Hi,
this patch makes static profile to be in range 0...2^30 rather than
0...10000. This is safe now as profile-counts are taking care of
possible overflow when the profile ends up cummulating too high after
inlining.
MThere are two testcases that needs adusting. dump-2.c simply checks
for specific value of counter that is now different. pr77445-2
now gets one extra mismatch reported. The mismatch was present before
too but due to low precision it was not visible.
Bootstrapped/regtested x86_64-linux, comitted.
Honza
* predict.c (determine_unlikely_bbs): Set cgraph node count to 0
when entry block was promoted unlikely.
(estimate_bb_frequencies): Increase frequency scale.
* profile-count.h (profile_count): Export precision info.
* gcc.dg/tree-ssa/dump-2.c: Fixup template for profile precision
changes.
* gcc.dg/tree-ssa/pr77445-2.c: Fixup template for profile precision
changes.
Index: predict.c
===================================================================
--- predict.c (revision 254884)
+++ predict.c (working copy)
@@ -3542,6 +3542,8 @@ determine_unlikely_bbs ()
bb->index, e->dest->index);
e->probability = profile_probability::never ();
}
+ if (ENTRY_BLOCK_PTR_FOR_FN (cfun)->count == profile_count::zero ())
+ cgraph_node::get (current_function_decl)->count = profile_count::zero ();
}
/* Estimate and propagate basic block frequencies using the given branch
@@ -3565,7 +3567,11 @@ estimate_bb_frequencies (bool force)
{
real_values_initialized = 1;
real_br_prob_base = REG_BR_PROB_BASE;
- real_bb_freq_max = BB_FREQ_MAX;
+ /* Scaling frequencies up to maximal profile count may result in
+ frequent overflows especially when inlining loops.
+ Small scalling results in unnecesary precision loss. Stay in
+ the half of the (exponential) range. */
+ real_bb_freq_max = (uint64_t)1 << (profile_count::n_bits / 2);
real_one_half = sreal (1, -1);
real_inv_br_prob_base = sreal (1) / real_br_prob_base;
real_almost_one = sreal (1) - real_inv_br_prob_base;
@@ -3610,6 +3616,8 @@ estimate_bb_frequencies (bool force)
freq_max = BLOCK_INFO (bb)->frequency;
freq_max = real_bb_freq_max / freq_max;
+ if (freq_max < 16)
+ freq_max = 16;
cfun->cfg->count_max = profile_count::uninitialized ();
FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR_FOR_FN (cfun), NULL, next_bb)
{
Index: profile-count.h
===================================================================
--- profile-count.h (revision 254884)
+++ profile-count.h (working copy)
@@ -605,11 +605,13 @@ class sreal;
class GTY(()) profile_count
{
+public:
/* Use 62bit to hold basic block counters. Should be at least
64bit. Although a counter cannot be negative, we use a signed
type to hold various extra stages. */
static const int n_bits = 61;
+private:
static const uint64_t max_count = ((uint64_t) 1 << n_bits) - 2;
static const uint64_t uninitialized_count = ((uint64_t) 1 << n_bits) - 1;
Index: testsuite/gcc.dg/tree-ssa/dump-2.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/dump-2.c (revision 254884)
+++ testsuite/gcc.dg/tree-ssa/dump-2.c (working copy)
@@ -6,4 +6,4 @@ int f(void)
return 0;
}
-/* { dg-final { scan-tree-dump "<bb \[0-9\]> \\\[local count: 10000\\\]:"
"optimized" } } */
+/* { dg-final { scan-tree-dump "<bb \[0-9\]> \\\[local count: " "optimized" }
} */
Index: testsuite/gcc.dg/tree-ssa/pr77445-2.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/pr77445-2.c (revision 254884)
+++ testsuite/gcc.dg/tree-ssa/pr77445-2.c (working copy)
@@ -120,7 +120,7 @@ enum STATES FMS( u8 **in , u32 *transiti
profile estimation stage. But the number of inconsistencies should not
increase much. */
/* { dg-final { scan-tree-dump "Jumps threaded: 1\[1-9\]" "thread1" } } */
-/* { dg-final { scan-tree-dump-times "Invalid sum" 2 "thread1" } } */
+/* { dg-final { scan-tree-dump-times "Invalid sum" 3 "thread1" } } */
/* { dg-final { scan-tree-dump-not "not considered" "thread1" } } */
/* { dg-final { scan-tree-dump-not "not considered" "thread2" } } */
/* { dg-final { scan-tree-dump-not "not considered" "thread3" } } */
