re PR rtl-optimization/80481 (Unoptimal additional copy instructions)

2018-01-12  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/80481
	* ira-color.c (get_cap_member): New function.
	(allocnos_conflict_by_live_ranges_p): Use it.
	(slot_coalesced_allocno_live_ranges_intersect_p): Add assert.
	(setup_slot_coalesced_allocno_live_ranges): Ditto.

2018-01-12  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/80481
	* g++.dg/pr80481.C: New.

From-SVN: r256590

gcc/ChangeLog

+2018-01-12  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/80481
+	* ira-color.c (get_cap_member): New function.
+	(allocnos_conflict_by_live_ranges_p): Use it.
+	(slot_coalesced_allocno_live_ranges_intersect_p): Add assert.
+	(setup_slot_coalesced_allocno_live_ranges): Ditto.
+
 2018-01-12  Uros Bizjak  <ubizjak@gmail.com>
 
 	PR target/83628

gcc/ira-color.c

@@ -1905,6 +1905,18 @@ assign_hard_reg (ira_allocno_t a, bool retry_p)
 /* An array used to sort copies.  */
 static ira_copy_t *sorted_copies;
 
+/* If allocno A is a cap, return non-cap allocno from which A is
+   created.  Otherwise, return A.  */
+static ira_allocno_t
+get_cap_member (ira_allocno_t a)
+{
+  ira_allocno_t member;
+  
+  while ((member = ALLOCNO_CAP_MEMBER (a)) != NULL)
+    a = member;
+  return a;
+}
+
 /* Return TRUE if live ranges of allocnos A1 and A2 intersect.  It is
    used to find a conflict for new allocnos or allocnos with the
    different allocno classes.  */
@@ -1924,6 +1936,10 @@ allocnos_conflict_by_live_ranges_p (ira_allocno_t a1, ira_allocno_t a2)
       && ORIGINAL_REGNO (reg1) == ORIGINAL_REGNO (reg2))
     return false;
 
+  /* We don't keep live ranges for caps because they can be quite big.
+     Use ranges of non-cap allocno from which caps are created.  */
+  a1 = get_cap_member (a1);
+  a2 = get_cap_member (a2);
   for (i = 0; i < n1; i++)
     {
       ira_object_t c1 = ALLOCNO_OBJECT (a1, i);
@@ -4027,7 +4043,7 @@ slot_coalesced_allocno_live_ranges_intersect_p (ira_allocno_t allocno, int n)
     {
       int i;
       int nr = ALLOCNO_NUM_OBJECTS (a);
-
+      gcc_assert (ALLOCNO_CAP_MEMBER (a) == NULL);
       for (i = 0; i < nr; i++)
 	{
 	  ira_object_t obj = ALLOCNO_OBJECT (a, i);
@@ -4057,6 +4073,7 @@ setup_slot_coalesced_allocno_live_ranges (ira_allocno_t allocno)
        a = ALLOCNO_COALESCE_DATA (a)->next)
     {
       int nr = ALLOCNO_NUM_OBJECTS (a);
+      gcc_assert (ALLOCNO_CAP_MEMBER (a) == NULL);
       for (i = 0; i < nr; i++)
 	{
 	  ira_object_t obj = ALLOCNO_OBJECT (a, i);

gcc/testsuite/ChangeLog

+2018-01-12  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/80481
+	* g++.dg/pr80481.C: New.
+
 2018-01-12  Uros Bizjak  <ubizjak@gmail.com>
 
 	PR target/83628

gcc/testsuite/g++.dg/pr80481.C

+// { dg-do compile { target i?86-*-* x86_64-*-* } }
+// { dg-options "-Ofast -funroll-loops -fopenmp -march=knl" }
+// { dg-final { scan-assembler-not "vmovaps" } }
+
+#include <math.h>
+
+#include <xmmintrin.h>
+
+#define max(a, b)   ( (a) > (b) ? (a) : (b) )
+
+struct Sdata {
+  float w; 
+  float s;
+  float r;
+  float t;
+  float v;
+};
+ extern int N1, N2, N3;
+
+#define func(p, up, down) ((p)*(up) + (1.0f-(p)) * (down))
+ 
+void foo (Sdata *in, int idx, float *out)
+{
+  float* y1 = (float*)_mm_malloc(sizeof(float) * N1,16);
+  float* y2  = (float*)_mm_malloc(sizeof(float) * N1,16);
+  float* y3  = (float*)_mm_malloc(sizeof(float) * N1,16);
+  float* y4  = (float*)_mm_malloc(sizeof(float) * N1,16); 
+
+  for (int k = idx; k < idx + N3; k++) {
+    float x1 = in[k].r;
+    float x2    = in[k].s;
+    float x3      = in[k].w;
+    float x4     = in[k].v;
+    float x5         = in[k].t;
+    x5 /= N2;
+    float u = exp(x4 * sqrt(x5));
+    float d = exp(-x4 * sqrt(x5));
+    float a = exp(x1 * x5);
+    float m = exp(-x1 * x5);
+    float p = (a - d) / (u - d);
+    y2[0] = x2;
+    y3[0] = float(1.f);
+    for (int i = 1; i <= N2; i++) {
+      y2[i] = u * y2[i - 1];
+      y3[i] = d * y3[i - 1];
+    }
+#pragma omp simd
+    for (int i = 0; i <= N2; i++) {
+      y1[i] =
+        max((x3 - y2[N2 - i] * y3[i]), float(0.f));
+    }
+    for (int i = N2 - 1; i >= 0; i--) {
+#pragma omp simd
+      for (int j = 0; j <= i; j++) {
+        y4[j] = func(p,y1[j],y1[j+1]) * m;
+      }
+#pragma omp simd
+      for (int j = 0; j <= i; j++) {
+        float t1 = y2[i - j] * y3[j];
+        float t2 = max(x3 - t1, float(0.f));
+        y1[j] = max(t2, y4[j]);
+      }
+    }
+    out[k] = y1[0];
+  }
+  _mm_free(y1);
+  _mm_free(y2);
+  _mm_free(y3);
+  _mm_free(y4);
+}