Function signatures and decorations match gcc/config/i386/smmintrin.h.
Also, copy tests for:
- _mm_cvtepi8_epi16, _mm_cvtepi8_epi32, _mm_cvtepi8_epi64
- _mm_cvtepi16_epi32, _mm_cvtepi16_epi64
- _mm_cvtepi32_epi64,
- _mm_cvtepu8_epi16, _mm_cvtepu8_epi32, _mm_cvtepu8_epi64
- _mm_cvtepu16_epi32, _mm_cvtepu16_epi64
- _mm_cvtepu32_epi64
from gcc/testsuite/gcc.target/i386.
sse4_1-pmovsxbd.c, sse4_1-pmovsxbq.c, and sse4_1-pmovsxbw.c were
modified from using "char" types to "signed char" types, because
the default is unsigned on powerpc.
2021-10-11 Paul A. Clarke <pc@us.ibm.com>
gcc
* config/rs6000/smmintrin.h (_mm_cvtepi8_epi16, _mm_cvtepi8_epi32,
_mm_cvtepi8_epi64, _mm_cvtepi16_epi32, _mm_cvtepi16_epi64,
_mm_cvtepi32_epi64, _mm_cvtepu8_epi16, _mm_cvtepu8_epi32,
_mm_cvtepu8_epi64, _mm_cvtepu16_epi32, _mm_cvtepu16_epi64,
_mm_cvtepu32_epi64): New.
gcc/testsuite
* gcc.target/powerpc/sse4_1-pmovsxbd.c: Copy from gcc.target/i386,
adjust dg directives to suit.
* gcc.target/powerpc/sse4_1-pmovsxbq.c: Same.
* gcc.target/powerpc/sse4_1-pmovsxbw.c: Same.
* gcc.target/powerpc/sse4_1-pmovsxdq.c: Same.
* gcc.target/powerpc/sse4_1-pmovsxwd.c: Same.
* gcc.target/powerpc/sse4_1-pmovsxwq.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxbd.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxbq.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxbw.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxdq.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxwd.c: Same.
* gcc.target/powerpc/sse4_1-pmovzxwq.c: Same.
return (__m128i) vec_max ((__v4su)__X, (__v4su)__Y);
}
+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. */
__inline __m128i
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 4];
+ int i[NUM];
+ signed char c[NUM * 4];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 4) + (i / 4) * 16] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 4)
+ dst.x [i / 4] = _mm_cvtepi8_epi32 (src.x [i / 4]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 4) + (i / 4) * 16] != dst.i[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target p8vector_hw } */
+/* { dg-options "-O2 -mpower8-vector" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ long long ll[NUM];
+ signed char c[NUM * 8];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 2) + (i / 2) * 16] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepi8_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 2) + (i / 2) * 16] != dst.ll[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 8];
+ short s[NUM];
+ signed char c[NUM * 2];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 8) + (i / 8) * 16] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 8)
+ dst.x [i / 8] = _mm_cvtepi8_epi16 (src.x [i / 8]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 8) + (i / 8) * 16] != dst.s[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target p8vector_hw } */
+/* { dg-options "-O2 -mpower8-vector" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ long long ll[NUM];
+ int i[NUM * 2];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.i[(i % 2) + (i / 2) * 4] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepi32_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.i[(i % 2) + (i / 2) * 4] != dst.ll[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 4];
+ int i[NUM];
+ short s[NUM * 2];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.s[(i % 4) + (i / 4) * 8] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 4)
+ dst.x [i / 4] = _mm_cvtepi16_epi32 (src.x [i / 4]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.s[(i % 4) + (i / 4) * 8] != dst.i[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target p8vector_hw } */
+/* { dg-options "-O2 -mpower8-vector" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ long long ll[NUM];
+ short s[NUM * 4];
+ } dst, src;
+ int i, sign = 1;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.s[(i % 2) + (i / 2) * 8] = i * i * sign;
+ sign = -sign;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepi16_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.s[(i % 2) + (i / 2) * 8] != dst.ll[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 4];
+ unsigned int i[NUM];
+ unsigned char c[NUM * 4];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 4) + (i / 4) * 16] = i * i;
+ if ((i % 4))
+ src.c[(i % 4) + (i / 4) * 16] |= 0x80;
+ }
+
+ for (i = 0; i < NUM; i += 4)
+ dst.x [i / 4] = _mm_cvtepu8_epi32 (src.x [i / 4]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 4) + (i / 4) * 16] != dst.i[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ unsigned long long ll[NUM];
+ unsigned char c[NUM * 8];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 2) + (i / 2) * 16] = i * i;
+ if ((i % 2))
+ src.c[(i % 2) + (i / 2) * 16] |= 0x80;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepu8_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 2) + (i / 2) * 16] != dst.ll[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 8];
+ unsigned short s[NUM];
+ unsigned char c[NUM * 2];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.c[(i % 8) + (i / 8) * 16] = i * i;
+ if ((i % 4))
+ src.c[(i % 8) + (i / 8) * 16] |= 0x80;
+ }
+
+ for (i = 0; i < NUM; i += 8)
+ dst.x [i / 8] = _mm_cvtepu8_epi16 (src.x [i / 8]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.c[(i % 8) + (i / 8) * 16] != dst.s[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ unsigned long long ll[NUM];
+ unsigned int i[NUM * 2];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.i[(i % 2) + (i / 2) * 4] = i * i;
+ if ((i % 2))
+ src.i[(i % 2) + (i / 2) * 4] |= 0x80000000;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepu32_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.i[(i % 2) + (i / 2) * 4] != dst.ll[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 4];
+ unsigned int i[NUM];
+ unsigned short s[NUM * 2];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.s[(i % 4) + (i / 4) * 8] = i * i;
+ if ((i % 4))
+ src.s[(i % 4) + (i / 4) * 8] |= 0x8000;
+ }
+
+ for (i = 0; i < NUM; i += 4)
+ dst.x [i / 4] = _mm_cvtepu16_epi32 (src.x [i / 4]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.s[(i % 4) + (i / 4) * 8] != dst.i[i])
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_hw } */
+/* { dg-options "-O2 -mvsx" } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 128
+
+static void
+TEST (void)
+{
+ union
+ {
+ __m128i x[NUM / 2];
+ unsigned long long ll[NUM];
+ unsigned short s[NUM * 4];
+ } dst, src;
+ int i;
+
+ for (i = 0; i < NUM; i++)
+ {
+ src.s[(i % 2) + (i / 2) * 8] = i * i;
+ if ((i % 2))
+ src.s[(i % 2) + (i / 2) * 8] |= 0x8000;
+ }
+
+ for (i = 0; i < NUM; i += 2)
+ dst.x [i / 2] = _mm_cvtepu16_epi64 (src.x [i / 2]);
+
+ for (i = 0; i < NUM; i++)
+ if (src.s[(i % 2) + (i / 2) * 8] != dst.ll[i])
+ abort ();
+}
projects / thirdparty / gcc.git / commitdiff
