Inline stage 1 (#53)

Author: piotrrzysko

build.gradle

@@ -136,24 +136,20 @@ jmh {
     jvmArgsPrepend = [
             '--add-modules=jdk.incubator.vector'
     ]
-    if (getBooleanProperty('jmh.profilersEnabled', false)) {
-        createDirIfDoesNotExist('./profilers')
-        if (OperatingSystem.current().isLinux()) {
-            def profilerList = [
-                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getLibPath('LD_LIBRARY_PATH')
-            ]
-            if (getBooleanProperty('jmh.jitLogEnabled', false)) {
-                createDirIfDoesNotExist('./profilers/perfasm')
-                profilerList += [
-                        'perfasm:intelSyntax=true;saveLog=true;saveLogTo=./profilers/perfasm'
-                ]
-            }
-            profilers = profilerList
-        } else if (OperatingSystem.current().isMacOsX()) {
-            profilers = [
-                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getLibPath('DYLD_LIBRARY_PATH')
-            ]
+    if (OperatingSystem.current().isLinux()) {
+        def profilerList = []
+        if (getBooleanProperty('jmh.asyncProfilerEnabled', false)) {
+            createDirIfDoesNotExist('./profilers/async')
+            profilerList += ['async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getLibPath('LD_LIBRARY_PATH')]
+        }
+        if (getBooleanProperty('jmh.perfAsmEnabled', false)) {
+            createDirIfDoesNotExist('./profilers/perfasm')
+            profilerList += ['perfasm:intelSyntax=true;saveLog=true;saveLogTo=./profilers/perfasm']
+        }
+        if (getBooleanProperty('jmh.perfEnabled', false)) {
+            profilerList += ['perf']
         }
+        profilers = profilerList
     }
     if (project.hasProperty('jmh.includes')) {
         includes = [project.findProperty('jmh.includes')]

src/jmh/java/org/simdjson/ParseAndSelectBenchmark.java

@@ -39,7 +39,7 @@ public void setup() throws IOException {
             buffer = is.readAllBytes();
             bufferPadded = padded(buffer);
         }
-        System.out.println("VectorSpecies = " + StructuralIndexer.BYTE_SPECIES);
+        System.out.println("VectorSpecies = " + VectorUtils.BYTE_SPECIES);
     }
 
     @Benchmark

src/jmh/java/org/simdjson/SchemaBasedParseAndSelectBenchmark.java

@@ -41,7 +41,7 @@ public void setup() throws IOException {
             buffer = is.readAllBytes();
             bufferPadded = padded(buffer);
         }
-        System.out.println("VectorSpecies = " + StructuralIndexer.BYTE_SPECIES);
+        System.out.println("VectorSpecies = " + VectorUtils.BYTE_SPECIES);
     }
 
     @Benchmark

src/jmh/java/org/simdjson/Utf8ValidatorBenchmark.java

@@ -1,7 +1,15 @@
 package org.simdjson;
 
 import com.google.common.base.Utf8;
-import org.openjdk.jmh.annotations.*;
+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.io.InputStream;
@@ -11,6 +19,7 @@
 @BenchmarkMode(Mode.Throughput)
 @OutputTimeUnit(TimeUnit.SECONDS)
 public class Utf8ValidatorBenchmark {
+
     @Param({"/twitter.json", "/gsoc-2018.json", "/github_events.json"})
     String fileName;
     byte[] bytes;
@@ -24,7 +33,7 @@ public void setup() throws IOException {
 
     @Benchmark
     public void utf8Validator() {
-        Utf8Validator.validate(bytes);
+        Utf8Validator.validate(bytes, bytes.length);
     }
 
     @Benchmark

src/main/java/org/simdjson/BlockReader.java

@@ -2,12 +2,10 @@
 
 public class SimdJsonParser {
 
-    private static final int STEP_SIZE = 64;
     private static final int PADDING = 64;
     private static final int DEFAULT_CAPACITY = 34 * 1024 * 1024; // we should be able to handle jsons <= 34MiB
     private static final int DEFAULT_MAX_DEPTH = 1024;
 
-    private final BlockReader reader;
     private final StructuralIndexer indexer;
     private final BitIndexes bitIndexes;
     private final JsonIterator jsonIterator;
@@ -24,23 +22,20 @@ public SimdJsonParser(int capacity, int maxDepth) {
         jsonIterator = new JsonIterator(bitIndexes, stringBuffer, capacity, maxDepth, PADDING);
         schemaBasedJsonIterator = new SchemaBasedJsonIterator(bitIndexes, stringBuffer, PADDING);
         paddedBuffer = new byte[capacity];
-        reader = new BlockReader(STEP_SIZE);
         indexer = new StructuralIndexer(bitIndexes);
     }
 
     public <T> T parse(byte[] buffer, int len, Class<T> expectedType) {
-        stage0(buffer);
         byte[] padded = padIfNeeded(buffer, len);
-        reset(padded, len);
-        stage1(padded);
+        reset();
+        stage1(padded, len);
         return schemaBasedJsonIterator.walkDocument(padded, len, expectedType);
     }
 
     public JsonValue parse(byte[] buffer, int len) {
-        stage0(buffer);
         byte[] padded = padIfNeeded(buffer, len);
-        reset(padded, len);
-        stage1(padded);
+        reset();
+        stage1(padded, len);
         return jsonIterator.walkDocument(padded, len);
     }
 
@@ -52,25 +47,13 @@ private byte[] padIfNeeded(byte[] buffer, int len) {
         return buffer;
     }
 
-    private void reset(byte[] buffer, int len) {
-        indexer.reset();
-        reader.reset(buffer, len);
+    private void reset() {
         bitIndexes.reset();
         jsonIterator.reset();
     }
 
-    private void stage0(byte[] buffer) {
-        Utf8Validator.validate(buffer);
-    }
-
-    private void stage1(byte[] buffer) {
-        while (reader.hasFullBlock()) {
-            int blockIndex = reader.getBlockIndex();
-            indexer.step(buffer, blockIndex, blockIndex);
-            reader.advance();
-        }
-        indexer.step(reader.remainder(), 0, reader.getBlockIndex());
-        reader.advance();
-        indexer.finish(reader.getBlockIndex());
+    private void stage1(byte[] buffer, int length) {
+        Utf8Validator.validate(buffer, length);
+        indexer.index(buffer, length);
     }
 }