Lines Matching +full:- +full:- +full:user
4 optimization at `-O3` with link-time optimization (`-flto`) will result in the
5 best performance. However, using `-march=native` can result in **WORSE**
17 These benchmarks were run with both `bc`'s compiled with the typical `-O2`
18 optimizations and no link-time optimization.
32 user 1.21
40 user 0.85
56 user 1.05
64 user 0.85
80 user 4.69
88 user 2.10
104 user 1.87
112 user 1.57
121 printf '1234567890^100000; halt\n' | time -p [bc] -q > /dev/null
128 user 11.30
136 user 0.72
146 --- ../timeconst.bc 2018-09-28 11:32:22.808669000 -0600
147 +++ ../timeconst.bc 2019-06-07 07:26:36.359913078 -0600
148 @@ -110,8 +110,10 @@
152 - halt
155 -hz = read();
156 -timeconst(hz)
167 time -p [bc] ../timeconst.bc > /dev/null
174 user 16.06
182 user 13.15
204 time -p [bc] ../test.bc > /dev/null
211 user 16.59
219 user 22.75
240 time -p [bc] ../test2.bc > /dev/null
247 user 17.30
255 user 16.96
267 I recommended for version `2.7.0`, which are `-O3 -flto -march=native`.
275 I also recommended `-march=native` on the grounds that newer instructions would
276 increase performance on math-heavy code. We will see if that assumption was
294 user 1.11
302 user 0.54
318 user 1.02
326 user 0.57
342 user 4.50
350 user 1.53
366 user 1.82
374 user 1.20
383 printf '1234567890^100000; halt\n' | time -p [bc] -q > /dev/null
390 user 11.07
398 user 0.70
407 time -p [bc] ../timeconst.bc > /dev/null
414 user 15.08
422 user 10.08
429 time -p [bc] ../test.bc > /dev/null
436 user 14.75
444 user 17.94
451 time -p [bc] ../test2.bc > /dev/null
458 user 14.83
466 user 13.52
470 ## Link-Time Optimization Only
472 Just for kicks, let's see if `-march=native` is even useful.
474 The optimizations I used for both `bc`'s were `-O3 -flto`.
488 user 1.05
496 user 0.52
512 user 1.10
520 user 0.57
536 user 4.30
544 user 1.49
560 user 1.81
568 user 1.23
577 printf '1234567890^100000; halt\n' | time -p [bc] -q > /dev/null
584 user 10.49
592 user 0.71
601 time -p [bc] ../timeconst.bc > /dev/null
608 user 14.81
616 user 10.15
623 time -p [bc] ../test.bc > /dev/null
630 user 14.99
638 user 16.84
645 time -p [bc] ../test2.bc > /dev/null
652 user 14.91
660 user 12.75
664 It turns out that `-march=native` can be a problem. As such, I have removed the
665 recommendation to build with `-march=native`.