[gcc r12-2752] Support cond_{smax, smin} for vector float/double modes under AVX512.

[hongtao Liu <liuhongt@gcc.gnu.org>]

https://gcc.gnu.org/g:f7aa81892eb54bc040ee6f7fd6134d800a5ee89c

commit r12-2752-gf7aa81892eb54bc040ee6f7fd6134d800a5ee89c
Author: liuhongt <hongtao.liu@intel.com>
Date:   Wed Aug 4 18:15:43 2021 +0800

    Support cond_{smax,smin} for vector float/double modes under AVX512.
    
    gcc/ChangeLog:
    
            * config/i386/sse.md (cond_<code><mode>): New expander.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/i386/cond_op_maxmin_double-1.c: New test.
            * gcc.target/i386/cond_op_maxmin_double-2.c: New test.
            * gcc.target/i386/cond_op_maxmin_float-1.c: New test.
            * gcc.target/i386/cond_op_maxmin_float-2.c: New test.

Diff:
---
 gcc/config/i386/sse.md                             | 18 ++++++
 .../gcc.target/i386/cond_op_maxmin_double-1.c      | 39 +++++++++++++
 .../gcc.target/i386/cond_op_maxmin_double-2.c      | 67 ++++++++++++++++++++++
 .../gcc.target/i386/cond_op_maxmin_float-1.c       |  8 +++
 .../gcc.target/i386/cond_op_maxmin_float-2.c       |  5 ++
 5 files changed, 137 insertions(+)

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 6035411ea75..51733a3849d 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2376,6 +2376,24 @@
    (set_attr "prefix" "orig,vex")
    (set_attr "mode" "SF")])
 
+(define_expand "cond_<code><mode>"
+  [(set (match_operand:VF 0 "register_operand")
+	(vec_merge:VF
+	  (smaxmin:VF
+	    (match_operand:VF 2 "vector_operand")
+	    (match_operand:VF 3 "vector_operand"))
+	  (match_operand:VF 4 "nonimm_or_0_operand")
+	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
+  "<MODE_SIZE> == 64 || TARGET_AVX512VL"
+{
+  emit_insn (gen_<code><mode>3_mask (operands[0],
+				     operands[2],
+				     operands[3],
+				     operands[4],
+				     operands[1]));
+  DONE;
+})
+
 (define_expand "<code><mode>3<mask_name><round_saeonly_name>"
   [(set (match_operand:VF 0 "register_operand")
 	(smaxmin:VF
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-1.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-1.c
new file mode 100644
index 00000000000..eda8e1974b9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-1.c
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=skylake-avx512 -fdump-tree-optimized" } */
+/* { dg-final { scan-tree-dump ".COND_MAX" "optimized" } } */
+/* { dg-final { scan-tree-dump ".COND_MIN" "optimized" } } */
+/* { dg-final { scan-assembler-times "vmaxpd"  1 } } */
+/* { dg-final { scan-assembler-times "vminpd"  1 } } */
+
+#include<math.h>
+#ifndef NUM
+#define NUM 800
+#endif
+#ifndef TYPE
+#define TYPE double
+#endif
+#ifndef FN_MAX
+#define FN_MAX fmax
+#endif
+#ifndef FN_MIN
+#define FN_MIN fmin
+#endif
+
+TYPE a[NUM], b[NUM], c[NUM], d[NUM], e[NUM], j[NUM];
+#define MAX FN_MAX
+#define MIN FN_MIN
+
+#define BIN(OPNAME, OP)				\
+  void						\
+  __attribute__ ((noipa,optimize ("Ofast")))	\
+  foo_##OPNAME ()				\
+  {						\
+    for (int i = 0; i != NUM; i++)		\
+      if (b[i] < c[i])				\
+	a[i] = (OP (d[i], e[i]));		\
+      else					\
+	a[i] = d[i] - e[i];			\
+  }
+
+BIN (max, MAX);
+BIN (min, MIN);
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-2.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-2.c
new file mode 100644
index 00000000000..c50a831000a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_double-2.c
@@ -0,0 +1,67 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512vl -mprefer-vector-width=256 -ffast-math" } */
+/* { dg-require-effective-target avx512vl } */
+
+#define AVX512VL
+#ifndef CHECK
+#define CHECK "avx512f-helper.h"
+#endif
+
+#include CHECK
+
+#include "cond_op_maxmin_double-1.c"
+#define BINO2(OPNAME, OP)			\
+  void						\
+  __attribute__ ((noipa))			\
+  foo_o2_##OPNAME ()				\
+  {						\
+    for (int i = 0; i != NUM; i++)		\
+      if (b[i] < c[i])				\
+	j[i] = OP(d[i], e[i]);			\
+      else					\
+	j[i] = d[i] - e[i];			\
+  }
+
+BINO2 (max, MAX);
+BINO2 (min, MIN);
+
+static void
+test_256 (void)
+{
+  int sign = -1;
+  for (int i = 0; i != NUM; i++)
+    {
+      a[i] = 0;
+      d[i] = i * 2;
+      e[i] = i * i * 3 - i * 9 + 153;
+      b[i] = i * 83;
+      c[i] = b[i] + sign;
+      sign *= -1;
+      j[i] = 1;
+    }
+  foo_max ();
+  foo_o2_max ();
+  for (int i = 0; i != NUM; i++)
+    {
+      if (a[i] != j[i])
+	abort ();
+      a[i] = 0;
+      b[i] = 1;
+    }
+
+  foo_min ();
+  foo_o2_min ();
+  for (int i = 0; i != NUM; i++)
+    {
+      if (a[i] != j[i])
+  	abort ();
+      a[i] = 0;
+      j[i] = 1;
+    }
+}
+
+static void
+test_128 ()
+{
+  
+}
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-1.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-1.c
new file mode 100644
index 00000000000..2d2157d87a5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-1.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=skylake-avx512 -DTYPE=float -fdump-tree-optimized -DFN_MAX=fmaxf -DFN_MIN=fminf" } */
+/* { dg-final { scan-tree-dump ".COND_MAX" "optimized" } } */
+/* { dg-final { scan-tree-dump ".COND_MIN" "optimized" } } */
+/* { dg-final { scan-assembler-times "vmaxps"  1 } } */
+/* { dg-final { scan-assembler-times "vminps"  1 } } */
+
+#include "cond_op_maxmin_double-1.c"
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-2.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-2.c
new file mode 100644
index 00000000000..fec784e5ded
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin_float-2.c
@@ -0,0 +1,5 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512vl -mprefer-vector-width=256 -DTYPE=float -DFN_MAX=fmaxf -DFN_MIN=fminf" } */
+/* { dg-require-effective-target avx512vl } */
+
+#include "cond_op_maxmin_double-2.c"