[#8] hrw: Do not create index slice for sorter

`ind` is only needed to index dist or weights, swap them directly.

```
goos: linux
goarch: amd64
pkg: git.frostfs.info/TrueCloudLab/hrw
cpu: 11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz
                                              │      0      │                  1                   │
                                              │   sec/op    │    sec/op     vs base                │
SortHashersByValue_Typed_fnv_10-8               596.2n ± 4%   580.1n ±  1%   -2.72% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_100-8              4.453µ ± 2%   4.215µ ±  2%   -5.35% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_1000-8             41.58µ ± 4%   39.40µ ±  1%   -5.23% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_10-8          624.5n ± 2%   599.6n ±  2%   -3.99% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_100-8         4.593µ ± 2%   4.337µ ±  5%   -5.56% (p=0.003 n=10)
SortHashersByWeightValueTyped_fnv_1000-8        4.896µ ± 8%   4.344µ ±  3%  -11.27% (p=0.000 n=10)
geomean                                         4.668µ        4.400µ         -5.75%

                                              │      0       │                  1                   │
                                              │     B/op     │     B/op      vs base                │
SortHashersByValue_Typed_fnv_10-8                 584.0 ± 0%     472.0 ± 0%  -19.18% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_100-8              4.367Ki ± 0%   3.461Ki ± 0%  -20.75% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_1000-8             39.80Ki ± 0%   31.77Ki ± 0%  -20.18% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_10-8            600.0 ± 0%     472.0 ± 0%  -21.33% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_100-8         4.383Ki ± 0%   3.461Ki ± 0%  -21.03% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_1000-8        4.383Ki ± 0%   3.461Ki ± 0%  -21.03% (p=0.000 n=10)
geomean                                         3.742Ki        3.070Ki       -17.96%

                                              │      0      │                 1                  │
                                              │  allocs/op  │  allocs/op   vs base               │
SortHashersByValue_Typed_fnv_10-8                17.00 ± 0%    16.00 ± 0%  -5.88% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_100-8               107.0 ± 0%    106.0 ± 0%  -0.93% (p=0.000 n=10)
SortHashersByValue_Typed_fnv_1000-8             1.007k ± 0%   1.006k ± 0%  -0.10% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_10-8           17.00 ± 0%    16.00 ± 0%  -5.88% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_100-8          107.0 ± 0%    106.0 ± 0%  -0.93% (p=0.000 n=10)
SortHashersByWeightValueTyped_fnv_1000-8         107.0 ± 0%    106.0 ± 0%  -0.93% (p=0.000 n=10)
geomean                                          115.3         113.0       -1.94%
```

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
This commit is contained in:
Evgenii Stratonikov 2023-06-01 19:34:37 +03:00
parent 2c085708de
commit c175ef4099

56
hrw.go
View file

@ -243,24 +243,6 @@ func ValidateWeights(weights []float64) error {
return nil return nil
} }
func newSorter(l int, byIndex bool, nodes []uint64, h uint64,
swap func(i, j int)) (*sorter, []int, []uint64) {
ind := make([]int, l)
dist := make([]uint64, l)
for i := 0; i < l; i++ {
ind[i] = i
dist[i] = getDistance(byIndex, i, nodes, h)
}
return &sorter{
l: l,
swap: func(i, j int) {
swap(i, j)
ind[i], ind[j] = ind[j], ind[i]
},
}, ind, dist
}
// sortByWeight sorts nodes by weight using provided swapper. // sortByWeight sorts nodes by weight using provided swapper.
// nodes contains hrw hashes. If it is nil, indices are used. // nodes contains hrw hashes. If it is nil, indices are used.
func sortByWeight(l int, byIndex bool, nodes []uint64, weights []float64, hash uint64, swap func(i, j int)) { func sortByWeight(l int, byIndex bool, nodes []uint64, weights []float64, hash uint64, swap func(i, j int)) {
@ -270,14 +252,23 @@ func sortByWeight(l int, byIndex bool, nodes []uint64, weights []float64, hash u
return return
} }
s, ind, dist := newSorter(l, byIndex, nodes, hash, swap) dist := make([]float64, l)
s.less = func(i, j int) bool { for i := 0; i < l; i++ {
ii, jj := ind[i], ind[j] d := getDistance(byIndex, i, nodes, hash)
// `maxUint64 - distance` makes the shorter distance more valuable // `maxUint64 - distance` makes the shorter distance more valuable
// it is necessary for operation with normalized values // it is necessary for operation with normalized values
wi := float64(^uint64(0)-dist[ii]) * weights[ii] dist[i] = float64(^uint64(0)-d) * weights[i]
wj := float64(^uint64(0)-dist[jj]) * weights[jj] }
return wi > wj // higher distance must be placed lower to be first
s := &sorter{
l: l,
swap: func(i, j int) {
swap(i, j)
dist[i], dist[j] = dist[j], dist[i]
},
less: func(i, j int) bool {
return dist[i] > dist[j] // higher distance must be placed lower to be first
},
} }
sort.Sort(s) sort.Sort(s)
} }
@ -285,9 +276,20 @@ func sortByWeight(l int, byIndex bool, nodes []uint64, weights []float64, hash u
// sortByDistance sorts nodes by hrw distance using provided swapper. // sortByDistance sorts nodes by hrw distance using provided swapper.
// nodes contains hrw hashes. If it is nil, indices are used. // nodes contains hrw hashes. If it is nil, indices are used.
func sortByDistance(l int, byIndex bool, nodes []uint64, hash uint64, swap func(i, j int)) { func sortByDistance(l int, byIndex bool, nodes []uint64, hash uint64, swap func(i, j int)) {
s, ind, dist := newSorter(l, byIndex, nodes, hash, swap) dist := make([]uint64, l)
s.less = func(i, j int) bool { for i := 0; i < l; i++ {
return dist[ind[i]] < dist[ind[j]] dist[i] = getDistance(byIndex, i, nodes, hash)
}
s := &sorter{
l: l,
swap: func(i, j int) {
swap(i, j)
dist[i], dist[j] = dist[j], dist[i]
},
less: func(i, j int) bool {
return dist[i] < dist[j]
},
} }
sort.Sort(s) sort.Sort(s)
} }