forked from OSchip/llvm-project
Reduce number of tasks in parallel_for_each.
TaskGroup has a fairly high overhead, so we don't want to partition
tasks into too small tasks. This patch partition tasks into up to
1024 tasks.
I compared this patch with the original LLD's parallel_for_each.
I reverted r287042 locally for comparison.
With this patch, time to self-link lld with debug info changed from
6.23 seconds to 4.62 seconds (-25.8%), with -threads and without -build-id.
With both -threads and -build-id, it improved from 11.71 seconds
to 4.94 seconds (-57.8%). Full results are below.
BTW, GNU gold takes 11.65 seconds to link the same binary.
NOW
--no-threads --build-id=none
6789.847776 task-clock (msec) # 1.000 CPUs utilized ( +- 1.86% )
685 context-switches # 0.101 K/sec ( +- 2.82% )
4 cpu-migrations # 0.001 K/sec ( +- 31.18% )
1,424,690 page-faults # 0.210 M/sec ( +- 1.07% )
21,339,542,522 cycles # 3.143 GHz ( +- 1.49% )
13,092,260,230 stalled-cycles-frontend # 61.35% frontend cycles idle ( +- 2.23% )
<not supported> stalled-cycles-backend
21,462,051,828 instructions # 1.01 insns per cycle
# 0.61 stalled cycles per insn ( +- 0.41% )
3,955,296,378 branches # 582.531 M/sec ( +- 0.39% )
75,699,909 branch-misses # 1.91% of all branches ( +- 0.08% )
6.787630744 seconds time elapsed ( +- 1.86% )
--threads --build-id=none
14767.148697 task-clock (msec) # 3.196 CPUs utilized ( +- 2.56% )
28,891 context-switches # 0.002 M/sec ( +- 1.99% )
905 cpu-migrations # 0.061 K/sec ( +- 5.49% )
1,262,122 page-faults # 0.085 M/sec ( +- 1.68% )
43,116,163,217 cycles # 2.920 GHz ( +- 3.07% )
33,690,171,242 stalled-cycles-frontend # 78.14% frontend cycles idle ( +- 3.67% )
<not supported> stalled-cycles-backend
22,836,731,536 instructions # 0.53 insns per cycle
# 1.48 stalled cycles per insn ( +- 1.13% )
4,382,712,998 branches # 296.788 M/sec ( +- 1.33% )
78,622,295 branch-misses # 1.79% of all branches ( +- 0.54% )
4.621228056 seconds time elapsed ( +- 1.90% )
--threads --build-id=sha1
24594.457135 task-clock (msec) # 4.974 CPUs utilized ( +- 1.78% )
29,902 context-switches # 0.001 M/sec ( +- 2.62% )
1,097 cpu-migrations # 0.045 K/sec ( +- 6.29% )
1,313,947 page-faults # 0.053 M/sec ( +- 2.36% )
70,516,415,741 cycles # 2.867 GHz ( +- 0.78% )
47,570,262,296 stalled-cycles-frontend # 67.46% frontend cycles idle ( +- 0.86% )
<not supported> stalled-cycles-backend
73,124,599,029 instructions # 1.04 insns per cycle
# 0.65 stalled cycles per insn ( +- 0.33% )
10,495,266,104 branches # 426.733 M/sec ( +- 0.41% )
91,444,149 branch-misses # 0.87% of all branches ( +- 0.83% )
4.944291711 seconds time elapsed ( +- 1.72% )
PREVIOUS
--threads --build-id=none
7307.437544 task-clock (msec) # 1.160 CPUs utilized ( +- 2.34% )
3,128 context-switches # 0.428 K/sec ( +- 4.37% )
352 cpu-migrations # 0.048 K/sec ( +- 5.98% )
1,354,450 page-faults # 0.185 M/sec ( +- 2.20% )
22,081,733,098 cycles # 3.022 GHz ( +- 1.46% )
13,709,991,267 stalled-cycles-frontend # 62.09% frontend cycles idle ( +- 1.77% )
<not supported> stalled-cycles-backend
21,634,468,895 instructions # 0.98 insns per cycle
# 0.63 stalled cycles per insn ( +- 0.86% )
3,993,062,361 branches # 546.438 M/sec ( +- 0.83% )
76,188,819 branch-misses # 1.91% of all branches ( +- 0.19% )
6.298101157 seconds time elapsed ( +- 2.03% )
--threads --build-id=sha1
12845.420265 task-clock (msec) # 1.097 CPUs utilized ( +- 1.95% )
4,020 context-switches # 0.313 K/sec ( +- 2.89% )
369 cpu-migrations # 0.029 K/sec ( +- 6.26% )
1,464,822 page-faults # 0.114 M/sec ( +- 1.37% )
40,668,449,813 cycles # 3.166 GHz ( +- 0.96% )
18,863,982,388 stalled-cycles-frontend # 46.38% frontend cycles idle ( +- 1.82% )
<not supported> stalled-cycles-backend
71,560,499,058 instructions # 1.76 insns per cycle
# 0.26 stalled cycles per insn ( +- 0.14% )
10,044,152,441 branches # 781.925 M/sec ( +- 0.19% )
87,835,773 branch-misses # 0.87% of all branches ( +- 0.09% )
11.711773314 seconds time elapsed ( +- 1.51% )
llvm-svn: 287140
This commit is contained in:
Rui Ueyama
parent
f4c5a0e630
commit
87ff6fef0f
|
|
@ -283,9 +283,20 @@ void parallel_for_each(Iterator begin, Iterator end, Func func) {
|
|||
#else
|
||||
template <class Iterator, class Func>
|
||||
void parallel_for_each(Iterator begin, Iterator end, Func func) {
|
||||
// TaskGroup has a relatively high overhead, so we want to reduce
|
||||
// the number of spawn() calls. We'll create up to 1024 tasks here.
|
||||
// (Note that 1024 is an arbitrary number. This code probably needs
|
||||
// improving to take the number of available cores into account.)
|
||||
ptrdiff_t taskSize = std::distance(begin, end) / 1024;
|
||||
if (taskSize == 0)
|
||||
taskSize = 1;
|
||||
|
||||
TaskGroup tg;
|
||||
for (; begin != end; ++begin)
|
||||
tg.spawn([=, &func] { func(*begin); });
|
||||
while (taskSize <= std::distance(begin, end)) {
|
||||
tg.spawn([=, &func] { std::for_each(begin, begin + taskSize, func); });
|
||||
begin += taskSize;
|
||||
}
|
||||
std::for_each(begin, end, func);
|
||||
}
|
||||
#endif
|
||||
} // end namespace lld
|
||||
|
|
|
|||
Loading…
Reference in New Issue