From 6a59dbb3768e170b626153d7bde7cce20be8da3e Mon Sep 17 00:00:00 2001 From: Klaus Post Date: Fri, 10 Nov 2023 02:20:07 -0800 Subject: [PATCH] zstd: Improve better/best compression (#877) * zstd: Improve better/best compression * Improve filling of hash table. * Skip similar checks. * Improve bit estimate precision. 0.02 -> 0.3% improvement observed (input -> output size difference - relative is bigger) --- zstd/enc_best.go | 44 +++++++++++++++++++++++++++----------------- zstd/enc_better.go | 17 ++++++++--------- 2 files changed, 35 insertions(+), 26 deletions(-) diff --git a/zstd/enc_best.go b/zstd/enc_best.go index 858f8f43a5..c81a15357a 100644 --- a/zstd/enc_best.go +++ b/zstd/enc_best.go @@ -43,7 +43,7 @@ func (m *match) estBits(bitsPerByte int32) { if m.rep < 0 { ofc = ofCode(uint32(m.s-m.offset) + 3) } else { - ofc = ofCode(uint32(m.rep)) + ofc = ofCode(uint32(m.rep) & 3) } // Cost, excluding ofTT, mlTT := fsePredefEnc[tableOffsets].ct.symbolTT[ofc], fsePredefEnc[tableMatchLengths].ct.symbolTT[mlc] @@ -227,7 +227,7 @@ encodeLoop: } } l := 4 + e.matchlen(s+4, offset+4, src) - if rep < 0 { + if true { // Extend candidate match backwards as far as possible. tMin := s - e.maxMatchOff if tMin < 0 { @@ -282,6 +282,7 @@ encodeLoop: // Load next and check... e.longTable[nextHashL] = prevEntry{offset: s + e.cur, prev: candidateL.offset} e.table[nextHashS] = prevEntry{offset: s + e.cur, prev: candidateS.offset} + index0 := s + 1 // Look far ahead, unless we have a really long match already... if best.length < goodEnough { @@ -357,19 +358,16 @@ encodeLoop: blk.sequences = append(blk.sequences, seq) // Index old s + 1 -> s - 1 - index0 := s + 1 s = best.s + best.length - nextEmit = s - if s >= sLimit { - if debugEncoder { - println("repeat ended", s, best.length) - } - break encodeLoop - } + // Index skipped... + end := s + if s > sLimit+4 { + end = sLimit + 4 + } off := index0 + e.cur - for index0 < s { + for index0 < end { cv0 := load6432(src, index0) h0 := hashLen(cv0, bestLongTableBits, bestLongLen) h1 := hashLen(cv0, bestShortTableBits, bestShortLen) @@ -378,6 +376,7 @@ encodeLoop: off++ index0++ } + switch best.rep { case 2, 4 | 1: offset1, offset2 = offset2, offset1 @@ -386,12 +385,17 @@ encodeLoop: case 4 | 3: offset1, offset2, offset3 = offset1-1, offset1, offset2 } + if s >= sLimit { + if debugEncoder { + println("repeat ended", s, best.length) + } + break encodeLoop + } continue } // A 4-byte match has been found. Update recent offsets. // We'll later see if more than 4 bytes. - index0 := s + 1 s = best.s t := best.offset offset1, offset2, offset3 = s-t, offset1, offset2 @@ -419,19 +423,25 @@ encodeLoop: } blk.sequences = append(blk.sequences, seq) nextEmit = s - if s >= sLimit { - break encodeLoop + + // Index old s + 1 -> s - 1 or sLimit + end := s + if s > sLimit-4 { + end = sLimit - 4 } - // Index old s + 1 -> s - 1 - for index0 < s { + off := index0 + e.cur + for index0 < end { cv0 := load6432(src, index0) h0 := hashLen(cv0, bestLongTableBits, bestLongLen) h1 := hashLen(cv0, bestShortTableBits, bestShortLen) - off := index0 + e.cur e.longTable[h0] = prevEntry{offset: off, prev: e.longTable[h0].offset} e.table[h1] = prevEntry{offset: off, prev: e.table[h1].offset} index0++ + off++ + } + if s >= sLimit { + break encodeLoop } } diff --git a/zstd/enc_better.go b/zstd/enc_better.go index 8582f31a7c..20d25b0e05 100644 --- a/zstd/enc_better.go +++ b/zstd/enc_better.go @@ -145,7 +145,7 @@ encodeLoop: var t int32 // We allow the encoder to optionally turn off repeat offsets across blocks canRepeat := len(blk.sequences) > 2 - var matched int32 + var matched, index0 int32 for { if debugAsserts && canRepeat && offset1 == 0 { @@ -162,6 +162,7 @@ encodeLoop: off := s + e.cur e.longTable[nextHashL] = prevEntry{offset: off, prev: candidateL.offset} e.table[nextHashS] = tableEntry{offset: off, val: uint32(cv)} + index0 = s + 1 if canRepeat { if repIndex >= 0 && load3232(src, repIndex) == uint32(cv>>(repOff*8)) { @@ -258,7 +259,6 @@ encodeLoop: } blk.sequences = append(blk.sequences, seq) - index0 := s + repOff2 s += lenght + repOff2 nextEmit = s if s >= sLimit { @@ -498,15 +498,15 @@ encodeLoop: } // Index match start+1 (long) -> s - 1 - index0 := s - l + 1 + off := index0 + e.cur for index0 < s-1 { cv0 := load6432(src, index0) cv1 := cv0 >> 8 h0 := hashLen(cv0, betterLongTableBits, betterLongLen) - off := index0 + e.cur e.longTable[h0] = prevEntry{offset: off, prev: e.longTable[h0].offset} e.table[hashLen(cv1, betterShortTableBits, betterShortLen)] = tableEntry{offset: off + 1, val: uint32(cv1)} index0 += 2 + off += 2 } cv = load6432(src, s) @@ -672,7 +672,7 @@ encodeLoop: var t int32 // We allow the encoder to optionally turn off repeat offsets across blocks canRepeat := len(blk.sequences) > 2 - var matched int32 + var matched, index0 int32 for { if debugAsserts && canRepeat && offset1 == 0 { @@ -691,6 +691,7 @@ encodeLoop: e.markLongShardDirty(nextHashL) e.table[nextHashS] = tableEntry{offset: off, val: uint32(cv)} e.markShortShardDirty(nextHashS) + index0 = s + 1 if canRepeat { if repIndex >= 0 && load3232(src, repIndex) == uint32(cv>>(repOff*8)) { @@ -726,7 +727,6 @@ encodeLoop: blk.sequences = append(blk.sequences, seq) // Index match start+1 (long) -> s - 1 - index0 := s + repOff s += lenght + repOff nextEmit = s @@ -790,7 +790,6 @@ encodeLoop: } blk.sequences = append(blk.sequences, seq) - index0 := s + repOff2 s += lenght + repOff2 nextEmit = s if s >= sLimit { @@ -1024,18 +1023,18 @@ encodeLoop: } // Index match start+1 (long) -> s - 1 - index0 := s - l + 1 + off := index0 + e.cur for index0 < s-1 { cv0 := load6432(src, index0) cv1 := cv0 >> 8 h0 := hashLen(cv0, betterLongTableBits, betterLongLen) - off := index0 + e.cur e.longTable[h0] = prevEntry{offset: off, prev: e.longTable[h0].offset} e.markLongShardDirty(h0) h1 := hashLen(cv1, betterShortTableBits, betterShortLen) e.table[h1] = tableEntry{offset: off + 1, val: uint32(cv1)} e.markShortShardDirty(h1) index0 += 2 + off += 2 } cv = load6432(src, s)