 +27,8 @@
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 32; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm256_loadu_si256 ((__m256i*)s1);	\
     source2.x = _mm256_loadu_si256 ((__m256i*)s2);	\
     dst1 = _mm256_cmp_epu8_mask (source1.x, source2.x, imm);\
@@ -45,10 +41,8 @@
 #undef CMP
 #define CMP(imm, rel)					\
     dst_ref = 0;					\
-    for (i = 0; i < 16; i++)				\
-    {							\
-      dst_ref = ((rel) << i) | dst_ref;			\
-    }							\
+    for (i = 0; i < SIZE; i++)				\
+      dst_ref = ((MASK_TYPE) (rel) << i) | dst_ref;	\
     source1.x = _mm_loadu_si128 ((__m128i*)s1);		\
     source2.x = _mm_loadu_si128 ((__m128i*)s2);		\
     dst1 = _mm_cmp_epu8_mask (source1.x, source2.x, imm);\
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vinsertf32x4-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vinsertf32x4-3.c
new file mode 100644
index 00000000000..239a7b81a94
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-vinsertf32x4-3.c
@@ -0,0 +1,59 @@
+/* { dg-do run } */
+/* { dg-options "-O0 -mavx512f" } */
+/* { dg-require-effective-target avx512f } */
+
+#define AVX512F
+
+#include "avx512f-helper.h"
+
+#define SIZE (AVX512F_LEN / 32)
+#include "avx512f-mask-type.h"
+#include "string.h"
+
+void static
+CALC (UNION_TYPE (AVX512F_LEN,) s1, union128 s2, float *res_ref, int imm)
+{
+  memcpy (res_ref, s1.a, SIZE * sizeof (float));
+  memcpy (res_ref + imm * 4, s2.a, 16);
+}
+
+void
+TEST (void)
+{
+  UNION_TYPE (AVX512F_LEN,) s1, res1, res2, res3;
+  union128 s2;
+  float res_ref[SIZE];
+  int j;
+
+  MASK_TYPE mask = (MASK_TYPE) 0xa55a;
+
+  for (j = 0; j < SIZE; j++)
+    {
+      s1.a[j] = j * j / 10.2;
+      res1.a[j] = DEFAULT_VALUE;
+      res2.a[j] = DEFAULT_VALUE;
+      res3.a[j] = DEFAULT_VALUE;
+    }
+
+  for (j = 0; j < 4; j++)
+    s2.a[j] = j * j * j / 2.03;
+
+  res1.x = INTRINSIC (_insertf32x4) (s1.x, s2.x, 1);
+  res2.x = INTRINSIC (_mask_insertf32x4) (res2.x, mask, s1.x, s2.x, 1);
+  res3.x = INTRINSIC (_maskz_insertf32x4) (mask, s1.x, s2.x, 1);
+
+  CALC (s1, s2, res_ref, 1);
+
+  if (UNION_CHECK (AVX512F_LEN,) (res1, res_ref))
+    abort ();
+
+  MASK_MERGE () (res_ref, mask, SIZE);
+
+  if (UNION_CHECK (AVX512F_LEN,) (res2, res_ref))
+    abort ();
+
+  MASK_ZERO () (res_ref, mask, SIZE);
+
+  if (UNION_CHECK (AVX512F_LEN,) (res3, res_ref))
+    abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vinserti32x4-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vinserti32x4-3.c
new file mode 100644
index 00000000000..05b32978c0b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-vinserti32x4-3.c
@@ -0,0 +1,59 @@
+/* { dg-do run } */
+/* { dg-options "-O0 -mavx512f" } */
+/* { dg-require-effective-target avx512f } */
+
+#define AVX512F
+
+#include "avx512f-helper.h"
+
+#define SIZE (AVX512F_LEN / 32)
+#include "avx512f-mask-type.h"
+#include "string.h"
+
+void static
+CALC (UNION_TYPE (AVX512F_LEN, i_d) s1, union128i_d s2, int *res_ref, int imm)
+{
+  memcpy (res_ref, s1.a, SIZE * sizeof (int));
+  memcpy (res_ref + imm * 4, s2.a, 16);
+}
+
+void
+TEST (void)
+{
+  UNION_TYPE (AVX512F_LEN, i_d) s1, res1, res2, res3;
+  union128i_d s2;
+  int res_ref[SIZE];
+  int j;
+
+  MASK_TYPE mask = (MASK_TYPE) 0xa55a;
+
+  for (j = 0; j < SIZE; j++)
+    {
+      s1.a[j] = j * j;
+      res1.a[j] = DEFAULT_VALUE;
+      res2.a[j] = DEFAULT_VALUE;
+      res3.a[j] = DEFAULT_VALUE;
+    }
+
+  for (j = 0; j < 4; j++)
+    s2.a[j] = j * j * j;
+
+  res1.x = INTRINSIC (_inserti32x4) (s1.x, s2.x, 1);
+  res2.x = INTRINSIC (_mask_inserti32x4) (res2.x, mask, s1.x, s2.x, 1);
+  res3.x = INTRINSIC (_maskz_inserti32x4) (mask, s1.x, s2.x, 1);
+
+  CALC (s1, s2, res_ref, 1);
+
+  if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
+    abort ();
+
+  MASK_MERGE (i_d) (res_ref, mask, SIZE);
+
+  if (UNION_CHECK (AVX512F_LEN, i_d) (res2, res_ref))
+    abort ();
+
+  MASK_ZERO (i_d) (res_ref, mask, SIZE);
+
+  if (UNION_CHECK (AVX512F_LEN, i_d) (res3, res_ref))
+    abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeb-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeb-2.c
new file mode 100644
index 00000000000..f83d809f925
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeb-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeb-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeub-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeub-2.c
new file mode 100644
index 00000000000..40618e5a4ad
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeub-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeub-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeub-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeuw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeuw-2.c
new file mode 100644
index 00000000000..0ce6bbdcbc0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgeuw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeuw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgeuw-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgew-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgew-2.c
new file mode 100644
index 00000000000..9852796bc92
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpgew-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgew-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpgew-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleb-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleb-2.c
new file mode 100644
index 00000000000..35c8d464334
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleb-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpleb-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpleb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleub-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleub-2.c
new file mode 100644
index 00000000000..ca4d84a4637
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleub-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpleub-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpleb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleuw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleuw-2.c
new file mode 100644
index 00000000000..bf8d7e6d27f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpleuw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpleuw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmplew-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmplew-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmplew-2.c
new file mode 100644
index 00000000000..6ff7ae8af27
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmplew-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmplew-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmplew-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltb-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltb-2.c
new file mode 100644
index 00000000000..46e66506a26
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltb-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltb-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltub-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltub-2.c
new file mode 100644
index 00000000000..13b49240a30
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltub-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltub-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltub-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltuw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltuw-2.c
new file mode 100644
index 00000000000..0c4dc77815e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltuw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltuw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltuw-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltw-2.c
new file mode 100644
index 00000000000..86fe9af08a1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpltw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpltw-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqb-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqb-2.c
new file mode 100644
index 00000000000..99356077c78
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqb-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpneqb-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpneqb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequb-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequb-2.c
new file mode 100644
index 00000000000..dff70c10974
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequb-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpnequb-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpnequb-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequw-2.c
new file mode 100644
index 00000000000..ebcd37f5da0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpnequw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpnequw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpnequw-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqw-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqw-2.c
new file mode 100644
index 00000000000..e19b6f58c5b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vpcmpneqw-2.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpneqw-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512bw-vpcmpneqw-2.c"