Line |
Hotness |
Pass |
Source |
Function / Inlining Chain |
1 |
|
|
// Taken from Adam Nemet's November 2016 LLVM talk |
|
2 |
|
|
|
|
3 |
|
|
|
|
4 |
|
|
|
|
5 |
|
|
int compute_sum_without_inlining (int arr[], int n) |
|
6 |
|
|
|
|
7 |
|
|
|
|
8 |
|
|
for (int i = 0; i < n; ++i) |
|
|
100.00 |
cunrolli |
^loop 1 iterates at most 2147483647 times
|
compute_sum_without_inlining
|
|
99.61 |
ivcanon |
^loop 1 iterates at most 2147483646 times
|
compute_sum_without_inlining
|
|
99.61 |
vect |
^=== analyzing loop ===
=== analyze_loop_nest ===
=== vect_analyze_loop_form ===
=== get_loop_niters ===
symbolic number of iterations is (unsigned int) n_9(D)
not vectorized: loop contains function calls or data references that cannot be analyzed
|
compute_sum_without_inlining
|
|
99.61 |
vect |
^vectorized 0 loops in function
|
compute_sum_without_inlining
|
|
99.61 |
cunroll |
^loop 1 iterates at most 2147483646 times
|
compute_sum_without_inlining
|
9 |
|
|
accumulate (arr[i], &sum); |
|
|
99.61 |
inline |
^not inlinable: compute_sum_without_inlining/0 -> accumulate/1, function body not available
|
compute_sum_without_inlining
|
10 |
|
|
|
|
11 |
|
|
|
|