From 44c663c54fc3d4344fac8af69367a73a477c7673 Mon Sep 17 00:00:00 2001 From: datalore Date: Thu, 3 Oct 2024 12:28:33 +0200 Subject: [PATCH] feat(io): Implemented zstd-compressed msgpack format --- go.mod | 13 ++++++++-- go.sum | 42 +++++++++++++++++++++++++++++++++ io.go | 73 +++++++++++++++++++++++++++++++++++++++++++-------------- main.go | 54 +++++++++++++++++++++++------------------- 4 files changed, 138 insertions(+), 44 deletions(-) diff --git a/go.mod b/go.mod index 17c0e72..4bab317 100644 --- a/go.mod +++ b/go.mod @@ -2,6 +2,15 @@ module datalore/prime-div go 1.23.0 -require github.com/wamuir/graft v0.9.0 +require ( + github.com/klauspost/compress v1.17.10 + github.com/vmihailenco/msgpack v4.0.4+incompatible + github.com/wamuir/graft v0.9.0 +) -require google.golang.org/protobuf v1.34.2 // indirect +require ( + github.com/golang/protobuf v1.5.2 // indirect + google.golang.org/appengine v1.6.8 // indirect + google.golang.org/protobuf v1.34.2 // indirect + gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect +) diff --git a/go.sum b/go.sum index 23633ba..5681479 100644 --- a/go.sum +++ b/go.sum @@ -1,8 +1,50 @@ +github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk= +github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw= +github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY= github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU= github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/klauspost/compress v1.17.10 h1:oXAz+Vh0PMUvJczoi+flxpnBEPxoER1IaAnU/NMPtT0= +github.com/klauspost/compress v1.17.10/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0= +github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI= +github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= +github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= +github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE= +github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= +github.com/vmihailenco/msgpack v4.0.4+incompatible h1:dSLoQfGFAo3F6OoNhwUmLwVgaUXK79GlxNBwueZn0xI= +github.com/vmihailenco/msgpack v4.0.4+incompatible/go.mod h1:fy3FlTQTDXWkZ7Bh6AcGMlsjHatGryHQYUTf1ShIgkk= github.com/wamuir/graft v0.9.0 h1:5DbPtr3MfWRq9bFHivbbvNic8h8jtcKK12Rxk0644iY= github.com/wamuir/graft v0.9.0/go.mod h1:k6NJX3fCM/xzh5NtHky9USdgHTcz2vAvHp4c23I6UK4= +github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= +golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= +golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4= golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +google.golang.org/appengine v1.6.8 h1:IhEN5q69dyKagZPYMSdIjS2HqprW324FRQZJcGqPAsM= +google.golang.org/appengine v1.6.8/go.mod h1:1jJ3jBArFh5pcgW8gCtRJnepW8FzD1V44FJffLiz/Ds= +google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw= +google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc= google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg= google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= diff --git a/io.go b/io.go index 34c727f..98769d4 100644 --- a/io.go +++ b/io.go @@ -6,45 +6,69 @@ import ( "log" "os" "strconv" + "time" + + "github.com/vmihailenco/msgpack" + "github.com/klauspost/compress/zstd" ) -func loadPrimes() []int64 { - return loadPrimesTxt() +func loadPrimes(useTxt bool) []int64 { + if useTxt { + return loadPrimesTxt() + } else { + return loadPrimesMsgpack() + } } func loadPrimesTxt() []int64 { - file, err := os.Open("prime.txt") - if err != nil { - log.Fatal(err) - } + file := must(os.Open("prime.txt")) + defer file.Close() var primes []int64 scanner := bufio.NewScanner(file) for scanner.Scan() { - nextPrime, err := strconv.ParseInt(scanner.Text(), 10, 64) - if err != nil { - log.Fatal(err) - } + nextPrime := must(strconv.ParseInt(scanner.Text(), 10, 64)) primes = append(primes, nextPrime) } - file.Close() - return primes } -func writePrimes(primes []int64) { - writePrimesTxt(primes) -} +func loadPrimesMsgpack() []int64 { + file := must(os.Open("prime.msgpack.zst")) + defer file.Close() -func writePrimesTxt(primes []int64) { - file, err := os.Create("prime.txt") + zstdDecoder := must(zstd.NewReader(file)) + defer zstdDecoder.Close() + + var primes []int64 + msgpackDecoder := msgpack.NewDecoder(zstdDecoder) + err := msgpackDecoder.Decode(&primes) if err != nil { log.Fatal(err) } + return primes +} + +func writePrimes(primes []int64, useTxt bool) { + startTime := time.Now() + + if useTxt { + writePrimesTxt(primes) + } else { + writePrimesMsgpack(primes) + } + + fmt.Printf("File writing took %v\n", time.Now().Sub(startTime)) +} + +func writePrimesTxt(primes []int64) { + file := must(os.Create("prime.txt")) + defer file.Close() + writer := bufio.NewWriter(file) for _, prime := range primes { @@ -52,5 +76,18 @@ func writePrimesTxt(primes []int64) { } writer.Flush() - file.Close() +} + +func writePrimesMsgpack(primes []int64) { + file := must(os.Create("prime.msgpack.zst")) + defer file.Close() + + zstdEncoder := must(zstd.NewWriter(file, zstd.WithEncoderLevel(zstd.SpeedBestCompression))) + defer zstdEncoder.Close() + + msgpackEncoder := msgpack.NewEncoder(zstdEncoder) + err := msgpackEncoder.Encode(&primes) + if err != nil { + log.Fatal(err) + } } diff --git a/main.go b/main.go index 2e92787..bcbe620 100644 --- a/main.go +++ b/main.go @@ -11,6 +11,15 @@ import ( "os" ) +type Config struct { + PrimeList bool + DontLoad bool + NumRoutines int + UseTensors bool + UseTxtRead bool + UseTxtWrite bool +} + func calculateProgress(start, end, step, index int64) float32 { steps := (end - start) / step current := index - start @@ -55,15 +64,15 @@ func checkIsDivisibleByPrime(number int64, offset, stride int, primes *[]int64, resultChannel <- false } -func generatePrimes(upperLimit int64, loadList bool, numRoutines int, useTensors bool) []int64 { +func generatePrimes(upperLimit int64, config Config) []int64 { var primes []int64 bootTime := time.Now() - if loadList { - primes = loadPrimes() - } else { + if config.DontLoad { primes = []int64{2, 3, 5} + } else { + primes = loadPrimes(config.UseTxtRead) } fmt.Printf("Startup time: %v\n", time.Now().Sub(bootTime)) @@ -73,10 +82,10 @@ func generatePrimes(upperLimit int64, loadList bool, numRoutines int, useTensors startTime := time.Now() - if useTensors { + if config.UseTensors { primes = generatePrimesGPU(upperLimit, primes, progress) } else { - primes = generatePrimesCPU(upperLimit, primes, numRoutines, progress) + primes = generatePrimesCPU(upperLimit, primes, config.NumRoutines, progress) } close(progress) @@ -159,17 +168,14 @@ func calculatePrimeParts(number int64, primes []int64) []int64 { } func main() { - var ( - primeList bool - dontLoad bool - numRoutines int - useTensors bool - ) + var config Config - flag.BoolVar(&primeList, "p", false, "Only calculate and print prime list") - flag.BoolVar(&dontLoad, "d", false, "Don't load precalculated primes, calculate from 0") - flag.IntVar(&numRoutines, "r", 0, "How many routines to use for calculation. 0 = number of available CPU cores") - flag.BoolVar(&useTensors, "t", false, "Use tensorflow") + flag.BoolVar(&config.PrimeList, "p", false, "Only calculate and print prime list") + flag.BoolVar(&config.DontLoad, "d", false, "Don't load precalculated primes, calculate from 0") + flag.IntVar(&config.NumRoutines, "r", 0, "How many routines to use for calculation. 0 = number of available CPU cores") + flag.BoolVar(&config.UseTensors, "t", false, "Use tensorflow") + flag.BoolVar(&config.UseTxtRead, "read-legacy", false, "Read legacy prime.txt file instead of prime.msgpack") + flag.BoolVar(&config.UseTxtWrite, "write-legacy", false, "Write legacy prime.txt file instead of prime.msgpack") flag.Parse() numStr := flag.Arg(0) @@ -184,20 +190,20 @@ func main() { log.Fatal(err) } - if primeList { - onlyGenerate(number, dontLoad, numRoutines, useTensors) + if config.PrimeList { + onlyGenerate(number, config) } else { - calculate(number, dontLoad, numRoutines, useTensors) + calculate(number, config) } } -func onlyGenerate(number int64, dontLoad bool, numRoutines int, useTensors bool) { - primes := generatePrimes(number, !dontLoad, numRoutines, useTensors) - writePrimes(primes) +func onlyGenerate(number int64, config Config) { + primes := generatePrimes(number, config) + writePrimes(primes, config.UseTxtWrite) } -func calculate(number int64, dontLoad bool, numRoutines int, useTensors bool) { - primes := generatePrimes(number, !dontLoad, numRoutines, useTensors) +func calculate(number int64, config Config) { + primes := generatePrimes(number, config) primeParts := calculatePrimeParts(number, primes)