https://gcc.gnu.org/g:924d2596c9ad1deb0acb78c32762608838ea7db4
commit 924d2596c9ad1deb0acb78c32762608838ea7db4
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Thu Oct 3 00:31:49 2024 -0400
Add vector-pair.h runtime tests.
2024-10-03 Michael Meissner <meiss...@linux.ibm.com>
gcc/testsuite
* gcc.target/powerpc/vpair-3-not-p10.c: New test.
* gcc.target/powerpc/vpair-3-p10.c: Likewise.
* gcc.target/powerpc/vpair-3.h: New test include.
* gcc.target/powerpc/vpair-4-not-p10.c: New test.
* gcc.target/powerpc/vpair-4-p10.c: Likewise.
* gcc.target/powerpc/vpair-4.h: New test include.
Diff:
---
gcc/testsuite/gcc.target/powerpc/vpair-3-not-p10.c | 15 +
gcc/testsuite/gcc.target/powerpc/vpair-3-p10.c | 14 +
gcc/testsuite/gcc.target/powerpc/vpair-3.h | 435 +++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/vpair-4-not-p10.c | 15 +
gcc/testsuite/gcc.target/powerpc/vpair-4-p10.c | 14 +
gcc/testsuite/gcc.target/powerpc/vpair-4.h | 435 +++++++++++++++++++++
6 files changed, 928 insertions(+)
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-3-not-p10.c
b/gcc/testsuite/gcc.target/powerpc/vpair-3-not-p10.c
new file mode 100644
index 000000000000..d1a1029417f0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-3-not-p10.c
@@ -0,0 +1,15 @@
+/* { dg-do run { target { vsx_hw } } } */
+/* { dg-options "-mvsx -O2 -ffast-math -mno-mma" } */
+
+/*
+ * This test of the double (f64) vector pair functions in vector-pair.h is run
+ * on VSX systems when the load/store vector pair instructions are not
+ * available.
+ *
+ * The -ffast-math option is used to just use the hardware sqrt, min, and max
+ * instructions without calling into the library.
+ *
+ * The -mno-mma option disables GCC from enabling the __vector_pair type.
+ */
+
+#include "vpair-3.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-3-p10.c
b/gcc/testsuite/gcc.target/powerpc/vpair-3-p10.c
new file mode 100644
index 000000000000..d78faf3fed47
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-3-p10.c
@@ -0,0 +1,14 @@
+/* { dg-do run { target { power10_hw } } } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2 -ffast-math -mmma" } */
+
+/*
+ * This test of the double (f64) vector pair functions in vector-pair.h is run
+ * on VSX systems when the load/store vector pair instructions are available.
+ *
+ * The -ffast-math option is used to just use the hardware sqrt, min, and max
+ * instructions without calling into the library.
+ *
+ * The -mmma option makes sure GC enables the __vector_pair type.
+ */
+
+#include "vpair-3.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-3.h
b/gcc/testsuite/gcc.target/powerpc/vpair-3.h
new file mode 100644
index 000000000000..e61ad23dd57e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-3.h
@@ -0,0 +1,435 @@
+/* Common include file to test the vector pair double functions. This is run
+ two times, once compiled for a non-power10 system that does not have the
+ vector pair load and store instructions, and once with power10 defaults that
+ has load/store vector pair. */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <vector-pair.h>
+
+#ifdef DEBUG
+#include <stdio.h>
+#endif
+
+#ifndef NUM
+#define NUM 16
+#endif
+
+static double result1[NUM];
+static double result2[NUM];
+static double in_a[NUM];
+static double in_b[NUM];
+static double in_c[NUM];
+
+/* vector pair tests. */
+
+void
+vpair_abs (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_abs (vr + i, va + i);
+}
+
+void
+vpair_nabs (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_nabs (vr + i, va + i);
+}
+
+void
+vpair_neg (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_neg (vr + i, va + i);
+}
+
+void
+vpair_sqrt (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_sqrt (vr + i, va + i);
+}
+
+void
+vpair_add (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_add (vr + i, va + i, vb + i);
+}
+
+void
+vpair_sub (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_sub (vr + i, va + i, vb + i);
+}
+
+void
+vpair_mul (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_mul (vr + i, va + i, vb + i);
+}
+
+void
+vpair_div (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_div (vr + i, va + i, vb + i);
+}
+
+void
+vpair_min (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_min (vr + i, va + i, vb + i);
+}
+
+void
+vpair_max (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_max (vr + i, va + i, vb + i);
+}
+
+void
+vpair_fma (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+ vector_pair_f64_t *vc = (vector_pair_f64_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_fma (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_fms (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+ vector_pair_f64_t *vc = (vector_pair_f64_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_fms (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_nfma (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+ vector_pair_f64_t *vc = (vector_pair_f64_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_nfma (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_nfms (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+ vector_pair_f64_t *vb = (vector_pair_f64_t *)b;
+ vector_pair_f64_t *vc = (vector_pair_f64_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_nfms (vr + i, va + i, vb + i, vc + i);
+}
+
+
+/* scalar tests. */
+
+void
+scalar_abs (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < 0.0) ? -a[i] : a[i];
+}
+
+void
+scalar_nabs (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < 0.0) ? a[i] : -a[i];
+}
+
+void
+scalar_neg (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = -a[i];
+}
+
+void
+scalar_sqrt (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_sqrt (a[i]);
+}
+
+void
+scalar_add (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] + b[i];
+}
+
+void
+scalar_sub (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] - b[i];
+}
+
+void
+scalar_mul (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] * b[i];
+}
+
+void
+scalar_div (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] / b[i];
+}
+
+void
+scalar_min (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < b[i]) ? a[i] : b[i];
+}
+
+void
+scalar_max (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] > b[i]) ? a[i] : b[i];
+}
+
+void
+scalar_fma (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_fma (a[i], b[i], c[i]);
+}
+
+void
+scalar_fms (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_fma (a[i], b[i], -c[i]);
+}
+
+void
+scalar_nfma (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = - __builtin_fma (a[i], b[i], c[i]);
+}
+
+void
+scalar_nfms (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = - __builtin_fma (a[i], b[i], -c[i]);
+}
+
+
+/* Check results. */
+void
+check (const char *name)
+{
+ size_t i;
+
+ for (i = 0; i < NUM; i++)
+ if (result1[i] != result2[i])
+ {
+#ifdef DEBUG
+ printf ("test #%ld failed, %g != %g, %s (%g, %g, %g).\n",
+ (long)i,
+ result1[i],
+ result2[i],
+ name,
+ in_a[i],
+ in_b[i],
+ in_c[i]);
+#endif
+ abort ();
+ }
+
+ return;
+}
+
+typedef void func_t (double *, double *, double *, double *, size_t);
+
+/* tests to run. */
+struct
+{
+ func_t *vpair_test;
+ func_t *scalar_test;
+ const char *name;
+} tests[] = {
+ { vpair_abs, scalar_abs, "abs" },
+ { vpair_nabs, scalar_nabs, "nabs" },
+ { vpair_neg, scalar_neg, "neg" },
+ { vpair_sqrt, scalar_sqrt, "sqrt" },
+ { vpair_add, scalar_add, "add" },
+ { vpair_sub, scalar_sub, "sub" },
+ { vpair_mul, scalar_mul, "mul" },
+ { vpair_div, scalar_div, "div" },
+ { vpair_min, scalar_min, "min" },
+ { vpair_max, scalar_max, "max" },
+ { vpair_fma, scalar_fma, "fma" },
+ { vpair_fms, scalar_fms, "fms" },
+ { vpair_nfma, scalar_nfma, "nfma" },
+ { vpair_nfms, scalar_nfms, "nfms" },
+};
+
+/* Run tests. */
+
+int
+main (void)
+{
+ size_t i;
+
+ /* Initialize the inputs. */
+ for (i = 0; i < NUM; i++)
+ {
+ double d = (double)(i + 1);
+ in_a[i] = d * d;
+ in_b[i] = d;
+ in_c[i] = d + 2.0;
+ }
+
+#ifdef DEBUG
+ printf ("Start tests\n");
+#endif
+
+ /* Run the tests. */
+ for (i = 0; i < sizeof (tests) / sizeof (tests[0]); i++)
+ {
+ tests[i].vpair_test (result1, in_a, in_b, in_c, NUM);
+ tests[i].scalar_test (result2, in_a, in_b, in_c, NUM);
+ check (tests[i].name);
+ }
+
+#ifdef DEBUG
+ printf ("End tests\n");
+#endif
+
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-4-not-p10.c
b/gcc/testsuite/gcc.target/powerpc/vpair-4-not-p10.c
new file mode 100644
index 000000000000..f57fbbf8b050
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-4-not-p10.c
@@ -0,0 +1,15 @@
+/* { dg-do run { target { vsx_hw } } } */
+/* { dg-options "-mvsx -O2 -ffast-math -mno-mma" } */
+
+/*
+ * This test of the float (f32) vector pair functions in vector-pair.h is run
+ * on VSX systems when the load/store vector pair instructions are not
+ * available.
+ *
+ * The -ffast-math option is used to just use the hardware sqrt, min, and max
+ * instructions without calling into the library.
+ *
+ * The -mno-mma option disables GCC from enabling the __vector_pair type.
+ */
+
+#include "vpair-4.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-4-p10.c
b/gcc/testsuite/gcc.target/powerpc/vpair-4-p10.c
new file mode 100644
index 000000000000..12291202c163
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-4-p10.c
@@ -0,0 +1,14 @@
+/* { dg-do run { target { power10_hw } } } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2 -ffast-math -mmma" } */
+
+/*
+ * This test of the float (f32) vector pair functions in vector-pair.h is run
+ * on VSX systems when the load/store vector pair instructions are available.
+ *
+ * The -ffast-math option is used to just use the hardware sqrt, min, and max
+ * instructions without calling into the library.
+ *
+ * The -mmma option makes sure GC enables the __vector_pair type.
+ */
+
+#include "vpair-4.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-4.h
b/gcc/testsuite/gcc.target/powerpc/vpair-4.h
new file mode 100644
index 000000000000..1a80cf5e639a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-4.h
@@ -0,0 +1,435 @@
+/* Common include file to test the vector pair float functions. This is run
+ two times, once compiled for a non-power10 system that does not have the
+ vector pair load and store instructions, and once with power10 defaults that
+ has load/store vector pair. */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <vector-pair.h>
+
+#ifdef DEBUG
+#include <stdio.h>
+#endif
+
+#ifndef NUM
+#define NUM 16
+#endif
+
+static float result1[NUM];
+static float result2[NUM];
+static float in_a[NUM];
+static float in_b[NUM];
+static float in_c[NUM];
+
+/* vector pair tests. */
+
+void
+vpair_abs (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_abs (vr + i, va + i);
+}
+
+void
+vpair_nabs (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_nabs (vr + i, va + i);
+}
+
+void
+vpair_neg (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_neg (vr + i, va + i);
+}
+
+void
+vpair_sqrt (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_sqrt (vr + i, va + i);
+}
+
+void
+vpair_add (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_add (vr + i, va + i, vb + i);
+}
+
+void
+vpair_sub (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_sub (vr + i, va + i, vb + i);
+}
+
+void
+vpair_mul (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_mul (vr + i, va + i, vb + i);
+}
+
+void
+vpair_div (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_div (vr + i, va + i, vb + i);
+}
+
+void
+vpair_min (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_min (vr + i, va + i, vb + i);
+}
+
+void
+vpair_max (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_max (vr + i, va + i, vb + i);
+}
+
+void
+vpair_fma (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+ vector_pair_f32_t *vc = (vector_pair_f32_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_fma (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_fms (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+ vector_pair_f32_t *vc = (vector_pair_f32_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_fms (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_nfma (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+ vector_pair_f32_t *vc = (vector_pair_f32_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_nfma (vr + i, va + i, vb + i, vc + i);
+}
+
+void
+vpair_nfms (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+ vector_pair_f32_t *vb = (vector_pair_f32_t *)b;
+ vector_pair_f32_t *vc = (vector_pair_f32_t *)c;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_nfms (vr + i, va + i, vb + i, vc + i);
+}
+
+
+/* scalar tests. */
+
+void
+scalar_abs (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < 0.0) ? -a[i] : a[i];
+}
+
+void
+scalar_nabs (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < 0.0) ? a[i] : -a[i];
+}
+
+void
+scalar_neg (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = -a[i];
+}
+
+void
+scalar_sqrt (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_sqrt (a[i]);
+}
+
+void
+scalar_add (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] + b[i];
+}
+
+void
+scalar_sub (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] - b[i];
+}
+
+void
+scalar_mul (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] * b[i];
+}
+
+void
+scalar_div (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = a[i] / b[i];
+}
+
+void
+scalar_min (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] < b[i]) ? a[i] : b[i];
+}
+
+void
+scalar_max (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = (a[i] > b[i]) ? a[i] : b[i];
+}
+
+void
+scalar_fma (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_fma (a[i], b[i], c[i]);
+}
+
+void
+scalar_fms (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = __builtin_fma (a[i], b[i], -c[i]);
+}
+
+void
+scalar_nfma (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = - __builtin_fma (a[i], b[i], c[i]);
+}
+
+void
+scalar_nfms (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i++)
+ r[i] = - __builtin_fma (a[i], b[i], -c[i]);
+}
+
+
+/* Check results. */
+void
+check (const char *name)
+{
+ size_t i;
+
+ for (i = 0; i < NUM; i++)
+ if (result1[i] != result2[i])
+ {
+#ifdef DEBUG
+ printf ("test #%ld failed, %g != %g, %s (%g, %g, %g).\n",
+ (long)i,
+ result1[i],
+ result2[i],
+ name,
+ in_a[i],
+ in_b[i],
+ in_c[i]);
+#endif
+ abort ();
+ }
+
+ return;
+}
+
+typedef void func_t (float *, float *, float *, float *, size_t);
+
+/* tests to run. */
+struct
+{
+ func_t *vpair_test;
+ func_t *scalar_test;
+ const char *name;
+} tests[] = {
+ { vpair_abs, scalar_abs, "abs" },
+ { vpair_nabs, scalar_nabs, "nabs" },
+ { vpair_neg, scalar_neg, "neg" },
+ { vpair_sqrt, scalar_sqrt, "sqrt" },
+ { vpair_add, scalar_add, "add" },
+ { vpair_sub, scalar_sub, "sub" },
+ { vpair_mul, scalar_mul, "mul" },
+ { vpair_div, scalar_div, "div" },
+ { vpair_min, scalar_min, "min" },
+ { vpair_max, scalar_max, "max" },
+ { vpair_fma, scalar_fma, "fma" },
+ { vpair_fms, scalar_fms, "fms" },
+ { vpair_nfma, scalar_nfma, "nfma" },
+ { vpair_nfms, scalar_nfms, "nfms" },
+};
+
+/* Run tests. */
+
+int
+main (void)
+{
+ size_t i;
+
+ /* Initialize the inputs. */
+ for (i = 0; i < NUM; i++)
+ {
+ float f = (float)(i + 1);
+ in_a[i] = f * f;
+ in_b[i] = f;
+ in_c[i] = f + 2.0f;
+ }
+
+#ifdef DEBUG
+ printf ("Start tests\n");
+#endif
+
+ /* Run the tests. */
+ for (i = 0; i < sizeof (tests) / sizeof (tests[0]); i++)
+ {
+ tests[i].vpair_test (result1, in_a, in_b, in_c, NUM);
+ tests[i].scalar_test (result2, in_a, in_b, in_c, NUM);
+ check (tests[i].name);
+ }
+
+#ifdef DEBUG
+ printf ("End tests\n");
+#endif
+
+ return 0;
+}
