mirror of
https://github.com/bloeys/nset.git
synced 2025-12-29 06:28:19 +00:00
Docs and bench
This commit is contained in:
Binary file not shown.
|
Before Width: | Height: | Size: 40 KiB |
BIN
.res/bench-getAllElements-10-million.png
Executable file
BIN
.res/bench-getAllElements-10-million.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
BIN
.res/bench-getIntersection-10-million.png
Executable file
BIN
.res/bench-getIntersection-10-million.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 39 KiB |
17
README.md
17
README.md
@ -138,14 +138,21 @@ Here NSet finishes in `0.1ms` but Map takes almost a second with `813ms`.
|
||||

|
||||
|
||||
Next we have `GetAllElements`, which simply returns an array of all the elements of NSet/Map (note this is dangerous in NSet. See [Memory characteristics](#memory-characteristics)).
|
||||

|
||||

|
||||
|
||||
With `GetAllElements` NSet is faster when its elements are closer together (or you have many numbers), but gets a lot slower when
|
||||
dealing with a few random numbers. This is because you might get two numbers like `1` and `1_000_000` which NSet
|
||||
With `GetAllElements` NSet is faster when its elements are closer together value wise (or if you have many numbers), but gets a lot slower when
|
||||
dealing with a few random numbers with a big difference between them. This is because you might get two numbers like `1` and `1_000_000` which NSet
|
||||
will store in two far away places with a lot of nothing in between. In a map these will be stored close together.
|
||||
|
||||
With 1M ordered elements NSet takes `~2ms` and map `~9ms`, but with a random 1M elements NSet takes `~129ms`
|
||||
while map takes `~9ms`. Map scales with the amount of elements, while NSet is affected by number distribution as well.
|
||||
With 10M ordered elements NSet takes `~31ms` and map `~97ms`, but with a random 10M elements NSet takes `~525ms`
|
||||
while map takes `~95ms`. Map scales with the amount of elements, while NSet is affected by number distribution as well.
|
||||
|
||||
Similar to getting elements is intersection:
|
||||
|
||||

|
||||
|
||||
Here NSet is always many times faster, but the effect of number distribution on NSet's performance is clear, while map's performance
|
||||
only scales with number of elements.
|
||||
|
||||
## How NSet works
|
||||
|
||||
|
||||
98
nset_test.go
98
nset_test.go
@ -447,6 +447,8 @@ func BenchmarkMapIsEq(b *testing.B) {
|
||||
}
|
||||
}
|
||||
|
||||
var getIntersectionNset *nset.NSet[uint32]
|
||||
|
||||
func BenchmarkNSetGetIntersection(b *testing.B) {
|
||||
|
||||
b.StopTimer()
|
||||
@ -459,7 +461,93 @@ func BenchmarkNSetGetIntersection(b *testing.B) {
|
||||
b.StartTimer()
|
||||
|
||||
for i := 0; i < b.N; i++ {
|
||||
s1.GetIntersection(s2)
|
||||
getIntersectionNset = s1.GetIntersection(s2)
|
||||
}
|
||||
}
|
||||
|
||||
var getIntersectionTempMap map[uint32]struct{}
|
||||
|
||||
func BenchmarkMapGetIntersection(b *testing.B) {
|
||||
|
||||
b.StopTimer()
|
||||
m1 := map[uint32]struct{}{}
|
||||
m2 := map[uint32]struct{}{}
|
||||
for i := uint32(0); i < maxBenchSize; i++ {
|
||||
m1[i] = struct{}{}
|
||||
m2[i] = struct{}{}
|
||||
}
|
||||
b.StartTimer()
|
||||
|
||||
getIntersection := func(m1, m2 map[uint32]struct{}) map[uint32]struct{} {
|
||||
|
||||
outMap := map[uint32]struct{}{}
|
||||
|
||||
for k := range m1 {
|
||||
if _, ok := m2[k]; ok {
|
||||
outMap[k] = struct{}{}
|
||||
}
|
||||
}
|
||||
|
||||
return outMap
|
||||
}
|
||||
|
||||
for i := 0; i < b.N; i++ {
|
||||
getIntersectionTempMap = getIntersection(m1, m2)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkNSetGetIntersectionRand(b *testing.B) {
|
||||
|
||||
b.StopTimer()
|
||||
|
||||
rand.Seed(RandSeed)
|
||||
|
||||
s1 := nset.NewNSet[uint32]()
|
||||
s2 := nset.NewNSet[uint32]()
|
||||
for i := uint32(0); i < maxBenchSize; i++ {
|
||||
|
||||
r := rand.Uint32()
|
||||
s1.Add(r)
|
||||
s2.Add(r)
|
||||
}
|
||||
b.StartTimer()
|
||||
|
||||
for i := 0; i < b.N; i++ {
|
||||
getIntersectionNset = s1.GetIntersection(s2)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkMapGetIntersectionRand(b *testing.B) {
|
||||
|
||||
b.StopTimer()
|
||||
|
||||
rand.Seed(RandSeed)
|
||||
|
||||
m1 := map[uint32]struct{}{}
|
||||
m2 := map[uint32]struct{}{}
|
||||
for i := uint32(0); i < maxBenchSize; i++ {
|
||||
|
||||
r := rand.Uint32()
|
||||
m1[r] = struct{}{}
|
||||
m2[r] = struct{}{}
|
||||
}
|
||||
b.StartTimer()
|
||||
|
||||
getIntersection := func(m1, m2 map[uint32]struct{}) map[uint32]struct{} {
|
||||
|
||||
outMap := map[uint32]struct{}{}
|
||||
|
||||
for k := range m1 {
|
||||
if _, ok := m2[k]; ok {
|
||||
outMap[k] = struct{}{}
|
||||
}
|
||||
}
|
||||
|
||||
return outMap
|
||||
}
|
||||
|
||||
for i := 0; i < b.N; i++ {
|
||||
getIntersectionTempMap = getIntersection(m1, m2)
|
||||
}
|
||||
}
|
||||
|
||||
@ -470,7 +558,7 @@ func BenchmarkNSetGetAllElements(b *testing.B) {
|
||||
b.StopTimer()
|
||||
|
||||
s1 := nset.NewNSet[uint32]()
|
||||
for i := uint32(0); i < 1000_000; i++ {
|
||||
for i := uint32(0); i < 10_000_000; i++ {
|
||||
s1.Add(i)
|
||||
}
|
||||
b.StartTimer()
|
||||
@ -488,7 +576,7 @@ func BenchmarkMapGetAllElements(b *testing.B) {
|
||||
b.StopTimer()
|
||||
|
||||
m1 := map[uint32]struct{}{}
|
||||
for i := uint32(0); i < 1000_000; i++ {
|
||||
for i := uint32(0); i < 10_000_000; i++ {
|
||||
m1[i] = struct{}{}
|
||||
}
|
||||
b.StartTimer()
|
||||
@ -517,7 +605,7 @@ func BenchmarkNSetGetAllElementsRand(b *testing.B) {
|
||||
|
||||
rand.Seed(RandSeed)
|
||||
s1 := nset.NewNSet[uint32]()
|
||||
for i := uint32(0); i < 1000_000; i++ {
|
||||
for i := uint32(0); i < 10_000_000; i++ {
|
||||
s1.Add(rand.Uint32())
|
||||
}
|
||||
b.StartTimer()
|
||||
@ -537,7 +625,7 @@ func BenchmarkMapGetAllElementsRand(b *testing.B) {
|
||||
rand.Seed(RandSeed)
|
||||
|
||||
m1 := map[uint32]struct{}{}
|
||||
for i := uint32(0); i < 1000_000; i++ {
|
||||
for i := uint32(0); i < 10_000_000; i++ {
|
||||
m1[rand.Uint32()] = struct{}{}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user