mikemccand commented on code in PR #13585: URL: https://github.com/apache/lucene/pull/13585#discussion_r1688752555
########## lucene/core/src/java/org/apache/lucene/codecs/lucene912/ForUtil.java: ########## @@ -0,0 +1,1148 @@ +// This file has been automatically generated, DO NOT EDIT + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.lucene.codecs.lucene912; + +import java.io.IOException; +import org.apache.lucene.store.DataInput; +import org.apache.lucene.store.DataOutput; + +// Inspired from https://fulmicoton.com/posts/bitpacking/ +// Encodes multiple integers in a long to get SIMD-like speedups. +// If bitsPerValue <= 8 then we pack 8 ints per long +// else if bitsPerValue <= 16 we pack 4 ints per long +// else we pack 2 ints per long +final class ForUtil { + + static final int BLOCK_SIZE = 128; + static final int BLOCK_SIZE_LOG2 = 7; + + private static long expandMask32(long mask32) { + return mask32 | (mask32 << 32); + } + + private static long expandMask16(long mask16) { + return expandMask32(mask16 | (mask16 << 16)); + } + + private static long expandMask8(long mask8) { + return expandMask16(mask8 | (mask8 << 8)); + } + + private static long mask32(int bitsPerValue) { + return expandMask32((1L << bitsPerValue) - 1); + } + + private static long mask16(int bitsPerValue) { + return expandMask16((1L << bitsPerValue) - 1); + } + + private static long mask8(int bitsPerValue) { + return expandMask8((1L << bitsPerValue) - 1); + } + + private static void expand8(long[] arr) { + for (int i = 0; i < 16; ++i) { + long l = arr[i]; + arr[i] = (l >>> 56) & 0xFFL; + arr[16 + i] = (l >>> 48) & 0xFFL; + arr[32 + i] = (l >>> 40) & 0xFFL; + arr[48 + i] = (l >>> 32) & 0xFFL; + arr[64 + i] = (l >>> 24) & 0xFFL; + arr[80 + i] = (l >>> 16) & 0xFFL; + arr[96 + i] = (l >>> 8) & 0xFFL; + arr[112 + i] = l & 0xFFL; + } + } + + private static void expand8To32(long[] arr) { + for (int i = 0; i < 16; ++i) { + long l = arr[i]; + arr[i] = (l >>> 24) & 0x000000FF000000FFL; + arr[16 + i] = (l >>> 16) & 0x000000FF000000FFL; + arr[32 + i] = (l >>> 8) & 0x000000FF000000FFL; + arr[48 + i] = l & 0x000000FF000000FFL; + } + } + + private static void collapse8(long[] arr) { + for (int i = 0; i < 16; ++i) { + arr[i] = + (arr[i] << 56) + | (arr[16 + i] << 48) + | (arr[32 + i] << 40) + | (arr[48 + i] << 32) + | (arr[64 + i] << 24) + | (arr[80 + i] << 16) + | (arr[96 + i] << 8) + | arr[112 + i]; + } + } + + private static void expand16(long[] arr) { + for (int i = 0; i < 32; ++i) { + long l = arr[i]; + arr[i] = (l >>> 48) & 0xFFFFL; + arr[32 + i] = (l >>> 32) & 0xFFFFL; + arr[64 + i] = (l >>> 16) & 0xFFFFL; + arr[96 + i] = l & 0xFFFFL; + } + } + + private static void expand16To32(long[] arr) { + for (int i = 0; i < 32; ++i) { + long l = arr[i]; + arr[i] = (l >>> 16) & 0x0000FFFF0000FFFFL; + arr[32 + i] = l & 0x0000FFFF0000FFFFL; + } + } + + private static void collapse16(long[] arr) { + for (int i = 0; i < 32; ++i) { + arr[i] = (arr[i] << 48) | (arr[32 + i] << 32) | (arr[64 + i] << 16) | arr[96 + i]; + } + } + + private static void expand32(long[] arr) { + for (int i = 0; i < 64; ++i) { + long l = arr[i]; + arr[i] = l >>> 32; + arr[64 + i] = l & 0xFFFFFFFFL; + } + } + + private static void collapse32(long[] arr) { + for (int i = 0; i < 64; ++i) { + arr[i] = (arr[i] << 32) | arr[64 + i]; + } + } + + private static void prefixSum8(long[] arr, long base) { + expand8To32(arr); + prefixSum32(arr, base); + } + + private static void prefixSum16(long[] arr, long base) { + // We need to move to the next primitive size to avoid overflows + expand16To32(arr); + prefixSum32(arr, base); + } + + private static void prefixSum32(long[] arr, long base) { + arr[0] += base << 32; + innerPrefixSum32(arr); + expand32(arr); + final long l = arr[BLOCK_SIZE / 2 - 1]; + for (int i = BLOCK_SIZE / 2; i < BLOCK_SIZE; ++i) { + arr[i] += l; + } + } + + // For some reason unrolling seems to help + private static void innerPrefixSum32(long[] arr) { + arr[1] += arr[0]; + arr[2] += arr[1]; + arr[3] += arr[2]; + arr[4] += arr[3]; + arr[5] += arr[4]; + arr[6] += arr[5]; + arr[7] += arr[6]; + arr[8] += arr[7]; + arr[9] += arr[8]; + arr[10] += arr[9]; + arr[11] += arr[10]; + arr[12] += arr[11]; + arr[13] += arr[12]; + arr[14] += arr[13]; + arr[15] += arr[14]; + arr[16] += arr[15]; + arr[17] += arr[16]; + arr[18] += arr[17]; + arr[19] += arr[18]; + arr[20] += arr[19]; + arr[21] += arr[20]; + arr[22] += arr[21]; + arr[23] += arr[22]; + arr[24] += arr[23]; + arr[25] += arr[24]; + arr[26] += arr[25]; + arr[27] += arr[26]; + arr[28] += arr[27]; + arr[29] += arr[28]; + arr[30] += arr[29]; + arr[31] += arr[30]; + arr[32] += arr[31]; + arr[33] += arr[32]; + arr[34] += arr[33]; + arr[35] += arr[34]; + arr[36] += arr[35]; + arr[37] += arr[36]; + arr[38] += arr[37]; + arr[39] += arr[38]; + arr[40] += arr[39]; + arr[41] += arr[40]; + arr[42] += arr[41]; + arr[43] += arr[42]; + arr[44] += arr[43]; + arr[45] += arr[44]; + arr[46] += arr[45]; + arr[47] += arr[46]; + arr[48] += arr[47]; + arr[49] += arr[48]; + arr[50] += arr[49]; + arr[51] += arr[50]; + arr[52] += arr[51]; + arr[53] += arr[52]; + arr[54] += arr[53]; + arr[55] += arr[54]; + arr[56] += arr[55]; + arr[57] += arr[56]; + arr[58] += arr[57]; + arr[59] += arr[58]; + arr[60] += arr[59]; + arr[61] += arr[60]; + arr[62] += arr[61]; + arr[63] += arr[62]; + } + + private final long[] tmp = new long[BLOCK_SIZE / 2]; + + /** Encode 128 integers from {@code longs} into {@code out}. */ + void encode(long[] longs, int bitsPerValue, DataOutput out) throws IOException { + final int nextPrimitive; + final int numLongs; + if (bitsPerValue <= 8) { + nextPrimitive = 8; + numLongs = BLOCK_SIZE / 8; + collapse8(longs); + } else if (bitsPerValue <= 16) { + nextPrimitive = 16; + numLongs = BLOCK_SIZE / 4; + collapse16(longs); + } else { + nextPrimitive = 32; + numLongs = BLOCK_SIZE / 2; + collapse32(longs); + } + + final int numLongsPerShift = bitsPerValue * 2; + int idx = 0; + int shift = nextPrimitive - bitsPerValue; + for (int i = 0; i < numLongsPerShift; ++i) { + tmp[i] = longs[idx++] << shift; + } + for (shift = shift - bitsPerValue; shift >= 0; shift -= bitsPerValue) { + for (int i = 0; i < numLongsPerShift; ++i) { + tmp[i] |= longs[idx++] << shift; + } + } + + final int remainingBitsPerLong = shift + bitsPerValue; + final long maskRemainingBitsPerLong; + if (nextPrimitive == 8) { + maskRemainingBitsPerLong = MASKS8[remainingBitsPerLong]; + } else if (nextPrimitive == 16) { + maskRemainingBitsPerLong = MASKS16[remainingBitsPerLong]; + } else { + maskRemainingBitsPerLong = MASKS32[remainingBitsPerLong]; + } + + int tmpIdx = 0; + int remainingBitsPerValue = bitsPerValue; + while (idx < numLongs) { + if (remainingBitsPerValue >= remainingBitsPerLong) { + remainingBitsPerValue -= remainingBitsPerLong; + tmp[tmpIdx++] |= (longs[idx] >>> remainingBitsPerValue) & maskRemainingBitsPerLong; + if (remainingBitsPerValue == 0) { + idx++; + remainingBitsPerValue = bitsPerValue; + } + } else { + final long mask1, mask2; + if (nextPrimitive == 8) { + mask1 = MASKS8[remainingBitsPerValue]; + mask2 = MASKS8[remainingBitsPerLong - remainingBitsPerValue]; + } else if (nextPrimitive == 16) { + mask1 = MASKS16[remainingBitsPerValue]; + mask2 = MASKS16[remainingBitsPerLong - remainingBitsPerValue]; + } else { + mask1 = MASKS32[remainingBitsPerValue]; + mask2 = MASKS32[remainingBitsPerLong - remainingBitsPerValue]; + } + tmp[tmpIdx] |= (longs[idx++] & mask1) << (remainingBitsPerLong - remainingBitsPerValue); + remainingBitsPerValue = bitsPerValue - remainingBitsPerLong + remainingBitsPerValue; + tmp[tmpIdx++] |= (longs[idx] >>> remainingBitsPerValue) & mask2; + } + } + + for (int i = 0; i < numLongsPerShift; ++i) { + out.writeLong(tmp[i]); + } + } + + /** Number of bytes required to encode 128 integers of {@code bitsPerValue} bits per value. */ + int numBytes(int bitsPerValue) { + return bitsPerValue << (BLOCK_SIZE_LOG2 - 3); + } + + private static void decodeSlow(int bitsPerValue, DataInput in, long[] tmp, long[] longs) Review Comment: No need to separate the commits like that. Maybe next time! We need a "make a new Codec format best practices guide". -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org