From 1bc5aee63eb72b341f506ad058502cd0361f0d10 Mon Sep 17 00:00:00 2001 From: Ben Cheng Date: Tue, 25 Mar 2014 22:37:19 -0700 Subject: Initial checkin of GCC 4.9.0 from trunk (r208799). Change-Id: I48a3c08bb98542aa215912a75f03c0890e497dba --- .../testsuite/gcc.target/i386/fma4-256-nmaccXX.c | 96 ++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 gcc-4.9/gcc/testsuite/gcc.target/i386/fma4-256-nmaccXX.c (limited to 'gcc-4.9/gcc/testsuite/gcc.target/i386/fma4-256-nmaccXX.c') diff --git a/gcc-4.9/gcc/testsuite/gcc.target/i386/fma4-256-nmaccXX.c b/gcc-4.9/gcc/testsuite/gcc.target/i386/fma4-256-nmaccXX.c new file mode 100644 index 000000000..261f302f2 --- /dev/null +++ b/gcc-4.9/gcc/testsuite/gcc.target/i386/fma4-256-nmaccXX.c @@ -0,0 +1,96 @@ +/* { dg-do run } */ +/* { dg-require-effective-target fma4 } */ +/* { dg-options "-O2 -mfma4" } */ + +#include "fma4-check.h" + +#include +#include + +#define NUM 20 + +union +{ + __m256 x[NUM]; + float f[NUM * 8]; + __m256d y[NUM]; + double d[NUM * 4]; +} 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_nmaccps () +{ + int i; + for (i = 0; i < NUM * 8; i++) + { + src1.f[i] = i; + src2.f[i] = i + 10; + src3.f[i] = i + 20; + } +} + +static void +init_nmaccpd () +{ + 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_nmaccps () +{ + int i, j, check_fails = 0; + for (i = 0; i < NUM * 8; i = i + 8) + for (j = 0; j < 8; 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_nmaccpd () +{ + int i, j, check_fails = 0; + for (i = 0; i < NUM * 4; i = i + 4) + for (j = 0; j < 4; 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 void +fma4_test (void) +{ + int i; + + init_nmaccps (); + + for (i = 0; i < NUM; i++) + dst.x[i] = _mm256_nmacc_ps (src1.x[i], src2.x[i], src3.x[i]); + + if (check_nmaccps ()) + abort (); + + init_nmaccpd (); + + for (i = 0; i < NUM; i++) + dst.y[i] = _mm256_nmacc_pd (src1.y[i], src2.y[i], src3.y[i]); + + if (check_nmaccpd ()) + abort (); + +} -- cgit v1.2.3