From: liuhongt <hongtao.liu@intel.com>
To: gcc-patches@gcc.gnu.org
Cc: crazylht@gmail.com, hjl.tools@gmail.com, ubizjak@gmail.com,
jakub@redhat.com
Subject: [PATCH 02/62] AVX512FP16: Add testcase for vector init and broadcast intrinsics.
Date: Thu, 1 Jul 2021 14:15:48 +0800 [thread overview]
Message-ID: <20210701061648.9447-3-hongtao.liu@intel.com> (raw)
In-Reply-To: <20210701061648.9447-1-hongtao.liu@intel.com>
gcc/testsuite/ChangeLog:
* gcc.target/i386/m512-check.h: Add union128h, union256h, union512h.
* gcc.target/i386/avx512fp16-10a.c: New test.
* gcc.target/i386/avx512fp16-10b.c: Ditto.
* gcc.target/i386/avx512fp16-1a.c: Ditto.
* gcc.target/i386/avx512fp16-1b.c: Ditto.
* gcc.target/i386/avx512fp16-1c.c: Ditto.
* gcc.target/i386/avx512fp16-1d.c: Ditto.
* gcc.target/i386/avx512fp16-1e.c: Ditto.
* gcc.target/i386/avx512fp16-2a.c: Ditto.
* gcc.target/i386/avx512fp16-2b.c: Ditto.
* gcc.target/i386/avx512fp16-2c.c: Ditto.
* gcc.target/i386/avx512fp16-3a.c: Ditto.
* gcc.target/i386/avx512fp16-3b.c: Ditto.
* gcc.target/i386/avx512fp16-3c.c: Ditto.
* gcc.target/i386/avx512fp16-4.c: Ditto.
* gcc.target/i386/avx512fp16-5.c: Ditto.
* gcc.target/i386/avx512fp16-6.c: Ditto.
* gcc.target/i386/avx512fp16-7.c: Ditto.
* gcc.target/i386/avx512fp16-8.c: Ditto.
* gcc.target/i386/avx512fp16-9a.c: Ditto.
* gcc.target/i386/avx512fp16-9b.c: Ditto.
---
.../gcc.target/i386/avx512fp16-10a.c | 14 ++
.../gcc.target/i386/avx512fp16-10b.c | 25 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-1a.c | 24 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-1b.c | 32 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-1c.c | 26 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-1d.c | 33 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-1e.c | 30 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-2a.c | 28 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-2b.c | 33 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-2c.c | 36 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-3a.c | 36 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-3b.c | 35 +++++
gcc/testsuite/gcc.target/i386/avx512fp16-3c.c | 40 ++++++
gcc/testsuite/gcc.target/i386/avx512fp16-4.c | 31 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-5.c | 133 ++++++++++++++++++
gcc/testsuite/gcc.target/i386/avx512fp16-6.c | 57 ++++++++
gcc/testsuite/gcc.target/i386/avx512fp16-7.c | 86 +++++++++++
gcc/testsuite/gcc.target/i386/avx512fp16-8.c | 53 +++++++
gcc/testsuite/gcc.target/i386/avx512fp16-9a.c | 27 ++++
gcc/testsuite/gcc.target/i386/avx512fp16-9b.c | 49 +++++++
gcc/testsuite/gcc.target/i386/m512-check.h | 38 ++++-
21 files changed, 865 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-10a.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-10b.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-1a.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-1b.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-1c.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-1d.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-1e.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-2a.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-2b.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-2c.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-3a.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-3b.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-3c.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-4.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-5.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-6.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-7.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-8.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-9a.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512fp16-9b.c
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-10a.c b/gcc/testsuite/gcc.target/i386/avx512fp16-10a.c
new file mode 100644
index 00000000000..f06ffffa822
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-10a.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <immintrin.h>
+
+__m128h
+__attribute__ ((noinline, noclone))
+set_128 (_Float16 x)
+{
+ return _mm_set_sh (x);
+}
+
+/* { dg-final { scan-assembler-times "vmovw\[ \t]\+\[^\n\r]*xmm0" 1 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vmovw\[ \t]\+\[^\n\r]*xmm0" 2 { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-10b.c b/gcc/testsuite/gcc.target/i386/avx512fp16-10b.c
new file mode 100644
index 00000000000..055edd7aaf5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-10b.c
@@ -0,0 +1,25 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-10a.c"
+
+union128h u128 = { ESP_FLOAT16, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+
+static void
+do_test (void)
+{
+ __m128h v128 = set_128 (ESP_FLOAT16);
+ union128h a128;
+
+ a128.x = v128;
+ if (check_union128h (a128, u128.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-1a.c b/gcc/testsuite/gcc.target/i386/avx512fp16-1a.c
new file mode 100644
index 00000000000..45c7bddeba5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-1a.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+typedef _Float16 __v8hf __attribute__ ((__vector_size__ (16)));
+typedef _Float16 __m128h __attribute__ ((__vector_size__ (16), __may_alias__));
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo1 (_Float16 x)
+{
+ return __extension__ (__m128h)(__v8hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo2 (_Float16 *x)
+{
+ return __extension__ (__m128h)(__v8hf) { *x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 3 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 2 { target { ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-1b.c b/gcc/testsuite/gcc.target/i386/avx512fp16-1b.c
new file mode 100644
index 00000000000..7560c625e25
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-1b.c
@@ -0,0 +1,32 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-1a.c"
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union128h u = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m128h v;
+ union128h a;
+ memset (&v, -1, sizeof (v));
+ v = foo1 (x);
+ a.x = v;
+ if (check_union128h (a, u.a))
+ abort ();
+ x = 33.3;
+ u.a[0] = x;
+ memset (&v, -1, sizeof (v));
+ v = foo2 (&x);
+ a.x = v;
+ if (check_union128h (a, u.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-1c.c b/gcc/testsuite/gcc.target/i386/avx512fp16-1c.c
new file mode 100644
index 00000000000..9814e9c0363
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-1c.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512fp16 -O2" } */
+/* { dg-final { scan-assembler-times "vmovsh" 2 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpinsrw" 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpinsrw" 2 { target { ia32 } } } } */
+
+typedef _Float16 __v8hf __attribute__ ((__vector_size__ (16)));
+typedef _Float16 __m128h __attribute__ ((__vector_size__ (16), __may_alias__));
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo1 (__m128h a, _Float16 f)
+{
+ __v8hf x = (__v8hf) a;
+ x[2] = f;
+ return (__m128h) x;
+}
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo2 (__m128h a, _Float16 f)
+{
+ __v8hf x = (__v8hf) a;
+ x[0] = f;
+ return (__m128h) x;
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-1d.c b/gcc/testsuite/gcc.target/i386/avx512fp16-1d.c
new file mode 100644
index 00000000000..cdaf656eb48
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-1d.c
@@ -0,0 +1,33 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-1c.c"
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union128h u = { -1.2f, 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f };
+ __m128h v;
+ union128h a, b;
+ v = foo1 (u.x, x);
+ a.x = v;
+ b = u;
+ b.a[2] = x;
+ if (check_union128h (a, b.a))
+ abort ();
+ x = 33.3;
+ b = u;
+ b.a[0] = x;
+ v = foo2 (u.x, x);
+ a.x = v;
+ if (check_union128h (a, b.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-1e.c b/gcc/testsuite/gcc.target/i386/avx512fp16-1e.c
new file mode 100644
index 00000000000..04d33cfcf2b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-1e.c
@@ -0,0 +1,30 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-1a.c"
+
+__m128h
+__attribute__ ((noinline,noclone))
+foo3 (__m128h x)
+{
+ return foo1(x[0]);
+}
+
+static void
+do_test (void)
+{
+ union128h u = { -1.2f, 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f };
+ union128h a, b = { -1.2f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f};
+ __m128h v;
+ v = foo3 (u.x);
+ a.x = v;
+ if (check_union128h (a, b.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-2a.c b/gcc/testsuite/gcc.target/i386/avx512fp16-2a.c
new file mode 100644
index 00000000000..c03138fb13d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-2a.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+typedef _Float16 __v16hf __attribute__ ((__vector_size__ (32)));
+typedef _Float16 __m256h __attribute__ ((__vector_size__ (32), __may_alias__));
+
+__m256h
+__attribute__ ((noinline, noclone))
+foo1 (_Float16 x)
+{
+ return __extension__ (__m256h)(__v16hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m256h
+__attribute__ ((noinline, noclone))
+foo2 (_Float16 *x)
+{
+ return __extension__ (__m256h)(__v16hf) { *x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 3 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 2 { target { ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-2b.c b/gcc/testsuite/gcc.target/i386/avx512fp16-2b.c
new file mode 100644
index 00000000000..100afd0f49c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-2b.c
@@ -0,0 +1,33 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-2a.c"
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union256h u = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m256h v;
+ union256h a;
+ memset (&v, -1, sizeof (v));
+ v = foo1 (x);
+ a.x = v;
+ if (check_union256h (a, u.a))
+ abort ();
+ x = 33.3;
+ u.a[0] = x;
+ memset (&v, -1, sizeof (v));
+ v = foo2 (&x);
+ a.x = v;
+ if (check_union256h (a, u.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-2c.c b/gcc/testsuite/gcc.target/i386/avx512fp16-2c.c
new file mode 100644
index 00000000000..cf4b42a4021
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-2c.c
@@ -0,0 +1,36 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-2a.c"
+
+__m256h
+__attribute__ ((noinline,noclone))
+foo3 (__m256h x)
+{
+ return foo1(x[0]);
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union256h u = { x, 3.5f, -5.9f, 0.0f, 0.0f, 0.0f, 7.7f, 0.0f,
+ 4.0f, -4.20f, 0.0f, 0.0f, 0.0f, -8.7f, 0.0f, 0.0f };
+
+ union256h exp = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m256h v;
+ union256h a;
+ memset (&v, -1, sizeof (v));
+ v = foo3 (u.x);
+ a.x = v;
+ if (check_union256h (a, exp.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-3a.c b/gcc/testsuite/gcc.target/i386/avx512fp16-3a.c
new file mode 100644
index 00000000000..126e7d9ee36
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-3a.c
@@ -0,0 +1,36 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+typedef _Float16 __v32hf __attribute__ ((__vector_size__ (64)));
+typedef _Float16 __m512h __attribute__ ((__vector_size__ (64), __may_alias__));
+
+__m512h
+__attribute__ ((noinline, noclone))
+foo1 (_Float16 x)
+{
+ return __extension__ (__m512h)(__v32hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m512h
+__attribute__ ((noinline, noclone))
+foo2 (_Float16 *x)
+{
+ return __extension__ (__m512h)(__v32hf) { *x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 3 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vmovw\[^\n\r]*xmm0" 2 { target { ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-3b.c b/gcc/testsuite/gcc.target/i386/avx512fp16-3b.c
new file mode 100644
index 00000000000..291db066bfa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-3b.c
@@ -0,0 +1,35 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-3a.c"
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union512h u = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m512h v;
+ union512h a;
+ memset (&v, -1, sizeof (v));
+ v = foo1 (x);
+ a.x = v;
+ if (check_union512h (a, u.a))
+ abort ();
+ x = 33.3;
+ u.a[0] = x;
+ memset (&v, -1, sizeof (v));
+ v = foo2 (&x);
+ a.x = v;
+ if (check_union512h (a, u.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-3c.c b/gcc/testsuite/gcc.target/i386/avx512fp16-3c.c
new file mode 100644
index 00000000000..21f9e16434a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-3c.c
@@ -0,0 +1,40 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-3a.c"
+
+__m512h
+__attribute__ ((noinline,noclone))
+foo3 (__m512h x)
+{
+ return foo1(x[0]);
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union512h u = { x, 3.5f, -5.9f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 2.0f, -2.3f, 0.0f, 0.0f, 10.4f, 0.0f, 0.0f, 0.0f,
+ 3.0f, -3.2f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 4.0f, -4.20f, 0.0f, 0.0f, 0.0f, -8.7f, 0.0f, 0.0f };
+
+ union512h exp = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m512h v;
+ union512h a;
+ memset (&v, -1, sizeof (v));
+ v = foo3 (u.x);
+ a.x = v;
+ if (check_union512h (a, exp.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-4.c b/gcc/testsuite/gcc.target/i386/avx512fp16-4.c
new file mode 100644
index 00000000000..1329a0434a0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-4.c
@@ -0,0 +1,31 @@
+/* { dg-do assemble { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+typedef _Float16 __m256h __attribute__ ((__vector_size__ (32), __may_alias__));
+typedef _Float16 __m512h __attribute__ ((__vector_size__ (64), __may_alias__));
+typedef _Float16 __m128h __attribute__ ((__vector_size__ (16), __may_alias__));
+
+extern __m128h x128, y128;
+extern __m256h x256, y256;
+extern __m512h x512, y512;
+
+__m128h
+foo1 (float f1, __m128h f2)
+{
+ x128 = y128;
+ return f2;
+}
+
+__m256h
+foo2 (float f1, __m256h f2)
+{
+ x256 = y256;
+ return f2;
+}
+
+__m512h
+foo3 (float f1, __m512h f2)
+{
+ x512 = y512;
+ return f2;
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-5.c b/gcc/testsuite/gcc.target/i386/avx512fp16-5.c
new file mode 100644
index 00000000000..d28b9651b8b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-5.c
@@ -0,0 +1,133 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo1 (_Float16 x)
+{
+ return __extension__ (__m128h)(__v8hf) { x, 0.0f, 0.0f, 0.0f,
+ 1.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m128h
+__attribute__ ((noinline, noclone))
+foo2 (_Float16 x, _Float16 y)
+{
+ return __extension__ (__m128h)(__v8hf) { x, 0.0f, 0.0f, y,
+ 3.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m256h
+__attribute__ ((noinline, noclone))
+foo3 (_Float16 x)
+{
+ return __extension__ (__m256h)(__v16hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 1.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m256h
+__attribute__ ((noinline, noclone))
+foo4 (_Float16 x, _Float16 y)
+{
+ return __extension__ (__m256h)(__v16hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, y,
+ 3.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m512h
+__attribute__ ((noinline, noclone))
+foo5 (_Float16 x)
+{
+ return __extension__ (__m512h)(__v32hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 1.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+__m512h
+__attribute__ ((noinline, noclone))
+foo6 (_Float16 x, _Float16 y)
+{
+ return __extension__ (__m512h)(__v32hf) { x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, y,
+ 3.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f };
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ _Float16 y = -35.7;
+ union128h u128 = { x, 0.0f, 0.0f, 0.0f, 1.0f, 0.0f, 0.0f, 0.0f };
+ union256h u256 = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 1.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ union512h u512 = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 1.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ __m128h v128;
+ __m256h v256;
+ __m512h v512;
+ union128h a128;
+ union256h a256;
+ union512h a512;
+
+ memset (&v128, -1, sizeof (v128));
+ v128 = foo1 (x);
+ a128.x = v128;
+ if (check_union128h (a128, u128.a))
+ abort ();
+ memset (&v128, -1, sizeof (v128));
+ u128.a[3] = y;
+ u128.a[4] = 3.0f;
+ v128 = foo2 (x, y);
+ a128.x = v128;
+ if (check_union128h (a128, u128.a))
+ abort ();
+
+ memset (&v256, -1, sizeof (v256));
+ v256 = foo3 (x);
+ a256.x = v256;
+ if (check_union256h (a256, u256.a))
+ abort ();
+ memset (&v256, -1, sizeof (v256));
+ u256.a[7] = y;
+ u256.a[8] = 3.0f;
+ v256 = foo4 (x, y);
+ a256.x = v256;
+ if (check_union256h (a256, u256.a))
+ abort ();
+
+ memset (&v512, -1, sizeof (v512));
+ v512 = foo5 (x);
+ a512.x = v512;
+ if (check_union512h (a512, u512.a))
+ abort ();
+ memset (&v512, -1, sizeof (v512));
+ u512.a[15] = y;
+ u512.a[16] = 3.0f;
+ v512 = foo6 (x, y);
+ a512.x = v512;
+ if (check_union512h (a512, u512.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-6.c b/gcc/testsuite/gcc.target/i386/avx512fp16-6.c
new file mode 100644
index 00000000000..d85a6c40603
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-6.c
@@ -0,0 +1,57 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+
+void
+__attribute__ ((noinline, noclone))
+foo128 (_Float16 *p, __m128h x)
+{
+ *p = ((__v8hf)x)[0];
+}
+
+void
+__attribute__ ((noinline, noclone))
+foo256 (_Float16 *p, __m256h x)
+{
+ *p = ((__v16hf)x)[0];
+}
+
+void
+__attribute__ ((noinline, noclone))
+foo512 (_Float16 *p, __m512h x)
+{
+ *p = ((__v32hf)x)[0];
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union128h u128 = { x, 0.0f, 0.0f, 0.0f, 1.0f, 0.0f, 0.0f, 0.0f };
+ union256h u256 = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ union512h u512 = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ _Float16 y;
+
+ foo128 (&y, u128.x);
+ if (x != y)
+ abort ();
+
+ foo256 (&y, u256.x);
+ if (x != y)
+ abort ();
+
+ foo512 (&y, u512.x);
+ if (x != y)
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-7.c b/gcc/testsuite/gcc.target/i386/avx512fp16-7.c
new file mode 100644
index 00000000000..26ae25fc0d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-7.c
@@ -0,0 +1,86 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+
+void
+__attribute__ ((noinline, noclone))
+foo128 (_Float16 *p, __m128h x)
+{
+ *p = ((__v8hf)x)[4];
+}
+
+void
+__attribute__ ((noinline, noclone))
+foo256 (_Float16 *p, __m256h x)
+{
+ *p = ((__v16hf)x)[10];
+}
+
+void
+__attribute__ ((noinline, noclone))
+foo512 (_Float16 *p, __m512h x)
+{
+ *p = ((__v32hf)x)[30];
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union128h u128 = { 0.0f, x, 0.0f, 0.0f, x, 0.0f, 0.0f, x };
+ union256h u256 = { x, 0.0f, 0.0f, 0.0f, x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, x, 0.0f, 0.0f, x, 0.0f, 0.0f };
+ union512h u512 = { x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, x, 0.0f, 0.0f, x, 0.0f };
+ __m128h v128 = _mm_setr_ph (0.0f, x, 0.0f, 0.0f,
+ x, 0.0f, 0.0f, x);
+ __m256h v256 = _mm256_setr_ph (x, 0.0f, 0.0f, 0.0f,
+ x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, x, 0.0f,
+ 0.0f, x, 0.0f, 0.0f);
+ __m512h v512 = _mm512_setr_ph (x, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, x, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, x, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, x,
+ 0.0f, 0.0f, x, 0.0f);
+ union128h a128;
+ union256h a256;
+ union512h a512;
+ _Float16 y;
+
+ a128.x = v128;
+ if (check_union128h (a128, u128.a))
+ abort ();
+
+ a256.x = v256;
+ if (check_union256h (a256, u256.a))
+ abort ();
+
+ a512.x = v512;
+ if (check_union512h (a512, u512.a))
+ abort ();
+
+ foo128 (&y, u128.x);
+ if (x != y)
+ abort ();
+
+ foo256 (&y, u256.x);
+ if (x != y)
+ abort ();
+
+ foo512 (&y, u512.x);
+ if (x != y)
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-8.c b/gcc/testsuite/gcc.target/i386/avx512fp16-8.c
new file mode 100644
index 00000000000..8f103751c2f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-8.c
@@ -0,0 +1,53 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+
+_Float16
+__attribute__ ((noinline, noclone))
+foo128 (__m128h x)
+{
+ return ((__v8hf)x)[4];
+}
+
+_Float16
+__attribute__ ((noinline, noclone))
+foo256 (__m256h x)
+{
+ return ((__v16hf)x)[10];
+}
+
+_Float16
+__attribute__ ((noinline, noclone))
+foo512 (__m512h x)
+{
+ return ((__v32hf)x)[30];
+}
+
+static void
+do_test (void)
+{
+ _Float16 x = 25.3;
+ union128h u128 = { 0.0f, 0.0f, 0.0f, 0.0f, x, 0.0f, 0.0f, 0.0f };
+ union256h u256 = { 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, x, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };
+ union512h u512 = { 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f,
+ 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, x, 0.0f };
+
+ if (foo128 (u128.x) != x)
+ abort ();
+
+ if (foo256 (u256.x) != x)
+ abort ();
+
+ if (foo512 (u512.x) != x)
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-9a.c b/gcc/testsuite/gcc.target/i386/avx512fp16-9a.c
new file mode 100644
index 00000000000..580ffb51e45
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-9a.c
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <immintrin.h>
+
+__m128h
+__attribute__ ((noinline, noclone))
+set1_128 (_Float16 x)
+{
+ return _mm_set1_ph (x);
+}
+
+__m256h
+__attribute__ ((noinline, noclone))
+set1_256 (_Float16 x)
+{
+ return _mm256_set1_ph (x);
+}
+
+__m512h
+__attribute__ ((noinline, noclone))
+set1_512 (_Float16 x)
+{
+ return _mm512_set1_ph (x);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastw\[ \t]\+\[^\n\r]*\[xyz\]mm0" 3 } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512fp16-9b.c b/gcc/testsuite/gcc.target/i386/avx512fp16-9b.c
new file mode 100644
index 00000000000..198b23e64b4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512fp16-9b.c
@@ -0,0 +1,49 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <string.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+#include "avx512-check.h"
+#include "avx512fp16-9a.c"
+
+union128h u128 = { ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16 };
+union256h u256 = { ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16 };
+union512h u512 = { ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16,
+ ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16, ESP_FLOAT16 };
+
+static void
+do_test (void)
+{
+ __m128h v128 = set1_128 (ESP_FLOAT16);
+ __m256h v256 = set1_256 (ESP_FLOAT16);
+ __m512h v512 = set1_512 (ESP_FLOAT16);
+ union128h a128;
+ union256h a256;
+ union512h a512;
+
+ a128.x = v128;
+ if (check_union128h (a128, u128.a))
+ abort ();
+
+ a256.x = v256;
+ if (check_union256h (a256, u256.a))
+ abort ();
+
+ a512.x = v512;
+ if (check_union512h (a512, u512.a))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/m512-check.h b/gcc/testsuite/gcc.target/i386/m512-check.h
index 6befaf0a9ba..68e74fce68d 100644
--- a/gcc/testsuite/gcc.target/i386/m512-check.h
+++ b/gcc/testsuite/gcc.target/i386/m512-check.h
@@ -60,7 +60,24 @@ typedef union
__m512i x;
unsigned long long a[8];
} union512i_uq;
-
+
+typedef union
+{
+ __m128h x;
+ _Float16 a[8];
+} union128h;
+
+typedef union
+{
+ __m256h x;
+ _Float16 a[16];
+} union256h;
+
+typedef union
+{
+ __m512h x;
+ _Float16 a[32];
+} union512h;
CHECK_EXP (union512i_b, char, "%d")
CHECK_EXP (union512i_w, short, "%d")
@@ -115,3 +132,22 @@ CHECK_ROUGH_EXP (union256, float, "%f")
CHECK_ROUGH_EXP (union256d, double, "%f")
CHECK_ROUGH_EXP (union128, float, "%f")
CHECK_ROUGH_EXP (union128d, double, "%f")
+
+#ifdef AVX512FP16
+
+CHECK_EXP (union128h, _Float16, "%f")
+CHECK_EXP (union256h, _Float16, "%f")
+CHECK_EXP (union512h, _Float16, "%f")
+
+#ifndef ESP_FLOAT16
+#define ESP_FLOAT16 0.27
+#endif
+
+CHECK_FP_EXP (union128h, _Float16, ESP_FLOAT16, "%f")
+CHECK_FP_EXP (union256h, _Float16, ESP_FLOAT16, "%f")
+CHECK_FP_EXP (union512h, _Float16, ESP_FLOAT16, "%f")
+
+CHECK_ROUGH_EXP (union128h, _Float16, "%f")
+CHECK_ROUGH_EXP (union256h, _Float16, "%f")
+CHECK_ROUGH_EXP (union512h, _Float16, "%f")
+#endif
--
2.18.1
next prev parent reply other threads:[~2021-07-01 6:16 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-01 6:15 [PATCH 00/62] Support all AVX512FP16 intrinsics liuhongt
2021-07-01 6:15 ` [PATCH 01/62] AVX512FP16: Support vector init/broadcast for FP16 liuhongt
2021-07-01 6:15 ` liuhongt [this message]
2021-07-01 6:15 ` [PATCH 03/62] AVX512FP16: Fix HF vector passing in variable arguments liuhongt
2021-07-01 6:15 ` [PATCH 04/62] AVX512FP16: Add ABI tests for xmm liuhongt
2021-07-01 6:15 ` [PATCH 05/62] AVX512FP16: Add ABI test for ymm liuhongt
2021-07-01 6:15 ` [PATCH 06/62] AVX512FP16: Add abi test for zmm liuhongt
2021-07-01 6:15 ` [PATCH 07/62] AVX512FP16: Add vaddph/vsubph/vdivph/vmulph liuhongt
2021-09-09 7:48 ` Hongtao Liu
2021-07-01 6:15 ` [PATCH 08/62] AVX512FP16: Add testcase for vaddph/vsubph/vmulph/vdivph liuhongt
2021-07-01 6:15 ` [PATCH 09/62] AVX512FP16: Enable _Float16 autovectorization liuhongt
2021-09-10 7:03 ` Hongtao Liu
2021-07-01 6:15 ` [PATCH 10/62] AVX512FP16: Add vaddsh/vsubsh/vmulsh/vdivsh liuhongt
2021-07-01 6:15 ` [PATCH 11/62] AVX512FP16: Add testcase for vaddsh/vsubsh/vmulsh/vdivsh liuhongt
2021-07-01 6:15 ` [PATCH 12/62] AVX512FP16: Add vmaxph/vminph/vmaxsh/vminsh liuhongt
2021-07-01 6:15 ` [PATCH 13/62] AVX512FP16: Add testcase for vmaxph/vmaxsh/vminph/vminsh liuhongt
2021-07-01 6:16 ` [PATCH 14/62] AVX512FP16: Add vcmpph/vcmpsh/vcomish/vucomish liuhongt
2021-07-01 6:16 ` [PATCH 15/62] AVX512FP16: Add testcase for vcmpph/vcmpsh/vcomish/vucomish liuhongt
2021-07-01 6:16 ` [PATCH 16/62] AVX512FP16: Add vsqrtph/vrsqrtph/vsqrtsh/vrsqrtsh liuhongt
2021-09-14 3:50 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 17/62] AVX512FP16: Add testcase for vsqrtph/vsqrtsh/vrsqrtph/vrsqrtsh liuhongt
2021-07-01 6:16 ` [PATCH 18/62] AVX512FP16: Add vrcpph/vrcpsh/vscalefph/vscalefsh liuhongt
2021-07-01 6:16 ` [PATCH 19/62] AVX512FP16: Add testcase for vrcpph/vrcpsh/vscalefph/vscalefsh liuhongt
2021-07-01 6:16 ` [PATCH 20/62] AVX512FP16: Add vreduceph/vreducesh/vrndscaleph/vrndscalesh liuhongt
2021-07-01 6:16 ` [PATCH 21/62] AVX512FP16: Add testcase for vreduceph/vreducesh/vrndscaleph/vrndscalesh liuhongt
2021-07-01 6:16 ` [PATCH 22/62] AVX512FP16: Add fpclass/getexp/getmant instructions liuhongt
2021-07-01 6:16 ` [PATCH 23/62] AVX512FP16: Add testcase for fpclass/getmant/getexp instructions liuhongt
2021-07-01 6:16 ` [PATCH 24/62] AVX512FP16: Add vmovw/vmovsh liuhongt
2021-09-16 5:08 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 25/62] AVX512FP16: Add testcase for vmovsh/vmovw liuhongt
2021-07-01 6:16 ` [PATCH 26/62] AVX512FP16: Add vcvtph2dq/vcvtph2qq/vcvtph2w/vcvtph2uw/vcvtph2uqq/vcvtph2udq liuhongt
2021-07-01 6:16 ` [PATCH 27/62] AVX512FP16: Add testcase for vcvtph2w/vcvtph2uw/vcvtph2dq/vcvtph2udq/vcvtph2qq/vcvtph2uqq liuhongt
2021-07-01 6:16 ` [PATCH 28/62] AVX512FP16: Add vcvtuw2ph/vcvtw2ph/vcvtdq2ph/vcvtudq2ph/vcvtqq2ph/vcvtuqq2ph liuhongt
2021-07-01 6:16 ` [PATCH 29/62] AVX512FP16: Add testcase for vcvtw2ph/vcvtuw2ph/vcvtdq2ph/vcvtudq2ph/vcvtqq2ph/vcvtuqq2ph liuhongt
2021-07-01 6:16 ` [PATCH 30/62] AVX512FP16: Add vcvtsh2si/vcvtsh2usi/vcvtsi2sh/vcvtusi2sh liuhongt
2021-09-17 8:07 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 31/62] AVX512FP16: Add testcase for vcvtsh2si/vcvtsh2usi/vcvtsi2sh/vcvtusi2sh liuhongt
2021-07-01 6:16 ` [PATCH 32/62] AVX512FP16: Add vcvttph2w/vcvttph2uw/vcvttph2dq/vcvttph2qq/vcvttph2udq/vcvttph2uqq liuhongt
2021-07-01 6:16 ` [PATCH 33/62] AVX512FP16: Add testcase for vcvttph2w/vcvttph2uw/vcvttph2dq/vcvttph2udq/vcvttph2qq/vcvttph2uqq liuhongt
2021-07-01 6:16 ` [PATCH 34/62] AVX512FP16: Add vcvttsh2si/vcvttsh2usi liuhongt
2021-07-01 6:16 ` [PATCH 35/62] AVX512FP16: Add vcvtph2pd/vcvtph2psx/vcvtpd2ph/vcvtps2phx liuhongt
2021-07-01 6:16 ` [PATCH 36/62] AVX512FP16: Add testcase for vcvtph2pd/vcvtph2psx/vcvtpd2ph/vcvtps2phx liuhongt
2021-07-01 6:16 ` [PATCH 37/62] AVX512FP16: Add vcvtsh2ss/vcvtsh2sd/vcvtss2sh/vcvtsd2sh liuhongt
2021-07-01 6:16 ` [PATCH 38/62] AVX512FP16: Add testcase for vcvtsh2sd/vcvtsh2ss/vcvtsd2sh/vcvtss2sh liuhongt
2021-07-01 6:16 ` [PATCH 39/62] AVX512FP16: Add intrinsics for casting between vector float16 and vector float32/float64/integer liuhongt
2021-07-01 6:16 ` [PATCH 40/62] AVX512FP16: Add vfmaddsub[132, 213, 231]ph/vfmsubadd[132, 213, 231]ph liuhongt
2021-09-18 7:04 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 41/62] AVX512FP16: Add testcase for " liuhongt
2021-07-01 6:16 ` [PATCH 42/62] AVX512FP16: Add FP16 fma instructions liuhongt
2021-07-01 6:16 ` [PATCH 43/62] AVX512FP16: Add testcase for " liuhongt
2021-07-01 6:16 ` [PATCH 44/62] AVX512FP16: Add scalar/vector bitwise operations, including liuhongt
2021-07-23 5:13 ` Hongtao Liu
2021-07-26 2:25 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 45/62] AVX512FP16: Add testcase for fp16 bitwise operations liuhongt
2021-07-01 6:16 ` [PATCH 46/62] AVX512FP16: Enable FP16 mask load/store liuhongt
2021-07-01 6:16 ` [PATCH 47/62] AVX512FP16: Add scalar fma instructions liuhongt
2021-07-01 6:16 ` [PATCH 48/62] AVX512FP16: Add testcase for scalar FMA instructions liuhongt
2021-07-01 6:16 ` [PATCH 49/62] AVX512FP16: Add vfcmaddcph/vfmaddcph/vfcmulcph/vfmulcph liuhongt
2021-09-22 4:38 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 50/62] AVX512FP16: Add testcases for vfcmaddcph/vfmaddcph/vfcmulcph/vfmulcph liuhongt
2021-07-01 6:16 ` [PATCH 51/62] AVX512FP16: Add vfcmaddcsh/vfmaddcsh/vfcmulcsh/vfmulcsh liuhongt
2021-07-01 6:16 ` [PATCH 52/62] AVX512FP16: Add testcases for vfcmaddcsh/vfmaddcsh/vfcmulcsh/vfmulcsh liuhongt
2021-07-01 6:16 ` [PATCH 53/62] AVX512FP16: Add expander for sqrthf2 liuhongt
2021-07-23 5:12 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 54/62] AVX512FP16: Add expander for ceil/floor/trunc/roundeven liuhongt
2021-07-01 6:16 ` [PATCH 55/62] AVX512FP16: Add expander for cstorehf4 liuhongt
2021-07-01 6:16 ` [PATCH 56/62] AVX512FP16: Optimize (_Float16) sqrtf ((float) f16) to sqrtf16 (f16) liuhongt
2021-07-01 9:50 ` Richard Biener
2021-07-01 10:23 ` Hongtao Liu
2021-07-01 12:43 ` Richard Biener
2021-07-01 21:48 ` Joseph Myers
2021-07-02 7:38 ` Richard Biener
2021-07-01 21:17 ` Joseph Myers
2021-07-01 6:16 ` [PATCH 57/62] AVX512FP16: Add expander for fmahf4 liuhongt
2021-07-01 6:16 ` [PATCH 58/62] AVX512FP16: Optimize for code like (_Float16) __builtin_ceif ((float) f16) liuhongt
2021-07-01 9:52 ` Richard Biener
2021-07-01 21:26 ` Joseph Myers
2021-07-02 7:36 ` Richard Biener
2021-07-02 11:46 ` Bernhard Reutner-Fischer
2021-07-04 5:17 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 59/62] AVX512FP16: Support load/store/abs intrinsics liuhongt
2021-09-22 10:30 ` Hongtao Liu
2021-07-01 6:16 ` [PATCH 60/62] AVX512FP16: Add reduce operators(add/mul/min/max) liuhongt
2021-07-01 6:16 ` [PATCH 61/62] AVX512FP16: Add complex conjugation intrinsic instructions liuhongt
2021-07-01 6:16 ` [PATCH 62/62] AVX512FP16: Add permutation and mask blend intrinsics liuhongt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210701061648.9447-3-hongtao.liu@intel.com \
--to=hongtao.liu@intel.com \
--cc=crazylht@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hjl.tools@gmail.com \
--cc=jakub@redhat.com \
--cc=ubizjak@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).