|
⇤ ← Revision 1 as of 2011-02-07 09:22:26
Size: 1412
Comment:
|
Size: 1468
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 11: | Line 11: |
| || 0m1.153s || j=0; time for i in {1..100000}; do ((j++)); done || || 0m1.381s || j=0; time for i in {1..100000}; do j=$((j+1)); done || || 0m1.498s || j=0; time for i in {1..100000}; do let j++; done || || 5m8.448s || j=0; time for i in {1..100000}; do j=$(expr $j + 1); done || |
|| 0m1.153s || {{{j=0; time for i in {1..100000}; do ((j++)); done}}} || || 0m1.381s || {{{j=0; time for i in {1..100000}; do j=$((j+1)); done}}} || || 0m1.498s || {{{j=0; time for i in {1..100000}; do let j++; done}}} || || 5m8.448s || {{{j=0; time for i in {1..100000}; do j=$(expr $j + 1); done}}} || |
| Line 22: | Line 22: |
| || 0m1.538s || printf -v i '%s ' {1..100000}; time { echo "$i" >/dev/null; } || || 0m3.112s || printf -v i '%s ' {1..100000}; time { echo $i >/dev/null; } || |
|| 0m1.538s || {{{printf -v i '%s ' {1..100000}; time { echo "$i" >/dev/null; } }}} || || 0m3.112s || {{{printf -v i '%s ' {1..100000}; time { echo $i >/dev/null; } }}} || |
| Line 31: | Line 31: |
| || 0m1.099s || time for i in {1..100000}; do [[ -d . ]]; done || || 0m2.110s || time for i in {1..100000}; do [ -d . ]; done || || 3m47.509s || time for i in {1..100000}; do /bin/test -d .; done || |
|| 0m1.099s || {{{time for i in {1..100000}; do [[ -d . ]]; done}}} || || 0m2.110s || {{{time for i in {1..100000}; do [ -d . ]; done}}} || || 3m47.509s || {{{time for i in {1..100000}; do /bin/test -d .; done}}} || |
Some rough benchmarks
To compare different approaches to a problem with regards to performance, here's some rough benchmarks which may be system-dependent. Feel free to run each test yourself to see how your system fares.
Results are always sorted with the winners on top. All tests were repeated multiple times to make sure deviations did not exceed acceptable levels or cross result boundaries.
Math
Time |
Code |
0m1.153s |
j=0; time for i in {1..100000}; do ((j++)); done |
0m1.381s |
j=0; time for i in {1..100000}; do j=$((j+1)); done |
0m1.498s |
j=0; time for i in {1..100000}; do let j++; done |
5m8.448s |
j=0; time for i in {1..100000}; do j=$(expr $j + 1); done |
As though you didn't already have enough reason to dump expr.
Quoting
Time |
Code |
0m1.538s |
printf -v i '%s ' {1..100000}; time { echo "$i" >/dev/null; } |
0m3.112s |
printf -v i '%s ' {1..100000}; time { echo $i >/dev/null; } |
Another good reason to always quote your expansions.
Testing
Time |
Code |
0m1.099s |
time for i in {1..100000}; do [[ -d . ]]; done |
0m2.110s |
time for i in {1..100000}; do [ -d . ]; done |
3m47.509s |
time for i in {1..100000}; do /bin/test -d .; done |
[[ isn't just more featureful, it's also twice as fast.