[gcc r14-6073] LoongArch: Optimize vector constant extract-{even/odd} permutation.

[LuluCheng]

https://gcc.gnu.org/g:6b226c2611f0ec01f2cc1319bc41af37518f2dfd

commit r14-6073-g6b226c2611f0ec01f2cc1319bc41af37518f2dfd
Author: Li Wei <liwei@loongson.cn>
Date:   Tue Nov 28 15:39:00 2023 +0800

    LoongArch: Optimize vector constant extract-{even/odd} permutation.
    
    For vector constant extract-{even/odd} permutation replace the default
    [x]vshuf instruction combination with [x]vilv{l/h} instruction, which
    can reduce instructions and improves performance.
    
    gcc/ChangeLog:
    
            * config/loongarch/loongarch.cc (loongarch_is_odd_extraction):
            Supplementary function prototype.
            (loongarch_is_even_extraction): Adjust.
            (loongarch_try_expand_lsx_vshuf_const): Adjust.
            (loongarch_is_extraction_permutation): Adjust.
            (loongarch_expand_vec_perm_const_2): Adjust.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/loongarch/lasx-extract-even_odd-opt.c: New test.

Diff:
---
 gcc/config/loongarch/loongarch.cc                  | 33 ++++++++++++-
 .../loongarch/lasx-extract-even_odd-opt.c          | 54 ++++++++++++++++++++++
 2 files changed, 85 insertions(+), 2 deletions(-)

diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index d3896d72bc2..f89c346815d 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -8672,6 +8672,12 @@ loongarch_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel)
     }
 }
 
+static bool
+loongarch_is_odd_extraction (struct expand_vec_perm_d *);
+
+static bool
+loongarch_is_even_extraction (struct expand_vec_perm_d *);
+
 static bool
 loongarch_try_expand_lsx_vshuf_const (struct expand_vec_perm_d *d)
 {
@@ -8694,6 +8700,24 @@ loongarch_try_expand_lsx_vshuf_const (struct expand_vec_perm_d *d)
       if (d->testing_p)
 	return true;
 
+      /* If match extract-even and extract-odd permutations pattern, use
+       * vselect much better than vshuf.  */
+      if (loongarch_is_odd_extraction (d)
+	  || loongarch_is_even_extraction (d))
+	{
+	  if (loongarch_expand_vselect_vconcat (d->target, d->op0, d->op1,
+						d->perm, d->nelt))
+	    return true;
+
+	  unsigned char perm2[MAX_VECT_LEN];
+	  for (i = 0; i < d->nelt; ++i)
+	    perm2[i] = (d->perm[i] + d->nelt) & (2 * d->nelt - 1);
+
+	  if (loongarch_expand_vselect_vconcat (d->target, d->op1, d->op0,
+						perm2, d->nelt))
+	    return true;
+	}
+
       for (i = 0; i < d->nelt; i += 1)
 	{
 	  rperm[i] = GEN_INT (d->perm[i]);
@@ -8878,7 +8902,7 @@ loongarch_is_even_extraction (struct expand_vec_perm_d *d)
 	  result = false;
 	  break;
 	}
-      buf += 1;
+      buf += 2;
     }
 
   return result;
@@ -8900,7 +8924,7 @@ loongarch_is_extraction_permutation (struct expand_vec_perm_d *d)
 	  result = false;
 	  break;
 	}
-      buf += 2;
+      buf += 1;
     }
 
   return result;
@@ -9377,6 +9401,11 @@ loongarch_expand_vec_perm_const_2 (struct expand_vec_perm_d *d)
 	 Selector after: { 1, 3, 1, 3 }.
 	 Even extraction selector sample: E_V4DImode, { 0, 2, 4, 6 }
 	 Selector after: { 0, 2, 0, 2 }.  */
+
+      /* Better implement of extract-even and extract-odd permutations.  */
+      if (loongarch_expand_vec_perm_even_odd (d))
+	return true;
+
       for (i = 0; i < d->nelt / 2; i += 1)
 	{
 	  idx = d->perm[i];
diff --git a/gcc/testsuite/gcc.target/loongarch/lasx-extract-even_odd-opt.c b/gcc/testsuite/gcc.target/loongarch/lasx-extract-even_odd-opt.c
new file mode 100644
index 00000000000..515f0c8621a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/lasx-extract-even_odd-opt.c
@@ -0,0 +1,54 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mlasx" } */
+/* { dg-final { scan-assembler "xvilvl.d" } } */
+/* { dg-final { scan-assembler "xvilvh.d" } } */
+
+#define CMUL(a, b, c)                                                         \
+  {                                                                           \
+    (c).ai = (a).ai * (b).ai - (a).bi * (b).bi;                               \
+    (c).bi = (a).ai * (b).bi + (a).bi * (b).ai;                               \
+    (c).ci = (a).ci * (b).ci - (a).di * (b).di;                               \
+    (c).di = (a).ci * (b).di + (a).di * (b).ci;                               \
+  }
+#define CSUM(a, b)                                                            \
+  {                                                                           \
+    (a).ai += (b).ai;                                                         \
+    (a).bi += (b).bi;                                                         \
+    (a).ci += (b).ci;                                                         \
+    (a).di += (b).di;                                                         \
+  }
+
+typedef struct
+{
+  double ai;
+  double bi;
+  double ci;
+  double di;
+} complex;
+
+typedef struct
+{
+  complex e[6][6];
+} matrix;
+
+typedef struct
+{
+  complex c[6];
+} vector;
+
+void
+mult_adj_mat_vec (matrix *a, vector *b, vector *c)
+{
+  register int i, j;
+  register complex x, y;
+  for (i = 0; i < 6; i++)
+    {
+      x.ai = x.bi = x.ci = x.di = 0.0;
+      for (j = 0; j < 6; j++)
+        {
+          CMUL (a->e[j][i], b->c[j], y);
+          CSUM (x, y);
+        }
+      c->c[i] = x;
+    }
+}