This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[AArch64] Implement some vca*_f[32,64] intrinsics
- From: Kyrill Tkachov <kyrylo dot tkachov at arm dot com>
- To: GCC Patches <gcc-patches at gcc dot gnu dot org>
- Cc: Marcus Shawcroft <Marcus dot Shawcroft at arm dot com>, Richard Earnshaw <Richard dot Earnshaw at arm dot com>
- Date: Mon, 23 Jun 2014 15:30:03 +0100
- Subject: [AArch64] Implement some vca*_f[32,64] intrinsics
- Authentication-results: sourceware.org; auth=none
Hi all,
This patch implements some absolute compare intrinsics in arm_neon.h.
Execution tests are added.
Tested aarch64-none-elf, aarch64_be-none-elf, bootstrapped on aarch64 linux
Ok for trunk?
2014-06-23 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* config/aarch64/arm_neon.h (vcage_f64): New intrinsic.
(vcagt_f64): Likewise.
(vcale_f64): Likewise.
(vcaled_f64): Likewise.
(vcales_f32): Likewise.
(vcalt_f64): Likewise.
(vcaltd_f64): Likewise.
(vcalts_f32): Likewise.
2014-06-23 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* gcc.target/aarch64/simd/vcage_f64.c: New test.
* gcc.target/aarch64/simd/vcagt_f64.c: Likewise.
* gcc.target/aarch64/simd/vcale_f64.c: Likewise.
* gcc.target/aarch64/simd/vcaled_f64.c: Likewise.
* gcc.target/aarch64/simd/vcales_f32.c: Likewise.
* gcc.target/aarch64/simd/vcalt_f64.c: Likewise.
* gcc.target/aarch64/simd/vcaltd_f64.c: Likewise.
* gcc.target/aarch64/simd/vcalts_f32.c: Likewise.commit f87169afe8bd853b4aa5ab3ed5e270de0cb95461
Author: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
Date: Thu Jun 19 09:37:54 2014 +0100
[AArch64] Implement vc* intrinsics
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 0ff6996..8fa469a 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -13823,6 +13823,12 @@ vaesimcq_u8 (uint8x16_t data)
/* vcage */
+__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
+vcage_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return vabs_f64 (__a) >= vabs_f64 (__b);
+}
+
__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcages_f32 (float32_t __a, float32_t __b)
{
@@ -13867,6 +13873,12 @@ vcagt_f32 (float32x2_t __a, float32x2_t __b)
return vabs_f32 (__a) > vabs_f32 (__b);
}
+__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
+vcagt_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return vabs_f64 (__a) > vabs_f64 (__b);
+}
+
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcagtq_f32 (float32x4_t __a, float32x4_t __b)
{
@@ -13893,6 +13905,24 @@ vcale_f32 (float32x2_t __a, float32x2_t __b)
return vabs_f32 (__a) <= vabs_f32 (__b);
}
+__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
+vcale_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return vabs_f64 (__a) <= vabs_f64 (__b);
+}
+
+__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
+vcaled_f64 (float64_t __a, float64_t __b)
+{
+ return __builtin_fabs (__a) <= __builtin_fabs (__b) ? -1 : 0;
+}
+
+__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
+vcales_f32 (float32_t __a, float32_t __b)
+{
+ return __builtin_fabsf (__a) <= __builtin_fabsf (__b) ? -1 : 0;
+}
+
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcaleq_f32 (float32x4_t __a, float32x4_t __b)
{
@@ -13913,6 +13943,18 @@ vcalt_f32 (float32x2_t __a, float32x2_t __b)
return vabs_f32 (__a) < vabs_f32 (__b);
}
+__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
+vcalt_f64 (float64x1_t __a, float64x1_t __b)
+{
+ return vabs_f64 (__a) < vabs_f64 (__b);
+}
+
+__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
+vcaltd_f64 (float64_t __a, float64_t __b)
+{
+ return __builtin_fabs (__a) < __builtin_fabs (__b) ? -1 : 0;
+}
+
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcaltq_f32 (float32x4_t __a, float32x4_t __b)
{
@@ -13925,6 +13967,12 @@ vcaltq_f64 (float64x2_t __a, float64x2_t __b)
return vabsq_f64 (__a) < vabsq_f64 (__b);
}
+__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
+vcalts_f32 (float32_t __a, float32_t __b)
+{
+ return __builtin_fabsf (__a) < __builtin_fabsf (__b) ? -1 : 0;
+}
+
/* vceq - vector. */
__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcage_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcage_f64.c
new file mode 100644
index 0000000..67dc8ae
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcage_f64.c
@@ -0,0 +1,42 @@
+/* Test the vcage_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+ float64x1_t arg1, arg2;
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) >= __builtin_fabs (in[j]) ? -1 : 0;
+ arg1 = (float64x1_t) { in[i] };
+ arg2 = (float64x1_t) { in[j] };
+ actual = vget_lane_u64 (vcage_f64 (arg1, arg2), 0);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facge\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcagt_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcagt_f64.c
new file mode 100644
index 0000000..8027716
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcagt_f64.c
@@ -0,0 +1,42 @@
+/* Test the vcagt_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+ float64x1_t arg1, arg2;
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) > __builtin_fabs (in[j]) ? -1 : 0;
+ arg1 = (float64x1_t) { in[i] };
+ arg2 = (float64x1_t) { in[j] };
+ actual = vget_lane_u64 (vcagt_f64 (arg1, arg2), 0);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n",in[i], in[j], expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facgt\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcale_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcale_f64.c
new file mode 100644
index 0000000..122d4ff
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcale_f64.c
@@ -0,0 +1,42 @@
+/* Test the vcale_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+ float64x1_t arg1, arg2;
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) <= __builtin_fabs (in[j]) ? -1 : 0;
+ arg1 = (float64x1_t) { in[i] };
+ arg2 = (float64x1_t) { in[j] };
+ actual = vget_lane_u64 (vcale_f64 (arg1, arg2), 0);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facge\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcaled_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcaled_f64.c
new file mode 100644
index 0000000..90baea3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcaled_f64.c
@@ -0,0 +1,40 @@
+/* Test the vcaled_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) <= __builtin_fabs (in[j]) ? -1 : 0;
+ actual = vcaled_f64 (in[i], in[j]);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facge\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcales_f32.c b/gcc/testsuite/gcc.target/aarch64/simd/vcales_f32.c
new file mode 100644
index 0000000..356e8f5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcales_f32.c
@@ -0,0 +1,40 @@
+/* Test the vcales_f32 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float32_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint32_t expected;
+ uint32_t actual;
+
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) <= __builtin_fabs (in[j]) ? -1 : 0;
+ actual = vcales_f32 (in[i], in[j]);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %d, got %d\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facge\[ \t\]+\[sS\]\[0-9\]+, ?\[sS\]\[0-9\]+, ?\[sS\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcalt_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcalt_f64.c
new file mode 100644
index 0000000..886fe4d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcalt_f64.c
@@ -0,0 +1,42 @@
+/* Test the vcalt_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+ float64x1_t arg1, arg2;
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) < __builtin_fabs (in[j]) ? -1 : 0;
+ arg1 = (float64x1_t) { in[i] };
+ arg2 = (float64x1_t) { in[j] };
+ actual = vget_lane_u64 (vcalt_f64 (arg1, arg2), 0);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facgt\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcaltd_f64.c b/gcc/testsuite/gcc.target/aarch64/simd/vcaltd_f64.c
new file mode 100644
index 0000000..bb4087f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcaltd_f64.c
@@ -0,0 +1,40 @@
+/* Test the vcaltd_f64 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float64_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint64_t expected;
+ uint64_t actual;
+
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) < __builtin_fabs (in[j]) ? -1 : 0;
+ actual = vcaltd_f64 (in[i], in[j]);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %ld, got %ld\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facgt\[ \t\]+\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+, ?\[dD\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vcalts_f32.c b/gcc/testsuite/gcc.target/aarch64/simd/vcalts_f32.c
new file mode 100644
index 0000000..b26d072
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vcalts_f32.c
@@ -0,0 +1,40 @@
+/* Test the vcalts_f32 AArch64 SIMD intrinsic. */
+
+/* { dg-do run } */
+/* { dg-options "-save-temps -O3" } */
+
+#include "arm_neon.h"
+#include <stdio.h>
+
+#define SIZE 6
+
+extern void abort (void);
+
+volatile float32_t in[SIZE] = { -10.4, -3.14, 0.0, 1.5, 5.3, 532.3 };
+
+int
+main (void)
+{
+ uint32_t expected;
+ uint32_t actual;
+
+ int i, j;
+
+ for (i = 0; i < SIZE; ++i)
+ for (j = 0; j < SIZE; ++j)
+ {
+ expected = __builtin_fabs (in[i]) < __builtin_fabs (in[j]) ? -1 : 0;
+ actual = vcalts_f32 (in[i], in[j]);
+
+ if (actual != expected)
+ {
+ fprintf (stderr, "Expected: %d, got %d\n", expected, actual);
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler "facgt\[ \t\]+\[sS\]\[0-9\]+, ?\[sS\]\[0-9\]+, ?\[sS\]\[0-9\]+\n" } } */
+/* { dg-final { cleanup-saved-temps } } */