The following patch corrects frequency/count values computed when generating
the switch blocks/peeled loop copies before the loop. The two main problem
areas were for the peeled copies duplicate_loop_to_header_edge was not using
the preheader frequency as part of the scale factor when peeling a copy of the
loop to the preheader edge, and the second was that the switch block generation
was just totally lacking code to compute correct freq/count values. Verified by
comparing freq/count values in the unroller dump before/after.
Bootstrap/regtest on powerpc64le with no new regressions. Ok for trunk?
-Pat
2016-09-20 Pat Haugen
PR rtl-optimization/68212
* cfgloopmanip.c (duplicate_loop_to_header_edge): Use preheader edge
frequency when computing scale factor for peeled copies.
* loop-unroll.c (unroll_loop_runtime_iterations): Fix freq/count
values for switch/peel blocks/edges.
Index: gcc/cfgloopmanip.c
===
--- gcc/cfgloopmanip.c (revision 240167)
+++ gcc/cfgloopmanip.c (working copy)
@@ -1276,10 +1276,13 @@ duplicate_loop_to_header_edge (struct lo
}
else
{
+ int preheader_freq = EDGE_FREQUENCY (e);
scale_main = REG_BR_PROB_BASE;
for (i = 0; i < ndupl; i++)
scale_main = combine_probabilities (scale_main, scale_step[i]);
- scale_act = REG_BR_PROB_BASE - prob_pass_thru;
+ if (preheader_freq > freq_in)
+ preheader_freq = freq_in;
+ scale_act = GCOV_COMPUTE_SCALE (preheader_freq, freq_in);
}
for (i = 0; i < ndupl; i++)
gcc_assert (scale_step[i] >= 0 && scale_step[i] <= REG_BR_PROB_BASE);
Index: gcc/loop-unroll.c
===
--- gcc/loop-unroll.c (revision 240167)
+++ gcc/loop-unroll.c (working copy)
@@ -858,7 +858,8 @@ unroll_loop_runtime_iterations (struct l
rtx_insn *init_code, *branch_code;
unsigned i, j, p;
basic_block preheader, *body, swtch, ezc_swtch;
- int may_exit_copy;
+ int may_exit_copy, iter_freq, new_freq;
+ gcov_type iter_count, new_count;
unsigned n_peel;
edge e;
bool extra_zero_check, last_may_exit;
@@ -952,6 +953,15 @@ unroll_loop_runtime_iterations (struct l
/* Record the place where switch will be built for preconditioning. */
swtch = split_edge (loop_preheader_edge (loop));
+ /* Compute frequency/count increments for each switch block and initialize
+ innermost switch block. Switch blocks and peeled loop copies are built
+ from innermost outward. */
+ iter_freq = new_freq = swtch->frequency / (max_unroll + 1);
+ iter_count = new_count = swtch->count / (max_unroll + 1);
+ swtch->frequency = new_freq;
+ swtch->count = new_count;
+ single_succ_edge (swtch)->count = new_count;
+
for (i = 0; i < n_peel; i++)
{
/* Peel the copy. */
@@ -969,6 +979,10 @@ unroll_loop_runtime_iterations (struct l
p = REG_BR_PROB_BASE / (i + 2);
preheader = split_edge (loop_preheader_edge (loop));
+ /* Add in frequency/count of edge from switch block. */
+ preheader->frequency += iter_freq;
+ preheader->count += iter_count;
+ single_succ_edge (preheader)->count = preheader->count;
branch_code = compare_and_jump_seq (copy_rtx (niter), GEN_INT (j), EQ,
block_label (preheader), p,
NULL);
@@ -980,9 +994,14 @@ unroll_loop_runtime_iterations (struct l
swtch = split_edge_and_insert (single_pred_edge (swtch), branch_code);
set_immediate_dominator (CDI_DOMINATORS, preheader, swtch);
single_succ_edge (swtch)->probability = REG_BR_PROB_BASE - p;
+ single_succ_edge (swtch)->count = new_count;
+ new_freq += iter_freq;
+ new_count += iter_count;
+ swtch->frequency = new_freq;
+ swtch->count = new_count;
e = make_edge (swtch, preheader,
single_succ_edge (swtch)->flags & EDGE_IRREDUCIBLE_LOOP);
- e->count = RDIV (preheader->count * REG_BR_PROB_BASE, p);
+ e->count = iter_count;
e->probability = p;
}
@@ -992,6 +1011,14 @@ unroll_loop_runtime_iterations (struct l
p = REG_BR_PROB_BASE / (max_unroll + 1);
swtch = ezc_swtch;
preheader = split_edge (loop_preheader_edge (loop));
+ /* Recompute frequency/count adjustments since initial peel copy may
+ have exited and reduced those values that were computed above. */
+ iter_freq = swtch->frequency / (max_unroll + 1);
+ iter_count = swtch->count / (max_unroll + 1);
+ /* Add in frequency/count of edge from switch block. */
+ preheader->frequency += iter_freq;
+ preheader->count += iter_count;
+ single_succ_edge (preheader)->count = preheader->count;
branch_code = compare_and_jump_seq (copy_rtx (niter), const0_rtx, EQ,
block_label (preheader), p,
NULL);
@@ -1000,9 +1027,10 @@ unroll_loop_runtime_iterations (struct l
swtch = split_edge_and_insert (single_succ_edge (swtch), branch_code);