Hi,
This patch implements the behavior of vadd_f64 and
vsub_f64 NEON intrinsics. Regression tests are added.
Regression tests for aarch64-none-elf completed with no
regressions.
OK?
Thanks,
Alex
gcc/testsuite/
2013-10-08 Alex Velenko <alex.vele...@arm.com>
* gcc.target/aarch64/vadd_f64.c: New testcase.
* gcc.target/aarch64/vsub_f64.c: New testcase.
gcc/
2013-10-08 Alex Velenko <alex.vele...@arm.com>
* config/aarch64/arm_neon.h (vadd_f64): Implementation added.
(vsub_f64): Likewise.
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 1bd098d2a9c3a204c0fb57ee3ef31cbb5f328d8e..b8791b7b5dd7123b6d708aeb2321986673a0c0cd 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -634,6 +634,12 @@ vadd_f32 (float32x2_t __a, float32x2_t __b)
return __a + __b;
}
+__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
+vadd_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return __a + __b;
+}
+
__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
@@ -1824,6 +1830,12 @@ vsub_f32 (float32x2_t __a, float32x2_t __b)
return __a - __b;
}
+__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
+vsub_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return __a - __b;
+}
+
__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsub_u8 (uint8x8_t __a, uint8x8_t __b)
{
diff --git a/gcc/testsuite/gcc.target/aarch64/vadd_f64.c b/gcc/testsuite/gcc.target/aarch64/vadd_f64.c
new file mode 100644
index 0000000000000000000000000000000000000000..c3bf7349597aa9b75e0bc34cfd4cde4dc16b95f3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vadd_f64.c
@@ -0,0 +1,114 @@
+/* Test vadd works correctly. */
+/* { dg-do run } */
+/* { dg-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+#define FLT_EPSILON __FLT_EPSILON__
+#define DBL_EPSILON __DBL_EPSILON__
+
+#define TESTA0 0.33333
+#define TESTA1 -1.7777
+#define TESTA2 0
+#define TESTA3 1.23456
+/* 2^54, double has 53 significand bits
+ according to Double-precision floating-point format. */
+#define TESTA4 18014398509481984
+#define TESTA5 (1.0 / TESTA4)
+
+#define TESTB0 0.66667
+#define TESTB1 2
+#define TESTB2 0
+#define TESTB3 -2
+#define TESTB4 1.0
+#define TESTB5 2.0
+
+#define ANSW0 1
+#define ANSW1 0.2223
+#define ANSW2 0
+#define ANSW3 -0.76544
+#define ANSW4 TESTA4
+#define ANSW5 2.0
+
+extern void abort (void);
+
+#define EPSILON __DBL_EPSILON__
+#define ABS(a) __builtin_fabs (a)
+#define ISNAN(a) __builtin_isnan (a)
+#define FP_equals(a, b, epsilon) \
+ ( \
+ ((a) == (b)) \
+ || (ISNAN (a) && ISNAN (b)) \
+ || (ABS (a - b) < epsilon) \
+ )
+
+int
+test_vadd_f64 ()
+{
+ float64x1_t a;
+ float64x1_t b;
+ float64x1_t c;
+
+ a = TESTA0;
+ b = TESTB0;
+ c = ANSW0;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA1;
+ b = TESTB1;
+ c = ANSW1;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA2;
+ b = TESTB2;
+ c = ANSW2;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA3;
+ b = TESTB3;
+ c = ANSW3;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA4;
+ b = TESTB4;
+ c = ANSW4;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA5;
+ b = TESTB5;
+ c = ANSW5;
+
+ a = vadd_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "fadd\\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 6 } } */
+
+int
+main (int argc, char **argv)
+{
+ if (test_vadd_f64 ())
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/vsub_f64.c b/gcc/testsuite/gcc.target/aarch64/vsub_f64.c
new file mode 100644
index 0000000000000000000000000000000000000000..abf4fc42d49dc695f435b1e0f331737c8e9367b0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vsub_f64.c
@@ -0,0 +1,116 @@
+/* Test vsub works correctly. */
+/* { dg-do run } */
+/* { dg-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+#define FLT_EPSILON __FLT_EPSILON__
+#define DBL_EPSILON __DBL_EPSILON__
+
+#define TESTA0 1
+#define TESTA1 0.2223
+#define TESTA2 0
+#define TESTA3 -0.76544
+/* 2^54, double has 53 significand bits
+ according to Double-precision floating-point format. */
+#define TESTA4 18014398509481984
+#define TESTA5 2.0
+
+#define TESTB0 0.66667
+#define TESTB1 2
+#define TESTB2 0
+#define TESTB3 -2
+#define TESTB4 1.0
+#define TESTB5 (1.0 / TESTA4)
+
+#define ANSW0 0.33333
+#define ANSW1 -1.7777
+#define ANSW2 0
+#define ANSW3 1.23456
+#define ANSW4 TESTA4
+#define ANSW5 2.0
+
+extern void abort (void);
+
+#define EPSILON __DBL_EPSILON__
+#define ISNAN(a) __builtin_isnan (a)
+/* FP_equals is implemented like this to execute subtraction
+ exectly once during a single test run. */
+#define FP_equals(a, b, epsilon) \
+( \
+ ((a) == (b)) \
+ || (ISNAN (a) && ISNAN (b)) \
+ || (((a > b) && (a < (b + epsilon))) \
+ || ((b > a) && (b < (a + epsilon)))) \
+)
+
+int
+test_vsub_f64 ()
+{
+ float64x1_t a;
+ float64x1_t b;
+ float64x1_t c;
+
+ a = TESTA0;
+ b = TESTB0;
+ c = ANSW0;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA1;
+ b = TESTB1;
+ c = ANSW1;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA2;
+ b = TESTB2;
+ c = ANSW2;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA3;
+ b = TESTB3;
+ c = ANSW3;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA4;
+ b = TESTB4;
+ c = ANSW4;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ a = TESTA5;
+ b = TESTB5;
+ c = ANSW5;
+
+ a = vsub_f64 (a, b);
+ if (!FP_equals (a, c, EPSILON))
+ return 1;
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "fsub\\td\[0-9\]+, d\[0-9\]+, d\[0-9\]+" 6 } } */
+
+int
+main (int argc, char **argv)
+{
+ if (test_vsub_f64 ())
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { cleanup-saved-temps } } */
