Skip to content

Number parsing #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 2, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,4 @@
.gradle
build
profilers
testdata
1 change: 0 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@ This implementation is still missing several features available in simdsjon. For

* Support for Unicode characters
* UTF-8 validation
* Full support for parsing floats
* Support for 512-bit vectors

## Code Sample
Expand Down
17 changes: 17 additions & 0 deletions build.gradle
Original file line number Diff line number Diff line change
@@ -1,10 +1,12 @@
import me.champeau.jmh.JmhBytecodeGeneratorTask
import org.gradle.internal.os.OperatingSystem
import org.ajoberstar.grgit.Grgit

plugins {
id 'java'
id 'scala'
id 'me.champeau.jmh' version '0.7.1'
id 'org.ajoberstar.grgit' version '5.2.0'
}

group = 'org.simdjson'
Expand Down Expand Up @@ -37,7 +39,22 @@ dependencies {
testRuntimeOnly group: 'org.junit.jupiter', name: 'junit-jupiter-engine', version: junitVersion
}

tasks.register('downloadTestData') {
doFirst {
def testDataDir = new File("${project.projectDir.getAbsolutePath()}/testdata")
if (!testDataDir.exists()) {
testDataDir.mkdir()
}
def numbersTestDataDir = new File("${testDataDir}/parse-number-fxx-test-data")
if (!numbersTestDataDir.exists()) {
def grgit = Grgit.clone(dir: numbersTestDataDir, uri: 'https://github.com/nigeltao/parse-number-fxx-test-data.git')
grgit.close()
}
}
}

test {
dependsOn downloadTestData
useJUnitPlatform()
jvmArgs += [
'--add-modules', 'jdk.incubator.vector',
Expand Down
49 changes: 49 additions & 0 deletions src/jmh/java/org/simdjson/NumberParserBenchmark.java
Original file line number Diff line number Diff line change
@@ -0,0 +1,49 @@
package org.simdjson;

import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.Level;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.annotations.Param;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.Setup;
import org.openjdk.jmh.annotations.State;

import java.io.IOException;
import java.util.concurrent.TimeUnit;

import static org.simdjson.SimdJsonPaddingUtil.padWithSpaces;

@State(Scope.Benchmark)
@BenchmarkMode(Mode.Throughput)
@OutputTimeUnit(TimeUnit.SECONDS)
public class NumberParserBenchmark {

private final Tape tape = new Tape(100);
private final NumberParser numberParser = new NumberParser(tape);

@Param({
"2.2250738585072013e-308", // fast path
"1.00000000000000188558920870223463870174566020691753515394643550663070558368373221972569761144603605635692374830246134201063722058e-309" // slow path
})
String number;
byte[] numberUtf8Bytes;

@Setup(Level.Trial)
public void setup() throws IOException {
numberUtf8Bytes = padWithSpaces(number);
}

@Benchmark
public double baseline() {
return Double.parseDouble(number);
}

@Benchmark
public double simdjson() {
tape.reset();
numberParser.parseNumber(numberUtf8Bytes, 0);
return tape.getDouble(0);
}
}
12 changes: 12 additions & 0 deletions src/jmh/java/org/simdjson/SimdJsonPaddingUtil.java
Original file line number Diff line number Diff line change
@@ -1,10 +1,22 @@
package org.simdjson;

import java.util.Arrays;

import static java.nio.charset.StandardCharsets.UTF_8;

class SimdJsonPaddingUtil {

static byte[] padded(byte[] src) {
byte[] bufferPadded = new byte[src.length + 64];
System.arraycopy(src, 0, bufferPadded, 0, src.length);
return bufferPadded;
}

static byte[] padWithSpaces(String str) {
byte[] strBytes = str.getBytes(UTF_8);
byte[] padded = new byte[strBytes.length + 64];
Arrays.fill(padded, (byte) ' ');
System.arraycopy(strBytes, 0, padded, 0, strBytes.length);
return padded;
}
}
3 changes: 3 additions & 0 deletions src/main/java/org/simdjson/JsonValue.java
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,9 @@ public String toString() {
case INT64 -> {
return String.valueOf(asLong());
}
case DOUBLE -> {
return String.valueOf(asDouble());
}
case TRUE_VALUE, FALSE_VALUE -> {
return String.valueOf(asBoolean());
}
Expand Down
Loading