i386: Fix up _mm*_mask_popcnt_epi* [PR93696]

As mentioned in the PR and as
https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_mask_popcnt_epi
also documents, _mm*_popcnt_epi* intrinsics are consistent with all other
unary AVX512* intrinsics regarding arguments, i.e. the
_mm*_whatever has just single argument (called a in the docs, and __A in the
GCC headers),
_mm*_mask_whatever has 3 arguments (called src, k, a in the docs and
_W, __U, __A in GCC headers) and
_mm*_maskz_whatever 2 arguments (called k, a in the docs and __U, __A in GCC
headers).  Unfortunately, whomever implemented the _mm*_popcnt_epi*
intrinsics got it wrong for the _mm*_mask_popcnt_epi* ones, calling the
args __A, __U, __B and not passing them in the canonical order to the
builtins, making it API incompatible with ICC as well as clang (tested on
godbolts clang 7/8/9/trunk and ICC 19.0.{0,1}, older clang/ICC don't
understand those, so it isn't that it used to be broken even in other
compilers and got changed afterwards).

2020-02-13  Jakub Jelinek  <jakub@redhat.com>

	PR target/93696
	* config/i386/avx512bitalgintrin.h (_mm512_mask_popcnt_epi8,
	_mm512_mask_popcnt_epi16, _mm256_mask_popcnt_epi8,
	_mm256_mask_popcnt_epi16, _mm_mask_popcnt_epi8,
	_mm_mask_popcnt_epi16): Rename __B argument to __A and __A to __W,
	pass __A to the builtin followed by __W instead of __A followed by
	__B.
	* config/i386/avx512vpopcntdqintrin.h (_mm512_mask_popcnt_epi32,
	_mm512_mask_popcnt_epi64): Likewise.
	* config/i386/avx512vpopcntdqvlintrin.h (_mm_mask_popcnt_epi32,
	_mm256_mask_popcnt_epi32, _mm_mask_popcnt_epi64,
	_mm256_mask_popcnt_epi64): Likewise.

	* gcc.target/i386/pr93696-1.c: New test.
	* gcc.target/i386/pr93696-2.c: New test.
	* gcc.target/i386/avx512bitalg-vpopcntw-1.c (TEST): Fix argument order
	of _mm*_mask_popcnt_*.
	* gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c (TEST): Likewise.
	* gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c (TEST): Likewise.
	* gcc.target/i386/avx512bitalg-vpopcntb-1.c (TEST): Likewise.
	* gcc.target/i386/avx512bitalg-vpopcntb.c (foo): Likewise.
	* gcc.target/i386/avx512bitalg-vpopcntbvl.c (foo): Likewise.
	* gcc.target/i386/avx512vpopcntdq-vpopcntd.c (foo): Likewise.
	* gcc.target/i386/avx512bitalg-vpopcntwvl.c (foo): Likewise.
	* gcc.target/i386/avx512bitalg-vpopcntw.c (foo): Likewise.
	* gcc.target/i386/avx512vpopcntdq-vpopcntq.c (foo): Likewise.

17 files changed, 226 insertions, 41 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 36a8956..371194d 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,18 @@
 2020-02-13  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/93696
+	* config/i386/avx512bitalgintrin.h (_mm512_mask_popcnt_epi8,
+	_mm512_mask_popcnt_epi16, _mm256_mask_popcnt_epi8,
+	_mm256_mask_popcnt_epi16, _mm_mask_popcnt_epi8,
+	_mm_mask_popcnt_epi16): Rename __B argument to __A and __A to __W,
+	pass __A to the builtin followed by __W instead of __A followed by
+	__B.
+	* config/i386/avx512vpopcntdqintrin.h (_mm512_mask_popcnt_epi32,
+	_mm512_mask_popcnt_epi64): Likewise.
+	* config/i386/avx512vpopcntdqvlintrin.h (_mm_mask_popcnt_epi32,
+	_mm256_mask_popcnt_epi32, _mm_mask_popcnt_epi64,
+	_mm256_mask_popcnt_epi64): Likewise.
+
 	PR tree-optimization/93582
 	* fold-const.h (shift_bytes_in_array_left,
 	shift_bytes_in_array_right): Declare.
diff --git a/gcc/config/i386/avx512bitalgintrin.h b/gcc/config/i386/avx512bitalgintrin.h
index d1dcb83..498d5d8 100644
--- a/gcc/config/i386/avx512bitalgintrin.h
+++ b/gcc/config/i386/avx512bitalgintrin.h
@@ -61,10 +61,10 @@ _mm512_popcnt_epi16 (__m512i __A)
 
 extern __inline __m512i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_popcnt_epi8 (__m512i __A, __mmask64 __U, __m512i __B)
+_mm512_mask_popcnt_epi8 (__m512i __W, __mmask64 __U, __m512i __A)
 {
   return (__m512i) __builtin_ia32_vpopcountb_v64qi_mask ((__v64qi) __A,
-							 (__v64qi) __B,
+							 (__v64qi) __W,
 							 (__mmask64) __U);
 }
 
@@ -79,10 +79,10 @@ _mm512_maskz_popcnt_epi8 (__mmask64 __U, __m512i __A)
 }
 extern __inline __m512i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_popcnt_epi16 (__m512i __A, __mmask32 __U, __m512i __B)
+_mm512_mask_popcnt_epi16 (__m512i __W, __mmask32 __U, __m512i __A)
 {
   return (__m512i) __builtin_ia32_vpopcountw_v32hi_mask ((__v32hi) __A,
-							(__v32hi) __B,
+							(__v32hi) __W,
 							(__mmask32) __U);
 }
 
@@ -127,10 +127,10 @@ _mm512_mask_bitshuffle_epi64_mask (__mmask64 __M, __m512i __A, __m512i __B)
 
 extern __inline __m256i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_popcnt_epi8 (__m256i __A, __mmask32 __U, __m256i __B)
+_mm256_mask_popcnt_epi8 (__m256i __W, __mmask32 __U, __m256i __A)
 {
   return (__m256i) __builtin_ia32_vpopcountb_v32qi_mask ((__v32qi) __A,
-							 (__v32qi) __B,
+							 (__v32qi) __W,
 							 (__mmask32) __U);
 }
 
@@ -222,10 +222,10 @@ _mm_popcnt_epi16 (__m128i __A)
 
 extern __inline __m256i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_popcnt_epi16 (__m256i __A, __mmask16 __U, __m256i __B)
+_mm256_mask_popcnt_epi16 (__m256i __W, __mmask16 __U, __m256i __A)
 {
   return (__m256i) __builtin_ia32_vpopcountw_v16hi_mask ((__v16hi) __A,
-							(__v16hi) __B,
+							(__v16hi) __W,
 							(__mmask16) __U);
 }
 
@@ -241,10 +241,10 @@ _mm256_maskz_popcnt_epi16 (__mmask16 __U, __m256i __A)
 
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_popcnt_epi8 (__m128i __A, __mmask16 __U, __m128i __B)
+_mm_mask_popcnt_epi8 (__m128i __W, __mmask16 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_vpopcountb_v16qi_mask ((__v16qi) __A,
-							 (__v16qi) __B,
+							 (__v16qi) __W,
 							 (__mmask16) __U);
 }
 
@@ -259,10 +259,10 @@ _mm_maskz_popcnt_epi8 (__mmask16 __U, __m128i __A)
 }
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_popcnt_epi16 (__m128i __A, __mmask8 __U, __m128i __B)
+_mm_mask_popcnt_epi16 (__m128i __W, __mmask8 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_vpopcountw_v8hi_mask ((__v8hi) __A,
-							(__v8hi) __B,
+							(__v8hi) __W,
 							(__mmask8) __U);
 }
 
diff --git a/gcc/config/i386/avx512vpopcntdqintrin.h b/gcc/config/i386/avx512vpopcntdqintrin.h
index 14778d1..967d01b 100644
--- a/gcc/config/i386/avx512vpopcntdqintrin.h
+++ b/gcc/config/i386/avx512vpopcntdqintrin.h
@@ -43,10 +43,10 @@ _mm512_popcnt_epi32 (__m512i __A)
 
 extern __inline __m512i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_popcnt_epi32 (__m512i __A, __mmask16 __U, __m512i __B)
+_mm512_mask_popcnt_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
 {
   return (__m512i) __builtin_ia32_vpopcountd_v16si_mask ((__v16si) __A,
-							 (__v16si) __B,
+							 (__v16si) __W,
 							 (__mmask16) __U);
 }
 
@@ -69,10 +69,10 @@ _mm512_popcnt_epi64 (__m512i __A)
 
 extern __inline __m512i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_popcnt_epi64 (__m512i __A, __mmask8 __U, __m512i __B)
+_mm512_mask_popcnt_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
 {
   return (__m512i) __builtin_ia32_vpopcountq_v8di_mask ((__v8di) __A,
-							(__v8di) __B,
+							(__v8di) __W,
 							(__mmask8) __U);
 }
 
diff --git a/gcc/config/i386/avx512vpopcntdqvlintrin.h b/gcc/config/i386/avx512vpopcntdqvlintrin.h
index 79a7df3..6890004 100644
--- a/gcc/config/i386/avx512vpopcntdqvlintrin.h
+++ b/gcc/config/i386/avx512vpopcntdqvlintrin.h
@@ -43,10 +43,10 @@ _mm_popcnt_epi32 (__m128i __A)
 
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_popcnt_epi32 (__m128i __A, __mmask16 __U, __m128i __B)
+_mm_mask_popcnt_epi32 (__m128i __W, __mmask16 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_vpopcountd_v4si_mask ((__v4si) __A,
-							 (__v4si) __B,
+							 (__v4si) __W,
 							 (__mmask16) __U);
 }
 
@@ -69,10 +69,10 @@ _mm256_popcnt_epi32 (__m256i __A)
 
 extern __inline __m256i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_popcnt_epi32 (__m256i __A, __mmask16 __U, __m256i __B)
+_mm256_mask_popcnt_epi32 (__m256i __W, __mmask16 __U, __m256i __A)
 {
   return (__m256i) __builtin_ia32_vpopcountd_v8si_mask ((__v8si) __A,
-							 (__v8si) __B,
+							 (__v8si) __W,
 							 (__mmask16) __U);
 }
 
@@ -95,10 +95,10 @@ _mm_popcnt_epi64 (__m128i __A)
 
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_popcnt_epi64 (__m128i __A, __mmask8 __U, __m128i __B)
+_mm_mask_popcnt_epi64 (__m128i __W, __mmask8 __U, __m128i __A)
 {
   return (__m128i) __builtin_ia32_vpopcountq_v2di_mask ((__v2di) __A,
-							(__v2di) __B,
+							(__v2di) __W,
 							(__mmask8) __U);
 }
 
@@ -121,10 +121,10 @@ _mm256_popcnt_epi64 (__m256i __A)
 
 extern __inline __m256i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_popcnt_epi64 (__m256i __A, __mmask8 __U, __m256i __B)
+_mm256_mask_popcnt_epi64 (__m256i __W, __mmask8 __U, __m256i __A)
 {
   return (__m256i) __builtin_ia32_vpopcountq_v4di_mask ((__v4di) __A,
-							(__v4di) __B,
+							(__v4di) __W,
 							(__mmask8) __U);
 }
 
@@ -144,4 +144,3 @@ _mm256_maskz_popcnt_epi64 (__mmask8 __U, __m256i __A)
 #endif /* __DISABLE_AVX512VPOPCNTDQVL__ */
 
 #endif /* _AVX512VPOPCNTDQVLINTRIN_H_INCLUDED */
-
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 2541353..93ce065 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,20 @@
 2020-02-13  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/93696
+	* gcc.target/i386/pr93696-1.c: New test.
+	* gcc.target/i386/pr93696-2.c: New test.
+	* gcc.target/i386/avx512bitalg-vpopcntw-1.c (TEST): Fix argument order
+	of _mm*_mask_popcnt_*.
+	* gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c (TEST): Likewise.
+	* gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c (TEST): Likewise.
+	* gcc.target/i386/avx512bitalg-vpopcntb-1.c (TEST): Likewise.
+	* gcc.target/i386/avx512bitalg-vpopcntb.c (foo): Likewise.
+	* gcc.target/i386/avx512bitalg-vpopcntbvl.c (foo): Likewise.
+	* gcc.target/i386/avx512vpopcntdq-vpopcntd.c (foo): Likewise.
+	* gcc.target/i386/avx512bitalg-vpopcntwvl.c (foo): Likewise.
+	* gcc.target/i386/avx512bitalg-vpopcntw.c (foo): Likewise.
+	* gcc.target/i386/avx512vpopcntdq-vpopcntq.c (foo): Likewise.
+
 	PR tree-optimization/93582
 	* gcc.dg/tree-ssa/pr93582-1.c: New test.
 	* gcc.dg/tree-ssa/pr93582-2.c: New test.
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb-1.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb-1.c
index 3dcd48f..697757b 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb-1.c
@@ -41,7 +41,7 @@ TEST (void)
   }
 
   res1.x = INTRINSIC (_popcnt_epi8)       (src.x);
-  res2.x = INTRINSIC (_mask_popcnt_epi8)  (src.x, mask, src0.x);
+  res2.x = INTRINSIC (_mask_popcnt_epi8)  (src0.x, mask, src.x);
   res3.x = INTRINSIC (_maskz_popcnt_epi8) (mask, src.x);
 
   if (UNION_CHECK (AVX512F_LEN, i_b) (res1, res_ref))
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb.c
index b23da58..246f925 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntb.c
@@ -13,7 +13,7 @@ int foo ()
   __mmask16 msk;
   __m512i c = _mm512_popcnt_epi8 (z);
   asm volatile ("" : "+v" (c));
-  c = _mm512_mask_popcnt_epi8 (z, msk, z1);
+  c = _mm512_mask_popcnt_epi8 (z1, msk, z);
   asm volatile ("" : "+v" (c));
   c = _mm512_maskz_popcnt_epi8 (msk, z);
   asm volatile ("" : "+v" (c));
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntbvl.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntbvl.c
index e6d60f7..8c7f45f 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntbvl.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntbvl.c
@@ -18,13 +18,13 @@ int foo ()
   __mmask16 msk16;
   __m256i c256 = _mm256_popcnt_epi8 (y);
   asm volatile ("" : "+v" (c256));
-  c256 = _mm256_mask_popcnt_epi8 (y, msk32, y_1);
+  c256 = _mm256_mask_popcnt_epi8 (y_1, msk32, y);
   asm volatile ("" : "+v" (c256));
   c256 = _mm256_maskz_popcnt_epi8 (msk32, y);
   asm volatile ("" : "+v" (c256));
   __m128i c128 = _mm_popcnt_epi8 (x);
   asm volatile ("" : "+v" (c128));
-  c128 = _mm_mask_popcnt_epi8 (x, msk16, x_1);
+  c128 = _mm_mask_popcnt_epi8 (x_1, msk16, x);
   asm volatile ("" : "+v" (c128));
   c128 = _mm_maskz_popcnt_epi8 (msk16, x);
   asm volatile ("" : "+v" (c128));
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw-1.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw-1.c
index 4f866db..0a725fe 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw-1.c
@@ -41,7 +41,7 @@ TEST (void)
   }
 
   res1.x = INTRINSIC (_popcnt_epi16)       (src.x);
-  res2.x = INTRINSIC (_mask_popcnt_epi16)  (src.x, mask, src0.x);
+  res2.x = INTRINSIC (_mask_popcnt_epi16)  (src0.x, mask, src.x);
   res3.x = INTRINSIC (_maskz_popcnt_epi16) (mask, src.x);
 
   if (UNION_CHECK (AVX512F_LEN, i_w) (res1, res_ref))
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw.c
index 2c49583..90663f4 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntw.c
@@ -13,7 +13,7 @@ int foo ()
   __mmask16 msk;
   __m512i c = _mm512_popcnt_epi16 (z);
   asm volatile ("" : "+v" (c));
-  c = _mm512_mask_popcnt_epi16 (z, msk, z1);
+  c = _mm512_mask_popcnt_epi16 (z1, msk, z);
   asm volatile ("" : "+v" (c));
   c = _mm512_maskz_popcnt_epi16 (msk, z);
   asm volatile ("" : "+v" (c));
diff --git a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntwvl.c b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntwvl.c
index b55adc6..3a646b5 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntwvl.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bitalg-vpopcntwvl.c
@@ -18,13 +18,13 @@ int foo ()
   __mmask8 msk8;
   __m256i c256 = _mm256_popcnt_epi16 (y);
   asm volatile ("" : "+v" (c256));
-  c256 = _mm256_mask_popcnt_epi16 (y, msk16, y_1);
+  c256 = _mm256_mask_popcnt_epi16 (y_1, msk16, y);
   asm volatile ("" : "+v" (c256));
   c256 = _mm256_maskz_popcnt_epi16 (msk16, y);
   asm volatile ("" : "+v" (c256));
   __m128i c128 = _mm_popcnt_epi16 (x);
   asm volatile ("" : "+v" (c128));
-  c128 = _mm_mask_popcnt_epi16 (x, msk8, x_1);
+  c128 = _mm_mask_popcnt_epi16 (x_1, msk8, x);
   asm volatile ("" : "+v" (c128));
   c128 = _mm_maskz_popcnt_epi16 (msk8, x);
   asm volatile ("" : "+v" (c128));
diff --git a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c
index 245dcd4..e7d6bb4 100644
--- a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd-1.c
@@ -40,7 +40,7 @@ TEST (void)
   }
 
   res1.x = INTRINSIC (_popcnt_epi32)       (src.x);
-  res2.x = INTRINSIC (_mask_popcnt_epi32)  (src.x, mask, src0.x);
+  res2.x = INTRINSIC (_mask_popcnt_epi32)  (src0.x, mask, src.x);
   res3.x = INTRINSIC (_maskz_popcnt_epi32) (mask, src.x);
 
   if (UNION_CHECK (AVX512F_LEN, i_d) (res1, res_ref))
diff --git a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd.c b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd.c
index c70f226..b4d82f9 100644
--- a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd.c
+++ b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd.c
@@ -22,19 +22,19 @@ int foo ()
   __mmask8 msk8;
   __m128i a = _mm_popcnt_epi32 (x);
   asm volatile ("" : "+v" (a));
-  a = _mm_mask_popcnt_epi32 (x, msk8, x_1);
+  a = _mm_mask_popcnt_epi32 (x_1, msk8, x);
   asm volatile ("" : "+v" (a));
   a = _mm_maskz_popcnt_epi32 (msk8, x);
   asm volatile ("" : "+v" (a));
   __m256i b = _mm256_popcnt_epi32 (y);
   asm volatile ("" : "+v" (b));
-  b = _mm256_mask_popcnt_epi32 (y, msk8, y_1);
+  b = _mm256_mask_popcnt_epi32 (y_1, msk8, y);
   asm volatile ("" : "+v" (b));
   b = _mm256_maskz_popcnt_epi32 (msk8, y);
   asm volatile ("" : "+v" (b));
   __m512i c = _mm512_popcnt_epi32 (z);
   asm volatile ("" : "+v" (c));
-  c = _mm512_mask_popcnt_epi32 (z, msk, z_1);
+  c = _mm512_mask_popcnt_epi32 (z_1, msk, z);
   asm volatile ("" : "+v" (c));
   c = _mm512_maskz_popcnt_epi32 (msk, z);
   asm volatile ("" : "+v" (c));
diff --git a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c
index 27555c4..2144cf3 100644
--- a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq-1.c
@@ -40,7 +40,7 @@ TEST (void)
   }
 
   res1.x = INTRINSIC (_popcnt_epi64)       (src.x);
-  res2.x = INTRINSIC (_mask_popcnt_epi64)  (src.x, mask, src0.x);
+  res2.x = INTRINSIC (_mask_popcnt_epi64)  (src0.x, mask, src.x);
   res3.x = INTRINSIC (_maskz_popcnt_epi64) (mask, src.x);
 
   if (UNION_CHECK (AVX512F_LEN, i_q) (res1, res_ref))
diff --git a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq.c b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq.c
index 9f400c0..e87d6c9 100644
--- a/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq.c
+++ b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq.c
@@ -21,19 +21,19 @@ int foo ()
   __mmask8 msk; 
   __m128i a = _mm_popcnt_epi64 (x);
   asm volatile ("" : "+v" (a));
-  a = _mm_mask_popcnt_epi64 (x, msk, x_1);
+  a = _mm_mask_popcnt_epi64 (x_1, msk, x);
   asm volatile ("" : "+v" (a));
   a = _mm_maskz_popcnt_epi64 (msk, x);
   asm volatile ("" : "+v" (a));
   __m256i b = _mm256_popcnt_epi64 (y);
   asm volatile ("" : "+v" (b));
-  b = _mm256_mask_popcnt_epi64 (y, msk, y_1);
+  b = _mm256_mask_popcnt_epi64 (y_1, msk, y);
   asm volatile ("" : "+v" (b));
   b = _mm256_maskz_popcnt_epi64 (msk, y);
   asm volatile ("" : "+v" (b));
   __m512i c = _mm512_popcnt_epi64 (z);
   asm volatile ("" : "+v" (c));
-  c = _mm512_mask_popcnt_epi64 (z, msk, z_1);
+  c = _mm512_mask_popcnt_epi64 (z_1, msk, z);
   asm volatile ("" : "+v" (c));
   c = _mm512_maskz_popcnt_epi64 (msk, z); 
   asm volatile ("" : "+v" (c));
diff --git a/gcc/testsuite/gcc.target/i386/pr93696-1.c b/gcc/testsuite/gcc.target/i386/pr93696-1.c
new file mode 100644
index 0000000..128bb98
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr93696-1.c
@@ -0,0 +1,79 @@
+/* PR target/93696 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512bitalg -mavx512vpopcntdq -mavx512vl -mavx512bw -masm=att" } */
+/* { dg-final { scan-assembler-times "vpopcnt\[bwdq]\t%\[xyz]mm1, %\[xyz]mm0\{%k\[0-7]\}\[^\{]" 12 } } */
+/* { dg-final { scan-assembler-not "vmovdq\[au]\[0-9]" } } */
+
+#include <x86intrin.h>
+
+__m128i
+f1 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_mask_popcnt_epi64 (x, m, y);
+}
+
+__m128i
+f2 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_mask_popcnt_epi32 (x, m, y);
+}
+
+__m128i
+f3 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_mask_popcnt_epi16 (x, m, y);
+}
+
+__m128i
+f4 (__m128i x, __mmask16 m, __m128i y)
+{
+  return _mm_mask_popcnt_epi8 (x, m, y);
+}
+
+__m256i
+f5 (__m256i x, __mmask8 m, __m256i y)
+{
+  return _mm256_mask_popcnt_epi64 (x, m, y);
+}
+
+__m256i
+f6 (__m256i x, __mmask8 m, __m256i y)
+{
+  return _mm256_mask_popcnt_epi32 (x, m, y);
+}
+
+__m256i
+f7 (__m256i x, __mmask16 m, __m256i y)
+{
+  return _mm256_mask_popcnt_epi16 (x, m, y);
+}
+
+__m256i
+f8 (__m256i x, __mmask32 m, __m256i y)
+{
+  return _mm256_mask_popcnt_epi8 (x, m, y);
+}
+
+__m512i
+f9 (__m512i x, __mmask8 m, __m512i y)
+{
+  return _mm512_mask_popcnt_epi64 (x, m, y);
+}
+
+__m512i
+f10 (__m512i x, __mmask16 m, __m512i y)
+{
+  return _mm512_mask_popcnt_epi32 (x, m, y);
+}
+
+__m512i
+f11 (__m512i x, __mmask32 m, __m512i y)
+{
+  return _mm512_mask_popcnt_epi16 (x, m, y);
+}
+
+__m512i
+f12 (__m512i x, __mmask64 m, __m512i y)
+{
+  return _mm512_mask_popcnt_epi8 (x, m, y);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr93696-2.c b/gcc/testsuite/gcc.target/i386/pr93696-2.c
new file mode 100644
index 0000000..25a298a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr93696-2.c
@@ -0,0 +1,79 @@
+/* PR target/93696 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512bitalg -mavx512vpopcntdq -mavx512vl -mavx512bw -masm=att" } */
+/* { dg-final { scan-assembler-times "vpopcnt\[bwdq]\t%\[xyz]mm1, %\[xyz]mm0\{%k\[0-7]\}\{z\}" 12 } } */
+/* { dg-final { scan-assembler-not "vmovdq\[au]\[0-9]" } } */
+
+#include <x86intrin.h>
+
+__m128i
+f1 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_maskz_popcnt_epi64 (m, y);
+}
+
+__m128i
+f2 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_maskz_popcnt_epi32 (m, y);
+}
+
+__m128i
+f3 (__m128i x, __mmask8 m, __m128i y)
+{
+  return _mm_maskz_popcnt_epi16 (m, y);
+}
+
+__m128i
+f4 (__m128i x, __mmask16 m, __m128i y)
+{
+  return _mm_maskz_popcnt_epi8 (m, y);
+}
+
+__m256i
+f5 (__m256i x, __mmask8 m, __m256i y)
+{
+  return _mm256_maskz_popcnt_epi64 (m, y);
+}
+
+__m256i
+f6 (__m256i x, __mmask8 m, __m256i y)
+{
+  return _mm256_maskz_popcnt_epi32 (m, y);
+}
+
+__m256i
+f7 (__m256i x, __mmask16 m, __m256i y)
+{
+  return _mm256_maskz_popcnt_epi16 (m, y);
+}
+
+__m256i
+f8 (__m256i x, __mmask32 m, __m256i y)
+{
+  return _mm256_maskz_popcnt_epi8 (m, y);
+}
+
+__m512i
+f9 (__m512i x, __mmask8 m, __m512i y)
+{
+  return _mm512_maskz_popcnt_epi64 (m, y);
+}
+
+__m512i
+f10 (__m512i x, __mmask16 m, __m512i y)
+{
+  return _mm512_maskz_popcnt_epi32 (m, y);
+}
+
+__m512i
+f11 (__m512i x, __mmask32 m, __m512i y)
+{
+  return _mm512_maskz_popcnt_epi16 (m, y);
+}
+
+__m512i
+f12 (__m512i x, __mmask64 m, __m512i y)
+{
+  return _mm512_maskz_popcnt_epi8 (m, y);
+}