From 448e99f5e858735f9de2ab5cf614dd2b171cee5d Mon Sep 17 00:00:00 2001
From: meissner <meissner@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Thu, 13 Sep 2007 02:17:51 +0000
Subject: Add AMD SSE5 support; Add iterator over function arguments; Add
 stdarg_p, prototype_p, function_args_count functions

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@128455 138bc75d-0d04-0410-961f-82ee72b054a4
---
 gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c | 139 +++++++++++++++++++++++++++
 1 file changed, 139 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c

(limited to 'gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c')

diff --git a/gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c b/gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c
new file mode 100644
index 00000000000..acf19f9742d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse5-nmsubXX.c
@@ -0,0 +1,139 @@
+/* { dg-do run { target i?86-*-* x86_64-*-* } } */
+/* { dg-require-effective-target sse5 } */
+/* { dg-options "-O2 -msse5" } */
+
+#include "sse5-check.h"
+
+#include <bmmintrin.h>
+#include <string.h>
+
+#define NUM 20
+
+union
+{
+  __m128 x[NUM];
+  float f[NUM * 4];
+  __m128d y[NUM];
+  double d[NUM * 2];
+} dst, res, src1, src2, src3;
+
+/* Note that in macc*,msub*,mnmacc* and mnsub* instructions, the intermdediate 
+   product is not rounded, only the addition is rounded. */
+
+static void
+init_nmsubps ()
+{
+  int i;
+  for (i = 0; i < NUM * 4; i++)
+    {
+      src1.f[i] = i;
+      src2.f[i] = i + 10;
+      src3.f[i] = i + 20;
+    }
+}
+
+static void
+init_nmsubpd ()
+{
+  int i;
+  for (i = 0; i < NUM * 4; i++)
+    {
+      src1.d[i] = i;
+      src2.d[i] = i + 10;
+      src3.d[i] = i + 20;
+    }
+}
+
+static int
+check_nmsubps ()
+{
+  int i, j, check_fails = 0;
+  for (i = 0; i < NUM * 4; i = i + 4)
+    for (j = 0; j < 4; j++)
+      {
+	res.f[i + j] = - (src1.f[i + j] * src2.f[i + j]) - src3.f[i + j];
+	if (dst.f[i + j] != res.f[i + j]) 
+	  check_fails++;
+      }
+  return check_fails++;
+}
+
+static int
+check_nmsubpd ()
+{
+  int i, j, check_fails = 0;
+  for (i = 0; i < NUM * 2; i = i + 2)
+    for (j = 0; j < 2; j++)
+      {
+	res.d[i + j] = - (src1.d[i + j] * src2.d[i + j]) - src3.d[i + j];
+	if (dst.d[i + j] != res.d[i + j]) 
+	  check_fails++;
+      }
+  return check_fails++;
+}
+
+
+static int
+check_nmsubss ()
+{
+  int i, j, check_fails = 0;
+  for (i = 0; i < NUM * 4; i = i + 4)
+    {
+      res.f[i] = - (src1.f[i] * src2.f[i]) - src3.f[i];
+      if (dst.f[i] != res.f[i]) 
+	check_fails++;
+    }	
+  return check_fails++;
+}
+
+static int
+check_nmsubsd ()
+{
+  int i, j, check_fails = 0;
+  for (i = 0; i < NUM * 2; i = i + 2)
+    {
+      res.d[i] = - (src1.d[i] * src2.d[i]) - src3.d[i];
+      if (dst.d[i] != res.d[i]) 
+	check_fails++;
+    }
+  return check_fails++;
+}
+
+static void
+sse5_test (void)
+{
+  int i;
+  
+  /* Check nmsubps */
+  init_nmsubps ();
+  
+  for (i = 0; i < NUM; i++)
+    dst.x[i] = _mm_nmsub_ps (src1.x[i], src2.x[i], src3.x[i]);
+  
+  if (check_nmsubps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4], &src3.f[i * 4])) 
+    abort ();
+  
+  /* check nmsubss */
+  for (i = 0; i < NUM; i++)
+    dst.x[i] = _mm_nmsub_ss (src1.x[i], src2.x[i], src3.x[i]);
+  
+  if (check_nmsubss (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4], &src3.f[i * 4])) 
+    abort ();
+  
+  /* Check nmsubpd */
+  init_nmsubpd ();
+  
+  for (i = 0; i < NUM; i++)
+    dst.y[i] = _mm_nmsub_pd (src1.y[i], src2.y[i], src3.y[i]);
+  
+  if (check_nmsubpd (&dst.y[i], &src1.d[i * 2], &src2.d[i * 2], &src3.d[i * 2])) 
+    abort ();
+  
+  /* Check nmsubps */
+  for (i = 0; i < NUM; i++)
+    dst.y[i] = _mm_nmsub_sd (src1.y[i], src2.y[i], src3.y[i]);
+  
+  if (check_nmsubsd (&dst.y[i], &src1.d[i * 2], &src2.d[i * 2], &src3.d[i * 2])) 
+    abort ();
+  
+}
-- 
cgit v1.2.1