[PowerPC] [Clang] Add SSE4 and BMI compatible intrinsics implementation for PowerPC

[qiucf]

Summary

The asserts are not included for bringing issue on cross-compiling.

[qiucf]

This breaks existing smm/tmm tests, will update/clean-up them before this.

[qiucf]

Rebase the fix.

[jsji]

clang/lib/Headers/ppc_wrappers/xmmintrin.h

1332

Can we have some pwr10 tests to test all these P10 specific codegen?

[qiucf]

Add P10 tests.

[jsji]

LGTM. Thanks!

[chapuni]

clang/lib/Headers/CMakeLists.txt

170 ↗

(On Diff #417887)

It doesn't contain <nmmintrin.h>, forgot?

[shchenz]

clang/lib/Headers/CMakeLists.txt

170 ↗

(On Diff #417887)

@qiucf Looks like an error here?

[qiucf]

Thanks, fixed by rG2459ed67805c. nmmintrin.h just includes smmintrin.h so it's not critical.

clang/lib/Headers/ppc_wrappers/bmi2intrin.h

+/*===---- bmiintrin.h - Implementation of BMI2 intrinsics on PowerPC -------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if !defined X86GPRINTRIN_H_
+#error "Never use <bmi2intrin.h> directly; include <x86gprintrin.h> instead."
+#endif
+
+#ifndef BMI2INTRIN_H_
+#define BMI2INTRIN_H_
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _bzhi_u32(unsigned int __X, unsigned int __Y) {
+  return ((__X << (32 - __Y)) >> (32 - __Y));
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _mulx_u32(unsigned int __X, unsigned int __Y, unsigned int *__P) {
+  unsigned long long __res = (unsigned long long)__X * __Y;
+  *__P = (unsigned int)(__res >> 32);
+  return (unsigned int)__res;
+}
+
+#ifdef __PPC64__
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _bzhi_u64(unsigned long long __X, unsigned long long __Y) {
+  return ((__X << (64 - __Y)) >> (64 - __Y));
+}
+
+/* __int128 requires base 64-bit.  */
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _mulx_u64(unsigned long long __X, unsigned long long __Y,
+              unsigned long long *__P) {
+  unsigned __int128 __res = (unsigned __int128)__X * __Y;
+  *__P = (unsigned long long)(__res >> 64);
+  return (unsigned long long)__res;
+}
+
+#ifdef _ARCH_PWR7
+/* popcount and bpermd require power7 minimum.  */
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _pdep_u64(unsigned long long __X, unsigned long long __M) {
+  unsigned long result = 0x0UL;
+  const unsigned long mask = 0x8000000000000000UL;
+  unsigned long m = __M;
+  unsigned long c, t;
+  unsigned long p;
+
+  /* The pop-count of the mask gives the number of the bits from
+   source to process.  This is also needed to shift bits from the
+   source into the correct position for the result.  */
+  p = 64 - __builtin_popcountl(__M);
+
+  /* The loop is for the number of '1' bits in the mask and clearing
+   each mask bit as it is processed.  */
+  while (m != 0) {
+    c = __builtin_clzl(m);
+    t = __X << (p - c);
+    m ^= (mask >> c);
+    result |= (t & (mask >> c));
+    p++;
+  }
+  return (result);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _pext_u64(unsigned long long __X, unsigned long long __M) {
+  unsigned long p = 0x4040404040404040UL; // initial bit permute control
+  const unsigned long mask = 0x8000000000000000UL;
+  unsigned long m = __M;
+  unsigned long c;
+  unsigned long result;
+
+  /* if the mask is constant and selects 8 bits or less we can use
+   the Power8 Bit permute instruction.  */
+  if (__builtin_constant_p(__M) && (__builtin_popcountl(__M) <= 8)) {
+    /* Also if the pext mask is constant, then the popcount is
+     constant, we can evaluate the following loop at compile
+     time and use a constant bit permute vector.  */
+    for (long i = 0; i < __builtin_popcountl(__M); i++) {
+      c = __builtin_clzl(m);
+      p = (p << 8) | c;
+      m ^= (mask >> c);
+    }
+    result = __builtin_bpermd(p, __X);
+  } else {
+    p = 64 - __builtin_popcountl(__M);
+    result = 0;
+    /* We could a use a for loop here, but that combined with
+     -funroll-loops can expand to a lot of code.  The while
+     loop avoids unrolling and the compiler commons the xor
+     from clearing the mask bit with the (m != 0) test.  The
+     result is a more compact loop setup and body.  */
+    while (m != 0) {
+      unsigned long t;
+      c = __builtin_clzl(m);
+      t = (__X & (mask >> c)) >> (p - c);
+      m ^= (mask >> c);
+      result |= (t);
+      p++;
+    }
+  }
+  return (result);
+}
+
+/* these 32-bit implementations depend on 64-bit pdep/pext
+   which depend on _ARCH_PWR7.  */
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _pdep_u32(unsigned int __X, unsigned int __Y) {
+  return _pdep_u64(__X, __Y);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _pext_u32(unsigned int __X, unsigned int __Y) {
+  return _pext_u64(__X, __Y);
+}
+#endif /* _ARCH_PWR7  */
+#endif /* __PPC64__  */
+
+#endif /* BMI2INTRIN_H_ */

clang/lib/Headers/ppc_wrappers/bmiintrin.h

+/*===---- bmiintrin.h - Implementation of BMI intrinsics on PowerPC --------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if !defined X86GPRINTRIN_H_
+#error "Never use <bmiintrin.h> directly; include <x86gprintrin.h> instead."
+#endif
+
+#ifndef BMIINTRIN_H_
+#define BMIINTRIN_H_
+
+extern __inline unsigned short
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __tzcnt_u16(unsigned short __X) {
+  return __builtin_ctz(__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __andn_u32(unsigned int __X, unsigned int __Y) {
+  return (~__X & __Y);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _bextr_u32(unsigned int __X, unsigned int __P, unsigned int __L) {
+  return ((__X << (32 - (__L + __P))) >> (32 - __L));
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __bextr_u32(unsigned int __X, unsigned int __Y) {
+  unsigned int __P, __L;
+  __P = __Y & 0xFF;
+  __L = (__Y >> 8) & 0xFF;
+  return (_bextr_u32(__X, __P, __L));
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsi_u32(unsigned int __X) {
+  return (__X & -__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsi_u32(unsigned int __X) {
+  return __blsi_u32(__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsmsk_u32(unsigned int __X) {
+  return (__X ^ (__X - 1));
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsmsk_u32(unsigned int __X) {
+  return __blsmsk_u32(__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsr_u32(unsigned int __X) {
+  return (__X & (__X - 1));
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsr_u32(unsigned int __X) {
+  return __blsr_u32(__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __tzcnt_u32(unsigned int __X) {
+  return __builtin_ctz(__X);
+}
+
+extern __inline unsigned int
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _tzcnt_u32(unsigned int __X) {
+  return __builtin_ctz(__X);
+}
+
+/* use the 64-bit shift, rotate, and count leading zeros instructions
+   for long long.  */
+#ifdef __PPC64__
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __andn_u64(unsigned long long __X, unsigned long long __Y) {
+  return (~__X & __Y);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _bextr_u64(unsigned long long __X, unsigned int __P, unsigned int __L) {
+  return ((__X << (64 - (__L + __P))) >> (64 - __L));
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __bextr_u64(unsigned long long __X, unsigned long long __Y) {
+  unsigned int __P, __L;
+  __P = __Y & 0xFF;
+  __L = (__Y & 0xFF00) >> 8;
+  return (_bextr_u64(__X, __P, __L));
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsi_u64(unsigned long long __X) {
+  return __X & -__X;
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsi_u64(unsigned long long __X) {
+  return __blsi_u64(__X);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsmsk_u64(unsigned long long __X) {
+  return (__X ^ (__X - 1));
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsmsk_u64(unsigned long long __X) {
+  return __blsmsk_u64(__X);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __blsr_u64(unsigned long long __X) {
+  return (__X & (__X - 1));
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _blsr_u64(unsigned long long __X) {
+  return __blsr_u64(__X);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    __tzcnt_u64(unsigned long long __X) {
+  return __builtin_ctzll(__X);
+}
+
+extern __inline unsigned long long
+    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+    _tzcnt_u64(unsigned long long __X) {
+  return __builtin_ctzll(__X);
+}
+#endif /* __PPC64__  */
+
+#endif /* BMIINTRIN_H_ */

clang/lib/Headers/ppc_wrappers/emmintrin.h

 #endif
 
 #ifndef EMMINTRIN_H_
 #define EMMINTRIN_H_
 
 #if defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))
 
 #include <altivec.h>
+#include <assert.h>
 
 /* We need definitions from the SSE header files.  */
 #include <xmmintrin.h>
 
 /* SSE2 */
 typedef __vector double __v2df;
 typedef __vector long long __v2di;
 typedef __vector unsigned long long __v2du;

   result [0] = ((__v2df) __B)[0];
   return (__m128d) result;
 }
 
 /* Load two DPFP values from P.  The address must be 16-byte aligned.  */
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_load_pd (double const *__P)
 {
+  assert(((unsigned long)__P & 0xfUL) == 0UL);
   return ((__m128d)vec_ld(0, (__v16qu*)__P));
 }
 
 /* Load two DPFP values from P.  The address need not be 16-byte aligned.  */
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_loadu_pd (double const *__P)
 {
   return (vec_vsx_ld(0, __P));

   __v2df __tmp = _mm_load_pd (__P);
   return (__m128d)vec_xxpermdi (__tmp, __tmp, 2);
 }
 
 /* Store two DPFP values.  The address must be 16-byte aligned.  */
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_store_pd (double *__P, __m128d __A)
 {
+  assert(((unsigned long)__P & 0xfUL) == 0UL);
   vec_st((__v16qu)__A, 0, (__v16qu*)__P);
 }
 
 /* Store two DPFP values.  The address need not be 16-byte aligned.  */
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_storeu_pd (double *__P, __m128d __A)
 {
   *(__m128d_u *)__P = __A;

 }
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_cmpnge_pd (__m128d __A, __m128d __B)
 {
   return ((__m128d)vec_cmplt ((__v2df) __A, (__v2df) __B));
 }
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_cmpord_pd (__m128d __A, __m128d __B)
 {
-#if _ARCH_PWR8
   __v2du c, d;
   /* Compare against self will return false (0's) if NAN.  */
   c = (__v2du)vec_cmpeq (__A, __A);
   d = (__v2du)vec_cmpeq (__B, __B);
-#else
-  __v2du a, b;
-  __v2du c, d;
-  const __v2du double_exp_mask  = {0x7ff0000000000000, 0x7ff0000000000000};
-  a = (__v2du)vec_abs ((__v2df)__A);
-  b = (__v2du)vec_abs ((__v2df)__B);
-  c = (__v2du)vec_cmpgt (double_exp_mask, a);
-  d = (__v2du)vec_cmpgt (double_exp_mask, b);
-#endif
   /* A != NAN and B != NAN.  */
   return ((__m128d)vec_and(c, d));
 }
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_cmpunord_pd (__m128d __A, __m128d __B)
 {
 #if _ARCH_PWR8

 _mm_loadl_epi64 (__m128i_u const *__P)
 {
   return _mm_set_epi64 ((__m64)0LL, *(__m64 *)__P);
 }
 
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_store_si128 (__m128i *__P, __m128i __B)
 {
+  assert(((unsigned long )__P & 0xfUL) == 0UL);
   vec_st ((__v16qu) __B, 0, (__v16qu*)__P);
 }
 
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_storeu_si128 (__m128i_u *__P, __m128i __B)
 {
   *__P = __B;
 }

    Signed Integer Word format with Saturate.  */
   __asm__(
       "xvcvdpsxws %x0,%x1"
       : "=wa" (temp)
       : "wa" (rounded)
       : );
 
 #ifdef _ARCH_PWR8
+#ifdef __LITTLE_ENDIAN__
   temp = vec_mergeo (temp, temp);
+#else
+  temp = vec_mergee (temp, temp);
+#endif
   result = (__v4si) vec_vpkudum ((__vector long long) temp,
          (__vector long long) vzero);
 #else
   {
     const __v16qu pkperm = {0x00, 0x01, 0x02, 0x03, 0x08, 0x09, 0x0a, 0x0b,
   0x14, 0x15, 0x16, 0x17, 0x1c, 0x1d, 0x1e, 0x1f };
     result = (__v4si) vec_perm ((__v16qu) temp, (__v16qu) vzero, pkperm);
   }

 
   __asm__(
       "xvcvdpsp %x0,%x1"
       : "=wa" (temp)
       : "wa" (__A)
       : );
 
 #ifdef _ARCH_PWR8
+#ifdef __LITTLE_ENDIAN__
   temp = vec_mergeo (temp, temp);
+#else
+  temp = vec_mergee (temp, temp);
+#endif
   result = (__v4sf) vec_vpkudum ((__vector long long) temp,
          (__vector long long) vzero);
 #else
   {
     const __v16qu pkperm = {0x00, 0x01, 0x02, 0x03, 0x08, 0x09, 0x0a, 0x0b,
   0x14, 0x15, 0x16, 0x17, 0x1c, 0x1d, 0x1e, 0x1f };
     result = (__v4sf) vec_perm ((__v16qu) temp, (__v16qu) vzero, pkperm);
   }

    Signed Integer Word format with Saturate.  */
   __asm__(
       "xvcvdpsxws %x0,%x1"
       : "=wa" (temp)
       : "wa" (__A)
       : );
 
 #ifdef _ARCH_PWR8
+#ifdef __LITTLE_ENDIAN__
   temp = vec_mergeo (temp, temp);
+#else
+  temp = vec_mergee (temp, temp);
+#endif
   result = (__v4si) vec_vpkudum ((__vector long long) temp,
          (__vector long long) vzero);
 #else
   {
     const __v16qu pkperm = {0x00, 0x01, 0x02, 0x03, 0x08, 0x09, 0x0a, 0x0b,
   0x14, 0x15, 0x16, 0x17, 0x1c, 0x1d, 0x1e, 0x1f };
     result = (__v4si) vec_perm ((__v16qu) temp, (__v16qu) vzero, pkperm);
   }

 
 #ifdef _ARCH_PWR8
 /* Intrinsic functions that require PowerISA 2.07 minimum.  */
 
 /* Creates a 2-bit mask from the most significant bits of the DPFP values.  */
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_pd (__m128d  __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((__v2du) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned int perm_mask =
     {
 #ifdef __LITTLE_ENDIAN__
   0x80800040, 0x80808080, 0x80808080, 0x80808080
 #else
       0x80808080, 0x80808080, 0x80808080, 0x80804000
 #endif
     };
 
   result = ((__vector unsigned long long)
       vec_vbpermq ((__vector unsigned char) __A,
        (__vector unsigned char) perm_mask));
 
 #ifdef __LITTLE_ENDIAN__
   return result[1];
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_packs_epi16 (__m128i __A, __m128i __B)
 {
   return (__m128i) vec_packs ((__v8hi) __A, (__v8hi)__B);
 }

 _mm_mul_su32 (__m64 __A, __m64 __B)
 {
   unsigned int a = __A;
   unsigned int b = __B;
 
   return ((__m64)a * (__m64)b);
 }
 
+#ifdef _ARCH_PWR8
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_mul_epu32 (__m128i __A, __m128i __B)
 {
 #if __GNUC__ < 8
   __v2du result;
 
 #ifdef __LITTLE_ENDIAN__
   /* VMX Vector Multiply Odd Unsigned Word.  */

       : "v" (__A), "v" (__B)
       : );
 #endif
   return (__m128i) result;
 #else
   return (__m128i) vec_mule ((__v4su)__A, (__v4su)__B);
 #endif
 }
+#endif
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_slli_epi16 (__m128i __A, int __B)
 {
   __v8hu lshift;
   __v8hi result = { 0, 0, 0, 0, 0, 0, 0, 0 };
 
   if (__B >= 0 && __B < 16)

   __v2du lshift;
   __vector __bool long long shmask;
   const __v2du shmax = { 64, 64 };
   __v2du result;
 
   lshift = vec_splat ((__v2du) __B, 0);
   shmask = vec_cmplt (lshift, shmax);
   result = vec_sl ((__v2du) __A, lshift);
-  result = (__v2du)vec_sel ((__v2df) shmask, (__v2df)result, shmask);
+  result = vec_sel ((__v2du) shmask, result, shmask);
 
   return (__m128i) result;
 }
 #endif
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sra_epi16 (__m128i __A, __m128i __B)
 {

   __v2du rshift;
   __vector __bool long long shmask;
   const __v2du shmax = { 64, 64 };
   __v2du result;
 
   rshift = vec_splat ((__v2du) __B, 0);
   shmask = vec_cmplt (rshift, shmax);
   result = vec_sr ((__v2du) __A, rshift);
-  result = (__v2du)vec_sel ((__v2df) shmask, (__v2df)result, shmask);
+  result = vec_sel ((__v2du) shmask, result, shmask);
 
   return (__m128i) result;
 }
 #endif
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_and_pd (__m128d __A, __m128d __B)
 {

 {
   return (__m128i) vec_min ((__v16qu) __A, (__v16qu)__B);
 }
 
 
 #ifdef _ARCH_PWR8
 /* Intrinsic functions that require PowerISA 2.07 minimum.  */
 
-/* Creates a 4-bit mask from the most significant bits of the SPFP values.  */
+/* Return a mask created from the most significant bit of each 8-bit
+   element in A.  */
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_epi8 (__m128i __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((__v16qu) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned char perm_mask =
     {
   0x78, 0x70, 0x68, 0x60, 0x58, 0x50, 0x48, 0x40,
   0x38, 0x30, 0x28, 0x20, 0x18, 0x10, 0x08, 0x00
     };
 
   result = ((__vector unsigned long long)
       vec_vbpermq ((__vector unsigned char) __A,
        (__vector unsigned char) perm_mask));
 
 #ifdef __LITTLE_ENDIAN__
   return result[1];
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_mulhi_epu16 (__m128i __A, __m128i __B)
 {
   __v4su w0, w1;
   __v16qu xform1 = {

   return (__m128i) vec_avg ((__v8hu)__A, (__v8hu)__B);
 }
 
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sad_epu8 (__m128i __A, __m128i __B)
 {
   __v16qu a, b;
-  __v16qu vmin, vmax, vabsdiff;
+  __v16qu vabsdiff;
   __v4si vsum;
   const __v4su zero = { 0, 0, 0, 0 };
   __v4si result;
 
   a = (__v16qu) __A;
   b = (__v16qu) __B;
-  vmin = vec_min (a, b);
-  vmax = vec_max (a, b);
+#ifndef _ARCH_PWR9
+  __v16qu vmin = vec_min (a, b);
+  __v16qu vmax = vec_max (a, b);
   vabsdiff = vec_sub (vmax, vmin);
+#else
+  vabsdiff = vec_absd (a, b);
+#endif
   /* Sum four groups of bytes into integers.  */
   vsum = (__vector signed int) vec_sum4s (vabsdiff, zero);
+#ifdef __LITTLE_ENDIAN__
+  /* Sum across four integers with two integer results.  */
+  asm ("vsum2sws %0,%1,%2" : "=v" (result) : "v" (vsum), "v" (zero));
+  /* Note: vec_sum2s could be used here, but on little-endian, vector
+     shifts are added that are not needed for this use-case.
+     A vector shift to correctly position the 32-bit integer results
+     (currently at [0] and [2]) to [1] and [3] would then need to be
+     swapped back again since the desired results are two 64-bit
+     integers ([1]|[0] and [3]|[2]).  Thus, no shift is performed.  */
+#else
   /* Sum across four integers with two integer results.  */
   result = vec_sum2s (vsum, (__vector signed int) zero);
   /* Rotate the sums into the correct position.  */
-#ifdef __LITTLE_ENDIAN__
-  result = vec_sld (result, result, 4);
-#else
   result = vec_sld (result, result, 6);
 #endif
-  /* Rotate the sums into the correct position.  */
   return (__m128i) result;
 }
 
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_stream_si32 (int *__A, int __B)
 {
   /* Use the data cache block touch for store transient.  */
   __asm__ (

clang/lib/Headers/ppc_wrappers/immintrin.h

+/*===---- immintrin.h - Implementation of Intel intrinsics on PowerPC ------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef IMMINTRIN_H_
+#define IMMINTRIN_H_
+
+#include <x86gprintrin.h>
+
+#include <mmintrin.h>
+
+#include <xmmintrin.h>
+
+#include <emmintrin.h>
+
+#include <pmmintrin.h>
+
+#include <tmmintrin.h>
+
+#include <smmintrin.h>
+
+#endif /* IMMINTRIN_H_ */

clang/lib/Headers/ppc_wrappers/nmmintrin.h

+/*===---- nmmintrin.h - Implementation of SSE4 intrinsics on PowerPC -------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef NO_WARN_X86_INTRINSICS
+/* This header is distributed to simplify porting x86_64 code that
+   makes explicit use of Intel intrinsics to powerpc64le.
+   It is the user's responsibility to determine if the results are
+   acceptable and make additional changes as necessary.
+   Note that much code that uses Intel intrinsics can be rewritten in
+   standard C or GNU C extensions, which are more portable and better
+   optimized across multiple targets.  */
+#endif
+
+#ifndef NMMINTRIN_H_
+#define NMMINTRIN_H_
+
+/* We just include SSE4.1 header file.  */
+#include <smmintrin.h>
+
+#endif /* NMMINTRIN_H_ */

clang/lib/Headers/ppc_wrappers/pmmintrin.h

 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_hsub_pd (__m128d __X, __m128d __Y)
 {
   return (__m128d) vec_sub (vec_mergeh ((__v2df) __X, (__v2df)__Y),
           vec_mergel ((__v2df) __X, (__v2df)__Y));
 }
 
+#ifdef _ARCH_PWR8
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movehdup_ps (__m128 __X)
 {
   return (__m128)vec_mergeo ((__v4su)__X, (__v4su)__X);
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_moveldup_ps (__m128 __X)
 {
   return (__m128)vec_mergee ((__v4su)__X, (__v4su)__X);
 }
+#endif
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_loaddup_pd (double const *__P)
 {
   return (__m128d) vec_splats (*__P);
 }
 
 extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))

clang/lib/Headers/ppc_wrappers/smmintrin.h

 #ifndef SMMINTRIN_H_
 #define SMMINTRIN_H_
 
 #if defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))
 
 #include <altivec.h>
 #include <tmmintrin.h>
 
-extern __inline int
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_extract_epi8(__m128i __X, const int __N) {
-  return (unsigned char)((__v16qi)__X)[__N & 15];
+/* Rounding mode macros. */
+#define _MM_FROUND_TO_NEAREST_INT       0x00
+#define _MM_FROUND_TO_ZERO              0x01
+#define _MM_FROUND_TO_POS_INF           0x02
+#define _MM_FROUND_TO_NEG_INF           0x03
+#define _MM_FROUND_CUR_DIRECTION        0x04
+
+#define _MM_FROUND_NINT   \
+  (_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_FLOOR  \
+  (_MM_FROUND_TO_NEG_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_CEIL   \
+  (_MM_FROUND_TO_POS_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_TRUNC  \
+  (_MM_FROUND_TO_ZERO | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_RINT   \
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_NEARBYINT  \
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC)
+
+#define _MM_FROUND_RAISE_EXC            0x00
+#define _MM_FROUND_NO_EXC               0x08
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_pd (__m128d __A, int __rounding)
+{
+  __v2df __r;
+  union {
+    double __fr;
+    long long __fpscr;
+  } __enables_save, __fpscr_save;
+
+  if (__rounding & _MM_FROUND_NO_EXC)
+    {
+      /* Save enabled exceptions, disable all exceptions,
+   and preserve the rounding mode.  */
+#ifdef _ARCH_PWR9
+      __asm__ ("mffsce %0" : "=f" (__fpscr_save.__fr));
+      __enables_save.__fpscr = __fpscr_save.__fpscr & 0xf8;
+#else
+      __fpscr_save.__fr = __builtin_mffs ();
+      __enables_save.__fpscr = __fpscr_save.__fpscr & 0xf8;
+      __fpscr_save.__fpscr &= ~0xf8;
+      __builtin_mtfsf (0b00000011, __fpscr_save.__fr);
+#endif
+      /* Insert an artificial "read/write" reference to the variable
+   read below, to ensure the compiler does not schedule
+   a read/use of the variable before the FPSCR is modified, above.
+   This can be removed if and when GCC PR102783 is fixed.
+       */
+      __asm__ ("" : "+wa" (__A));
     }
 
-extern __inline int
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_extract_epi32(__m128i __X, const int __N) {
-  return ((__v4si)__X)[__N & 3];
+  switch (__rounding)
+    {
+      case _MM_FROUND_TO_NEAREST_INT:
+  __fpscr_save.__fr = __builtin_mffsl ();
+  __attribute__ ((fallthrough));
+      case _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC:
+  __builtin_set_fpscr_rn (0b00);
+  /* Insert an artificial "read/write" reference to the variable
+     read below, to ensure the compiler does not schedule
+     a read/use of the variable before the FPSCR is modified, above.
+     This can be removed if and when GCC PR102783 is fixed.
+   */
+  __asm__ ("" : "+wa" (__A));
+
+  __r = vec_rint ((__v2df) __A);
+
+  /* Insert an artificial "read" reference to the variable written
+     above, to ensure the compiler does not schedule the computation
+     of the value after the manipulation of the FPSCR, below.
+     This can be removed if and when GCC PR102783 is fixed.
+   */
+  __asm__ ("" : : "wa" (__r));
+  __builtin_set_fpscr_rn (__fpscr_save.__fpscr);
+  break;
+      case _MM_FROUND_TO_NEG_INF:
+      case _MM_FROUND_TO_NEG_INF | _MM_FROUND_NO_EXC:
+  __r = vec_floor ((__v2df) __A);
+  break;
+      case _MM_FROUND_TO_POS_INF:
+      case _MM_FROUND_TO_POS_INF | _MM_FROUND_NO_EXC:
+  __r = vec_ceil ((__v2df) __A);
+  break;
+      case _MM_FROUND_TO_ZERO:
+      case _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC:
+  __r = vec_trunc ((__v2df) __A);
+  break;
+      case _MM_FROUND_CUR_DIRECTION:
+  __r = vec_rint ((__v2df) __A);
+  break;
+    }
+  if (__rounding & _MM_FROUND_NO_EXC)
+    {
+      /* Insert an artificial "read" reference to the variable written
+   above, to ensure the compiler does not schedule the computation
+   of the value after the manipulation of the FPSCR, below.
+   This can be removed if and when GCC PR102783 is fixed.
+       */
+      __asm__ ("" : : "wa" (__r));
+      /* Restore enabled exceptions.  */
+      __fpscr_save.__fr = __builtin_mffsl ();
+      __fpscr_save.__fpscr |= __enables_save.__fpscr;
+      __builtin_mtfsf (0b00000011, __fpscr_save.__fr);
+    }
+  return (__m128d) __r;
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_sd (__m128d __A, __m128d __B, int __rounding)
+{
+  __B = _mm_round_pd (__B, __rounding);
+  __v2df __r = { ((__v2df) __B)[0], ((__v2df) __A)[1] };
+  return (__m128d) __r;
 }
 
-extern __inline int
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_extract_epi64(__m128i __X, const int __N) {
-  return ((__v2di)__X)[__N & 1];
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ps (__m128 __A, int __rounding)
+{
+  __v4sf __r;
+  union {
+    double __fr;
+    long long __fpscr;
+  } __enables_save, __fpscr_save;
+
+  if (__rounding & _MM_FROUND_NO_EXC)
+    {
+      /* Save enabled exceptions, disable all exceptions,
+   and preserve the rounding mode.  */
+#ifdef _ARCH_PWR9
+      __asm__ ("mffsce %0" : "=f" (__fpscr_save.__fr));
+      __enables_save.__fpscr = __fpscr_save.__fpscr & 0xf8;
+#else
+      __fpscr_save.__fr = __builtin_mffs ();
+      __enables_save.__fpscr = __fpscr_save.__fpscr & 0xf8;
+      __fpscr_save.__fpscr &= ~0xf8;
+      __builtin_mtfsf (0b00000011, __fpscr_save.__fr);
+#endif
+      /* Insert an artificial "read/write" reference to the variable
+   read below, to ensure the compiler does not schedule
+   a read/use of the variable before the FPSCR is modified, above.
+   This can be removed if and when GCC PR102783 is fixed.
+       */
+      __asm__ ("" : "+wa" (__A));
     }
 
-extern __inline int
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_extract_ps(__m128 __X, const int __N) {
+  switch (__rounding)
+    {
+      case _MM_FROUND_TO_NEAREST_INT:
+  __fpscr_save.__fr = __builtin_mffsl ();
+  __attribute__ ((fallthrough));
+      case _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC:
+  __builtin_set_fpscr_rn (0b00);
+  /* Insert an artificial "read/write" reference to the variable
+     read below, to ensure the compiler does not schedule
+     a read/use of the variable before the FPSCR is modified, above.
+     This can be removed if and when GCC PR102783 is fixed.
+   */
+  __asm__ ("" : "+wa" (__A));
+
+  __r = vec_rint ((__v4sf) __A);
+
+  /* Insert an artificial "read" reference to the variable written
+     above, to ensure the compiler does not schedule the computation
+     of the value after the manipulation of the FPSCR, below.
+     This can be removed if and when GCC PR102783 is fixed.
+   */
+  __asm__ ("" : : "wa" (__r));
+  __builtin_set_fpscr_rn (__fpscr_save.__fpscr);
+  break;
+      case _MM_FROUND_TO_NEG_INF:
+      case _MM_FROUND_TO_NEG_INF | _MM_FROUND_NO_EXC:
+  __r = vec_floor ((__v4sf) __A);
+  break;
+      case _MM_FROUND_TO_POS_INF:
+      case _MM_FROUND_TO_POS_INF | _MM_FROUND_NO_EXC:
+  __r = vec_ceil ((__v4sf) __A);
+  break;
+      case _MM_FROUND_TO_ZERO:
+      case _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC:
+  __r = vec_trunc ((__v4sf) __A);
+  break;
+      case _MM_FROUND_CUR_DIRECTION:
+  __r = vec_rint ((__v4sf) __A);
+  break;
+    }
+  if (__rounding & _MM_FROUND_NO_EXC)
+    {
+      /* Insert an artificial "read" reference to the variable written
+   above, to ensure the compiler does not schedule the computation
+   of the value after the manipulation of the FPSCR, below.
+   This can be removed if and when GCC PR102783 is fixed.
+       */
+      __asm__ ("" : : "wa" (__r));
+      /* Restore enabled exceptions.  */
+      __fpscr_save.__fr = __builtin_mffsl ();
+      __fpscr_save.__fpscr |= __enables_save.__fpscr;
+      __builtin_mtfsf (0b00000011, __fpscr_save.__fr);
+    }
+  return (__m128) __r;
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ss (__m128 __A, __m128 __B, int __rounding)
+{
+  __B = _mm_round_ps (__B, __rounding);
+  __v4sf __r = (__v4sf) __A;
+  __r[0] = ((__v4sf) __B)[0];
+  return (__m128) __r;
+}
+
+#define _mm_ceil_pd(V)     _mm_round_pd ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_sd(D, V)  _mm_round_sd ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_pd(V)    _mm_round_pd((V), _MM_FROUND_FLOOR)
+#define _mm_floor_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_FLOOR)
+
+#define _mm_ceil_ps(V)     _mm_round_ps ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_ss(D, V)  _mm_round_ss ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_ps(V)    _mm_round_ps ((V), _MM_FROUND_FLOOR)
+#define _mm_floor_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_FLOOR)
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_insert_epi8 (__m128i const __A, int const __D, int const __N)
+{
+  __v16qi result = (__v16qi)__A;
+
+  result [__N & 0xf] = __D;
+
+  return (__m128i) result;
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_insert_epi32 (__m128i const __A, int const __D, int const __N)
+{
+  __v4si result = (__v4si)__A;
+
+  result [__N & 3] = __D;
+
+  return (__m128i) result;
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_insert_epi64 (__m128i const __A, long long const __D, int const __N)
+{
+  __v2di result = (__v2di)__A;
+
+  result [__N & 1] = __D;
+
+  return (__m128i) result;
+}
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_extract_epi8 (__m128i __X, const int __N)
+{
+  return (unsigned char) ((__v16qi)__X)[__N & 15];
+}
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_extract_epi32 (__m128i __X, const int __N)
+{
   return ((__v4si)__X)[__N & 3];
 }
 
-extern __inline __m128i
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_blend_epi16(__m128i __A, __m128i __B, const int __imm8) {
-  __v16qi __charmask = vec_splats((signed char)__imm8);
-  __charmask = vec_gb(__charmask);
-  __v8hu __shortmask = (__v8hu)vec_unpackh(__charmask);
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_extract_epi64 (__m128i __X, const int __N)
+{
+  return ((__v2di)__X)[__N & 1];
+}
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_extract_ps (__m128 __X, const int __N)
+{
+  return ((__v4si)__X)[__N & 3];
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blend_epi16 (__m128i __A, __m128i __B, const int __imm8)
+{
+  __v16qi __charmask = vec_splats ((signed char) __imm8);
+  __charmask = vec_gb (__charmask);
+  __v8hu __shortmask = (__v8hu) vec_unpackh (__charmask);
   #ifdef __BIG_ENDIAN__
-  __shortmask = vec_reve(__shortmask);
+  __shortmask = vec_reve (__shortmask);
   #endif
-  return (__m128i)vec_sel((__v8hu)__A, (__v8hu)__B, __shortmask);
+  return (__m128i) vec_sel ((__v8hu) __A, (__v8hu) __B, __shortmask);
 }
+#endif
 
-extern __inline __m128i
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_blendv_epi8(__m128i __A, __m128i __B, __m128i __mask) {
-  const __v16qu __seven = vec_splats((unsigned char)0x07);
-  __v16qu __lmask = vec_sra((__v16qu)__mask, __seven);
-  return (__m128i)vec_sel((__v16qu)__A, (__v16qu)__B, __lmask);
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blendv_epi8 (__m128i __A, __m128i __B, __m128i __mask)
+{
+#ifdef _ARCH_PWR10
+  return (__m128i) vec_blendv ((__v16qi) __A, (__v16qi) __B, (__v16qu) __mask);
+#else
+  const __v16qu __seven = vec_splats ((unsigned char) 0x07);
+  __v16qu __lmask = vec_sra ((__v16qu) __mask, __seven);
+  return (__m128i) vec_sel ((__v16qi) __A, (__v16qi) __B, __lmask);
+#endif
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blend_ps (__m128 __A, __m128 __B, const int __imm8)
+{
+  __v16qu __pcv[] =
+    {
+      {  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
+      { 16, 17, 18, 19,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
+      {  0,  1,  2,  3, 20, 21, 22, 23,  8,  9, 10, 11, 12, 13, 14, 15 },
+      { 16, 17, 18, 19, 20, 21, 22, 23,  8,  9, 10, 11, 12, 13, 14, 15 },
+      {  0,  1,  2,  3,  4,  5,  6,  7, 24, 25, 26, 27, 12, 13, 14, 15 },
+      { 16, 17, 18, 19,  4,  5,  6,  7, 24, 25, 26, 27, 12, 13, 14, 15 },
+      {  0,  1,  2,  3, 20, 21, 22, 23, 24, 25, 26, 27, 12, 13, 14, 15 },
+      { 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 12, 13, 14, 15 },
+      {  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 28, 29, 30, 31 },
+      { 16, 17, 18, 19,  4,  5,  6,  7,  8,  9, 10, 11, 28, 29, 30, 31 },
+      {  0,  1,  2,  3, 20, 21, 22, 23,  8,  9, 10, 11, 28, 29, 30, 31 },
+      { 16, 17, 18, 19, 20, 21, 22, 23,  8,  9, 10, 11, 28, 29, 30, 31 },
+      {  0,  1,  2,  3,  4,  5,  6,  7, 24, 25, 26, 27, 28, 29, 30, 31 },
+      { 16, 17, 18, 19,  4,  5,  6,  7, 24, 25, 26, 27, 28, 29, 30, 31 },
+      {  0,  1,  2,  3, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31 },
+      { 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31 },
+    };
+  __v16qu __r = vec_perm ((__v16qu) __A, (__v16qu)__B, __pcv[__imm8]);
+  return (__m128) __r;
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blendv_ps (__m128 __A, __m128 __B, __m128 __mask)
+{
+#ifdef _ARCH_PWR10
+  return (__m128) vec_blendv ((__v4sf) __A, (__v4sf) __B, (__v4su) __mask);
+#else
+  const __v4si __zero = {0};
+  const __vector __bool int __boolmask = vec_cmplt ((__v4si) __mask, __zero);
+  return (__m128) vec_sel ((__v4su) __A, (__v4su) __B, (__v4su) __boolmask);
+#endif
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blend_pd (__m128d __A, __m128d __B, const int __imm8)
+{
+  __v16qu __pcv[] =
+    {
+      {  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
+      { 16, 17, 18, 19, 20, 21, 22, 23,  8,  9, 10, 11, 12, 13, 14, 15 },
+      {  0,  1,  2,  3,  4,  5,  6,  7, 24, 25, 26, 27, 28, 29, 30, 31 },
+      { 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31 }
+    };
+  __v16qu __r = vec_perm ((__v16qu) __A, (__v16qu)__B, __pcv[__imm8]);
+  return (__m128d) __r;
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_blendv_pd (__m128d __A, __m128d __B, __m128d __mask)
+{
+#ifdef _ARCH_PWR10
+  return (__m128d) vec_blendv ((__v2df) __A, (__v2df) __B, (__v2du) __mask);
+#else
+  const __v2di __zero = {0};
+  const __vector __bool long long __boolmask = vec_cmplt ((__v2di) __mask, __zero);
+  return (__m128d) vec_sel ((__v2du) __A, (__v2du) __B, (__v2du) __boolmask);
+#endif
 }
+#endif
 
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testz_si128 (__m128i __A, __m128i __B)
+{
+  /* Note: This implementation does NOT set "zero" or "carry" flags.  */
+  const __v16qu __zero = {0};
+  return vec_all_eq (vec_and ((__v16qu) __A, (__v16qu) __B), __zero);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testc_si128 (__m128i __A, __m128i __B)
+{
+  /* Note: This implementation does NOT set "zero" or "carry" flags.  */
+  const __v16qu __zero = {0};
+  const __v16qu __notA = vec_nor ((__v16qu) __A, (__v16qu) __A);
+  return vec_all_eq (vec_and ((__v16qu) __notA, (__v16qu) __B), __zero);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_testnzc_si128 (__m128i __A, __m128i __B)
+{
+  /* Note: This implementation does NOT set "zero" or "carry" flags.  */
+  return _mm_testz_si128 (__A, __B) == 0 && _mm_testc_si128 (__A, __B) == 0;
+}
+
+#define _mm_test_all_zeros(M, V) _mm_testz_si128 ((M), (V))
+
+#define _mm_test_all_ones(V) \
+  _mm_testc_si128 ((V), _mm_cmpeq_epi32 ((V), (V)))
+
+#define _mm_test_mix_ones_zeros(M, V) _mm_testnzc_si128 ((M), (V))
+
+#ifdef _ARCH_PWR8
 extern __inline __m128i
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_insert_epi8(__m128i const __A, int const __D, int const __N) {
-  __v16qi result = (__v16qi)__A;
-  result[__N & 0xf] = __D;
-  return (__m128i)result;
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpeq_epi64 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_cmpeq ((__v2di) __X, (__v2di) __Y);
 }
+#endif
 
 extern __inline __m128i
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_insert_epi32(__m128i const __A, int const __D, int const __N) {
-  __v4si result = (__v4si)__A;
-  result[__N & 3] = __D;
-  return (__m128i)result;
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epi8 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_min ((__v16qi)__X, (__v16qi)__Y);
 }
 
 extern __inline __m128i
-    __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-    _mm_insert_epi64(__m128i const __A, long long const __D, int const __N) {
-  __v2di result = (__v2di)__A;
-  result[__N & 1] = __D;
-  return (__m128i)result;
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epu16 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_min ((__v8hu)__X, (__v8hu)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epi32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_min ((__v4si)__X, (__v4si)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_min_epu32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_min ((__v4su)__X, (__v4su)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epi8 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_max ((__v16qi)__X, (__v16qi)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epu16 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_max ((__v8hu)__X, (__v8hu)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epi32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_max ((__v4si)__X, (__v4si)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_max_epu32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_max ((__v4su)__X, (__v4su)__Y);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mullo_epi32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_mul ((__v4su) __X, (__v4su) __Y);
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mul_epi32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_mule ((__v4si) __X, (__v4si) __Y);
+}
+#endif
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi8_epi16 (__m128i __A)
+{
+  return (__m128i) vec_unpackh ((__v16qi) __A);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi8_epi32 (__m128i __A)
+{
+  __A = (__m128i) vec_unpackh ((__v16qi) __A);
+  return (__m128i) vec_unpackh ((__v8hi) __A);
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi8_epi64 (__m128i __A)
+{
+  __A = (__m128i) vec_unpackh ((__v16qi) __A);
+  __A = (__m128i) vec_unpackh ((__v8hi) __A);
+  return (__m128i) vec_unpackh ((__v4si) __A);
 }
+#endif
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi16_epi32 (__m128i __A)
+{
+  return (__m128i) vec_unpackh ((__v8hi) __A);
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi16_epi64 (__m128i __A)
+{
+  __A = (__m128i) vec_unpackh ((__v8hi) __A);
+  return (__m128i) vec_unpackh ((__v4si) __A);
+}
+#endif
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepi32_epi64 (__m128i __A)
+{
+  return (__m128i) vec_unpackh ((__v4si) __A);
+}
+#endif
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu8_epi16 (__m128i __A)
+{
+  const __v16qu __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v16qu) __A, __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v16qu) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu8_epi32 (__m128i __A)
+{
+  const __v16qu __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v16qu) __A, __zero);
+  __A = (__m128i) vec_mergeh ((__v8hu) __A, (__v8hu) __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v16qu) __A);
+  __A = (__m128i) vec_mergeh ((__v8hu) __zero, (__v8hu) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu8_epi64 (__m128i __A)
+{
+  const __v16qu __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v16qu) __A, __zero);
+  __A = (__m128i) vec_mergeh ((__v8hu) __A, (__v8hu) __zero);
+  __A = (__m128i) vec_mergeh ((__v4su) __A, (__v4su) __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v16qu) __A);
+  __A = (__m128i) vec_mergeh ((__v8hu) __zero, (__v8hu) __A);
+  __A = (__m128i) vec_mergeh ((__v4su) __zero, (__v4su) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu16_epi32 (__m128i __A)
+{
+  const __v8hu __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v8hu) __A, __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v8hu) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu16_epi64 (__m128i __A)
+{
+  const __v8hu __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v8hu) __A, __zero);
+  __A = (__m128i) vec_mergeh ((__v4su) __A, (__v4su) __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v8hu) __A);
+  __A = (__m128i) vec_mergeh ((__v4su) __zero, (__v4su) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtepu32_epi64 (__m128i __A)
+{
+  const __v4su __zero = {0};
+#ifdef __LITTLE_ENDIAN__
+  __A = (__m128i) vec_mergeh ((__v4su) __A, __zero);
+#else /* __BIG_ENDIAN__.  */
+  __A = (__m128i) vec_mergeh (__zero, (__v4su) __A);
+#endif /* __BIG_ENDIAN__.  */
+  return __A;
+}
+
+/* Return horizontal packed word minimum and its index in bits [15:0]
+   and bits [18:16] respectively.  */
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_minpos_epu16 (__m128i __A)
+{
+  union __u
+    {
+      __m128i __m;
+      __v8hu __uh;
+    };
+  union __u __u = { .__m = __A }, __r = { .__m = {0} };
+  unsigned short __ridx = 0;
+  unsigned short __rmin = __u.__uh[__ridx];
+  for (unsigned long __i = 1; __i < 8; __i++)
+    {
+      if (__u.__uh[__i] < __rmin)
+  {
+    __rmin = __u.__uh[__i];
+    __ridx = __i;
+  }
+    }
+  __r.__uh[0] = __rmin;
+  __r.__uh[1] = __ridx;
+  return __r.__m;
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_packus_epi32 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_packsu ((__v4si) __X, (__v4si) __Y);
+}
+
+#ifdef _ARCH_PWR8
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmpgt_epi64 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) vec_cmpgt ((__v2di) __X, (__v2di) __Y);
+}
+#endif
 
 #else
 #include_next <smmintrin.h>
 #endif /* defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))   \
         */
 
-#endif /* _SMMINTRIN_H_ */
+#endif /* SMMINTRIN_H_ */

clang/lib/Headers/ppc_wrappers/tmmintrin.h

 #endif
 
 #ifndef TMMINTRIN_H_
 #define TMMINTRIN_H_
 
 #if defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))
 
 #include <altivec.h>
+#include <assert.h>
 
 /* We need definitions from the SSE header files.  */
 #include <pmmintrin.h>
 
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_abs_epi16 (__m128i __A)
 {

   __v16qi __C = (__v16qi) (__v2du) { __A, __A };
   __v16qi __D = (__v16qi) (__v2du) { __B, __B };
   __vector __bool char __select = vec_cmplt ((__v16qi) __D, __zero);
   __C = vec_perm ((__v16qi) __C, (__v16qi) __C, (__v16qu) __D);
   __C = vec_sel (__C, __zero, __select);
   return (__m64) ((__v2du) (__C))[0];
 }
 
+#ifdef _ARCH_PWR8
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_epi8 (__m128i __A, __m128i __B)
 {
   const __v16qi __zero = { 0 };
   __v16qi __selectneg = (__v16qi) vec_cmplt ((__v16qi) __B, __zero);
   __v16qi __selectpos =
     (__v16qi) vec_neg ((__v16qi) vec_cmpgt ((__v16qi) __B, __zero));
   __v16qi __conv = vec_add (__selectneg, __selectpos);
   return (__m128i) vec_mul ((__v16qi) __A, (__v16qi) __conv);
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_epi16 (__m128i __A, __m128i __B)
 {
   const __v8hi __zero = { 0 };
   __v8hi __selectneg = (__v8hi) vec_cmplt ((__v8hi) __B, __zero);
   __v8hi __selectpos =
     (__v8hi) vec_neg ((__v8hi) vec_cmpgt ((__v8hi) __B, __zero));
   __v8hi __conv = vec_add (__selectneg, __selectpos);
   return (__m128i) vec_mul ((__v8hi) __A, (__v8hi) __conv);
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_epi32 (__m128i __A, __m128i __B)
 {
   const __v4si __zero = { 0 };
   __v4si __selectneg = (__v4si) vec_cmplt ((__v4si) __B, __zero);
   __v4si __selectpos =
     (__v4si) vec_neg ((__v4si) vec_cmpgt ((__v4si) __B, __zero));
   __v4si __conv = vec_add (__selectneg, __selectpos);
   return (__m128i) vec_mul ((__v4si) __A, (__v4si) __conv);
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m64
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_pi8 (__m64 __A, __m64 __B)
 {
   const __v16qi __zero = { 0 };
   __v16qi __C = (__v16qi) (__v2du) { __A, __A };
   __v16qi __D = (__v16qi) (__v2du) { __B, __B };
   __C = (__v16qi) _mm_sign_epi8 ((__m128i) __C, (__m128i) __D);
   return (__m64) ((__v2du) (__C))[0];
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m64
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_pi16 (__m64 __A, __m64 __B)
 {
   const __v8hi __zero = { 0 };
   __v8hi __C = (__v8hi) (__v2du) { __A, __A };
   __v8hi __D = (__v8hi) (__v2du) { __B, __B };
   __C = (__v8hi) _mm_sign_epi16 ((__m128i) __C, (__m128i) __D);
   return (__m64) ((__v2du) (__C))[0];
 }
+#endif
 
+#ifdef _ARCH_PWR8
 extern __inline __m64
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_sign_pi32 (__m64 __A, __m64 __B)
 {
   const __v4si __zero = { 0 };
   __v4si __C = (__v4si) (__v2du) { __A, __A };
   __v4si __D = (__v4si) (__v2du) { __B, __B };
   __C = (__v4si) _mm_sign_epi32 ((__m128i) __C, (__m128i) __D);
   return (__m64) ((__v2du) (__C))[0];
 }
+#endif
 
 extern __inline __m128i
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_maddubs_epi16 (__m128i __A, __m128i __B)
 {
   __v8hi __unsigned = vec_splats ((signed short) 0x00ff);
   __v8hi __C = vec_and (vec_unpackh ((__v16qi) __A), __unsigned);
   __v8hi __D = vec_and (vec_unpackl ((__v16qi) __A), __unsigned);

clang/lib/Headers/ppc_wrappers/x86gprintrin.h

+/*===--- x86gprintrin.h - Implementation of X86 GPR intrinsics on PowerPC --===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef X86GPRINTRIN_H_
+#define X86GPRINTRIN_H_
+
+#include <bmiintrin.h>
+
+#include <bmi2intrin.h>
+
+#endif /* X86GPRINTRIN_H_ */

clang/lib/Headers/ppc_wrappers/x86intrin.h

+/*===---- x86intrin.h - Implementation of X86 intrinsics on PowerPC --------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef NO_WARN_X86_INTRINSICS
+/* This header is distributed to simplify porting x86_64 code that
+   makes explicit use of Intel intrinsics to powerpc64le.
+   It is the user's responsibility to determine if the results are
+   acceptable and make additional changes as necessary.
+   Note that much code that uses Intel intrinsics can be rewritten in
+   standard C or GNU C extensions, which are more portable and better
+   optimized across multiple targets.  */
+#error "Please read comment above.  Use -DNO_WARN_X86_INTRINSICS to disable this error."
+#endif
+
+#ifndef X86INTRIN_H_
+#define X86INTRIN_H_
+
+#ifdef __ALTIVEC__
+#include <immintrin.h>
+#endif /* __ALTIVEC__ */
+
+#endif /* X86INTRIN_H_ */

clang/lib/Headers/ppc_wrappers/xmmintrin.h

    portable <fenv.h> instead of access MXSCR directly.
 
    Most SSE scalar float intrinsic operations can be performed more
    efficiently as C language float scalar operations or optimized to
    use vector SIMD operations. We recommend this for new applications. */
 #error "Please read comment above. Use -DNO_WARN_X86_INTRINSICS to disable this error."
 #endif
 
-#ifndef _XMMINTRIN_H_INCLUDED
-#define _XMMINTRIN_H_INCLUDED
-
-#if defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))
+#ifndef XMMINTRIN_H_
+#define XMMINTRIN_H_
 
 /* Define four value permute mask */
 #define _MM_SHUFFLE(w,x,y,z) (((w) << 6) | ((x) << 4) | ((y) << 2) | (z))
 
 #include <altivec.h>
 
 /* Avoid collisions between altivec.h and strict adherence to C++ and
    C11 standards.  This should eventually be done inside altivec.h itself,
    but only after testing a full distro build.  */
 #if defined(__STRICT_ANSI__) && (defined(__cplusplus) || \
          (defined(__STDC_VERSION__) &&  \
           __STDC_VERSION__ >= 201112L))
 #undef vector
 #undef pixel
 #undef bool
 #endif
 
+#include <assert.h>
+
 /* We need type definitions from the MMX header file.  */
 #include <mmintrin.h>
 
 /* Get _mm_malloc () and _mm_free ().  */
 #if __STDC_HOSTED__
 #include <mm_malloc.h>
 #endif
 
 /* The Intel API is flexible enough that we must allow aliasing with other
    vector types, and their scalar components.  */
-typedef vector float __m128 __attribute__((__may_alias__));
+typedef float __m128 __attribute__ ((__vector_size__ (16), __may_alias__));
 
 /* Unaligned version of the same type.  */
-typedef vector float __m128_u __attribute__((__may_alias__, __aligned__(1)));
+typedef float __m128_u __attribute__ ((__vector_size__ (16), __may_alias__,
+               __aligned__ (1)));
 
 /* Internal data types for implementing the intrinsics.  */
-typedef vector float __v4sf;
+typedef float __v4sf __attribute__ ((__vector_size__ (16)));
 
 /* Create an undefined vector.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_undefined_ps (void)
 {
   __m128 __Y = __Y;
   return __Y;
 }
 
 /* Create a vector of zeros.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_setzero_ps (void)
 {
   return __extension__ (__m128){ 0.0f, 0.0f, 0.0f, 0.0f };
 }
 
 /* Load four SPFP values from P.  The address must be 16-byte aligned.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_load_ps (float const *__P)
 {
+  assert(((unsigned long)__P & 0xfUL) == 0UL);
   return ((__m128)vec_ld(0, (__v4sf*)__P));
 }
 
 /* Load four SPFP values from P.  The address need not be 16-byte aligned.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_loadu_ps (float const *__P)
 {
   return (vec_vsx_ld(0, __P));

 {
   return __extension__ (__m128)(__v4sf){ __Z, __Y, __X, __W };
 }
 
 /* Store four SPFP values.  The address must be 16-byte aligned.  */
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_store_ps (float *__P, __m128 __A)
 {
+  assert(((unsigned long)__P & 0xfUL) == 0UL);
   vec_st((__v4sf)__A, 0, (__v4sf*)__P);
 }
 
 /* Store four SPFP values.  The address need not be 16-byte aligned.  */
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_storeu_ps (float *__P, __m128 __A)
 {
   *(__m128_u *)__P = __A;

   return ((__v4sf)__A)[0];
 }
 
 /* Convert the lower SPFP value to a 32-bit integer according to the current
    rounding mode.  */
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_cvtss_si32 (__m128 __A)
 {
-  __m64 res = 0;
+  int res;
 #ifdef _ARCH_PWR8
   double dtmp;
   __asm__(
 #ifdef __LITTLE_ENDIAN__
       "xxsldwi %x0,%x0,%x0,3;\n"
 #endif
       "xscvspdp %x2,%x0;\n"
       "fctiw  %2,%2;\n"

 
 /* Convert the lower SPFP value to a 32-bit integer according to the
    current rounding mode.  */
 
 /* Intel intrinsic.  */
 extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_cvtss_si64 (__m128 __A)
 {
-  __m64 res = 0;
-#ifdef _ARCH_PWR8
+  long long res;
+#if defined (_ARCH_PWR8) && defined (__powerpc64__)
   double dtmp;
   __asm__(
 #ifdef __LITTLE_ENDIAN__
       "xxsldwi %x0,%x0,%x0,3;\n"
 #endif
       "xscvspdp %x2,%x0;\n"
       "fctid  %2,%2;\n"
       "mfvsrd  %1,%x2;\n"

   *__P = __a[0];
 }
 
 #ifdef _ARCH_PWR8
 /* Intrinsic functions that require PowerISA 2.07 minimum.  */
 
 /* Creates a 4-bit mask from the most significant bits of the SPFP values.  */
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_ps (__m128  __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((__vector unsigned int) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned int perm_mask =
     {
 #ifdef __LITTLE_ENDIAN__
   0x00204060, 0x80808080, 0x80808080, 0x80808080
 #else
       0x80808080, 0x80808080, 0x80808080, 0x00204060
 #endif
     };
 
   result = ((__vector unsigned long long)
       vec_vbpermq ((__vector unsigned char) __A,
        (__vector unsigned char) perm_mask));
 
 #ifdef __LITTLE_ENDIAN__
   return result[1];
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */
 
 /* Create a vector with all four elements equal to *P.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_load1_ps (float const *__P)
 {
   return _mm_set1_ps (*__P);

 {
   return _mm_min_pu8 (__A, __B);
 }
 
 /* Create an 8-bit mask of the signs of 8-bit values.  */
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_pi8 (__m64 __A)
 {
+#ifdef __powerpc64__
   unsigned long long p =
 #ifdef __LITTLE_ENDIAN__
                          0x0008101820283038UL; // permute control for sign bits
 #else
                          0x3830282018100800UL; // permute control for sign bits
 #endif
   return __builtin_bpermd (p, __A);
+#else
+#ifdef __LITTLE_ENDIAN__
+  unsigned int mask = 0x20283038UL;
+  unsigned int r1 = __builtin_bpermd (mask, __A) & 0xf;
+  unsigned int r2 = __builtin_bpermd (mask, __A >> 32) & 0xf;
+#else
+  unsigned int mask = 0x38302820UL;
+  unsigned int r1 = __builtin_bpermd (mask, __A >> 32) & 0xf;
+  unsigned int r2 = __builtin_bpermd (mask, __A) & 0xf;
+#endif
+  return (r2 << 4) | r1;
+#endif
 }
 
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _m_pmovmskb (__m64 __A)
 {
   return _mm_movemask_pi8 (__A);
 }
 

 /* For backward source compatibility.  */
 //# include <emmintrin.h>
 
 #else
 #include_next <xmmintrin.h>
 #endif /* defined(__ppc64__) && (defined(__linux__) || defined(__FreeBSD__))   \
         */
 
-#endif /* _XMMINTRIN_H_INCLUDED */
+#endif /* XMMINTRIN_H_ */