mirror of
https://github.com/golang/go.git
synced 2025-12-08 06:10:04 +00:00
internal/bytealg: optimize index function for ppc64le/power9
Optimized index2to16 loop by unrolling the loop by 4. Multiple benchmark tests show performance improvement on POWER9. Similar improvements are seen on POWER10. Added tests to ensure changes work fine. name old time/op new time/op delta Index/10 18.3ns ± 0% 19.7ns ±25% ~ Index/32 75.3ns ± 0% 69.2ns ± 0% -8.22% Index/4K 5.53µs ± 0% 3.69µs ± 0% -33.20% Index/4M 5.64ms ± 0% 3.75ms ± 0% -33.55% Index/64M 92.9ms ± 0% 61.6ms ± 0% -33.69% IndexHard2 1.41ms ± 0% 0.93ms ± 0% -33.75% CountHard2 1.41ms ± 0% 0.93ms ± 0% -33.75% Change-Id: If9331df6a141a4716724b8cb648d2b91bdf17e5f Reviewed-on: https://go-review.googlesource.com/c/go/+/377016 Reviewed-by: Cherry Mui <cherryyz@google.com> Reviewed-by: David Chase <drchase@google.com> Reviewed-by: Paul Murphy <murp@ibm.com> TryBot-Result: Gopher Robot <gobot@golang.org> Run-TryBot: Archana Ravindar <aravind5@in.ibm.com>
This commit is contained in:
parent
c386269ed8
commit
7ca1e2aa56
2 changed files with 149 additions and 79 deletions
|
|
@ -140,6 +140,36 @@ var indexTests = []BinOpTest{
|
|||
{"abc", "c", 2},
|
||||
{"abc", "x", -1},
|
||||
{"barfoobarfooyyyzzzyyyzzzyyyzzzyyyxxxzzzyyy", "x", 33},
|
||||
{"fofofofooofoboo", "oo", 7},
|
||||
{"fofofofofofoboo", "ob", 11},
|
||||
{"fofofofofofoboo", "boo", 12},
|
||||
{"fofofofofofoboo", "oboo", 11},
|
||||
{"fofofofofoooboo", "fooo", 8},
|
||||
{"fofofofofofoboo", "foboo", 10},
|
||||
{"fofofofofofoboo", "fofob", 8},
|
||||
{"fofofofofofofoffofoobarfoo", "foffof", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffof", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofo", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofo", 13},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoo", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoo", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoob", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoob", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofooba", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofooba", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoobar", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoobar", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoobarf", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoobarf", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoobarfo", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoobarfo", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "foffofoobarfoo", 13},
|
||||
{"fofofofofofofoffofoobarfoo", "foffofoobarfoo", 12},
|
||||
{"fofofofofoofofoffofoobarfoo", "ofoffofoobarfoo", 12},
|
||||
{"fofofofofofofoffofoobarfoo", "ofoffofoobarfoo", 11},
|
||||
{"fofofofofoofofoffofoobarfoo", "fofoffofoobarfoo", 11},
|
||||
{"fofofofofofofoffofoobarfoo", "fofoffofoobarfoo", 10},
|
||||
{"fofofofofoofofoffofoobarfoo", "foobars", -1},
|
||||
{"foofyfoobarfoobar", "y", 4},
|
||||
{"oooooooooooooooooooooo", "r", -1},
|
||||
{"oxoxoxoxoxoxoxoxoxoxoxoy", "oy", 22},
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue