[PATCH] Don't reduce estimated unrolled size for innermost loop.

[liuhongt <hongtao.liu@intel.com>]

As testcase in the PR, O3 cunrolli may prevent vectorization for the
innermost loop and increase register pressure.
The patch removes the 1/3 reduction of unr_insn for innermost loop for UL_ALL.
ul != UR_ALL is needed since some small loop complete unrolling at O2 relies
the reduction.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
No big impact for SPEC2017.
Ok for trunk?

gcc/ChangeLog:

	PR tree-optimization/112325
	* tree-ssa-loop-ivcanon.cc (estimated_unrolled_size): Add 2
	new parameters: loop and ul, and remove unr_insns reduction
	for innermost loop.
	(try_unroll_loop_completely): Pass loop and ul to
	estimated_unrolled_size.

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/pr112325.c: New test.
	* gcc.dg/vect/pr69783.c: Add extra option --param
	max-completely-peeled-insns=300.
---
 gcc/testsuite/gcc.dg/tree-ssa/pr112325.c | 57 ++++++++++++++++++++++++
 gcc/testsuite/gcc.dg/vect/pr69783.c      |  2 +-
 gcc/tree-ssa-loop-ivcanon.cc             | 16 +++++--
 3 files changed, 71 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr112325.c

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr112325.c b/gcc/testsuite/gcc.dg/tree-ssa/pr112325.c
new file mode 100644
index 00000000000..14208b3e7f8
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr112325.c
@@ -0,0 +1,57 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-cunrolli-details" } */
+
+typedef unsigned short ggml_fp16_t;
+static float table_f32_f16[1 << 16];
+
+inline static float ggml_lookup_fp16_to_fp32(ggml_fp16_t f) {
+    unsigned short s;
+    __builtin_memcpy(&s, &f, sizeof(unsigned short));
+    return table_f32_f16[s];
+}
+
+typedef struct {
+    ggml_fp16_t d;
+    ggml_fp16_t m;
+    unsigned char qh[4];
+    unsigned char qs[32 / 2];
+} block_q5_1;
+
+typedef struct {
+    float d;
+    float s;
+    char qs[32];
+} block_q8_1;
+
+void ggml_vec_dot_q5_1_q8_1(const int n, float * restrict s, const void * restrict vx, const void * restrict vy) {
+    const int qk = 32;
+    const int nb = n / qk;
+
+    const block_q5_1 * restrict x = vx;
+    const block_q8_1 * restrict y = vy;
+
+    float sumf = 0.0;
+
+    for (int i = 0; i < nb; i++) {
+        unsigned qh;
+        __builtin_memcpy(&qh, x[i].qh, sizeof(qh));
+
+        int sumi = 0;
+
+        for (int j = 0; j < qk/2; ++j) {
+            const unsigned char xh_0 = ((qh >> (j + 0)) << 4) & 0x10;
+            const unsigned char xh_1 = ((qh >> (j + 12)) ) & 0x10;
+
+            const int x0 = (x[i].qs[j] & 0xF) | xh_0;
+            const int x1 = (x[i].qs[j] >> 4) | xh_1;
+
+            sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]);
+        }
+
+        sumf += (ggml_lookup_fp16_to_fp32(x[i].d)*y[i].d)*sumi + ggml_lookup_fp16_to_fp32(x[i].m)*y[i].s;
+    }
+
+    *s = sumf;
+}
+
+/* { dg-final { scan-tree-dump {(?n)Not unrolling loop [1-9] \(--param max-completely-peel-times limit reached} "cunrolli"} } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr69783.c b/gcc/testsuite/gcc.dg/vect/pr69783.c
index 5df95d0ce4e..a1f75514d72 100644
--- a/gcc/testsuite/gcc.dg/vect/pr69783.c
+++ b/gcc/testsuite/gcc.dg/vect/pr69783.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target vect_float } */
-/* { dg-additional-options "-Ofast -funroll-loops" } */
+/* { dg-additional-options "-Ofast -funroll-loops --param max-completely-peeled-insns=300" } */
 
 #define NXX 516
 #define NYY 516
diff --git a/gcc/tree-ssa-loop-ivcanon.cc b/gcc/tree-ssa-loop-ivcanon.cc
index bf017137260..5e0eca647a1 100644
--- a/gcc/tree-ssa-loop-ivcanon.cc
+++ b/gcc/tree-ssa-loop-ivcanon.cc
@@ -444,7 +444,9 @@ tree_estimate_loop_size (class loop *loop, edge exit, edge edge_to_cancel,
 
 static unsigned HOST_WIDE_INT
 estimated_unrolled_size (struct loop_size *size,
-			 unsigned HOST_WIDE_INT nunroll)
+			 unsigned HOST_WIDE_INT nunroll,
+			 enum unroll_level ul,
+			 class loop* loop)
 {
   HOST_WIDE_INT unr_insns = ((nunroll)
   			     * (HOST_WIDE_INT) (size->overall
@@ -453,7 +455,15 @@ estimated_unrolled_size (struct loop_size *size,
     unr_insns = 0;
   unr_insns += size->last_iteration - size->last_iteration_eliminated_by_peeling;
 
-  unr_insns = unr_insns * 2 / 3;
+  /* For innermost loop, loop body is not likely to be simplied as much as 1/3.
+     and may increase a lot of register pressure.
+     UL != UL_ALL is need to unroll small loop at O2.  */
+  class loop *loop_father = loop_outer (loop);
+  if (loop->inner || !loop_father
+      || loop_father->latch == EXIT_BLOCK_PTR_FOR_FN (cfun)
+      || ul != UL_ALL)
+    unr_insns = unr_insns * 2 / 3;
+
   if (unr_insns <= 0)
     unr_insns = 1;
 
@@ -837,7 +847,7 @@ try_unroll_loop_completely (class loop *loop,
 
 	  unsigned HOST_WIDE_INT ninsns = size.overall;
 	  unsigned HOST_WIDE_INT unr_insns
-	    = estimated_unrolled_size (&size, n_unroll);
+	    = estimated_unrolled_size (&size, n_unroll, ul, loop);
 	  if (dump_file && (dump_flags & TDF_DETAILS))
 	    {
 	      fprintf (dump_file, "  Loop size: %d\n", (int) ninsns);
-- 
2.31.1