From 76b505b05468084e961f92135f08631709ae8ae9 Mon Sep 17 00:00:00 2001 From: Sebastiaan van Stijn Date: Fri, 28 Aug 2026 20:36:33 +0200 Subject: [PATCH] vendor: github.com/klauspost/compress v1.19.2 full diff: https://github.com/klauspost/compress/compare/v1.18.7...v1.19.2 Signed-off-by: Sebastiaan van Stijn --- vendor.mod | 2 +- vendor.sum | 4 +- .../github.com/klauspost/compress/README.md | 12 + .../klauspost/compress/huff0/build_table.go | 168 + .../compress/huff0/decompress_amd64.go | 203 +- .../compress/huff0/decompress_amd64.s | 4 +- .../compress/huff0/decompress_arm64.go | 37 + .../compress/huff0/decompress_arm64.s | 851 +++++ .../compress/huff0/decompress_asm.go | 193 ++ .../compress/huff0/decompress_generic.go | 2 +- .../compress/internal/snapref/decode.go | 2 +- .../klauspost/compress/zstd/README.md | 37 +- .../klauspost/compress/zstd/blockdec.go | 9 +- .../klauspost/compress/zstd/dict.go | 88 +- .../klauspost/compress/zstd/enc_base.go | 28 + .../klauspost/compress/zstd/enc_best.go | 15 + .../klauspost/compress/zstd/enc_better.go | 18 + .../klauspost/compress/zstd/enc_dfast.go | 16 + .../klauspost/compress/zstd/enc_fast.go | 17 + .../klauspost/compress/zstd/enc_jobs.go | 352 +++ .../klauspost/compress/zstd/encoder.go | 210 +- .../compress/zstd/encoder_options.go | 69 +- .../compress/zstd/fse_decoder_amd64.s | 2 +- .../compress/zstd/fse_decoder_arm64.s | 153 + ...se_decoder_amd64.go => fse_decoder_asm.go} | 8 +- .../compress/zstd/fse_decoder_generic.go | 2 +- .../klauspost/compress/zstd/seqdec_amd64.go | 362 +-- .../klauspost/compress/zstd/seqdec_amd64.s | 6 +- .../klauspost/compress/zstd/seqdec_arm64.go | 70 + .../klauspost/compress/zstd/seqdec_arm64.s | 2750 +++++++++++++++++ .../klauspost/compress/zstd/seqdec_asm.go | 316 ++ .../klauspost/compress/zstd/seqdec_generic.go | 2 +- .../klauspost/compress/zstd/snappy.go | 7 +- vendor/modules.txt | 2 +- 34 files changed, 5438 insertions(+), 579 deletions(-) create mode 100644 vendor/github.com/klauspost/compress/huff0/build_table.go create mode 100644 vendor/github.com/klauspost/compress/huff0/decompress_arm64.go create mode 100644 vendor/github.com/klauspost/compress/huff0/decompress_arm64.s create mode 100644 vendor/github.com/klauspost/compress/huff0/decompress_asm.go create mode 100644 vendor/github.com/klauspost/compress/zstd/enc_jobs.go create mode 100644 vendor/github.com/klauspost/compress/zstd/fse_decoder_arm64.s rename vendor/github.com/klauspost/compress/zstd/{fse_decoder_amd64.go => fse_decoder_asm.go} (81%) create mode 100644 vendor/github.com/klauspost/compress/zstd/seqdec_arm64.go create mode 100644 vendor/github.com/klauspost/compress/zstd/seqdec_arm64.s create mode 100644 vendor/github.com/klauspost/compress/zstd/seqdec_asm.go diff --git a/vendor.mod b/vendor.mod index 0a21b030550f..e6209387e333 100644 --- a/vendor.mod +++ b/vendor.mod @@ -87,7 +87,7 @@ require ( github.com/gorilla/mux v1.8.1 // indirect github.com/grpc-ecosystem/grpc-gateway/v2 v2.30.0 // indirect github.com/inconshreveable/mousetrap v1.1.0 // indirect - github.com/klauspost/compress v1.18.7 // indirect + github.com/klauspost/compress v1.19.2 // indirect github.com/moby/docker-image-spec v1.3.1 // indirect github.com/moby/sys/user v0.4.1 // indirect github.com/moby/sys/userns v0.2.0 // indirect diff --git a/vendor.sum b/vendor.sum index 9332aca82a1e..2294d4834509 100644 --- a/vendor.sum +++ b/vendor.sum @@ -78,8 +78,8 @@ github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8= github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck= -github.com/klauspost/compress v1.18.7 h1:aUyZsS4kH3QTKurYhAOwAHxllVPnOthb3vPfnF1Ehjw= -github.com/klauspost/compress v1.18.7/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ= +github.com/klauspost/compress v1.19.2 h1:hMRETovs/pu/dVWN7zIT1PGG8t509MwT6bO7XSi26R8= +github.com/klauspost/compress v1.19.2/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ= github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc= github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw= github.com/mattn/go-runewidth v0.0.28 h1:rPyg2ybwEKPebvpzVWe1gKBkH8EQFkxO4Y0hjBeLaBU= diff --git a/vendor/github.com/klauspost/compress/README.md b/vendor/github.com/klauspost/compress/README.md index fb023f2cf215..0e9f170d0120 100644 --- a/vendor/github.com/klauspost/compress/README.md +++ b/vendor/github.com/klauspost/compress/README.md @@ -27,6 +27,18 @@ Use the links above for more information on each. # changelog +* Jul 1st, 2026 [1.19.0](https://github.com/klauspost/compress/releases/tag/v1.19.0) + * zstd: Add true concurrent stream encodingin https://github.com/klauspost/compress/pull/1136 + * zstd: arm64 decoder asm by @lizthegrey in https://github.com/klauspost/compress/pull/1160 + * flate: Add inflate checkpoints in https://github.com/klauspost/compress/pull/1154 + * zstd: avoid unused BuildDict encoder allocation by @snissn in https://github.com/klauspost/compress/pull/1147 + * snappy/s2: Limit length of varint in `decodedLen` by @eustas in https://github.com/klauspost/compress/pull/1148 + * gzhttp: match qvalue parameter case-insensitively (RFC 7231) by @z9z in https://github.com/klauspost/compress/pull/1149 + * zip: add NameDecoder callback for legacy encoding rewrite by @SAY-5 in https://github.com/klauspost/compress/pull/1150 + * huff0: Allow building tables from histogram in https://github.com/klauspost/compress/pull/1155 + * huff0: Allow building table from oversized histogram in https://github.com/klauspost/compress/pull/1156 + * s2sx: Clean symlink targets in https://github.com/klauspost/compress/pull/1163 + * Feb 9th, 2026 [1.18.4](https://github.com/klauspost/compress/releases/tag/v1.18.4) * gzhttp: Add zstandard to server handler wrapper https://github.com/klauspost/compress/pull/1121 * zstd: Add ResetWithOptions to encoder/decoder https://github.com/klauspost/compress/pull/1122 diff --git a/vendor/github.com/klauspost/compress/huff0/build_table.go b/vendor/github.com/klauspost/compress/huff0/build_table.go new file mode 100644 index 000000000000..e3757c87e0ff --- /dev/null +++ b/vendor/github.com/klauspost/compress/huff0/build_table.go @@ -0,0 +1,168 @@ +package huff0 + +import "errors" + +// BuildCTable builds a Huffman compression table from a precomputed symbol +// histogram and installs it as the previous (reuse) table on s. +// +// After this call: +// - EstimateSize/CanUseTable can probe the table against other histograms. +// - Compress1X/Compress4X with Reuse = ReusePolicyMust will encode without +// emitting a new table header. +// - TransferCTable can hand the table to a sibling Scratch. +// +// count[i] is the number of occurrences of symbol i. The histogram must have +// at least 2 distinct non-zero symbols; ErrUseRLE is returned for a single +// symbol and an error is returned for an empty histogram. +func (s *Scratch) BuildCTable(count *[256]uint32) error { + if s == nil { + return errors.New("huff0: BuildCTable on nil Scratch") + } + if count == nil { + return errors.New("huff0: nil count passed to BuildCTable") + } + var err error + s, err = s.prepare(nil) + if err != nil { + return err + } + s.count = *count + var total, maxCount int + var symLen uint16 + for i, v := range s.count { + total += int(v) + if int(v) > maxCount { + maxCount = int(v) + } + if v != 0 { + symLen = uint16(i) + 1 + } + } + if total == 0 { + return errors.New("huff0: empty histogram") + } + if symLen < 2 || maxCount == total { + return ErrUseRLE + } + // huff0's internal rank table assumes total ≤ BlockSizeMax (it uses + // highBit32(count+1) + 1 as a rank index into a fixed-size array). + // Histograms summed across multiple blocks can exceed that; scale the + // counts down preserving the distribution. Non-zero entries round up so + // rare symbols stay representable. + if total > BlockSizeMax { + shift := uint(0) + for total>>shift > BlockSizeMax { + shift++ + } + round := uint32(1<> shift + if scaled == 0 { + scaled = 1 + } + s.count[i] = scaled + newTotal += int(scaled) + if int(scaled) > newMax { + newMax = int(scaled) + } + } + total = newTotal + maxCount = newMax + if maxCount == total { + return ErrUseRLE + } + } + s.symbolLen = symLen + s.maxCount = maxCount + s.srcLen = total + if err := s.buildCTable(); err != nil { + return err + } + if cap(s.prevTable) < len(s.cTable) { + s.prevTable = make(cTable, 0, maxSymbolValue+1) + } + s.prevTable = s.prevTable[:len(s.cTable)] + copy(s.prevTable, s.cTable) + s.prevTableLog = s.actualTableLog + // Force the next Compress* to recount from real input. + s.clearCount = true + s.maxCount = 0 + return nil +} + +// EstimateSize returns an estimated compressed payload size in bytes for the +// supplied histogram using the table currently stored in prevTable. It returns +// -1 when the table cannot encode every non-zero symbol of hist (i.e. when +// CanUseTable would return false). The estimate excludes the table header. +func (s *Scratch) EstimateSize(hist *[256]uint32) int { + if s == nil || hist == nil || len(s.prevTable) == 0 { + return -1 + } + pt := s.prevTable + nbBits := uint32(7) + for i, v := range hist { + if v == 0 { + continue + } + if i >= len(pt) || pt[i].nBits == 0 { + return -1 + } + nbBits += uint32(pt[i].nBits) * v + } + return int(nbBits >> 3) +} + +// CanUseTable reports whether the table in prevTable can encode every +// non-zero symbol present in hist. +func (s *Scratch) CanUseTable(hist *[256]uint32) bool { + if s == nil || hist == nil || len(s.prevTable) == 0 { + return false + } + pt := s.prevTable + for i, v := range hist { + if v == 0 { + continue + } + if i >= len(pt) || pt[i].nBits == 0 { + return false + } + } + return true +} + +// AppendTable serializes the table currently stored in prevTable (e.g. as +// installed by BuildCTable or carried over from a previous Compress call) +// into a self-delimiting zstd-style header and appends it to dst. The +// returned slice can be parsed back by ReadTable. +func (s *Scratch) AppendTable(dst []byte) ([]byte, error) { + if s == nil || len(s.prevTable) == 0 { + return dst, errors.New("huff0: AppendTable with empty table") + } + // cTable.write reads s.actualTableLog, s.symbolLen, s.huffWeight, s.fse + // and writes into s.Out. Save/restore Out so we don't disturb in-flight + // compression buffers. + saveOut := s.Out + saveTL := s.actualTableLog + saveSL := s.symbolLen + if s.fse == nil { + // Lazily init in case AppendTable is called on a fresh Scratch. + if _, err := s.prepare(nil); err != nil { + return dst, err + } + saveOut = s.Out + } + s.Out = s.Out[:0] + s.actualTableLog = s.prevTableLog + s.symbolLen = uint16(len(s.prevTable)) + if err := s.prevTable.write(s); err != nil { + s.Out, s.actualTableLog, s.symbolLen = saveOut, saveTL, saveSL + return dst, err + } + dst = append(dst, s.Out...) + s.Out, s.actualTableLog, s.symbolLen = saveOut, saveTL, saveSL + return dst, nil +} diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go index 2d6ef64be15b..7035d656d991 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go +++ b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go @@ -1,222 +1,49 @@ //go:build amd64 && !appengine && !noasm && gc -// This file contains the specialisation of Decoder.Decompress4X -// and Decoder.Decompress1X that use an asm implementation of thir main loops. +// amd64 stubs and dispatch for the asm loops used by decompress_asm.go. package huff0 import ( - "errors" - "fmt" - "github.com/klauspost/compress/internal/cpuinfo" ) -// decompress4x_main_loop_x86 is an x86 assembler implementation +// decompress4x_main_loop_amd64 is an x86 assembler implementation // of Decompress4X when tablelog > 8. // //go:noescape func decompress4x_main_loop_amd64(ctx *decompress4xContext) -// decompress4x_8b_loop_x86 is an x86 assembler implementation +// decompress4x_8b_main_loop_amd64 is an x86 assembler implementation // of Decompress4X when tablelog <= 8 which decodes 4 entries // per loop. // //go:noescape func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext) -// fallback8BitSize is the size where using Go version is faster. -const fallback8BitSize = 800 - -type decompress4xContext struct { - pbr *[4]bitReaderShifted - peekBits uint8 - out *byte - dstEvery int - tbl *dEntrySingle - decoded int - limit *byte -} - -// Decompress4X will decompress a 4X encoded stream. -// The length of the supplied input must match the end of a block exactly. -// The *capacity* of the dst slice must match the destination size of -// the uncompressed data exactly. -func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) { - if len(d.dt.single) == 0 { - return nil, errors.New("no table loaded") - } - if len(src) < 6+(4*1) { - return nil, errors.New("input too small") - } - - use8BitTables := d.actualTableLog <= 8 - if cap(dst) < fallback8BitSize && use8BitTables { - return d.decompress4X8bit(dst, src) - } - - var br [4]bitReaderShifted - // Decode "jump table" - start := 6 - for i := range 3 { - length := int(src[i*2]) | (int(src[i*2+1]) << 8) - if start+length >= len(src) { - return nil, errors.New("truncated input (or invalid offset)") - } - err := br[i].init(src[start : start+length]) - if err != nil { - return nil, err - } - start += length - } - err := br[3].init(src[start:]) - if err != nil { - return nil, err - } - - // destination, offset to match first output - dstSize := cap(dst) - dst = dst[:dstSize] - out := dst - dstEvery := (dstSize + 3) / 4 - - const tlSize = 1 << tableLogMax - const tlMask = tlSize - 1 - single := d.dt.single[:tlSize] - - var decoded int - - if len(out) > 4*4 && !(br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4) { - ctx := decompress4xContext{ - pbr: &br, - peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast() - out: &out[0], - dstEvery: dstEvery, - tbl: &single[0], - limit: &out[dstEvery-4], // Always stop decoding when first buffer gets here to avoid writing OOB on last. - } - if use8BitTables { - decompress4x_8b_main_loop_amd64(&ctx) - } else { - decompress4x_main_loop_amd64(&ctx) - } - - decoded = ctx.decoded - out = out[decoded/4:] - } - - // Decode remaining. - remainBytes := dstEvery - (decoded / 4) - for i := range br { - offset := dstEvery * i - endsAt := min(offset+remainBytes, len(out)) - br := &br[i] - bitsLeft := br.remaining() - for bitsLeft > 0 { - br.fill() - if offset >= endsAt { - return nil, errors.New("corruption detected: stream overrun 4") - } - - // Read value and increment offset. - val := br.peekBitsFast(d.actualTableLog) - v := single[val&tlMask].entry - nBits := uint8(v) - br.advance(nBits) - bitsLeft -= uint(nBits) - out[offset] = uint8(v >> 8) - offset++ - } - if offset != endsAt { - return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt) - } - decoded += offset - dstEvery*i - err = br.close() - if err != nil { - return nil, err - } - } - if dstSize != decoded { - return nil, errors.New("corruption detected: short output block") - } - return dst, nil -} - -// decompress4x_main_loop_x86 is an x86 assembler implementation +// decompress1x_main_loop_amd64 is an x86 assembler implementation // of Decompress1X when tablelog > 8. // //go:noescape func decompress1x_main_loop_amd64(ctx *decompress1xContext) -// decompress4x_main_loop_x86 is an x86 with BMI2 assembler implementation +// decompress1x_main_loop_bmi2 is an x86 with BMI2 assembler implementation // of Decompress1X when tablelog > 8. // //go:noescape func decompress1x_main_loop_bmi2(ctx *decompress1xContext) -type decompress1xContext struct { - pbr *bitReaderShifted - peekBits uint8 - out *byte - outCap int - tbl *dEntrySingle - decoded int +func decompress4x_main_loop_asm(ctx *decompress4xContext) { + decompress4x_main_loop_amd64(ctx) } -// Error reported by asm implementations -const error_max_decoded_size_exeeded = -1 - -// Decompress1X will decompress a 1X encoded stream. -// The cap of the output buffer will be the maximum decompressed size. -// The length of the supplied input must match the end of a block exactly. -func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) { - if len(d.dt.single) == 0 { - return nil, errors.New("no table loaded") - } - var br bitReaderShifted - err := br.init(src) - if err != nil { - return dst, err - } - maxDecodedSize := cap(dst) - dst = dst[:maxDecodedSize] - - const tlSize = 1 << tableLogMax - const tlMask = tlSize - 1 - - if maxDecodedSize >= 4 { - ctx := decompress1xContext{ - pbr: &br, - out: &dst[0], - outCap: maxDecodedSize, - peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast() - tbl: &d.dt.single[0], - } - - if cpuinfo.HasBMI2() { - decompress1x_main_loop_bmi2(&ctx) - } else { - decompress1x_main_loop_amd64(&ctx) - } - if ctx.decoded == error_max_decoded_size_exeeded { - return nil, ErrMaxDecodedSizeExceeded - } - - dst = dst[:ctx.decoded] - } +func decompress4x_8b_main_loop_asm(ctx *decompress4xContext) { + decompress4x_8b_main_loop_amd64(ctx) +} - // br < 8, so uint8 is fine - bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead - for bitsLeft > 0 { - br.fill() - if len(dst) >= maxDecodedSize { - br.close() - return nil, ErrMaxDecodedSizeExceeded - } - v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask] - nBits := uint8(v.entry) - br.advance(nBits) - bitsLeft -= nBits - dst = append(dst, uint8(v.entry>>8)) +func decompress1x_main_loop_asm(ctx *decompress1xContext) { + if cpuinfo.HasBMI2() { + decompress1x_main_loop_bmi2(ctx) + } else { + decompress1x_main_loop_amd64(ctx) } - return dst, br.close() } diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s index c4c7ab2d1fe3..c5d4a710a093 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s +++ b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s @@ -1,6 +1,6 @@ -// Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT. +// Code generated by command: go run gen.go -out ../decompress.s -arch amd64,arm64 -pkg=huff0. DO NOT EDIT. -//go:build amd64 && !appengine && !noasm && gc +//go:build !appengine && !noasm && gc // func decompress4x_main_loop_amd64(ctx *decompress4xContext) TEXT ·decompress4x_main_loop_amd64(SB), $0-8 diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_arm64.go b/vendor/github.com/klauspost/compress/huff0/decompress_arm64.go new file mode 100644 index 000000000000..8ba3c810e60a --- /dev/null +++ b/vendor/github.com/klauspost/compress/huff0/decompress_arm64.go @@ -0,0 +1,37 @@ +//go:build arm64 && !appengine && !noasm && gc + +// arm64 stubs and dispatch for the asm loops used by decompress_asm.go. +// The asm (decompress_arm64.s) is generated by the avo arm64 lowering +// printer from the same source as the amd64 asm; see _generate/gen.go. +package huff0 + +// decompress4x_main_loop_arm64 is an arm64 assembler implementation +// of Decompress4X when tablelog > 8. +// +//go:noescape +func decompress4x_main_loop_arm64(ctx *decompress4xContext) + +// decompress4x_8b_main_loop_arm64 is an arm64 assembler implementation +// of Decompress4X when tablelog <= 8 which decodes 4 entries +// per loop. +// +//go:noescape +func decompress4x_8b_main_loop_arm64(ctx *decompress4xContext) + +// decompress1x_main_loop_arm64 is an arm64 assembler implementation +// of Decompress1X when tablelog > 8. +// +//go:noescape +func decompress1x_main_loop_arm64(ctx *decompress1xContext) + +func decompress4x_main_loop_asm(ctx *decompress4xContext) { + decompress4x_main_loop_arm64(ctx) +} + +func decompress4x_8b_main_loop_asm(ctx *decompress4xContext) { + decompress4x_8b_main_loop_arm64(ctx) +} + +func decompress1x_main_loop_asm(ctx *decompress1xContext) { + decompress1x_main_loop_arm64(ctx) +} diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_arm64.s b/vendor/github.com/klauspost/compress/huff0/decompress_arm64.s new file mode 100644 index 000000000000..e16012721a1c --- /dev/null +++ b/vendor/github.com/klauspost/compress/huff0/decompress_arm64.s @@ -0,0 +1,851 @@ +// Code generated by command: go run gen.go -out ../decompress.s -arch amd64,arm64 -pkg=huff0. DO NOT EDIT. +// EXPERIMENTAL arm64 output lowered from an amd64 avo program. + +//go:build arm64 && !appengine && !noasm && gc + +// func decompress4x_main_loop_amd64(ctx *decompress4xContext) +TEXT ·decompress4x_main_loop_arm64(SB), $0-8 + // Preload values + MOVD ctx+0(FP), R0 + MOVBU 8(R0), R6 + MOVD 16(R0), R3 + MOVD 48(R0), R5 + MOVD 24(R0), R7 + MOVD 32(R0), R8 + MOVD (R0), R9 + + // Main loop +main_loop: + MOVD $0, R2 + CMP R5, R3 + CSET GE, R16 + BFI $0, R16, $8, R2 + + // br0.fillFast32() + MOVD 32(R9), R10 + MOVBU 40(R9), R11 + CMP $0x20, R11 + BLS skip_fill0 + MOVD 24(R9), R0 + SUB $0x20, R11, R11 + SUB $0x04, R0, R0 + MOVD (R9), R12 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R12, R0, R15 + MOVWU (R15), R12 + MOVD R11, R1 + LSL R1, R12, R12 + MOVD R0, 24(R9) + ORR R12, R10, R10 + + // exhausted += (br0.off < 4) + CMP $0x04, R0 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill0: + // val0 := br0.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br0.peekTopBits(peekBits) + MOVD R6, R1 + MOVD R10, R12 + LSR R1, R12, R12 + + // v1 := table[val1&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v1.entry)) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // these two writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + MOVH R0, (R3) + + // update the bitreader structure + MOVD R10, 32(R9) + MOVB R11, 40(R9) + + // br1.fillFast32() + MOVD 80(R9), R10 + MOVBU 88(R9), R11 + CMP $0x20, R11 + BLS skip_fill1 + MOVD 72(R9), R0 + SUB $0x20, R11, R11 + SUB $0x04, R0, R0 + MOVD 48(R9), R12 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R12, R0, R15 + MOVWU (R15), R12 + MOVD R11, R1 + LSL R1, R12, R12 + MOVD R0, 72(R9) + ORR R12, R10, R10 + + // exhausted += (br1.off < 4) + CMP $0x04, R0 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill1: + // val0 := br1.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br1.peekTopBits(peekBits) + MOVD R6, R1 + MOVD R10, R12 + LSR R1, R12, R12 + + // v1 := table[val1&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v1.entry)) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // these two writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + ADD R7, R3, R15 + MOVH R0, (R15) + + // update the bitreader structure + MOVD R10, 80(R9) + MOVB R11, 88(R9) + + // br2.fillFast32() + MOVD 128(R9), R10 + MOVBU 136(R9), R11 + CMP $0x20, R11 + BLS skip_fill2 + MOVD 120(R9), R0 + SUB $0x20, R11, R11 + SUB $0x04, R0, R0 + MOVD 96(R9), R12 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R12, R0, R15 + MOVWU (R15), R12 + MOVD R11, R1 + LSL R1, R12, R12 + MOVD R0, 120(R9) + ORR R12, R10, R10 + + // exhausted += (br2.off < 4) + CMP $0x04, R0 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill2: + // val0 := br2.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br2.peekTopBits(peekBits) + MOVD R6, R1 + MOVD R10, R12 + LSR R1, R12, R12 + + // v1 := table[val1&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v1.entry)) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // these two writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + ADD R7<<1, R3, R15 + MOVH R0, (R15) + + // update the bitreader structure + MOVD R10, 128(R9) + MOVB R11, 136(R9) + + // br3.fillFast32() + MOVD 176(R9), R10 + MOVBU 184(R9), R11 + CMP $0x20, R11 + BLS skip_fill3 + MOVD 168(R9), R0 + SUB $0x20, R11, R11 + SUB $0x04, R0, R0 + MOVD 144(R9), R12 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R12, R0, R15 + MOVWU (R15), R12 + MOVD R11, R1 + LSL R1, R12, R12 + MOVD R0, 168(R9) + ORR R12, R10, R10 + + // exhausted += (br3.off < 4) + CMP $0x04, R0 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill3: + // val0 := br3.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br3.peekTopBits(peekBits) + MOVD R6, R1 + MOVD R10, R12 + LSR R1, R12, R12 + + // v1 := table[val1&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v1.entry)) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // these two writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + ADD R7<<1, R7, R1 + ADD R1, R3, R15 + MOVH R0, (R15) + + // update the bitreader structure + MOVD R10, 176(R9) + MOVB R11, 184(R9) + ADD $0x02, R3, R3 + AND $0xff, R2, R15 + AND $0xff, R2, R16 + TST R16, R15 + BEQ main_loop + MOVD ctx+0(FP), R0 + MOVD 16(R0), R16 + SUB R16, R3, R3 + LSL $0x02, R3, R3 + MOVD R3, 40(R0) + RET + +// func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext) +TEXT ·decompress4x_8b_main_loop_arm64(SB), $0-8 + // Preload values + MOVD ctx+0(FP), R1 + MOVBU 8(R1), R6 + MOVD 16(R1), R3 + MOVD 48(R1), R5 + MOVD 24(R1), R7 + MOVD 32(R1), R8 + MOVD (R1), R9 + + // Main loop +main_loop: + MOVD $0, R2 + CMP R5, R3 + CSET GE, R16 + BFI $0, R16, $8, R2 + + // br0.fillFast32() + MOVD 32(R9), R10 + MOVBU 40(R9), R11 + CMP $0x20, R11 + BLS skip_fill0 + MOVD 24(R9), R12 + SUB $0x20, R11, R11 + SUB $0x04, R12, R12 + MOVD (R9), R13 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R13, R12, R15 + MOVWU (R15), R13 + MOVD R11, R1 + LSL R1, R13, R13 + MOVD R12, 24(R9) + ORR R13, R10, R10 + + // exhausted += (br0.off < 4) + CMP $0x04, R12 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill0: + // val0 := br0.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br0.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v1 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v1.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // val2 := br0.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v2 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v2.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val3 := br0.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v3 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br0.advance(uint8(v3.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // these four writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + // out[id * dstEvery + 3] = uint8(v2.entry >> 8) + // out[id * dstEvery + 4] = uint8(v3.entry >> 8) + MOVW R0, (R3) + + // update the bitreader structure + MOVD R10, 32(R9) + MOVB R11, 40(R9) + + // br1.fillFast32() + MOVD 80(R9), R10 + MOVBU 88(R9), R11 + CMP $0x20, R11 + BLS skip_fill1 + MOVD 72(R9), R12 + SUB $0x20, R11, R11 + SUB $0x04, R12, R12 + MOVD 48(R9), R13 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R13, R12, R15 + MOVWU (R15), R13 + MOVD R11, R1 + LSL R1, R13, R13 + MOVD R12, 72(R9) + ORR R13, R10, R10 + + // exhausted += (br1.off < 4) + CMP $0x04, R12 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill1: + // val0 := br1.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br1.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v1 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v1.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // val2 := br1.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v2 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v2.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val3 := br1.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v3 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br1.advance(uint8(v3.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // these four writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + // out[id * dstEvery + 3] = uint8(v2.entry >> 8) + // out[id * dstEvery + 4] = uint8(v3.entry >> 8) + ADD R7, R3, R15 + MOVW R0, (R15) + + // update the bitreader structure + MOVD R10, 80(R9) + MOVB R11, 88(R9) + + // br2.fillFast32() + MOVD 128(R9), R10 + MOVBU 136(R9), R11 + CMP $0x20, R11 + BLS skip_fill2 + MOVD 120(R9), R12 + SUB $0x20, R11, R11 + SUB $0x04, R12, R12 + MOVD 96(R9), R13 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R13, R12, R15 + MOVWU (R15), R13 + MOVD R11, R1 + LSL R1, R13, R13 + MOVD R12, 120(R9) + ORR R13, R10, R10 + + // exhausted += (br2.off < 4) + CMP $0x04, R12 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill2: + // val0 := br2.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br2.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v1 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v1.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // val2 := br2.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v2 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v2.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val3 := br2.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v3 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br2.advance(uint8(v3.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // these four writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + // out[id * dstEvery + 3] = uint8(v2.entry >> 8) + // out[id * dstEvery + 4] = uint8(v3.entry >> 8) + ADD R7<<1, R3, R15 + MOVW R0, (R15) + + // update the bitreader structure + MOVD R10, 128(R9) + MOVB R11, 136(R9) + + // br3.fillFast32() + MOVD 176(R9), R10 + MOVBU 184(R9), R11 + CMP $0x20, R11 + BLS skip_fill3 + MOVD 168(R9), R12 + SUB $0x20, R11, R11 + SUB $0x04, R12, R12 + MOVD 144(R9), R13 + + // b.value |= uint64(low) << (b.bitsRead & 63) + ADD R13, R12, R15 + MOVWU (R15), R13 + MOVD R11, R1 + LSL R1, R13, R13 + MOVD R12, 168(R9) + ORR R13, R10, R10 + + // exhausted += (br3.off < 4) + CMP $0x04, R12 + CSINC HS, R2, R2, R16 + BFI $0, R16, $8, R2 + +skip_fill3: + // val0 := br3.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v0 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v0.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val1 := br3.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v1 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v1.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // val2 := br3.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v2 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v2.entry) + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + + // val3 := br3.peekTopBits(peekBits) + MOVD R10, R12 + MOVD R6, R1 + LSR R1, R12, R12 + + // v3 := table[val0&mask] + ADD R12<<1, R8, R15 + MOVHU (R15), R1 + + // br3.advance(uint8(v3.entry) + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + LSL R1, R10, R10 + ADD R1, R11, R15 + BFI $0, R15, $8, R11 + REVW R0, R0 + + // these four writes get coalesced + // out[id * dstEvery + 0] = uint8(v0.entry >> 8) + // out[id * dstEvery + 1] = uint8(v1.entry >> 8) + // out[id * dstEvery + 3] = uint8(v2.entry >> 8) + // out[id * dstEvery + 4] = uint8(v3.entry >> 8) + ADD R7<<1, R7, R1 + ADD R1, R3, R15 + MOVW R0, (R15) + + // update the bitreader structure + MOVD R10, 176(R9) + MOVB R11, 184(R9) + ADD $0x04, R3, R3 + AND $0xff, R2, R15 + AND $0xff, R2, R16 + TST R16, R15 + BEQ main_loop + MOVD ctx+0(FP), R0 + MOVD 16(R0), R16 + SUB R16, R3, R3 + LSL $0x02, R3, R3 + MOVD R3, 40(R0) + RET + +// func decompress1x_main_loop_amd64(ctx *decompress1xContext) +TEXT ·decompress1x_main_loop_arm64(SB), $0-8 + MOVD ctx+0(FP), R1 + MOVD 16(R1), R2 + MOVD 24(R1), R3 + CMP $0x04, R3 + BLO error_max_decoded_size_exceeded + ADD R3, R2, R3 + MOVD (R1), R5 + MOVD (R5), R7 + MOVD 24(R5), R8 + MOVD 32(R5), R9 + MOVBU 40(R5), R10 + MOVD 32(R1), R5 + MOVBU 8(R1), R6 + JMP loop_condition + +main_loop: + // Check if we have room for 4 bytes in the output buffer + ADD $4, R2, R1 + CMP R3, R1 + BGE error_max_decoded_size_exceeded + + // Decode 4 values + CMP $0x20, R10 + BLT bitReader_fillFast_1_end + SUB $0x20, R10, R10 + SUB $0x04, R8, R8 + ADD R8, R7, R15 + MOVWU (R15), R11 + MOVD R10, R1 + LSL R1, R11, R11 + ORR R11, R9, R9 + +bitReader_fillFast_1_end: + MOVD R6, R1 + MOVD R9, R11 + LSR R1, R11, R11 + ADD R11<<1, R5, R15 + MOVHU (R15), R1 + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + MOVBU R1, R1 + ADD R1, R10, R10 + LSL R1, R9, R9 + MOVD R6, R1 + MOVD R9, R11 + LSR R1, R11, R11 + ADD R11<<1, R5, R15 + MOVHU (R15), R1 + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + MOVBU R1, R1 + ADD R1, R10, R10 + LSL R1, R9, R9 + REVW R0, R0 + CMP $0x20, R10 + BLT bitReader_fillFast_2_end + SUB $0x20, R10, R10 + SUB $0x04, R8, R8 + ADD R8, R7, R15 + MOVWU (R15), R11 + MOVD R10, R1 + LSL R1, R11, R11 + ORR R11, R9, R9 + +bitReader_fillFast_2_end: + MOVD R6, R1 + MOVD R9, R11 + LSR R1, R11, R11 + ADD R11<<1, R5, R15 + MOVHU (R15), R1 + UBFX $8, R1, $8, R16 + BFI $8, R16, $8, R0 + MOVBU R1, R1 + ADD R1, R10, R10 + LSL R1, R9, R9 + MOVD R6, R1 + MOVD R9, R11 + LSR R1, R11, R11 + ADD R11<<1, R5, R15 + MOVHU (R15), R1 + UBFX $8, R1, $8, R16 + BFI $0, R16, $8, R0 + MOVBU R1, R1 + ADD R1, R10, R10 + LSL R1, R9, R9 + REVW R0, R0 + + // Store the decoded values + MOVW R0, (R2) + ADD $0x04, R2, R2 + +loop_condition: + CMP $0x08, R8 + BGE main_loop + + // Update ctx structure + MOVD ctx+0(FP), R0 + MOVD 16(R0), R16 + SUB R16, R2, R2 + MOVD R2, 40(R0) + MOVD (R0), R0 + MOVD R8, 24(R0) + MOVD R9, 32(R0) + MOVB R10, 40(R0) + RET + + // Report error +error_max_decoded_size_exceeded: + MOVD ctx+0(FP), R0 + MOVD $-1, R1 + MOVD R1, 40(R0) + RET + +// skipped decompress1x_main_loop_bmi2 (generic twin preferred on arm64) diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_asm.go b/vendor/github.com/klauspost/compress/huff0/decompress_asm.go new file mode 100644 index 000000000000..4854dd43653e --- /dev/null +++ b/vendor/github.com/klauspost/compress/huff0/decompress_asm.go @@ -0,0 +1,193 @@ +//go:build (amd64 || arm64) && !appengine && !noasm && gc + +// This file contains the specialisation of Decoder.Decompress4X +// and Decoder.Decompress1X that use an asm implementation of their main loops. +// The asm function stubs and any per-arch dispatch live in decompress_amd64.go +// and decompress_arm64.go. +package huff0 + +import ( + "errors" + "fmt" +) + +// fallback8BitSize is the size where using Go version is faster. +const fallback8BitSize = 800 + +type decompress4xContext struct { + pbr *[4]bitReaderShifted + peekBits uint8 + out *byte + dstEvery int + tbl *dEntrySingle + decoded int + limit *byte +} + +// Decompress4X will decompress a 4X encoded stream. +// The length of the supplied input must match the end of a block exactly. +// The *capacity* of the dst slice must match the destination size of +// the uncompressed data exactly. +func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) { + if len(d.dt.single) == 0 { + return nil, errors.New("no table loaded") + } + if len(src) < 6+(4*1) { + return nil, errors.New("input too small") + } + + use8BitTables := d.actualTableLog <= 8 + if cap(dst) < fallback8BitSize && use8BitTables { + return d.decompress4X8bit(dst, src) + } + + var br [4]bitReaderShifted + // Decode "jump table" + start := 6 + for i := range 3 { + length := int(src[i*2]) | (int(src[i*2+1]) << 8) + if start+length >= len(src) { + return nil, errors.New("truncated input (or invalid offset)") + } + err := br[i].init(src[start : start+length]) + if err != nil { + return nil, err + } + start += length + } + err := br[3].init(src[start:]) + if err != nil { + return nil, err + } + + // destination, offset to match first output + dstSize := cap(dst) + dst = dst[:dstSize] + out := dst + dstEvery := (dstSize + 3) / 4 + + const tlSize = 1 << tableLogMax + const tlMask = tlSize - 1 + single := d.dt.single[:tlSize] + + var decoded int + + if len(out) > 4*4 && !(br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4) { + ctx := decompress4xContext{ + pbr: &br, + peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast() + out: &out[0], + dstEvery: dstEvery, + tbl: &single[0], + limit: &out[dstEvery-4], // Always stop decoding when first buffer gets here to avoid writing OOB on last. + } + if use8BitTables { + decompress4x_8b_main_loop_asm(&ctx) + } else { + decompress4x_main_loop_asm(&ctx) + } + + decoded = ctx.decoded + out = out[decoded/4:] + } + + // Decode remaining. + remainBytes := dstEvery - (decoded / 4) + for i := range br { + offset := dstEvery * i + endsAt := min(offset+remainBytes, len(out)) + br := &br[i] + bitsLeft := br.remaining() + for bitsLeft > 0 { + br.fill() + if offset >= endsAt { + return nil, errors.New("corruption detected: stream overrun 4") + } + + // Read value and increment offset. + val := br.peekBitsFast(d.actualTableLog) + v := single[val&tlMask].entry + nBits := uint8(v) + br.advance(nBits) + bitsLeft -= uint(nBits) + out[offset] = uint8(v >> 8) + offset++ + } + if offset != endsAt { + return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt) + } + decoded += offset - dstEvery*i + err = br.close() + if err != nil { + return nil, err + } + } + if dstSize != decoded { + return nil, errors.New("corruption detected: short output block") + } + return dst, nil +} + +type decompress1xContext struct { + pbr *bitReaderShifted + peekBits uint8 + out *byte + outCap int + tbl *dEntrySingle + decoded int +} + +// Error reported by asm implementations +const error_max_decoded_size_exeeded = -1 + +// Decompress1X will decompress a 1X encoded stream. +// The cap of the output buffer will be the maximum decompressed size. +// The length of the supplied input must match the end of a block exactly. +func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) { + if len(d.dt.single) == 0 { + return nil, errors.New("no table loaded") + } + var br bitReaderShifted + err := br.init(src) + if err != nil { + return dst, err + } + maxDecodedSize := cap(dst) + dst = dst[:maxDecodedSize] + + const tlSize = 1 << tableLogMax + const tlMask = tlSize - 1 + + if maxDecodedSize >= 4 { + ctx := decompress1xContext{ + pbr: &br, + out: &dst[0], + outCap: maxDecodedSize, + peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast() + tbl: &d.dt.single[0], + } + + decompress1x_main_loop_asm(&ctx) + if ctx.decoded == error_max_decoded_size_exeeded { + return nil, ErrMaxDecodedSizeExceeded + } + + dst = dst[:ctx.decoded] + } + + // br < 8, so uint8 is fine + bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead + for bitsLeft > 0 { + br.fill() + if len(dst) >= maxDecodedSize { + br.close() + return nil, ErrMaxDecodedSizeExceeded + } + v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask] + nBits := uint8(v.entry) + br.advance(nBits) + bitsLeft -= nBits + dst = append(dst, uint8(v.entry>>8)) + } + return dst, br.close() +} diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_generic.go b/vendor/github.com/klauspost/compress/huff0/decompress_generic.go index 610392322240..e1bca5c686e5 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_generic.go +++ b/vendor/github.com/klauspost/compress/huff0/decompress_generic.go @@ -1,4 +1,4 @@ -//go:build !amd64 || appengine || !gc || noasm +//go:build (!amd64 && !arm64) || appengine || !gc || noasm // This file contains a generic implementation of Decoder.Decompress4X. package huff0 diff --git a/vendor/github.com/klauspost/compress/internal/snapref/decode.go b/vendor/github.com/klauspost/compress/internal/snapref/decode.go index a2c82fcd2263..584b7574b208 100644 --- a/vendor/github.com/klauspost/compress/internal/snapref/decode.go +++ b/vendor/github.com/klauspost/compress/internal/snapref/decode.go @@ -31,7 +31,7 @@ func DecodedLen(src []byte) (int, error) { // that the length header occupied. func decodedLen(src []byte) (blockLen, headerLen int, err error) { v, n := binary.Uvarint(src) - if n <= 0 || v > 0xffffffff { + if n <= 0 || n > 5 || v > 0xffffffff { return 0, 0, ErrCorrupt } diff --git a/vendor/github.com/klauspost/compress/zstd/README.md b/vendor/github.com/klauspost/compress/zstd/README.md index c11d7fa28e32..a5aeeaed06f5 100644 --- a/vendor/github.com/klauspost/compress/zstd/README.md +++ b/vendor/github.com/klauspost/compress/zstd/README.md @@ -75,14 +75,47 @@ The above is fine for big encodes. However, whenever possible try to *reuse* the To reuse the encoder, you can use the `Reset(io.Writer)` function to change to another output. This will allow the encoder to reuse all resources and avoid wasteful allocations. -Currently stream encoding has 'light' concurrency, meaning up to 2 goroutines can be working on part -of a stream. This is independent of the `WithEncoderConcurrency(n)`, but that is likely to change +By default, stream encoding has 'light' concurrency, meaning up to 2 goroutines can be working on part +of a stream. This is independent of the `WithEncoderConcurrency(n)`, but that is likely to change in the future. So if you want to limit concurrency for future updates, specify the concurrency you would like. If you would like stream encoding to be done without spawning async goroutines, use `WithEncoderConcurrency(1)` which will compress input as each block is completed, blocking on writes until each has completed. +#### Parallel Stream Compression + +For maximum throughput on large streams, use `WithConcurrentBlocks(true)` together with +`WithEncoderConcurrency(n)` where n is the number of CPU cores you want to use. +This splits the input into large sections (jobs) that are compressed simultaneously by multiple goroutines, +similar to how the C zstd library does multithreaded compression. + +```Go +enc, err := zstd.NewWriter(out, + zstd.WithEncoderLevel(zstd.SpeedDefault), + zstd.WithEncoderConcurrency(runtime.GOMAXPROCS(0)), + zstd.WithConcurrentBlocks(true), +) +``` + +Each non-first job receives an overlap prefix from the previous job for match context, +so compression ratio is only marginally affected. Output is flushed in order, +producing a valid single-frame zstd stream. + +Benchmark on 1.8GB GOB stream (AMD Ryzen 9 9950X): + +| Level | 1 thread | 4 threads | 16 threads | 1T ratio | 16T ratio | +|---------|:----------:|:------------------:|:-------------------:|:--------:|:---------:| +| fastest | 783 MB/s | 2950 MB/s (3.8×) | 6939 MB/s (8.9×) | 12.24% | 12.26% | +| default | 728 MB/s | 2533 MB/s (3.5×) | 5340 MB/s (7.3×) | 10.67% | 10.68% | +| better | 434 MB/s | 1105 MB/s (2.5×) | 2206 MB/s (5.1×) | 9.14% | 9.21% | +| best | 129 MB/s | 367 MB/s (2.8×) | 884 MB/s (6.8×) | 8.48% | 8.63% | + +Notes: +* Not compatible with dictionary encoding. +* `Flush()` dispatches the current partial job, so latency-sensitive callers can force output. +* `EncodeAll` is unaffected — it uses its own concurrency via the encoder pool. + You can specify your desired compression level using `WithEncoderLevel()` option. Currently only pre-defined compression settings can be specified. diff --git a/vendor/github.com/klauspost/compress/zstd/blockdec.go b/vendor/github.com/klauspost/compress/zstd/blockdec.go index 2329e996f86e..51f9da03875b 100644 --- a/vendor/github.com/klauspost/compress/zstd/blockdec.go +++ b/vendor/github.com/klauspost/compress/zstd/blockdec.go @@ -400,8 +400,9 @@ func (b *blockDec) decodeLiterals(in []byte, hist *history) (remain []byte, err } } var err error - // Use our out buffer. - huff.MaxDecodedSize = litRegenSize + // Decoder.Decompress* uses cap(dst) for the size limit. Do not write + // MaxDecodedSize on hist.huffTree: with a trained dictionary that + // pointer aliases the shared dict.litEnc and concurrent DecodeAll races. if fourStreams { literals, err = huff.Decoder().Decompress4X(b.literalBuf[:0:litRegenSize], literals) } else { @@ -673,10 +674,6 @@ func (b *blockDec) executeSequences(hist *history) error { hbytes := hist.b if len(hbytes) > hist.windowSize { hbytes = hbytes[len(hbytes)-hist.windowSize:] - // We do not need history anymore. - if hist.dict != nil { - hist.dict.content = nil - } } hist.decoders.windowSize = hist.windowSize hist.decoders.out = b.dst[:0] diff --git a/vendor/github.com/klauspost/compress/zstd/dict.go b/vendor/github.com/klauspost/compress/zstd/dict.go index 2ffbfdf379e6..67f40e791490 100644 --- a/vendor/github.com/klauspost/compress/zstd/dict.go +++ b/vendor/github.com/klauspost/compress/zstd/dict.go @@ -230,7 +230,7 @@ func BuildDict(o BuildDictOptions) ([]byte, error) { } block := blockEnc{lowMem: false} block.init() - enc := encoder(&bestFastEncoder{fastBase: fastBase{maxMatchOff: int32(maxMatchLen), bufferReset: math.MaxInt32 - int32(maxMatchLen*2), lowMem: false}}) + var enc encoder if o.Level != 0 { eOpts := encoderOptions{ level: o.Level, @@ -242,6 +242,7 @@ func BuildDict(o BuildDictOptions) ([]byte, error) { enc = eOpts.encoder() } else { o.Level = SpeedBestCompression + enc = encoder(&bestFastEncoder{fastBase: fastBase{maxMatchOff: int32(maxMatchLen), bufferReset: math.MaxInt32 - int32(maxMatchLen*2), lowMem: false}}) } var ( remain [256]int @@ -295,40 +296,81 @@ func BuildDict(o BuildDictOptions) ([]byte, error) { if offset > 3 { newOffsets[offset-3]++ } else { - newOffsets[uint32(o.Offsets[offset-1])]++ + // Repeat codes reference the training Offsets. Skip unset + // (zero) entries so they are not ranked as real offsets. + prev := o.Offsets[offset-1] + if prev > 0 { + newOffsets[uint32(prev)]++ + } } } } // Find most used offsets. var sortedOffsets []uint32 for k := range newOffsets { + if k == 0 { + continue + } sortedOffsets = append(sortedOffsets, k) } sort.Slice(sortedOffsets, func(i, j int) bool { a, b := sortedOffsets[i], sortedOffsets[j] - if a == b { + ca, cb := newOffsets[a], newOffsets[b] + if ca == cb { // Prefer the longer offset - return sortedOffsets[i] > sortedOffsets[j] + return a > b } - return newOffsets[sortedOffsets[i]] > newOffsets[sortedOffsets[j]] + return ca > cb }) - if len(sortedOffsets) > 3 { - if debug { - print("Offsets:") - for i, v := range sortedOffsets { - if i > 20 { - break - } - printf("[%d: %d],", v, newOffsets[v]) + if debug { + print("Offsets:") + for i, v := range sortedOffsets { + if i > 20 { + break } - println("") + printf("[%d: %d],", v, newOffsets[v]) + } + println("") + } + // Dictionary recent-offsets must be three positive values within the + // history. Ranked matches may be fewer (or empty when only unset + // repeat codes were seen), so fill remaining slots with defaults. + used := make(map[int]bool, 3) + var finalOffsets [3]int + nOff := 0 + for _, v := range sortedOffsets { + iv := int(v) + if iv <= 0 || iv > len(hist) || used[iv] { + continue + } + finalOffsets[nOff] = iv + used[iv] = true + nOff++ + if nOff == 3 { + break } - - sortedOffsets = sortedOffsets[:3] } - for i, v := range sortedOffsets { - o.Offsets[i] = int(v) + for _, def := range []int{1, 4, 8} { + if nOff == 3 { + break + } + if def <= len(hist) && !used[def] { + finalOffsets[nOff] = def + used[def] = true + nOff++ + } + } + for def := 1; nOff < 3 && def <= len(hist); def++ { + if !used[def] { + finalOffsets[nOff] = def + used[def] = true + nOff++ + } + } + if nOff < 3 { + return nil, fmt.Errorf("could not determine 3 valid dictionary offsets (history size %d)", len(hist)) } + o.Offsets = finalOffsets if debug { println("New repeat offsets", o.Offsets) } @@ -336,6 +378,9 @@ func BuildDict(o BuildDictOptions) ([]byte, error) { if nUsed == 0 || seqs == 0 { return nil, fmt.Errorf("%d blocks, %d sequences found", nUsed, seqs) } + if litTotal == 0 { + return nil, errors.New("0 literals found") + } if debug { println("Sequences:", seqs, "Blocks:", nUsed, "Literals:", litTotal) } @@ -516,11 +561,10 @@ func BuildDict(o BuildDictOptions) ([]byte, error) { out.Write(binary.LittleEndian.AppendUint32(nil, uint32(o.Offsets[1]))) out.Write(binary.LittleEndian.AppendUint32(nil, uint32(o.Offsets[2]))) out.Write(hist) + if _, err := loadDict(out.Bytes()); err != nil { + return nil, fmt.Errorf("built dictionary failed validation: %w", err) + } if debug { - _, err := loadDict(out.Bytes()) - if err != nil { - panic(err) - } i, err := InspectDictionary(out.Bytes()) if err != nil { panic(err) diff --git a/vendor/github.com/klauspost/compress/zstd/enc_base.go b/vendor/github.com/klauspost/compress/zstd/enc_base.go index c4de134a7a4d..c4fea575d6b3 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_base.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_base.go @@ -128,6 +128,34 @@ func (e *fastBase) matchlen(s, t int32, src []byte) int32 { return int32(matchLen(src[s:], src[t:])) } +// resetBasePrefix resets the encoder state and loads prefix as initial history. +// This is used for parallel job encoding where non-first jobs need overlap context. +// Rep offsets are set to defaults [1,4,8] (invalidated, matching C behavior). +func (e *fastBase) resetBasePrefix(prefix []byte) { + if e.blk == nil { + e.blk = &blockEnc{lowMem: e.lowMem} + e.blk.init() + } else { + e.blk.reset(nil) + } + e.blk.initNewEncode() + if e.crc == nil { + e.crc = xxhash.New() + } else { + e.crc.Reset() + } + e.blk.dictLitEnc = nil + e.ensureHist(len(prefix) + maxCompressedBlockSize) + // Bump cur so old table entries fall outside the window. + // When cur >= bufferReset, leave it; the first Encode call + // will shift/clear tables, preserving valid prefix entries. + if e.cur < e.bufferReset { + e.cur += e.maxMatchOff + int32(len(e.hist)) + } + e.hist = e.hist[:0] + e.hist = append(e.hist, prefix...) +} + // Reset the encoding table. func (e *fastBase) resetBase(d *dict, singleBlock bool) { if e.blk == nil { diff --git a/vendor/github.com/klauspost/compress/zstd/enc_best.go b/vendor/github.com/klauspost/compress/zstd/enc_best.go index 851799322bd8..c71382dde65f 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_best.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_best.go @@ -551,3 +551,18 @@ func (e *bestFastEncoder) Reset(d *dict, singleBlock bool) { // Reset table to initial state copy(e.table[:], e.dictTable) } + +func (e *bestFastEncoder) ResetPrefix(prefix []byte) { + e.resetBasePrefix(prefix) + if len(prefix) < 8 { + return + } + end := e.cur + int32(len(prefix)) - 8 + for i := e.cur; i < end; i++ { + cv := load6432(prefix, i-e.cur) + h := hashLen(cv, bestLongTableBits, bestLongLen) + e.longTable[h] = prevEntry{offset: i, prev: e.longTable[h].offset} + h0 := hashLen(cv, bestShortTableBits, bestShortLen) + e.table[h0] = prevEntry{offset: i, prev: e.table[h0].offset} + } +} diff --git a/vendor/github.com/klauspost/compress/zstd/enc_better.go b/vendor/github.com/klauspost/compress/zstd/enc_better.go index 3305f09248c0..523d57f3ad64 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_better.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_better.go @@ -1096,6 +1096,20 @@ func (e *betterFastEncoder) Reset(d *dict, singleBlock bool) { } } +func (e *betterFastEncoder) ResetPrefix(prefix []byte) { + e.resetBasePrefix(prefix) + if len(prefix) < 8 { + return + } + end := e.cur + int32(len(prefix)) - 8 + for i := e.cur; i < end; i += 2 { + cv := load6432(prefix, i-e.cur) + h := hashLen(cv, betterLongTableBits, betterLongLen) + e.longTable[h] = prevEntry{offset: i, prev: e.longTable[h].offset} + e.table[hashLen(cv>>8, betterShortTableBits, betterShortLen)] = tableEntry{val: uint32(cv >> 8), offset: i + 1} + } +} + // ResetDict will reset and set a dictionary if not nil func (e *betterFastEncoderDict) Reset(d *dict, singleBlock bool) { e.resetBase(d, singleBlock) @@ -1229,6 +1243,10 @@ func (e *betterFastEncoderDict) Reset(d *dict, singleBlock bool) { e.allDirty = false } +func (e *betterFastEncoderDict) ResetPrefix([]byte) { + panic("ResetPrefix not supported for dict encoders") +} + func (e *betterFastEncoderDict) markLongShardDirty(entryNum uint32) { e.longTableShardDirty[entryNum/betterLongTableShardSize] = true } diff --git a/vendor/github.com/klauspost/compress/zstd/enc_dfast.go b/vendor/github.com/klauspost/compress/zstd/enc_dfast.go index 2fb6da112bcd..712ba7ab5824 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_dfast.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_dfast.go @@ -1037,6 +1037,18 @@ func (e *doubleFastEncoder) Reset(d *dict, singleBlock bool) { } } +func (e *doubleFastEncoder) ResetPrefix(prefix []byte) { + e.fastEncoder.ResetPrefix(prefix) + if len(prefix) < 8 { + return + } + end := e.cur + int32(len(prefix)) - 8 + for i := e.cur + 1; i < end; i += 2 { + cv := load6432(prefix, i-e.cur) + e.longTable[hashLen(cv, dFastLongTableBits, dFastLongLen)] = tableEntry{val: uint32(cv), offset: i} + } +} + // ResetDict will reset and set a dictionary if not nil func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) { allDirty := e.allDirty @@ -1102,6 +1114,10 @@ func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) { } } +func (e *doubleFastEncoderDict) ResetPrefix([]byte) { + panic("ResetPrefix not supported for dict encoders") +} + func (e *doubleFastEncoderDict) markLongShardDirty(entryNum uint32) { e.longTableShardDirty[entryNum/dLongTableShardSize] = true } diff --git a/vendor/github.com/klauspost/compress/zstd/enc_fast.go b/vendor/github.com/klauspost/compress/zstd/enc_fast.go index 5e104f1a4828..06045e24630d 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_fast.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_fast.go @@ -797,6 +797,19 @@ func (e *fastEncoder) Reset(d *dict, singleBlock bool) { } } +func (e *fastEncoder) ResetPrefix(prefix []byte) { + e.resetBasePrefix(prefix) + if len(prefix) < 8 { + return + } + end := e.cur + int32(len(prefix)) - 8 + // Index every 4th + for i := e.cur + 1; i < end; i += 4 { + cv := load6432(prefix, i-e.cur) + e.table[hashLen(cv, tableBits, tableFastHashLen)] = tableEntry{val: uint32(cv), offset: i} + } +} + // ResetDict will reset and set a dictionary if not nil func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) { e.resetBase(d, singleBlock) @@ -866,6 +879,10 @@ func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) { e.allDirty = false } +func (e *fastEncoderDict) ResetPrefix([]byte) { + panic("ResetPrefix not supported for dict encoders") +} + func (e *fastEncoderDict) markAllShardsDirty() { e.allDirty = true } diff --git a/vendor/github.com/klauspost/compress/zstd/enc_jobs.go b/vendor/github.com/klauspost/compress/zstd/enc_jobs.go new file mode 100644 index 000000000000..95ce67ac05a7 --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/enc_jobs.go @@ -0,0 +1,352 @@ +// Copyright 2019+ Klaus Post. All rights reserved. +// License information can be found in the LICENSE file. +// Based on work by Yann Collet, released under BSD License. + +package zstd + +import ( + "fmt" + rdebug "runtime/debug" + "sync" +) + +type encJob struct { + prefix []byte // overlap from previous job (nil for first) + input []byte // job's own input data (swapped from filling) + last bool // last block of last job gets last=true + output []byte // compressed blocks (filled by worker) + err error // encoding error + done chan struct{} // closed when complete +} + +type jobState struct { + jobSize int + overlapSize int + filling []byte // accumulates input up to jobSize + nextPrefix []byte // overlap prefix prepared for the next dispatched job + + jobSeq int // next job sequence number + + jobCh chan *encJob // dispatch to workers + resultCh chan *encJob // ordered results to flusher + + workerWg sync.WaitGroup + flusherWg sync.WaitGroup + + mu sync.Mutex + flushedSeq int // last flushed sequence number + cond *sync.Cond + + flusherErr error + started bool + + inputPool sync.Pool // *[]byte buffers of jobSize cap + outputPool sync.Pool // *[]byte buffers for compressed output + overlapPool sync.Pool // *[]byte buffers for overlap prefixes +} + +func (e *Encoder) startJobWorkers() { + js := &e.state.jobs + n := e.o.concurrent + js.jobCh = make(chan *encJob, n) + js.resultCh = make(chan *encJob, n) + js.flushedSeq = 0 + js.cond = sync.NewCond(&js.mu) + + // Workers borrow encoders from the shared e.encoders pool per-job. + // Ensure the pool is initialized before any worker tries to borrow. + e.init.Do(e.initialize) + + for range n { + js.workerWg.Add(1) + go e.jobWorker() + } + js.flusherWg.Add(1) + go e.jobFlusher() + js.started = true +} + +func (e *Encoder) jobWorker() { + js := &e.state.jobs + defer js.workerWg.Done() + for job := range js.jobCh { + enc := <-e.encoders + e.compressJob(enc, job) + e.encoders <- enc + close(job.done) + } +} + +func (e *Encoder) compressJob(enc encoder, job *encJob) { + defer func() { + if r := recover(); r != nil { + job.err = fmt.Errorf("panic in parallel job: %v", r) + rdebug.PrintStack() + } + }() + + if len(job.prefix) > 0 { + enc.ResetPrefix(job.prefix) + } else { + enc.Reset(nil, false) + } + + data := job.input + if len(data) == 0 && job.last { + blk := enc.Block() + blk.reset(nil) + blk.last = true + blk.encodeRaw(nil) + job.output = append(job.output, blk.output...) + return + } + + blk := enc.Block() + for len(data) > 0 { + todo := data + if len(todo) > e.o.blockSize { + todo = todo[:e.o.blockSize] + } + data = data[len(todo):] + + blk.pushOffsets() + enc.Encode(blk, todo) + blk.last = len(data) == 0 && job.last + + err := blk.encode(todo, e.o.noEntropy, !e.o.allLitEntropy) + if err != nil { + job.err = err + return + } + job.output = append(job.output, blk.output...) + blk.reset(nil) + } +} + +func (js *jobState) getInputBuf(size int) []byte { + if v := js.inputPool.Get(); v != nil { + bp := v.(*[]byte) + b := *bp + if cap(b) >= size { + return b[:0] + } + } + return make([]byte, 0, size) +} + +func (js *jobState) putInputBuf(b []byte) { + if cap(b) > 0 { + b = b[:0] + js.inputPool.Put(&b) + } +} + +func (js *jobState) getOutputBuf(size int) []byte { + if v := js.outputPool.Get(); v != nil { + bp := v.(*[]byte) + b := *bp + if cap(b) >= size { + return b[:0] + } + } + return make([]byte, 0, size) +} + +func (js *jobState) putOutputBuf(b []byte) { + if cap(b) > 0 { + b = b[:0] + js.outputPool.Put(&b) + } +} + +func (js *jobState) getOverlapBuf(size int) []byte { + if v := js.overlapPool.Get(); v != nil { + bp := v.(*[]byte) + b := *bp + if cap(b) >= size { + return b[:size] + } + } + return make([]byte, size) +} + +func (js *jobState) putOverlapBuf(b []byte) { + if cap(b) > 0 { + b = b[:0] + js.overlapPool.Put(&b) + } +} + +func (e *Encoder) jobFlusher() { + js := &e.state.jobs + defer js.flusherWg.Done() + for job := range js.resultCh { + <-job.done + // Worker has fully exited compressJob, so the prefix is no longer + // in use. Return it to the pool regardless of outcome. + if job.prefix != nil { + js.putOverlapBuf(job.prefix) + job.prefix = nil + } + if job.err != nil { + js.mu.Lock() + js.flusherErr = job.err + js.cond.Broadcast() + js.mu.Unlock() + for range js.resultCh { + } + return + } + if len(job.output) > 0 { + _, err := e.state.w.Write(job.output) + if err != nil { + js.mu.Lock() + js.flusherErr = err + js.cond.Broadcast() + js.mu.Unlock() + for range js.resultCh { + } + return + } + e.state.nWritten += int64(len(job.output)) + } + // Return buffers to pools. + js.putInputBuf(job.input) + js.putOutputBuf(job.output) + job.input = nil + job.output = nil + + js.mu.Lock() + js.flushedSeq++ + js.cond.Broadcast() + js.mu.Unlock() + } +} + +func (e *Encoder) shutdownJobWorkers() { + js := &e.state.jobs + if !js.started { + return + } + close(js.jobCh) + js.workerWg.Wait() + close(js.resultCh) + js.flusherWg.Wait() + js.started = false +} + +// waitAllJobs blocks until all dispatched jobs have been flushed. +func (e *Encoder) waitAllJobs() { + js := &e.state.jobs + if !js.started { + return + } + js.mu.Lock() + for js.flushedSeq < js.jobSeq && js.flusherErr == nil { + js.cond.Wait() + } + js.mu.Unlock() +} + +func (e *Encoder) dispatchJob(final bool) error { + s := &e.state + js := &s.jobs + + js.mu.Lock() + fErr := js.flusherErr + js.mu.Unlock() + if fErr != nil { + return fErr + } + + if !s.headerWritten { + // Single-block optimization: fall through to encodeAll path. + if final && len(js.filling) > 0 && len(js.filling) <= e.o.blockSize { + s.current = e.encodeAll(s.encoder, js.filling, s.current[:0]) + var n2 int + n2, s.err = s.w.Write(s.current) + if s.err != nil { + return s.err + } + s.nWritten += int64(n2) + s.nInput += int64(len(js.filling)) + s.current = s.current[:0] + js.filling = js.filling[:0] + s.headerWritten = true + s.fullFrameWritten = true + s.eofWritten = true + return nil + } + if final && len(js.filling) == 0 && !e.o.fullZero { + s.headerWritten = true + s.fullFrameWritten = true + s.eofWritten = true + return nil + } + + var tmp [maxHeaderSize]byte + fh := frameHeader{ + ContentSize: uint64(s.frameContentSize), + WindowSize: uint32(s.encoder.WindowSize(s.frameContentSize)), + SingleSegment: false, + Checksum: e.o.crc, + DictID: 0, + } + dst := fh.appendTo(tmp[:0]) + var n2 int + n2, s.err = s.w.Write(dst) + if s.err != nil { + return s.err + } + s.nWritten += int64(n2) + s.headerWritten = true + } + + if len(js.filling) == 0 && !final { + return nil + } + + if !js.started { + e.startJobWorkers() + } + + // Estimate output size for pooled buffer. + outputEst := max(len(js.filling)/2, 512) + + job := &encJob{ + last: final, + done: make(chan struct{}), + output: js.getOutputBuf(outputEst), + } + + // Each job owns its prefix slice; the flusher returns it to the pool + // after <-job.done, so workers and dispatch never share a buffer. + if js.nextPrefix != nil { + job.prefix = js.nextPrefix + js.nextPrefix = nil + } + + // Build the next job's prefix from the tail of this job's input. + if !final && len(js.filling) > 0 { + overlapLen := min(js.overlapSize, len(js.filling)) + np := js.getOverlapBuf(overlapLen) + copy(np, js.filling[len(js.filling)-overlapLen:]) + js.nextPrefix = np + } + + // Swap filling buffer into job — zero-copy for the input data. + job.input = js.filling + js.filling = js.getInputBuf(js.jobSize) + + s.nInput += int64(len(job.input)) + js.jobSeq++ + + if final { + s.eofWritten = true + } + + js.resultCh <- job + js.jobCh <- job + + return nil +} diff --git a/vendor/github.com/klauspost/compress/zstd/encoder.go b/vendor/github.com/klauspost/compress/zstd/encoder.go index 0f2a00a00332..6ee96d8730ca 100644 --- a/vendor/github.com/klauspost/compress/zstd/encoder.go +++ b/vendor/github.com/klauspost/compress/zstd/encoder.go @@ -38,6 +38,7 @@ type encoder interface { WindowSize(size int64) int32 UseBlock(*blockEnc) Reset(d *dict, singleBlock bool) + ResetPrefix(prefix []byte) } type encoderState struct { @@ -60,6 +61,9 @@ type encoderState struct { wg sync.WaitGroup // This waitgroup indicates we have a block encoding/writing. wWg sync.WaitGroup + + // Parallel job state (used when concurrentBlocks is enabled). + jobs jobState } // NewWriter will create a new Zstandard encoder. @@ -74,6 +78,9 @@ func NewWriter(w io.Writer, opts ...EOption) (*Encoder, error) { return nil, err } } + if e.o.concurrentBlocks && (e.o.dict != nil || e.o.concurrent <= 1) { + e.o.concurrentBlocks = false + } if w != nil { e.Reset(w) } @@ -95,12 +102,31 @@ func (e *Encoder) initialize() { // as a new, independent stream. func (e *Encoder) Reset(w io.Writer) { s := &e.state + + if e.o.concurrentBlocks { + e.shutdownJobWorkers() + js := &s.jobs + js.jobSize = e.o.jobSize() + js.overlapSize = e.o.overlapSize() + // js.filling is allocated lazily on first Write/ReadFrom so callers + // that only use EncodeAll don't pay the (up to ~32 MB) jobSize cost. + js.filling = js.filling[:0] + if js.nextPrefix != nil { + js.putOverlapBuf(js.nextPrefix) + js.nextPrefix = nil + } + js.jobSeq = 0 + js.flushedSeq = 0 + js.flusherErr = nil + js.started = false + } + s.wg.Wait() s.wWg.Wait() if cap(s.filling) == 0 { s.filling = make([]byte, 0, e.o.blockSize) } - if e.o.concurrent > 1 { + if e.o.concurrent > 1 && !e.o.concurrentBlocks { if cap(s.current) == 0 { s.current = make([]byte, 0, e.o.blockSize) } @@ -145,6 +171,9 @@ func (e *Encoder) ResetWithOptions(w io.Writer, opts ...EOption) error { } } hasDict := e.o.dict != nil + if e.o.concurrentBlocks && hasDict { + e.o.concurrentBlocks = false + } if hadDict != hasDict { // Dict presence changed — encoder type must be recreated. e.state.encoder = nil @@ -176,6 +205,49 @@ func (e *Encoder) Write(p []byte) (n int, err error) { if s.eofWritten { return 0, ErrEncoderClosed } + if e.o.concurrentBlocks { + return e.writeJobs(p) + } + return e.writeBlocks(p) +} + +func (e *Encoder) writeJobs(p []byte) (n int, err error) { + s := &e.state + js := &s.jobs + jobSize := js.jobSize + if cap(js.filling) == 0 && len(p) > 0 { + js.filling = make([]byte, 0, jobSize) + } + for len(p) > 0 { + if len(p)+len(js.filling) < jobSize { + if e.o.crc { + _, _ = s.encoder.CRC().Write(p) + } + js.filling = append(js.filling, p...) + return n + len(p), nil + } + add := p + if len(p)+len(js.filling) > jobSize { + add = add[:jobSize-len(js.filling)] + } + if e.o.crc { + _, _ = s.encoder.CRC().Write(add) + } + js.filling = append(js.filling, add...) + p = p[len(add):] + n += len(add) + if len(js.filling) < jobSize { + return n, nil + } + if err := e.dispatchJob(false); err != nil { + return n, err + } + } + return n, nil +} + +func (e *Encoder) writeBlocks(p []byte) (n int, err error) { + s := &e.state for len(p) > 0 { if len(p)+len(s.filling) < e.o.blockSize { if e.o.crc { @@ -374,6 +446,10 @@ func (e *Encoder) ReadFrom(r io.Reader) (n int64, err error) { println("Using ReadFrom") } + if e.o.concurrentBlocks { + return e.readFromJobs(r) + } + // Flush any current writes. if len(e.state.filling) > 0 { if err := e.nextBlock(false); err != nil { @@ -387,7 +463,6 @@ func (e *Encoder) ReadFrom(r io.Reader) (n int64, err error) { if e.o.crc { _, _ = e.state.encoder.CRC().Write(src[:n2]) } - // src is now the unfilled part... src = src[n2:] n += int64(n2) switch err { @@ -420,15 +495,63 @@ func (e *Encoder) ReadFrom(r io.Reader) (n int64, err error) { } } +func (e *Encoder) readFromJobs(r io.Reader) (n int64, err error) { + js := &e.state.jobs + jobSize := js.jobSize + + // Flush any current filling. + if len(js.filling) > 0 { + if err := e.dispatchJob(false); err != nil { + return 0, err + } + } + + if cap(js.filling) < jobSize { + js.filling = make([]byte, 0, jobSize) + } + js.filling = js.filling[:jobSize] + src := js.filling + for { + n2, err := r.Read(src) + if e.o.crc { + _, _ = e.state.encoder.CRC().Write(src[:n2]) + } + src = src[n2:] + n += int64(n2) + switch err { + case io.EOF: + js.filling = js.filling[:len(js.filling)-len(src)] + return n, nil + case nil: + default: + e.state.err = err + return n, err + } + if len(src) > 0 { + continue + } + if err = e.dispatchJob(false); err != nil { + return n, err + } + if cap(js.filling) < jobSize { + js.filling = make([]byte, 0, jobSize) + } + js.filling = js.filling[:jobSize] + src = js.filling + } +} + // Flush will send the currently written data to output // and block until everything has been written. // This should only be used on rare occasions where pushing the currently queued data is critical. func (e *Encoder) Flush() error { s := &e.state + if e.o.concurrentBlocks { + return e.flushJobs() + } if len(s.filling) > 0 { err := e.nextBlock(false) if err != nil { - // Ignore Flush after Close. if errors.Is(s.err, ErrEncoderClosed) { return nil } @@ -438,7 +561,6 @@ func (e *Encoder) Flush() error { s.wg.Wait() s.wWg.Wait() if s.err != nil { - // Ignore Flush after Close. if errors.Is(s.err, ErrEncoderClosed) { return nil } @@ -447,6 +569,20 @@ func (e *Encoder) Flush() error { return s.writeErr } +func (e *Encoder) flushJobs() error { + js := &e.state.jobs + if len(js.filling) > 0 { + if err := e.dispatchJob(false); err != nil { + return err + } + } + e.waitAllJobs() + js.mu.Lock() + fErr := js.flusherErr + js.mu.Unlock() + return fErr +} + // Close will flush the final output and close the stream. // The function will block until everything has been written. // The Encoder can still be re-used after calling this. @@ -455,12 +591,16 @@ func (e *Encoder) Close() error { if s.encoder == nil { return nil } + if e.o.concurrentBlocks { + return e.closeJobs() + } if s.w == nil { if len(s.filling) == 0 && !s.headerWritten && !s.eofWritten && s.nInput == 0 { return nil } return errors.New("zstd: encoder has no writer") } + err := e.nextBlock(true) if err != nil { if errors.Is(s.err, ErrEncoderClosed) { @@ -511,6 +651,68 @@ func (e *Encoder) Close() error { return s.err } +func (e *Encoder) closeJobs() error { + s := &e.state + js := &s.jobs + + if errors.Is(s.err, ErrEncoderClosed) { + return nil + } + + if s.w == nil { + if len(js.filling) == 0 && !s.headerWritten && !s.eofWritten && s.nInput == 0 { + return nil + } + return errors.New("zstd: encoder has no writer") + } + + if err := e.dispatchJob(true); err != nil { + e.shutdownJobWorkers() + if errors.Is(s.err, ErrEncoderClosed) { + return nil + } + return err + } + + if s.frameContentSize > 0 && s.nInput != s.frameContentSize { + e.shutdownJobWorkers() + return fmt.Errorf("frame content size %d given, but %d bytes was written", s.frameContentSize, s.nInput) + } + + if s.fullFrameWritten { + e.shutdownJobWorkers() + s.err = ErrEncoderClosed + return nil + } + + e.shutdownJobWorkers() + if js.flusherErr != nil { + return js.flusherErr + } + + // Write CRC + if e.o.crc { + var tmp [4]byte + _, s.err = s.w.Write(s.encoder.AppendCRC(tmp[:0])) + s.nWritten += 4 + } + + // Add padding + if s.err == nil && e.o.pad > 0 { + add := calcSkippableFrame(s.nWritten, int64(e.o.pad)) + frame, err := skippableFrame(js.filling[:0], add, rand.Reader) + if err != nil { + return err + } + _, s.err = s.w.Write(frame) + } + if s.err == nil { + s.err = ErrEncoderClosed + return nil + } + return s.err +} + // EncodeAll will encode all input in src and append it to dst. // This function can be called concurrently, but each call will only run on a single goroutine. // If empty input is given, nothing is returned, unless WithZeroFrames is specified. diff --git a/vendor/github.com/klauspost/compress/zstd/encoder_options.go b/vendor/github.com/klauspost/compress/zstd/encoder_options.go index e217be0a17ac..a80814967396 100644 --- a/vendor/github.com/klauspost/compress/zstd/encoder_options.go +++ b/vendor/github.com/klauspost/compress/zstd/encoder_options.go @@ -14,22 +14,23 @@ type EOption func(*encoderOptions) error // options retains accumulated state of multiple options. type encoderOptions struct { - resetOpt bool - concurrent int - level EncoderLevel - single *bool - pad int - blockSize int - windowSize int - crc bool - fullZero bool - noEntropy bool - allLitEntropy bool - customWindow bool - customALEntropy bool - customBlockSize bool - lowMem bool - dict *dict + resetOpt bool + concurrent int + level EncoderLevel + single *bool + pad int + blockSize int + windowSize int + crc bool + fullZero bool + noEntropy bool + allLitEntropy bool + customWindow bool + customALEntropy bool + customBlockSize bool + lowMem bool + dict *dict + concurrentBlocks bool } func (o *encoderOptions) setDefault() { @@ -333,6 +334,42 @@ func WithLowerEncoderMem(b bool) EOption { } } +// WithConcurrentBlocks enables job-based parallel compression for streams. +// When enabled and concurrent > 1, input is split into large sections (jobs) +// that are compressed simultaneously by multiple goroutines. +// Each non-first job receives an overlap prefix from the previous job for match context. +// Output is flushed in order, producing a valid single-frame zstd stream. +// +// Currently disabled when used with dictionary encoding. +// Cannot be changed with ResetWithOptions. +func WithConcurrentBlocks(b bool) EOption { + return func(o *encoderOptions) error { + if o.resetOpt && b != o.concurrentBlocks { + return errors.New("WithConcurrentBlocks cannot be changed on Reset") + } + o.concurrentBlocks = b + return nil + } +} + +// jobSize returns the input section size per parallel job. +func (o *encoderOptions) jobSize() int { + s := max(o.windowSize*4, 512<<10) + return s +} + +// overlapSize returns the overlap prefix size for parallel jobs. +func (o *encoderOptions) overlapSize() int { + switch o.level { + case SpeedBestCompression: + return o.windowSize / 2 + case SpeedBetterCompression: + return o.windowSize / 4 + default: + return o.windowSize / 8 + } +} + // WithEncoderDict allows to register a dictionary that will be used for the encode. // // The slice dict must be in the [dictionary format] produced by diff --git a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s b/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s index bcde39869535..deeadc49eb03 100644 --- a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s +++ b/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s @@ -1,4 +1,4 @@ -// Code generated by command: go run gen_fse.go -out ../fse_decoder_amd64.s -pkg=zstd. DO NOT EDIT. +// Code generated by command: go run gen_fse.go -out ../fse_decoder.s -arch amd64,arm64 -pkg=zstd. DO NOT EDIT. //go:build !appengine && !noasm && gc && !noasm diff --git a/vendor/github.com/klauspost/compress/zstd/fse_decoder_arm64.s b/vendor/github.com/klauspost/compress/zstd/fse_decoder_arm64.s new file mode 100644 index 000000000000..77ee3913f056 --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/fse_decoder_arm64.s @@ -0,0 +1,153 @@ +// Code generated by command: go run gen_fse.go -out ../fse_decoder.s -arch amd64,arm64 -pkg=zstd. DO NOT EDIT. +// EXPERIMENTAL arm64 output lowered from an amd64 avo program. + +//go:build arm64 && !appengine && !noasm && gc && !noasm + +// func buildDtable_asm(s *fseDecoder, ctx *buildDtableAsmContext) int +TEXT ·buildDtable_asm(SB), $0-24 + MOVD ctx+8(FP), R1 + MOVD s+0(FP), R6 + + // Load values + MOVBU 4098(R6), R2 + MOVD $0, R0 + MOVD $1, R16 + LSL R2, R16, R16 + ORR R16, R0, R0 + MOVD (R1), R3 + MOVD 16(R1), R5 + SUB $1, R0, R7 + MOVD 8(R1), R1 + MOVHU 4096(R6), R6 + + // End load values + // Init, lay down lowprob symbols + MOVD $0, R8 + JMP init_main_loop_condition + +init_main_loop: + ADD R8<<1, R1, R15 + MOVH (R15), R9 + AND $0xffff, R9, R15 + MOVD $-1, R16 + AND $0xffff, R16, R16 + CMP R16, R15 + BNE do_not_update_high_threshold + ADD R7<<3, R5, R15 + MOVB R8, 1(R15) + SUB $1, R7, R7 + MOVD $0x0000000000000001, R9 + +do_not_update_high_threshold: + ADD R8<<1, R3, R15 + MOVH R9, (R15) + ADD $1, R8, R8 + +init_main_loop_condition: + CMP R6, R8 + BLT init_main_loop + + // Spread symbols + // Calculate table step + MOVD R0, R8 + LSR $0x01, R8, R8 + MOVD R0, R9 + LSR $0x03, R9, R9 + ADD R9, R8, R8 + ADD $3, R8, R8 + + // Fill add bits values + SUB $1, R0, R9 + MOVD $0, R10 + MOVD $0, R11 + JMP spread_main_loop_condition + +spread_main_loop: + MOVD $0, R12 + ADD R11<<1, R1, R15 + MOVH (R15), R13 + JMP spread_inner_loop_condition + +spread_inner_loop: + ADD R10<<3, R5, R15 + MOVB R11, 1(R15) + +adjust_position: + ADD R8, R10, R10 + AND R9, R10, R10 + CMP R7, R10 + BGT adjust_position + ADD $1, R12, R12 + +spread_inner_loop_condition: + CMP R13, R12 + BLT spread_inner_loop + ADD $1, R11, R11 + +spread_main_loop_condition: + CMP R6, R11 + BLT spread_main_loop + TST R10, R10 + BEQ spread_check_ok + MOVD ctx+8(FP), R0 + MOVD R10, 24(R0) + MOVD $+1, R16 + MOVD R16, ret+16(FP) + RET + +spread_check_ok: + // Build Decoding table + MOVD $0, R6 + +build_table_main_table: + ADD R6<<3, R5, R15 + MOVBU 1(R15), R1 + ADD R1<<1, R3, R15 + MOVHU (R15), R7 + ADD $1, R7, R8 + ADD R1<<1, R3, R15 + MOVH R8, (R15) + MOVD R7, R8 + CLZ R8, R16 + MOVD $63, R8 + SUB R16, R8, R8 + MOVD R2, R1 + SUB R8, R1, R1 + LSL R1, R7, R7 + SUB R0, R7, R7 + ADD R6<<3, R5, R15 + MOVB R1, (R15) + ADD R6<<3, R5, R15 + MOVH R7, 2(R15) + CMP R0, R7 + BLE build_table_check1_ok + MOVD ctx+8(FP), R1 + MOVD R7, 24(R1) + MOVD R0, 32(R1) + MOVD $+2, R16 + MOVD R16, ret+16(FP) + RET + +build_table_check1_ok: + AND $0xff, R1, R15 + AND $0xff, R1, R16 + TST R16, R15 + BNE build_table_check2_ok + AND $0xffff, R7, R15 + AND $0xffff, R6, R16 + CMP R16, R15 + BNE build_table_check2_ok + MOVD ctx+8(FP), R0 + MOVD R7, 24(R0) + MOVD R6, 32(R0) + MOVD $+3, R16 + MOVD R16, ret+16(FP) + RET + +build_table_check2_ok: + ADD $1, R6, R6 + CMP R0, R6 + BLT build_table_main_table + MOVD $+0, R16 + MOVD R16, ret+16(FP) + RET diff --git a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.go b/vendor/github.com/klauspost/compress/zstd/fse_decoder_asm.go similarity index 81% rename from vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.go rename to vendor/github.com/klauspost/compress/zstd/fse_decoder_asm.go index b8c8607b5dfb..4ffc7e3c9fd5 100644 --- a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.go +++ b/vendor/github.com/klauspost/compress/zstd/fse_decoder_asm.go @@ -1,4 +1,4 @@ -//go:build amd64 && !appengine && !noasm && gc +//go:build (amd64 || arm64) && !appengine && !noasm && gc package zstd @@ -6,6 +6,10 @@ import ( "fmt" ) +// buildDtable_asm is generated by _generate/gen_fse.go and lowered to each +// architecture (amd64 by goasm, arm64 by the avo arm64 lowering printer). The +// Go side is identical across architectures, so it lives here. + type buildDtableAsmContext struct { // inputs stateTable *uint16 @@ -18,7 +22,7 @@ type buildDtableAsmContext struct { errParam2 uint64 } -// buildDtable_asm is an x86 assembly implementation of fseDecoder.buildDtable. +// buildDtable_asm is an assembly implementation of fseDecoder.buildDtable. // Function returns non-zero exit code on error. // //go:noescape diff --git a/vendor/github.com/klauspost/compress/zstd/fse_decoder_generic.go b/vendor/github.com/klauspost/compress/zstd/fse_decoder_generic.go index 2138f8091a99..38fd2ccb2a92 100644 --- a/vendor/github.com/klauspost/compress/zstd/fse_decoder_generic.go +++ b/vendor/github.com/klauspost/compress/zstd/fse_decoder_generic.go @@ -1,4 +1,4 @@ -//go:build !amd64 || appengine || !gc || noasm +//go:build (!amd64 && !arm64) || appengine || !gc || noasm package zstd diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go index 18c3703ddc95..1281da885c50 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go @@ -3,321 +3,83 @@ package zstd import ( - "fmt" - "io" - "github.com/klauspost/compress/internal/cpuinfo" ) -type decodeSyncAsmContext struct { - llTable []decSymbol - mlTable []decSymbol - ofTable []decSymbol - llState uint64 - mlState uint64 - ofState uint64 - iteration int - litRemain int - out []byte - outPosition int - literals []byte - litPosition int - history []byte - windowSize int - ll int // set on error (not for all errors, please refer to _generate/gen.go) - ml int // set on error (not for all errors, please refer to _generate/gen.go) - mo int // set on error (not for all errors, please refer to _generate/gen.go) -} +// The shared decode/decodeSync/executeSimple wrappers and context structs live +// in seqdec_asm.go; this file only declares the amd64 asm routines and the +// dispatch helpers that pick the BMI2 / non-BMI2 (and 56-bit / safe) variant. -// sequenceDecs_decodeSync_amd64 implements the main loop of sequenceDecs.decodeSync in x86 asm. +// sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm. // // Please refer to seqdec_generic.go for the reference implementation. // //go:noescape -func sequenceDecs_decodeSync_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int +func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int -// sequenceDecs_decodeSync_bmi2 implements the main loop of sequenceDecs.decodeSync in x86 asm with BMI2 extensions. +// sequenceDecs_decode_56_amd64 implements the main loop of sequenceDecs in x86 asm. // //go:noescape -func sequenceDecs_decodeSync_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int +func sequenceDecs_decode_56_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int -// sequenceDecs_decodeSync_safe_amd64 does the same as above, but does not write more than output buffer. +// sequenceDecs_decode_bmi2 implements the main loop of sequenceDecs in x86 asm with BMI2 extensions. // //go:noescape -func sequenceDecs_decodeSync_safe_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int +func sequenceDecs_decode_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int -// sequenceDecs_decodeSync_safe_bmi2 does the same as above, but does not write more than output buffer. +// sequenceDecs_decode_56_bmi2 implements the main loop of sequenceDecs in x86 asm with BMI2 extensions. // //go:noescape -func sequenceDecs_decodeSync_safe_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int - -// decode sequences from the stream with the provided history but without a dictionary. -func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) { - if len(s.dict) > 0 { - return false, nil - } - if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSize { - return false, nil - } - - // FIXME: Using unsafe memory copies leads to rare, random crashes - // with fuzz testing. It is therefore disabled for now. - const useSafe = true - /* - useSafe := false - if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSizeAlloc { - useSafe = true - } - if s.maxSyncLen > 0 && cap(s.out)-len(s.out)-compressedBlockOverAlloc < int(s.maxSyncLen) { - useSafe = true - } - if cap(s.literals) < len(s.literals)+compressedBlockOverAlloc { - useSafe = true - } - */ - - br := s.br - - maxBlockSize := min(s.windowSize, maxCompressedBlockSize) - - ctx := decodeSyncAsmContext{ - llTable: s.litLengths.fse.dt[:maxTablesize], - mlTable: s.matchLengths.fse.dt[:maxTablesize], - ofTable: s.offsets.fse.dt[:maxTablesize], - llState: uint64(s.litLengths.state.state), - mlState: uint64(s.matchLengths.state.state), - ofState: uint64(s.offsets.state.state), - iteration: s.nSeqs - 1, - litRemain: len(s.literals), - out: s.out, - outPosition: len(s.out), - literals: s.literals, - windowSize: s.windowSize, - history: hist, - } - - s.seqSize = 0 - startSize := len(s.out) +func sequenceDecs_decode_56_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int - var errCode int +// decodeAsm runs the sequenceDecs decode loop, choosing the BMI2 / 56-bit variant. +func decodeAsm(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext, lte56bits bool) int { if cpuinfo.HasBMI2() { - if useSafe { - errCode = sequenceDecs_decodeSync_safe_bmi2(s, br, &ctx) - } else { - errCode = sequenceDecs_decodeSync_bmi2(s, br, &ctx) - } - } else { - if useSafe { - errCode = sequenceDecs_decodeSync_safe_amd64(s, br, &ctx) - } else { - errCode = sequenceDecs_decodeSync_amd64(s, br, &ctx) - } - } - switch errCode { - case noError: - break - - case errorMatchLenOfsMismatch: - return true, fmt.Errorf("zero matchoff and matchlen (%d) > 0", ctx.ml) - - case errorMatchLenTooBig: - return true, fmt.Errorf("match len (%d) bigger than max allowed length", ctx.ml) - - case errorMatchOffTooBig: - return true, fmt.Errorf("match offset (%d) bigger than current history (%d)", - ctx.mo, ctx.outPosition+len(hist)-startSize) - - case errorNotEnoughLiterals: - return true, fmt.Errorf("unexpected literal count, want %d bytes, but only %d is available", - ctx.ll, ctx.litRemain+ctx.ll) - - case errorOverread: - return true, io.ErrUnexpectedEOF - - case errorNotEnoughSpace: - size := ctx.outPosition + ctx.ll + ctx.ml - if debugDecoder { - println("msl:", s.maxSyncLen, "cap", cap(s.out), "bef:", startSize, "sz:", size-startSize, "mbs:", maxBlockSize, "outsz:", cap(s.out)-startSize) + if lte56bits { + return sequenceDecs_decode_56_bmi2(s, br, ctx) } - return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) - - default: - return true, fmt.Errorf("sequenceDecs_decode returned erroneous code %d", errCode) - } - - s.seqSize += ctx.litRemain - if s.seqSize > maxBlockSize { - return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) + return sequenceDecs_decode_bmi2(s, br, ctx) } - err := br.close() - if err != nil { - printf("Closing sequences: %v, %+v\n", err, *br) - return true, err + if lte56bits { + return sequenceDecs_decode_56_amd64(s, br, ctx) } - - s.literals = s.literals[ctx.litPosition:] - t := ctx.outPosition - s.out = s.out[:t] - - // Add final literals - s.out = append(s.out, s.literals...) - if debugDecoder { - t += len(s.literals) - if t != len(s.out) { - panic(fmt.Errorf("length mismatch, want %d, got %d", len(s.out), t)) - } - } - - return true, nil + return sequenceDecs_decode_amd64(s, br, ctx) } -// -------------------------------------------------------------------------------- - -type decodeAsmContext struct { - llTable []decSymbol - mlTable []decSymbol - ofTable []decSymbol - llState uint64 - mlState uint64 - ofState uint64 - iteration int - seqs []seqVals - litRemain int -} - -const noError = 0 - -// error reported when mo == 0 && ml > 0 -const errorMatchLenOfsMismatch = 1 - -// error reported when ml > maxMatchLen -const errorMatchLenTooBig = 2 - -// error reported when mo > available history or mo > s.windowSize -const errorMatchOffTooBig = 3 - -// error reported when the sum of literal lengths exeeceds the literal buffer size -const errorNotEnoughLiterals = 4 - -// error reported when capacity of `out` is too small -const errorNotEnoughSpace = 5 - -// error reported when bits are overread. -const errorOverread = 6 - -// sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm. +// sequenceDecs_decodeSync_amd64 implements the main loop of sequenceDecs.decodeSync in x86 asm. // // Please refer to seqdec_generic.go for the reference implementation. // //go:noescape -func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int +func sequenceDecs_decodeSync_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int -// sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm. -// -// Please refer to seqdec_generic.go for the reference implementation. +// sequenceDecs_decodeSync_bmi2 implements the main loop of sequenceDecs.decodeSync in x86 asm with BMI2 extensions. // //go:noescape -func sequenceDecs_decode_56_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int +func sequenceDecs_decodeSync_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int -// sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm with BMI2 extensions. +// sequenceDecs_decodeSync_safe_amd64 does the same as above, but does not write more than output buffer. // //go:noescape -func sequenceDecs_decode_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int +func sequenceDecs_decodeSync_safe_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int -// sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm with BMI2 extensions. +// sequenceDecs_decodeSync_safe_bmi2 does the same as above, but does not write more than output buffer. // //go:noescape -func sequenceDecs_decode_56_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int - -// decode sequences from the stream without the provided history. -func (s *sequenceDecs) decode(seqs []seqVals) error { - br := s.br - - maxBlockSize := min(s.windowSize, maxCompressedBlockSize) - - ctx := decodeAsmContext{ - llTable: s.litLengths.fse.dt[:maxTablesize], - mlTable: s.matchLengths.fse.dt[:maxTablesize], - ofTable: s.offsets.fse.dt[:maxTablesize], - llState: uint64(s.litLengths.state.state), - mlState: uint64(s.matchLengths.state.state), - ofState: uint64(s.offsets.state.state), - seqs: seqs, - iteration: len(seqs) - 1, - litRemain: len(s.literals), - } - - if debugDecoder { - println("decode: decoding", len(seqs), "sequences", br.remain(), "bits remain on stream") - } +func sequenceDecs_decodeSync_safe_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int - s.seqSize = 0 - lte56bits := s.maxBits+s.offsets.fse.actualTableLog+s.matchLengths.fse.actualTableLog+s.litLengths.fse.actualTableLog <= 56 - var errCode int +// decodeSyncAsm runs the decodeSync loop, choosing the BMI2 / safe variant. +func decodeSyncAsm(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext, safe bool) int { if cpuinfo.HasBMI2() { - if lte56bits { - errCode = sequenceDecs_decode_56_bmi2(s, br, &ctx) - } else { - errCode = sequenceDecs_decode_bmi2(s, br, &ctx) - } - } else { - if lte56bits { - errCode = sequenceDecs_decode_56_amd64(s, br, &ctx) - } else { - errCode = sequenceDecs_decode_amd64(s, br, &ctx) + if safe { + return sequenceDecs_decodeSync_safe_bmi2(s, br, ctx) } + return sequenceDecs_decodeSync_bmi2(s, br, ctx) } - if errCode != 0 { - i := len(seqs) - ctx.iteration - 1 - switch errCode { - case errorMatchLenOfsMismatch: - ml := ctx.seqs[i].ml - return fmt.Errorf("zero matchoff and matchlen (%d) > 0", ml) - - case errorMatchLenTooBig: - ml := ctx.seqs[i].ml - return fmt.Errorf("match len (%d) bigger than max allowed length", ml) - - case errorNotEnoughLiterals: - ll := ctx.seqs[i].ll - return fmt.Errorf("unexpected literal count, want %d bytes, but only %d is available", ll, ctx.litRemain+ll) - case errorOverread: - return io.ErrUnexpectedEOF - } - - return fmt.Errorf("sequenceDecs_decode_amd64 returned erroneous code %d", errCode) + if safe { + return sequenceDecs_decodeSync_safe_amd64(s, br, ctx) } - - if ctx.litRemain < 0 { - return fmt.Errorf("literal count is too big: total available %d, total requested %d", - len(s.literals), len(s.literals)-ctx.litRemain) - } - - s.seqSize += ctx.litRemain - if s.seqSize > maxBlockSize { - return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) - } - if debugDecoder { - println("decode: ", br.remain(), "bits remain on stream. code:", errCode) - } - err := br.close() - if err != nil { - printf("Closing sequences: %v, %+v\n", err, *br) - } - return err -} - -// -------------------------------------------------------------------------------- - -type executeAsmContext struct { - seqs []seqVals - seqIndex int - out []byte - history []byte - literals []byte - outPosition int - litPosition int - windowSize int + return sequenceDecs_decodeSync_amd64(s, br, ctx) } // sequenceDecs_executeSimple_amd64 implements the main loop of sequenceDecs.executeSimple in x86 asm. @@ -334,54 +96,10 @@ func sequenceDecs_executeSimple_amd64(ctx *executeAsmContext) bool //go:noescape func sequenceDecs_executeSimple_safe_amd64(ctx *executeAsmContext) bool -// executeSimple handles cases when dictionary is not used. -func (s *sequenceDecs) executeSimple(seqs []seqVals, hist []byte) error { - // Ensure we have enough output size... - if len(s.out)+s.seqSize+compressedBlockOverAlloc > cap(s.out) { - addBytes := s.seqSize + len(s.out) + compressedBlockOverAlloc - s.out = append(s.out, make([]byte, addBytes)...) - s.out = s.out[:len(s.out)-addBytes] - } - - if debugDecoder { - printf("Execute %d seqs with literals: %d into %d bytes\n", len(seqs), len(s.literals), s.seqSize) - } - - var t = len(s.out) - out := s.out[:t+s.seqSize] - - ctx := executeAsmContext{ - seqs: seqs, - seqIndex: 0, - out: out, - history: hist, - outPosition: t, - litPosition: 0, - literals: s.literals, - windowSize: s.windowSize, +// executeSimpleAsm runs the executeSimple loop, choosing the safe variant. +func executeSimpleAsm(ctx *executeAsmContext, safe bool) bool { + if safe { + return sequenceDecs_executeSimple_safe_amd64(ctx) } - var ok bool - if cap(s.literals) < len(s.literals)+compressedBlockOverAlloc { - ok = sequenceDecs_executeSimple_safe_amd64(&ctx) - } else { - ok = sequenceDecs_executeSimple_amd64(&ctx) - } - if !ok { - return fmt.Errorf("match offset (%d) bigger than current history (%d)", - seqs[ctx.seqIndex].mo, ctx.outPosition+len(hist)) - } - s.literals = s.literals[ctx.litPosition:] - t = ctx.outPosition - - // Add final literals - copy(out[t:], s.literals) - if debugDecoder { - t += len(s.literals) - if t != len(out) { - panic(fmt.Errorf("length mismatch, want %d, got %d, ss: %d", len(out), t, s.seqSize)) - } - } - s.out = out - - return nil + return sequenceDecs_executeSimple_amd64(ctx) } diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s index a708ca6d3d9d..4d3188ff49b9 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s @@ -1,4 +1,4 @@ -// Code generated by command: go run gen.go -out ../seqdec_amd64.s -pkg=zstd. DO NOT EDIT. +// Code generated by command: go run gen.go -out ../seqdec.s -arch amd64,arm64 -pkg=zstd. DO NOT EDIT. //go:build !appengine && !noasm && gc && !noasm @@ -2081,7 +2081,7 @@ sequenceDecs_decodeSync_amd64_match_len_ofs_ok: MOVQ 16(SP), R13 // Check if we have enough space in s.out - LEAQ (AX)(R13*1), R14 + LEAQ 16(AX)(R13*1), R14 ADDQ R10, R14 CMPQ R14, 32(SP) JA error_not_enough_space @@ -2601,7 +2601,7 @@ sequenceDecs_decodeSync_bmi2_match_len_ofs_ok: MOVQ 16(SP), R13 // Check if we have enough space in s.out - LEAQ (CX)(R13*1), R14 + LEAQ 16(CX)(R13*1), R14 ADDQ R9, R14 CMPQ R14, 32(SP) JA error_not_enough_space diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.go b/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.go new file mode 100644 index 000000000000..5ad262acff0e --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.go @@ -0,0 +1,70 @@ +//go:build arm64 && !appengine && !noasm && gc + +package zstd + +// The shared decode/decodeSync/executeSimple wrappers and context structs live +// in seqdec_asm.go; this file only declares the arm64 asm routines (generated +// by the avo arm64 lowering printer) and the dispatch helpers. arm64 has no +// BMI2, so each helper selects only between the 56-bit / safe variants. + +// sequenceDecs_decode_arm64 implements the main loop of sequenceDecs in arm64 asm. +// +// Please refer to seqdec_generic.go for the reference implementation. +// +//go:noescape +func sequenceDecs_decode_arm64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int + +// sequenceDecs_decode_56_arm64 implements the main loop of sequenceDecs in arm64 asm. +// +//go:noescape +func sequenceDecs_decode_56_arm64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int + +// decodeAsm runs the sequenceDecs decode loop, choosing the 56-bit variant. +func decodeAsm(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext, lte56bits bool) int { + if lte56bits { + return sequenceDecs_decode_56_arm64(s, br, ctx) + } + return sequenceDecs_decode_arm64(s, br, ctx) +} + +// sequenceDecs_decodeSync_arm64 implements the main loop of sequenceDecs.decodeSync in arm64 asm. +// +// Please refer to seqdec_generic.go for the reference implementation. +// +//go:noescape +func sequenceDecs_decodeSync_arm64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int + +// sequenceDecs_decodeSync_safe_arm64 does the same as above, but does not write more than output buffer. +// +//go:noescape +func sequenceDecs_decodeSync_safe_arm64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int + +// decodeSyncAsm runs the decodeSync loop, choosing the safe variant. +func decodeSyncAsm(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext, safe bool) int { + if safe { + return sequenceDecs_decodeSync_safe_arm64(s, br, ctx) + } + return sequenceDecs_decodeSync_arm64(s, br, ctx) +} + +// sequenceDecs_executeSimple_arm64 implements the main loop of sequenceDecs.executeSimple in arm64 asm. +// +// Returns false if a match offset is too big. +// +// Please refer to seqdec_generic.go for the reference implementation. +// +//go:noescape +func sequenceDecs_executeSimple_arm64(ctx *executeAsmContext) bool + +// Same as above, but with safe memcopies +// +//go:noescape +func sequenceDecs_executeSimple_safe_arm64(ctx *executeAsmContext) bool + +// executeSimpleAsm runs the executeSimple loop, choosing the safe variant. +func executeSimpleAsm(ctx *executeAsmContext, safe bool) bool { + if safe { + return sequenceDecs_executeSimple_safe_arm64(ctx) + } + return sequenceDecs_executeSimple_arm64(ctx) +} diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.s b/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.s new file mode 100644 index 000000000000..6f54ef21ba12 --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_arm64.s @@ -0,0 +1,2750 @@ +// Code generated by command: go run gen.go -out ../seqdec.s -arch amd64,arm64 -pkg=zstd. DO NOT EDIT. +// EXPERIMENTAL arm64 output lowered from an amd64 avo program. + +//go:build arm64 && !appengine && !noasm && gc && !noasm + +// func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int +// Requires: CMOV +TEXT ·sequenceDecs_decode_arm64(SB), $8-32 + MOVD br+8(FP), R1 + MOVD 24(R1), R2 + MOVBU 40(R1), R3 + MOVD (R1), R0 + MOVD 32(R1), R5 + ADD R5, R0, R0 + MOVD R0, 8(RSP) + MOVD ctx+16(FP), R0 + MOVD 72(R0), R6 + MOVD 80(R0), R7 + MOVD 88(R0), R8 + MOVD 104(R0), R9 + MOVD s+0(FP), R0 + MOVD 144(R0), R10 + MOVD 152(R0), R11 + MOVD 160(R0), R12 + +sequenceDecs_decode_amd64_main_loop: + MOVD 8(RSP), R13 + + // Fill bitreader to have enough for the offset and match length. + CMP $0x08, R5 + BLT sequenceDecs_decode_amd64_fill_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R13, R13 + MOVD (R13), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decode_amd64_fill_end + +sequenceDecs_decode_amd64_fill_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decode_amd64_fill_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decode_amd64_fill_end + LSL $0x08, R2, R2 + SUB $0x01, R13, R13 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R13), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decode_amd64_fill_byte_by_byte + +sequenceDecs_decode_amd64_fill_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decode_amd64_fill_end: + // Update offset + MOVD R8, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_amd64_of_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_amd64_of_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_amd64_of_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_amd64_of_update_zero: + MOVD R0, 16(R9) + + // Update match length + MOVD R7, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_amd64_ml_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_amd64_ml_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_amd64_ml_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_amd64_ml_update_zero: + MOVD R0, 8(R9) + + // Fill bitreader to have enough for the remaining + CMP $0x08, R5 + BLT sequenceDecs_decode_amd64_fill_2_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R13, R13 + MOVD (R13), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decode_amd64_fill_2_end + +sequenceDecs_decode_amd64_fill_2_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decode_amd64_fill_2_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decode_amd64_fill_2_end + LSL $0x08, R2, R2 + SUB $0x01, R13, R13 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R13), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decode_amd64_fill_2_byte_by_byte + +sequenceDecs_decode_amd64_fill_2_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decode_amd64_fill_2_end: + // Update literal length + MOVD R6, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_amd64_ll_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_amd64_ll_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_amd64_ll_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_amd64_ll_update_zero: + MOVD R0, (R9) + + // Fill bitreader for state updates + MOVD R13, 8(RSP) + MOVD R8, R0 + LSR $0x08, R0, R0 + MOVBU R0, R0 + MOVD ctx+16(FP), R1 + MOVD 96(R1), R16 + CMP $0x00, R16 + BEQ sequenceDecs_decode_amd64_skip_update + + // Update Literal Length State + MOVBU R6, R13 + LSRW $0x10, R6, R6 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R6, R6 + + // Load ctx.llTable + MOVD ctx+16(FP), R1 + MOVD (R1), R1 + ADD R6<<3, R1, R15 + MOVD (R15), R6 + + // Update Match Length State + MOVBU R7, R13 + LSRW $0x10, R7, R7 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R7, R7 + + // Load ctx.mlTable + MOVD ctx+16(FP), R1 + MOVD 24(R1), R1 + ADD R7<<3, R1, R15 + MOVD (R15), R7 + + // Update Offset State + MOVBU R8, R13 + LSRW $0x10, R8, R8 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R8, R8 + + // Load ctx.ofTable + MOVD ctx+16(FP), R1 + MOVD 48(R1), R1 + ADD R8<<3, R1, R15 + MOVD (R15), R8 + +sequenceDecs_decode_amd64_skip_update: + // Adjust offset + MOVD 16(R9), R1 + CMP $0x01, R0 + BLS sequenceDecs_decode_amd64_adjust_offsetB_1_or_0 + MOVD R11, R12 + MOVD R10, R11 + MOVD R1, R10 + JMP sequenceDecs_decode_amd64_after_adjust + +sequenceDecs_decode_amd64_adjust_offsetB_1_or_0: + MOVD (R9), R16 + CMP $0x00000000, R16 + BNE sequenceDecs_decode_amd64_adjust_offset_maybezero + ADD $1, R1, R1 + JMP sequenceDecs_decode_amd64_adjust_offset_nonzero + +sequenceDecs_decode_amd64_adjust_offset_maybezero: + TST R1, R1 + BNE sequenceDecs_decode_amd64_adjust_offset_nonzero + MOVD R10, R1 + JMP sequenceDecs_decode_amd64_after_adjust + +sequenceDecs_decode_amd64_adjust_offset_nonzero: + CMP $0x01, R1 + BLO sequenceDecs_decode_amd64_adjust_zero + BEQ sequenceDecs_decode_amd64_adjust_one + CMP $0x02, R1 + BHI sequenceDecs_decode_amd64_adjust_three + JMP sequenceDecs_decode_amd64_adjust_two + +sequenceDecs_decode_amd64_adjust_zero: + MOVD R10, R0 + JMP sequenceDecs_decode_amd64_adjust_test_temp_valid + +sequenceDecs_decode_amd64_adjust_one: + MOVD R11, R0 + JMP sequenceDecs_decode_amd64_adjust_test_temp_valid + +sequenceDecs_decode_amd64_adjust_two: + MOVD R12, R0 + JMP sequenceDecs_decode_amd64_adjust_test_temp_valid + +sequenceDecs_decode_amd64_adjust_three: + SUB $1, R10, R0 + +sequenceDecs_decode_amd64_adjust_test_temp_valid: + TST R0, R0 + BNE sequenceDecs_decode_amd64_adjust_temp_valid + MOVD $0x00000001, R0 + +sequenceDecs_decode_amd64_adjust_temp_valid: + CMP $0x01, R1 + CSEL NE, R11, R12, R12 + MOVD R10, R11 + MOVD R0, R10 + MOVD R0, R1 + +sequenceDecs_decode_amd64_after_adjust: + MOVD R1, 16(R9) + + // Check values + MOVD 8(R9), R0 + MOVD (R9), R13 + ADD R13, R0, R14 + MOVD s+0(FP), R4 + MOVD 256(R4), R16 + ADD R14, R16, R16 + MOVD R16, 256(R4) + MOVD ctx+16(FP), R14 + MOVD 128(R14), R16 + SUBS R13, R16, R16 + MOVD R16, 128(R14) + BMI error_not_enough_literals + CMP $0x00020002, R0 + BHI sequenceDecs_decode_amd64_error_match_len_too_big + TST R1, R1 + BNE sequenceDecs_decode_amd64_match_len_ofs_ok + TST R0, R0 + BNE sequenceDecs_decode_amd64_error_match_len_ofs_mismatch + +sequenceDecs_decode_amd64_match_len_ofs_ok: + ADD $0x18, R9, R9 + MOVD ctx+16(FP), R0 + MOVD 96(R0), R16 + SUBS $1, R16, R16 + MOVD R16, 96(R0) + BPL sequenceDecs_decode_amd64_main_loop + MOVD s+0(FP), R0 + MOVD R10, 144(R0) + MOVD R11, 152(R0) + MOVD R12, 160(R0) + MOVD br+8(FP), R0 + MOVD R2, 24(R0) + MOVB R3, 40(R0) + MOVD R5, 32(R0) + + // Return success + MOVD $0x00000000, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match length error +sequenceDecs_decode_amd64_error_match_len_ofs_mismatch: + MOVD $0x00000001, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match too long error +sequenceDecs_decode_amd64_error_match_len_too_big: + MOVD $0x00000002, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match offset too long error + MOVD $0x00000003, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough literals error +error_not_enough_literals: + MOVD $0x00000004, R16 + MOVD R16, ret+24(FP) + RET + + // Return with overread error +error_overread: + MOVD $0x00000006, R16 + MOVD R16, ret+24(FP) + RET + +// func sequenceDecs_decode_56_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int +// Requires: CMOV +TEXT ·sequenceDecs_decode_56_arm64(SB), $8-32 + MOVD br+8(FP), R1 + MOVD 24(R1), R2 + MOVBU 40(R1), R3 + MOVD (R1), R0 + MOVD 32(R1), R5 + ADD R5, R0, R0 + MOVD R0, 8(RSP) + MOVD ctx+16(FP), R0 + MOVD 72(R0), R6 + MOVD 80(R0), R7 + MOVD 88(R0), R8 + MOVD 104(R0), R9 + MOVD s+0(FP), R0 + MOVD 144(R0), R10 + MOVD 152(R0), R11 + MOVD 160(R0), R12 + +sequenceDecs_decode_56_amd64_main_loop: + MOVD 8(RSP), R13 + + // Fill bitreader to have enough for the offset and match length. + CMP $0x08, R5 + BLT sequenceDecs_decode_56_amd64_fill_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R13, R13 + MOVD (R13), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decode_56_amd64_fill_end + +sequenceDecs_decode_56_amd64_fill_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decode_56_amd64_fill_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decode_56_amd64_fill_end + LSL $0x08, R2, R2 + SUB $0x01, R13, R13 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R13), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decode_56_amd64_fill_byte_by_byte + +sequenceDecs_decode_56_amd64_fill_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decode_56_amd64_fill_end: + // Update offset + MOVD R8, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_56_amd64_of_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_56_amd64_of_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_56_amd64_of_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_56_amd64_of_update_zero: + MOVD R0, 16(R9) + + // Update match length + MOVD R7, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_56_amd64_ml_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_56_amd64_ml_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_56_amd64_ml_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_56_amd64_ml_update_zero: + MOVD R0, 8(R9) + + // Update literal length + MOVD R6, R0 + MOVD R3, R1 + MOVD R2, R14 + LSL R1, R14, R14 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decode_56_amd64_ll_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decode_56_amd64_ll_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decode_56_amd64_ll_update_zero + NEG R1, R1 + LSR R1, R14, R14 + ADD R14, R0, R0 + +sequenceDecs_decode_56_amd64_ll_update_zero: + MOVD R0, (R9) + + // Fill bitreader for state updates + MOVD R13, 8(RSP) + MOVD R8, R0 + LSR $0x08, R0, R0 + MOVBU R0, R0 + MOVD ctx+16(FP), R1 + MOVD 96(R1), R16 + CMP $0x00, R16 + BEQ sequenceDecs_decode_56_amd64_skip_update + + // Update Literal Length State + MOVBU R6, R13 + LSRW $0x10, R6, R6 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R6, R6 + + // Load ctx.llTable + MOVD ctx+16(FP), R1 + MOVD (R1), R1 + ADD R6<<3, R1, R15 + MOVD (R15), R6 + + // Update Match Length State + MOVBU R7, R13 + LSRW $0x10, R7, R7 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R7, R7 + + // Load ctx.mlTable + MOVD ctx+16(FP), R1 + MOVD 24(R1), R1 + ADD R7<<3, R1, R15 + MOVD (R15), R7 + + // Update Offset State + MOVBU R8, R13 + LSRW $0x10, R8, R8 + ADD R13, R3, R1 + MOVD R2, R14 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R14, R14 + MOVD $0x00000001, R4 + BFI $0, R13, $8, R1 + LSLW R1, R4, R4 + SUBW $1, R4, R4 + AND R4, R14, R14 + ADD R14, R8, R8 + + // Load ctx.ofTable + MOVD ctx+16(FP), R1 + MOVD 48(R1), R1 + ADD R8<<3, R1, R15 + MOVD (R15), R8 + +sequenceDecs_decode_56_amd64_skip_update: + // Adjust offset + MOVD 16(R9), R1 + CMP $0x01, R0 + BLS sequenceDecs_decode_56_amd64_adjust_offsetB_1_or_0 + MOVD R11, R12 + MOVD R10, R11 + MOVD R1, R10 + JMP sequenceDecs_decode_56_amd64_after_adjust + +sequenceDecs_decode_56_amd64_adjust_offsetB_1_or_0: + MOVD (R9), R16 + CMP $0x00000000, R16 + BNE sequenceDecs_decode_56_amd64_adjust_offset_maybezero + ADD $1, R1, R1 + JMP sequenceDecs_decode_56_amd64_adjust_offset_nonzero + +sequenceDecs_decode_56_amd64_adjust_offset_maybezero: + TST R1, R1 + BNE sequenceDecs_decode_56_amd64_adjust_offset_nonzero + MOVD R10, R1 + JMP sequenceDecs_decode_56_amd64_after_adjust + +sequenceDecs_decode_56_amd64_adjust_offset_nonzero: + CMP $0x01, R1 + BLO sequenceDecs_decode_56_amd64_adjust_zero + BEQ sequenceDecs_decode_56_amd64_adjust_one + CMP $0x02, R1 + BHI sequenceDecs_decode_56_amd64_adjust_three + JMP sequenceDecs_decode_56_amd64_adjust_two + +sequenceDecs_decode_56_amd64_adjust_zero: + MOVD R10, R0 + JMP sequenceDecs_decode_56_amd64_adjust_test_temp_valid + +sequenceDecs_decode_56_amd64_adjust_one: + MOVD R11, R0 + JMP sequenceDecs_decode_56_amd64_adjust_test_temp_valid + +sequenceDecs_decode_56_amd64_adjust_two: + MOVD R12, R0 + JMP sequenceDecs_decode_56_amd64_adjust_test_temp_valid + +sequenceDecs_decode_56_amd64_adjust_three: + SUB $1, R10, R0 + +sequenceDecs_decode_56_amd64_adjust_test_temp_valid: + TST R0, R0 + BNE sequenceDecs_decode_56_amd64_adjust_temp_valid + MOVD $0x00000001, R0 + +sequenceDecs_decode_56_amd64_adjust_temp_valid: + CMP $0x01, R1 + CSEL NE, R11, R12, R12 + MOVD R10, R11 + MOVD R0, R10 + MOVD R0, R1 + +sequenceDecs_decode_56_amd64_after_adjust: + MOVD R1, 16(R9) + + // Check values + MOVD 8(R9), R0 + MOVD (R9), R13 + ADD R13, R0, R14 + MOVD s+0(FP), R4 + MOVD 256(R4), R16 + ADD R14, R16, R16 + MOVD R16, 256(R4) + MOVD ctx+16(FP), R14 + MOVD 128(R14), R16 + SUBS R13, R16, R16 + MOVD R16, 128(R14) + BMI error_not_enough_literals + CMP $0x00020002, R0 + BHI sequenceDecs_decode_56_amd64_error_match_len_too_big + TST R1, R1 + BNE sequenceDecs_decode_56_amd64_match_len_ofs_ok + TST R0, R0 + BNE sequenceDecs_decode_56_amd64_error_match_len_ofs_mismatch + +sequenceDecs_decode_56_amd64_match_len_ofs_ok: + ADD $0x18, R9, R9 + MOVD ctx+16(FP), R0 + MOVD 96(R0), R16 + SUBS $1, R16, R16 + MOVD R16, 96(R0) + BPL sequenceDecs_decode_56_amd64_main_loop + MOVD s+0(FP), R0 + MOVD R10, 144(R0) + MOVD R11, 152(R0) + MOVD R12, 160(R0) + MOVD br+8(FP), R0 + MOVD R2, 24(R0) + MOVB R3, 40(R0) + MOVD R5, 32(R0) + + // Return success + MOVD $0x00000000, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match length error +sequenceDecs_decode_56_amd64_error_match_len_ofs_mismatch: + MOVD $0x00000001, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match too long error +sequenceDecs_decode_56_amd64_error_match_len_too_big: + MOVD $0x00000002, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match offset too long error + MOVD $0x00000003, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough literals error +error_not_enough_literals: + MOVD $0x00000004, R16 + MOVD R16, ret+24(FP) + RET + + // Return with overread error +error_overread: + MOVD $0x00000006, R16 + MOVD R16, ret+24(FP) + RET + +// skipped sequenceDecs_decode_bmi2 (generic twin preferred on arm64) + +// skipped sequenceDecs_decode_56_bmi2 (generic twin preferred on arm64) + +// func sequenceDecs_executeSimple_amd64(ctx *executeAsmContext) bool +// Requires: SSE +TEXT ·sequenceDecs_executeSimple_arm64(SB), $8-9 + MOVD ctx+0(FP), R9 + MOVD 8(R9), R1 + TST R1, R1 + BEQ empty_seqs + MOVD (R9), R0 + MOVD 24(R9), R2 + MOVD 32(R9), R3 + MOVD 80(R9), R5 + MOVD 104(R9), R6 + MOVD 120(R9), R7 + MOVD 56(R9), R8 + MOVD 64(R9), R9 + ADD R9, R8, R8 + + // seqsBase += 24 * seqIndex + ADD R2<<1, R2, R10 + LSL $0x03, R10, R10 + ADD R10, R0, R0 + + // outBase += outPosition + ADD R6, R3, R3 + +main_loop: + MOVD (R0), R10 + MOVD 16(R0), R11 + MOVD 8(R0), R12 + + // Copy literals + TST R10, R10 + BEQ check_offset + MOVD $0, R13 + +copy_1: + ADD R13, R5, R15 + VLD1 (R15), [V0.B16] + ADD R13, R3, R15 + VST1 [V0.B16], (R15) + ADD $0x10, R13, R13 + CMP R10, R13 + BLO copy_1 + ADD R10, R5, R5 + ADD R10, R3, R3 + ADD R10, R6, R6 + + // Malformed input if seq.mo > t+len(hist) || seq.mo > s.windowSize) +check_offset: + ADD R9, R6, R10 + CMP R10, R11 + BGT error_match_off_too_big + CMP R7, R11 + BGT error_match_off_too_big + + // Copy match from history + MOVD R11, R10 + SUBS R6, R10, R10 + BLS copy_match + MOVD R8, R13 + SUB R10, R13, R13 + CMP R10, R12 + BGT copy_all_from_history + MOVD R12, R10 + SUBS $0x10, R10, R10 + BLO copy_4_small + +copy_4_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R13, R13 + ADD $0x10, R3, R3 + SUBS $0x10, R10, R10 + BHS copy_4_loop + ADD R10, R13, R13 + ADD $16, R13, R13 + ADD R10, R3, R3 + ADD $16, R3, R3 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_4_end + +copy_4_small: + CMP $0x03, R12 + BEQ copy_4_move_3 + CMP $0x08, R12 + BLO copy_4_move_4through7 + JMP copy_4_move_8through16 + +copy_4_move_3: + MOVHU (R13), R10 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R11 + MOVH R10, (R3) + MOVB R11, 2(R3) + ADD R12, R13, R13 + ADD R12, R3, R3 + JMP copy_4_end + +copy_4_move_4through7: + MOVWU (R13), R10 + ADD R12, R13, R15 + MOVWU -4(R15), R11 + MOVW R10, (R3) + ADD R12, R3, R15 + MOVW R11, -4(R15) + ADD R12, R13, R13 + ADD R12, R3, R3 + JMP copy_4_end + +copy_4_move_8through16: + MOVD (R13), R10 + ADD R12, R13, R15 + MOVD -8(R15), R11 + MOVD R10, (R3) + ADD R12, R3, R15 + MOVD R11, -8(R15) + ADD R12, R13, R13 + ADD R12, R3, R3 + +copy_4_end: + ADD R12, R6, R6 + ADD $0x18, R0, R0 + ADD $1, R2, R2 + CMP R1, R2 + BLO main_loop + JMP loop_finished + +copy_all_from_history: + MOVD R10, R14 + SUBS $0x10, R14, R14 + BLO copy_5_small + +copy_5_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R13, R13 + ADD $0x10, R3, R3 + SUBS $0x10, R14, R14 + BHS copy_5_loop + ADD R14, R13, R13 + ADD $16, R13, R13 + ADD R14, R3, R3 + ADD $16, R3, R3 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_5_end + +copy_5_small: + CMP $0x03, R10 + BEQ copy_5_move_3 + BLO copy_5_move_1or2 + CMP $0x08, R10 + BLO copy_5_move_4through7 + JMP copy_5_move_8through16 + +copy_5_move_1or2: + MOVBU (R13), R16 + BFI $0, R16, $8, R14 + ADD R10, R13, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R4 + MOVB R14, (R3) + ADD R10, R3, R15 + MOVB R4, -1(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_3: + MOVHU (R13), R14 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R4 + MOVH R14, (R3) + MOVB R4, 2(R3) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_4through7: + MOVWU (R13), R14 + ADD R10, R13, R15 + MOVWU -4(R15), R4 + MOVW R14, (R3) + ADD R10, R3, R15 + MOVW R4, -4(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_8through16: + MOVD (R13), R14 + ADD R10, R13, R15 + MOVD -8(R15), R4 + MOVD R14, (R3) + ADD R10, R3, R15 + MOVD R4, -8(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + +copy_5_end: + ADD R10, R6, R6 + SUB R10, R12, R12 + + // Copy match from the current buffer +copy_match: + MOVD R3, R10 + SUB R11, R10, R10 + + // ml <= mo + CMP R11, R12 + BHI copy_overlapping_match + + // Copy non-overlapping match + ADD R12, R6, R6 + MOVD R3, R11 + ADD R12, R3, R3 + +copy_2: + VLD1 (R10), [V0.B16] + VST1 [V0.B16], (R11) + ADD $0x10, R10, R10 + ADD $0x10, R11, R11 + SUBS $0x10, R12, R12 + BHI copy_2 + JMP handle_loop + + // Copy overlapping match +copy_overlapping_match: + ADD R12, R6, R6 + +copy_slow_3: + MOVBU (R10), R16 + BFI $0, R16, $8, R11 + MOVB R11, (R3) + ADD $1, R10, R10 + ADD $1, R3, R3 + SUBS $1, R12, R12 + BNE copy_slow_3 + +handle_loop: + ADD $0x18, R0, R0 + ADD $1, R2, R2 + CMP R1, R2 + BLO main_loop + +loop_finished: + // Return value + MOVD $0x01, R16 + MOVB R16, ret+8(FP) + + // Update the context + MOVD ctx+0(FP), R0 + MOVD R2, 24(R0) + MOVD R6, 104(R0) + MOVD 80(R0), R16 + SUB R16, R5, R5 + MOVD R5, 112(R0) + RET + +error_match_off_too_big: + // Return value + MOVD $0x00, R16 + MOVB R16, ret+8(FP) + + // Update the context + MOVD ctx+0(FP), R0 + MOVD R2, 24(R0) + MOVD R6, 104(R0) + MOVD 80(R0), R16 + SUB R16, R5, R5 + MOVD R5, 112(R0) + RET + +empty_seqs: + // Return value + MOVD $0x01, R16 + MOVB R16, ret+8(FP) + RET + +// func sequenceDecs_executeSimple_safe_amd64(ctx *executeAsmContext) bool +// Requires: SSE +TEXT ·sequenceDecs_executeSimple_safe_arm64(SB), $8-9 + MOVD ctx+0(FP), R9 + MOVD 8(R9), R1 + TST R1, R1 + BEQ empty_seqs + MOVD (R9), R0 + MOVD 24(R9), R2 + MOVD 32(R9), R3 + MOVD 80(R9), R5 + MOVD 104(R9), R6 + MOVD 120(R9), R7 + MOVD 56(R9), R8 + MOVD 64(R9), R9 + ADD R9, R8, R8 + + // seqsBase += 24 * seqIndex + ADD R2<<1, R2, R10 + LSL $0x03, R10, R10 + ADD R10, R0, R0 + + // outBase += outPosition + ADD R6, R3, R3 + +main_loop: + MOVD (R0), R10 + MOVD 16(R0), R11 + MOVD 8(R0), R12 + + // Copy literals + TST R10, R10 + BEQ check_offset + MOVD R10, R13 + SUBS $0x10, R13, R13 + BLO copy_1_small + +copy_1_loop: + VLD1 (R5), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R5, R5 + ADD $0x10, R3, R3 + SUBS $0x10, R13, R13 + BHS copy_1_loop + ADD R13, R5, R5 + ADD $16, R5, R5 + ADD R13, R3, R3 + ADD $16, R3, R3 + ADD $-16, R5, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_1_end + +copy_1_small: + CMP $0x03, R10 + BEQ copy_1_move_3 + BLO copy_1_move_1or2 + CMP $0x08, R10 + BLO copy_1_move_4through7 + JMP copy_1_move_8through16 + +copy_1_move_1or2: + MOVBU (R5), R16 + BFI $0, R16, $8, R13 + ADD R10, R5, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R14 + MOVB R13, (R3) + ADD R10, R3, R15 + MOVB R14, -1(R15) + ADD R10, R5, R5 + ADD R10, R3, R3 + JMP copy_1_end + +copy_1_move_3: + MOVHU (R5), R13 + MOVBU 2(R5), R16 + BFI $0, R16, $8, R14 + MOVH R13, (R3) + MOVB R14, 2(R3) + ADD R10, R5, R5 + ADD R10, R3, R3 + JMP copy_1_end + +copy_1_move_4through7: + MOVWU (R5), R13 + ADD R10, R5, R15 + MOVWU -4(R15), R14 + MOVW R13, (R3) + ADD R10, R3, R15 + MOVW R14, -4(R15) + ADD R10, R5, R5 + ADD R10, R3, R3 + JMP copy_1_end + +copy_1_move_8through16: + MOVD (R5), R13 + ADD R10, R5, R15 + MOVD -8(R15), R14 + MOVD R13, (R3) + ADD R10, R3, R15 + MOVD R14, -8(R15) + ADD R10, R5, R5 + ADD R10, R3, R3 + +copy_1_end: + ADD R10, R6, R6 + + // Malformed input if seq.mo > t+len(hist) || seq.mo > s.windowSize) +check_offset: + ADD R9, R6, R10 + CMP R10, R11 + BGT error_match_off_too_big + CMP R7, R11 + BGT error_match_off_too_big + + // Copy match from history + MOVD R11, R10 + SUBS R6, R10, R10 + BLS copy_match + MOVD R8, R13 + SUB R10, R13, R13 + CMP R10, R12 + BGT copy_all_from_history + MOVD R12, R10 + SUBS $0x10, R10, R10 + BLO copy_4_small + +copy_4_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R13, R13 + ADD $0x10, R3, R3 + SUBS $0x10, R10, R10 + BHS copy_4_loop + ADD R10, R13, R13 + ADD $16, R13, R13 + ADD R10, R3, R3 + ADD $16, R3, R3 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_4_end + +copy_4_small: + CMP $0x03, R12 + BEQ copy_4_move_3 + CMP $0x08, R12 + BLO copy_4_move_4through7 + JMP copy_4_move_8through16 + +copy_4_move_3: + MOVHU (R13), R10 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R11 + MOVH R10, (R3) + MOVB R11, 2(R3) + ADD R12, R13, R13 + ADD R12, R3, R3 + JMP copy_4_end + +copy_4_move_4through7: + MOVWU (R13), R10 + ADD R12, R13, R15 + MOVWU -4(R15), R11 + MOVW R10, (R3) + ADD R12, R3, R15 + MOVW R11, -4(R15) + ADD R12, R13, R13 + ADD R12, R3, R3 + JMP copy_4_end + +copy_4_move_8through16: + MOVD (R13), R10 + ADD R12, R13, R15 + MOVD -8(R15), R11 + MOVD R10, (R3) + ADD R12, R3, R15 + MOVD R11, -8(R15) + ADD R12, R13, R13 + ADD R12, R3, R3 + +copy_4_end: + ADD R12, R6, R6 + ADD $0x18, R0, R0 + ADD $1, R2, R2 + CMP R1, R2 + BLO main_loop + JMP loop_finished + +copy_all_from_history: + MOVD R10, R14 + SUBS $0x10, R14, R14 + BLO copy_5_small + +copy_5_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R13, R13 + ADD $0x10, R3, R3 + SUBS $0x10, R14, R14 + BHS copy_5_loop + ADD R14, R13, R13 + ADD $16, R13, R13 + ADD R14, R3, R3 + ADD $16, R3, R3 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_5_end + +copy_5_small: + CMP $0x03, R10 + BEQ copy_5_move_3 + BLO copy_5_move_1or2 + CMP $0x08, R10 + BLO copy_5_move_4through7 + JMP copy_5_move_8through16 + +copy_5_move_1or2: + MOVBU (R13), R16 + BFI $0, R16, $8, R14 + ADD R10, R13, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R4 + MOVB R14, (R3) + ADD R10, R3, R15 + MOVB R4, -1(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_3: + MOVHU (R13), R14 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R4 + MOVH R14, (R3) + MOVB R4, 2(R3) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_4through7: + MOVWU (R13), R14 + ADD R10, R13, R15 + MOVWU -4(R15), R4 + MOVW R14, (R3) + ADD R10, R3, R15 + MOVW R4, -4(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + JMP copy_5_end + +copy_5_move_8through16: + MOVD (R13), R14 + ADD R10, R13, R15 + MOVD -8(R15), R4 + MOVD R14, (R3) + ADD R10, R3, R15 + MOVD R4, -8(R15) + ADD R10, R13, R13 + ADD R10, R3, R3 + +copy_5_end: + ADD R10, R6, R6 + SUB R10, R12, R12 + + // Copy match from the current buffer +copy_match: + MOVD R3, R10 + SUB R11, R10, R10 + + // ml <= mo + CMP R11, R12 + BHI copy_overlapping_match + + // Copy non-overlapping match + ADD R12, R6, R6 + MOVD R12, R11 + SUBS $0x10, R11, R11 + BLO copy_2_small + +copy_2_loop: + VLD1 (R10), [V0.B16] + VST1 [V0.B16], (R3) + ADD $0x10, R10, R10 + ADD $0x10, R3, R3 + SUBS $0x10, R11, R11 + BHS copy_2_loop + ADD R11, R10, R10 + ADD $16, R10, R10 + ADD R11, R3, R3 + ADD $16, R3, R3 + ADD $-16, R10, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R3, R15 + VST1 [V0.B16], (R15) + JMP copy_2_end + +copy_2_small: + CMP $0x03, R12 + BEQ copy_2_move_3 + BLO copy_2_move_1or2 + CMP $0x08, R12 + BLO copy_2_move_4through7 + JMP copy_2_move_8through16 + +copy_2_move_1or2: + MOVBU (R10), R16 + BFI $0, R16, $8, R11 + ADD R12, R10, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R13 + MOVB R11, (R3) + ADD R12, R3, R15 + MOVB R13, -1(R15) + ADD R12, R10, R10 + ADD R12, R3, R3 + JMP copy_2_end + +copy_2_move_3: + MOVHU (R10), R11 + MOVBU 2(R10), R16 + BFI $0, R16, $8, R13 + MOVH R11, (R3) + MOVB R13, 2(R3) + ADD R12, R10, R10 + ADD R12, R3, R3 + JMP copy_2_end + +copy_2_move_4through7: + MOVWU (R10), R11 + ADD R12, R10, R15 + MOVWU -4(R15), R13 + MOVW R11, (R3) + ADD R12, R3, R15 + MOVW R13, -4(R15) + ADD R12, R10, R10 + ADD R12, R3, R3 + JMP copy_2_end + +copy_2_move_8through16: + MOVD (R10), R11 + ADD R12, R10, R15 + MOVD -8(R15), R13 + MOVD R11, (R3) + ADD R12, R3, R15 + MOVD R13, -8(R15) + ADD R12, R10, R10 + ADD R12, R3, R3 + +copy_2_end: + JMP handle_loop + + // Copy overlapping match +copy_overlapping_match: + ADD R12, R6, R6 + +copy_slow_3: + MOVBU (R10), R16 + BFI $0, R16, $8, R11 + MOVB R11, (R3) + ADD $1, R10, R10 + ADD $1, R3, R3 + SUBS $1, R12, R12 + BNE copy_slow_3 + +handle_loop: + ADD $0x18, R0, R0 + ADD $1, R2, R2 + CMP R1, R2 + BLO main_loop + +loop_finished: + // Return value + MOVD $0x01, R16 + MOVB R16, ret+8(FP) + + // Update the context + MOVD ctx+0(FP), R0 + MOVD R2, 24(R0) + MOVD R6, 104(R0) + MOVD 80(R0), R16 + SUB R16, R5, R5 + MOVD R5, 112(R0) + RET + +error_match_off_too_big: + // Return value + MOVD $0x00, R16 + MOVB R16, ret+8(FP) + + // Update the context + MOVD ctx+0(FP), R0 + MOVD R2, 24(R0) + MOVD R6, 104(R0) + MOVD 80(R0), R16 + SUB R16, R5, R5 + MOVD R5, 112(R0) + RET + +empty_seqs: + // Return value + MOVD $0x01, R16 + MOVB R16, ret+8(FP) + RET + +// func sequenceDecs_decodeSync_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int +// Requires: CMOV, SSE +TEXT ·sequenceDecs_decodeSync_arm64(SB), $64-32 + MOVD br+8(FP), R1 + MOVD 24(R1), R2 + MOVBU 40(R1), R3 + MOVD (R1), R0 + MOVD 32(R1), R5 + ADD R5, R0, R0 + MOVD R0, 8(RSP) + MOVD ctx+16(FP), R0 + MOVD 72(R0), R6 + MOVD 80(R0), R7 + MOVD 88(R0), R8 + MOVD $0, R1 + MOVD R1, 16(RSP) + MOVD R1, 24(RSP) + MOVD R1, 32(RSP) + MOVD 112(R0), R9 + MOVD 128(R0), R1 + MOVD R1, 40(RSP) + MOVD 144(R0), R10 + MOVD 136(R0), R11 + MOVD 200(R0), R1 + MOVD R1, 64(RSP) + MOVD 176(R0), R1 + MOVD R1, 56(RSP) + MOVD 184(R0), R0 + MOVD R0, 48(RSP) + MOVD 48(RSP), R0 + MOVD 56(RSP), R16 + ADD R0, R16, R16 + MOVD R16, 56(RSP) + + // Calculate pointer to s.out[cap(s.out)] (a past-end pointer) + MOVD 40(RSP), R16 + ADD R9, R16, R16 + MOVD R16, 40(RSP) + + // outBase += outPosition + ADD R11, R9, R9 + +sequenceDecs_decodeSync_amd64_main_loop: + MOVD 8(RSP), R12 + + // Fill bitreader to have enough for the offset and match length. + CMP $0x08, R5 + BLT sequenceDecs_decodeSync_amd64_fill_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R12, R12 + MOVD (R12), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decodeSync_amd64_fill_end + +sequenceDecs_decodeSync_amd64_fill_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decodeSync_amd64_fill_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decodeSync_amd64_fill_end + LSL $0x08, R2, R2 + SUB $0x01, R12, R12 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R12), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decodeSync_amd64_fill_byte_by_byte + +sequenceDecs_decodeSync_amd64_fill_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decodeSync_amd64_fill_end: + // Update offset + MOVD R8, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_amd64_of_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_amd64_of_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_amd64_of_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_amd64_of_update_zero: + MOVD R0, 16(RSP) + + // Update match length + MOVD R7, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_amd64_ml_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_amd64_ml_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_amd64_ml_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_amd64_ml_update_zero: + MOVD R0, 24(RSP) + + // Fill bitreader to have enough for the remaining + CMP $0x08, R5 + BLT sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R12, R12 + MOVD (R12), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decodeSync_amd64_fill_2_end + +sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decodeSync_amd64_fill_2_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decodeSync_amd64_fill_2_end + LSL $0x08, R2, R2 + SUB $0x01, R12, R12 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R12), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte + +sequenceDecs_decodeSync_amd64_fill_2_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decodeSync_amd64_fill_2_end: + // Update literal length + MOVD R6, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_amd64_ll_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_amd64_ll_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_amd64_ll_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_amd64_ll_update_zero: + MOVD R0, 32(RSP) + + // Fill bitreader for state updates + MOVD R12, 8(RSP) + MOVD R8, R0 + LSR $0x08, R0, R0 + MOVBU R0, R0 + MOVD ctx+16(FP), R1 + MOVD 96(R1), R16 + CMP $0x00, R16 + BEQ sequenceDecs_decodeSync_amd64_skip_update + + // Update Literal Length State + MOVBU R6, R12 + LSRW $0x10, R6, R6 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R6, R6 + + // Load ctx.llTable + MOVD ctx+16(FP), R1 + MOVD (R1), R1 + ADD R6<<3, R1, R15 + MOVD (R15), R6 + + // Update Match Length State + MOVBU R7, R12 + LSRW $0x10, R7, R7 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R7, R7 + + // Load ctx.mlTable + MOVD ctx+16(FP), R1 + MOVD 24(R1), R1 + ADD R7<<3, R1, R15 + MOVD (R15), R7 + + // Update Offset State + MOVBU R8, R12 + LSRW $0x10, R8, R8 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R8, R8 + + // Load ctx.ofTable + MOVD ctx+16(FP), R1 + MOVD 48(R1), R1 + ADD R8<<3, R1, R15 + MOVD (R15), R8 + +sequenceDecs_decodeSync_amd64_skip_update: + // Adjust offset + MOVD s+0(FP), R1 + MOVD 16(RSP), R12 + CMP $0x01, R0 + BLS sequenceDecs_decodeSync_amd64_adjust_offsetB_1_or_0 + ADD $144, R1, R15 + VLD1 (R15), [V0.B16] + MOVD R12, 144(R1) + ADD $152, R1, R15 + VST1 [V0.B16], (R15) + JMP sequenceDecs_decodeSync_amd64_after_adjust + +sequenceDecs_decodeSync_amd64_adjust_offsetB_1_or_0: + MOVD 32(RSP), R16 + CMP $0x00000000, R16 + BNE sequenceDecs_decodeSync_amd64_adjust_offset_maybezero + ADD $1, R12, R12 + JMP sequenceDecs_decodeSync_amd64_adjust_offset_nonzero + +sequenceDecs_decodeSync_amd64_adjust_offset_maybezero: + TST R12, R12 + BNE sequenceDecs_decodeSync_amd64_adjust_offset_nonzero + MOVD 144(R1), R12 + JMP sequenceDecs_decodeSync_amd64_after_adjust + +sequenceDecs_decodeSync_amd64_adjust_offset_nonzero: + MOVD R12, R0 + MOVD $0, R13 + MOVD $-1, R14 + CMP $0x03, R12 + CSEL EQ, R13, R0, R0 + CSEL EQ, R14, R13, R13 + ADD R0<<3, R1, R15 + MOVD 144(R15), R16 + ADDS R16, R13, R13 + BNE sequenceDecs_decodeSync_amd64_adjust_temp_valid + MOVD $0x00000001, R13 + +sequenceDecs_decodeSync_amd64_adjust_temp_valid: + CMP $0x01, R12 + BEQ sequenceDecs_decodeSync_amd64_adjust_skip + MOVD 152(R1), R0 + MOVD R0, 160(R1) + +sequenceDecs_decodeSync_amd64_adjust_skip: + MOVD 144(R1), R0 + MOVD R0, 152(R1) + MOVD R13, 144(R1) + MOVD R13, R12 + +sequenceDecs_decodeSync_amd64_after_adjust: + MOVD R12, 16(RSP) + + // Check values + MOVD 24(RSP), R0 + MOVD 32(RSP), R1 + ADD R1, R0, R13 + MOVD s+0(FP), R14 + MOVD 256(R14), R16 + ADD R13, R16, R16 + MOVD R16, 256(R14) + MOVD ctx+16(FP), R13 + MOVD 104(R13), R16 + SUBS R1, R16, R16 + MOVD R16, 104(R13) + BMI error_not_enough_literals + CMP $0x00020002, R0 + BHI sequenceDecs_decodeSync_amd64_error_match_len_too_big + TST R12, R12 + BNE sequenceDecs_decodeSync_amd64_match_len_ofs_ok + TST R0, R0 + BNE sequenceDecs_decodeSync_amd64_error_match_len_ofs_mismatch + +sequenceDecs_decodeSync_amd64_match_len_ofs_ok: + MOVD 32(RSP), R0 + MOVD 16(RSP), R1 + MOVD 24(RSP), R12 + + // Check if we have enough space in s.out + ADD R12, R0, R13 + ADD $16, R13, R13 + ADD R9, R13, R13 + MOVD 40(RSP), R16 + CMP R16, R13 + BHI error_not_enough_space + + // Copy literals + TST R0, R0 + BEQ check_offset + MOVD $0, R13 + +copy_1: + ADD R13, R10, R15 + VLD1 (R15), [V0.B16] + ADD R13, R9, R15 + VST1 [V0.B16], (R15) + ADD $0x10, R13, R13 + CMP R0, R13 + BLO copy_1 + ADD R0, R10, R10 + ADD R0, R9, R9 + ADD R0, R11, R11 + + // Malformed input if seq.mo > t+len(hist) || seq.mo > s.windowSize) +check_offset: + MOVD R11, R0 + MOVD 48(RSP), R16 + ADD R16, R0, R0 + CMP R0, R1 + BGT error_match_off_too_big + MOVD 64(RSP), R16 + CMP R16, R1 + BGT error_match_off_too_big + + // Copy match from history + MOVD R1, R0 + SUBS R11, R0, R0 + BLS copy_match + MOVD 56(RSP), R13 + SUB R0, R13, R13 + CMP R0, R12 + BGT copy_all_from_history + MOVD R12, R0 + SUBS $0x10, R0, R0 + BLO copy_4_small + +copy_4_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R13, R13 + ADD $0x10, R9, R9 + SUBS $0x10, R0, R0 + BHS copy_4_loop + ADD R0, R13, R13 + ADD $16, R13, R13 + ADD R0, R9, R9 + ADD $16, R9, R9 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_4_end + +copy_4_small: + CMP $0x03, R12 + BEQ copy_4_move_3 + CMP $0x08, R12 + BLO copy_4_move_4through7 + JMP copy_4_move_8through16 + +copy_4_move_3: + MOVHU (R13), R0 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R1 + MOVH R0, (R9) + MOVB R1, 2(R9) + ADD R12, R13, R13 + ADD R12, R9, R9 + JMP copy_4_end + +copy_4_move_4through7: + MOVWU (R13), R0 + ADD R12, R13, R15 + MOVWU -4(R15), R1 + MOVW R0, (R9) + ADD R12, R9, R15 + MOVW R1, -4(R15) + ADD R12, R13, R13 + ADD R12, R9, R9 + JMP copy_4_end + +copy_4_move_8through16: + MOVD (R13), R0 + ADD R12, R13, R15 + MOVD -8(R15), R1 + MOVD R0, (R9) + ADD R12, R9, R15 + MOVD R1, -8(R15) + ADD R12, R13, R13 + ADD R12, R9, R9 + +copy_4_end: + ADD R12, R11, R11 + JMP handle_loop + JMP loop_finished + +copy_all_from_history: + MOVD R0, R14 + SUBS $0x10, R14, R14 + BLO copy_5_small + +copy_5_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R13, R13 + ADD $0x10, R9, R9 + SUBS $0x10, R14, R14 + BHS copy_5_loop + ADD R14, R13, R13 + ADD $16, R13, R13 + ADD R14, R9, R9 + ADD $16, R9, R9 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_5_end + +copy_5_small: + CMP $0x03, R0 + BEQ copy_5_move_3 + BLO copy_5_move_1or2 + CMP $0x08, R0 + BLO copy_5_move_4through7 + JMP copy_5_move_8through16 + +copy_5_move_1or2: + MOVBU (R13), R16 + BFI $0, R16, $8, R14 + ADD R0, R13, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R4 + MOVB R14, (R9) + ADD R0, R9, R15 + MOVB R4, -1(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_3: + MOVHU (R13), R14 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R4 + MOVH R14, (R9) + MOVB R4, 2(R9) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_4through7: + MOVWU (R13), R14 + ADD R0, R13, R15 + MOVWU -4(R15), R4 + MOVW R14, (R9) + ADD R0, R9, R15 + MOVW R4, -4(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_8through16: + MOVD (R13), R14 + ADD R0, R13, R15 + MOVD -8(R15), R4 + MOVD R14, (R9) + ADD R0, R9, R15 + MOVD R4, -8(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + +copy_5_end: + ADD R0, R11, R11 + SUB R0, R12, R12 + + // Copy match from the current buffer +copy_match: + MOVD R9, R0 + SUB R1, R0, R0 + + // ml <= mo + CMP R1, R12 + BHI copy_overlapping_match + + // Copy non-overlapping match + ADD R12, R11, R11 + MOVD R9, R1 + ADD R12, R9, R9 + +copy_2: + VLD1 (R0), [V0.B16] + VST1 [V0.B16], (R1) + ADD $0x10, R0, R0 + ADD $0x10, R1, R1 + SUBS $0x10, R12, R12 + BHI copy_2 + JMP handle_loop + + // Copy overlapping match +copy_overlapping_match: + ADD R12, R11, R11 + +copy_slow_3: + MOVBU (R0), R16 + BFI $0, R16, $8, R1 + MOVB R1, (R9) + ADD $1, R0, R0 + ADD $1, R9, R9 + SUBS $1, R12, R12 + BNE copy_slow_3 + +handle_loop: + MOVD ctx+16(FP), R0 + MOVD 96(R0), R16 + SUBS $1, R16, R16 + MOVD R16, 96(R0) + BPL sequenceDecs_decodeSync_amd64_main_loop + +loop_finished: + MOVD br+8(FP), R0 + MOVD R2, 24(R0) + MOVB R3, 40(R0) + MOVD R5, 32(R0) + + // Update the context + MOVD ctx+16(FP), R0 + MOVD R11, 136(R0) + MOVD 144(R0), R1 + SUB R1, R10, R10 + MOVD R10, 168(R0) + + // Return success + MOVD $0x00000000, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match length error +sequenceDecs_decodeSync_amd64_error_match_len_ofs_mismatch: + MOVD 24(RSP), R0 + MOVD ctx+16(FP), R1 + MOVD R0, 216(R1) + MOVD $0x00000001, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match too long error +sequenceDecs_decodeSync_amd64_error_match_len_too_big: + MOVD ctx+16(FP), R0 + MOVD 24(RSP), R1 + MOVD R1, 216(R0) + MOVD $0x00000002, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match offset too long error +error_match_off_too_big: + MOVD ctx+16(FP), R0 + MOVD 16(RSP), R1 + MOVD R1, 224(R0) + MOVD R11, 136(R0) + MOVD $0x00000003, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough literals error +error_not_enough_literals: + MOVD ctx+16(FP), R0 + MOVD 32(RSP), R1 + MOVD R1, 208(R0) + MOVD $0x00000004, R16 + MOVD R16, ret+24(FP) + RET + + // Return with overread error +error_overread: + MOVD $0x00000006, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough output space error +error_not_enough_space: + MOVD ctx+16(FP), R0 + MOVD 32(RSP), R1 + MOVD R1, 208(R0) + MOVD 24(RSP), R1 + MOVD R1, 216(R0) + MOVD R11, 136(R0) + MOVD $0x00000005, R16 + MOVD R16, ret+24(FP) + RET + +// skipped sequenceDecs_decodeSync_bmi2 (generic twin preferred on arm64) + +// func sequenceDecs_decodeSync_safe_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int +// Requires: CMOV, SSE +TEXT ·sequenceDecs_decodeSync_safe_arm64(SB), $64-32 + MOVD br+8(FP), R1 + MOVD 24(R1), R2 + MOVBU 40(R1), R3 + MOVD (R1), R0 + MOVD 32(R1), R5 + ADD R5, R0, R0 + MOVD R0, 8(RSP) + MOVD ctx+16(FP), R0 + MOVD 72(R0), R6 + MOVD 80(R0), R7 + MOVD 88(R0), R8 + MOVD $0, R1 + MOVD R1, 16(RSP) + MOVD R1, 24(RSP) + MOVD R1, 32(RSP) + MOVD 112(R0), R9 + MOVD 128(R0), R1 + MOVD R1, 40(RSP) + MOVD 144(R0), R10 + MOVD 136(R0), R11 + MOVD 200(R0), R1 + MOVD R1, 64(RSP) + MOVD 176(R0), R1 + MOVD R1, 56(RSP) + MOVD 184(R0), R0 + MOVD R0, 48(RSP) + MOVD 48(RSP), R0 + MOVD 56(RSP), R16 + ADD R0, R16, R16 + MOVD R16, 56(RSP) + + // Calculate pointer to s.out[cap(s.out)] (a past-end pointer) + MOVD 40(RSP), R16 + ADD R9, R16, R16 + MOVD R16, 40(RSP) + + // outBase += outPosition + ADD R11, R9, R9 + +sequenceDecs_decodeSync_safe_amd64_main_loop: + MOVD 8(RSP), R12 + + // Fill bitreader to have enough for the offset and match length. + CMP $0x08, R5 + BLT sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R12, R12 + MOVD (R12), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decodeSync_safe_amd64_fill_end + +sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decodeSync_safe_amd64_fill_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decodeSync_safe_amd64_fill_end + LSL $0x08, R2, R2 + SUB $0x01, R12, R12 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R12), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte + +sequenceDecs_decodeSync_safe_amd64_fill_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decodeSync_safe_amd64_fill_end: + // Update offset + MOVD R8, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_safe_amd64_of_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_safe_amd64_of_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_safe_amd64_of_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_safe_amd64_of_update_zero: + MOVD R0, 16(RSP) + + // Update match length + MOVD R7, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_safe_amd64_ml_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_safe_amd64_ml_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_safe_amd64_ml_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_safe_amd64_ml_update_zero: + MOVD R0, 24(RSP) + + // Fill bitreader to have enough for the remaining + CMP $0x08, R5 + BLT sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte + MOVD R3, R0 + LSR $0x03, R0, R0 + SUB R0, R12, R12 + MOVD (R12), R2 + SUB R0, R5, R5 + AND $0x07, R3, R3 + JMP sequenceDecs_decodeSync_safe_amd64_fill_2_end + +sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte: + CMP $0x00, R5 + BLE sequenceDecs_decodeSync_safe_amd64_fill_2_check_overread + CMP $0x07, R3 + BLE sequenceDecs_decodeSync_safe_amd64_fill_2_end + LSL $0x08, R2, R2 + SUB $0x01, R12, R12 + SUB $0x01, R5, R5 + SUB $0x08, R3, R3 + MOVBU (R12), R0 + ORR R0, R2, R2 + JMP sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte + +sequenceDecs_decodeSync_safe_amd64_fill_2_check_overread: + CMP $0x40, R3 + BHI error_overread + +sequenceDecs_decodeSync_safe_amd64_fill_2_end: + // Update literal length + MOVD R6, R0 + MOVD R3, R1 + MOVD R2, R13 + LSL R1, R13, R13 + UBFX $8, R0, $8, R16 + BFI $0, R16, $8, R1 + LSR $0x20, R0, R0 + TST R1, R1 + BEQ sequenceDecs_decodeSync_safe_amd64_ll_update_zero + ADD R1, R3, R3 + CMP $0x40, R3 + BHI sequenceDecs_decodeSync_safe_amd64_ll_update_zero + CMP $0x40, R1 + BHS sequenceDecs_decodeSync_safe_amd64_ll_update_zero + NEG R1, R1 + LSR R1, R13, R13 + ADD R13, R0, R0 + +sequenceDecs_decodeSync_safe_amd64_ll_update_zero: + MOVD R0, 32(RSP) + + // Fill bitreader for state updates + MOVD R12, 8(RSP) + MOVD R8, R0 + LSR $0x08, R0, R0 + MOVBU R0, R0 + MOVD ctx+16(FP), R1 + MOVD 96(R1), R16 + CMP $0x00, R16 + BEQ sequenceDecs_decodeSync_safe_amd64_skip_update + + // Update Literal Length State + MOVBU R6, R12 + LSRW $0x10, R6, R6 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R6, R6 + + // Load ctx.llTable + MOVD ctx+16(FP), R1 + MOVD (R1), R1 + ADD R6<<3, R1, R15 + MOVD (R15), R6 + + // Update Match Length State + MOVBU R7, R12 + LSRW $0x10, R7, R7 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R7, R7 + + // Load ctx.mlTable + MOVD ctx+16(FP), R1 + MOVD 24(R1), R1 + ADD R7<<3, R1, R15 + MOVD (R15), R7 + + // Update Offset State + MOVBU R8, R12 + LSRW $0x10, R8, R8 + ADD R12, R3, R1 + MOVD R2, R13 + MOVD R1, R3 + NEG R1, R16 + ROR R16, R13, R13 + MOVD $0x00000001, R14 + BFI $0, R12, $8, R1 + LSLW R1, R14, R14 + SUBW $1, R14, R14 + AND R14, R13, R13 + ADD R13, R8, R8 + + // Load ctx.ofTable + MOVD ctx+16(FP), R1 + MOVD 48(R1), R1 + ADD R8<<3, R1, R15 + MOVD (R15), R8 + +sequenceDecs_decodeSync_safe_amd64_skip_update: + // Adjust offset + MOVD s+0(FP), R1 + MOVD 16(RSP), R12 + CMP $0x01, R0 + BLS sequenceDecs_decodeSync_safe_amd64_adjust_offsetB_1_or_0 + ADD $144, R1, R15 + VLD1 (R15), [V0.B16] + MOVD R12, 144(R1) + ADD $152, R1, R15 + VST1 [V0.B16], (R15) + JMP sequenceDecs_decodeSync_safe_amd64_after_adjust + +sequenceDecs_decodeSync_safe_amd64_adjust_offsetB_1_or_0: + MOVD 32(RSP), R16 + CMP $0x00000000, R16 + BNE sequenceDecs_decodeSync_safe_amd64_adjust_offset_maybezero + ADD $1, R12, R12 + JMP sequenceDecs_decodeSync_safe_amd64_adjust_offset_nonzero + +sequenceDecs_decodeSync_safe_amd64_adjust_offset_maybezero: + TST R12, R12 + BNE sequenceDecs_decodeSync_safe_amd64_adjust_offset_nonzero + MOVD 144(R1), R12 + JMP sequenceDecs_decodeSync_safe_amd64_after_adjust + +sequenceDecs_decodeSync_safe_amd64_adjust_offset_nonzero: + MOVD R12, R0 + MOVD $0, R13 + MOVD $-1, R14 + CMP $0x03, R12 + CSEL EQ, R13, R0, R0 + CSEL EQ, R14, R13, R13 + ADD R0<<3, R1, R15 + MOVD 144(R15), R16 + ADDS R16, R13, R13 + BNE sequenceDecs_decodeSync_safe_amd64_adjust_temp_valid + MOVD $0x00000001, R13 + +sequenceDecs_decodeSync_safe_amd64_adjust_temp_valid: + CMP $0x01, R12 + BEQ sequenceDecs_decodeSync_safe_amd64_adjust_skip + MOVD 152(R1), R0 + MOVD R0, 160(R1) + +sequenceDecs_decodeSync_safe_amd64_adjust_skip: + MOVD 144(R1), R0 + MOVD R0, 152(R1) + MOVD R13, 144(R1) + MOVD R13, R12 + +sequenceDecs_decodeSync_safe_amd64_after_adjust: + MOVD R12, 16(RSP) + + // Check values + MOVD 24(RSP), R0 + MOVD 32(RSP), R1 + ADD R1, R0, R13 + MOVD s+0(FP), R14 + MOVD 256(R14), R16 + ADD R13, R16, R16 + MOVD R16, 256(R14) + MOVD ctx+16(FP), R13 + MOVD 104(R13), R16 + SUBS R1, R16, R16 + MOVD R16, 104(R13) + BMI error_not_enough_literals + CMP $0x00020002, R0 + BHI sequenceDecs_decodeSync_safe_amd64_error_match_len_too_big + TST R12, R12 + BNE sequenceDecs_decodeSync_safe_amd64_match_len_ofs_ok + TST R0, R0 + BNE sequenceDecs_decodeSync_safe_amd64_error_match_len_ofs_mismatch + +sequenceDecs_decodeSync_safe_amd64_match_len_ofs_ok: + MOVD 32(RSP), R0 + MOVD 16(RSP), R1 + MOVD 24(RSP), R12 + + // Check if we have enough space in s.out + ADD R12, R0, R13 + ADD R9, R13, R13 + MOVD 40(RSP), R16 + CMP R16, R13 + BHI error_not_enough_space + + // Copy literals + TST R0, R0 + BEQ check_offset + MOVD R0, R13 + SUBS $0x10, R13, R13 + BLO copy_1_small + +copy_1_loop: + VLD1 (R10), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R10, R10 + ADD $0x10, R9, R9 + SUBS $0x10, R13, R13 + BHS copy_1_loop + ADD R13, R10, R10 + ADD $16, R10, R10 + ADD R13, R9, R9 + ADD $16, R9, R9 + ADD $-16, R10, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_1_end + +copy_1_small: + CMP $0x03, R0 + BEQ copy_1_move_3 + BLO copy_1_move_1or2 + CMP $0x08, R0 + BLO copy_1_move_4through7 + JMP copy_1_move_8through16 + +copy_1_move_1or2: + MOVBU (R10), R16 + BFI $0, R16, $8, R13 + ADD R0, R10, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R14 + MOVB R13, (R9) + ADD R0, R9, R15 + MOVB R14, -1(R15) + ADD R0, R10, R10 + ADD R0, R9, R9 + JMP copy_1_end + +copy_1_move_3: + MOVHU (R10), R13 + MOVBU 2(R10), R16 + BFI $0, R16, $8, R14 + MOVH R13, (R9) + MOVB R14, 2(R9) + ADD R0, R10, R10 + ADD R0, R9, R9 + JMP copy_1_end + +copy_1_move_4through7: + MOVWU (R10), R13 + ADD R0, R10, R15 + MOVWU -4(R15), R14 + MOVW R13, (R9) + ADD R0, R9, R15 + MOVW R14, -4(R15) + ADD R0, R10, R10 + ADD R0, R9, R9 + JMP copy_1_end + +copy_1_move_8through16: + MOVD (R10), R13 + ADD R0, R10, R15 + MOVD -8(R15), R14 + MOVD R13, (R9) + ADD R0, R9, R15 + MOVD R14, -8(R15) + ADD R0, R10, R10 + ADD R0, R9, R9 + +copy_1_end: + ADD R0, R11, R11 + + // Malformed input if seq.mo > t+len(hist) || seq.mo > s.windowSize) +check_offset: + MOVD R11, R0 + MOVD 48(RSP), R16 + ADD R16, R0, R0 + CMP R0, R1 + BGT error_match_off_too_big + MOVD 64(RSP), R16 + CMP R16, R1 + BGT error_match_off_too_big + + // Copy match from history + MOVD R1, R0 + SUBS R11, R0, R0 + BLS copy_match + MOVD 56(RSP), R13 + SUB R0, R13, R13 + CMP R0, R12 + BGT copy_all_from_history + MOVD R12, R0 + SUBS $0x10, R0, R0 + BLO copy_4_small + +copy_4_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R13, R13 + ADD $0x10, R9, R9 + SUBS $0x10, R0, R0 + BHS copy_4_loop + ADD R0, R13, R13 + ADD $16, R13, R13 + ADD R0, R9, R9 + ADD $16, R9, R9 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_4_end + +copy_4_small: + CMP $0x03, R12 + BEQ copy_4_move_3 + CMP $0x08, R12 + BLO copy_4_move_4through7 + JMP copy_4_move_8through16 + +copy_4_move_3: + MOVHU (R13), R0 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R1 + MOVH R0, (R9) + MOVB R1, 2(R9) + ADD R12, R13, R13 + ADD R12, R9, R9 + JMP copy_4_end + +copy_4_move_4through7: + MOVWU (R13), R0 + ADD R12, R13, R15 + MOVWU -4(R15), R1 + MOVW R0, (R9) + ADD R12, R9, R15 + MOVW R1, -4(R15) + ADD R12, R13, R13 + ADD R12, R9, R9 + JMP copy_4_end + +copy_4_move_8through16: + MOVD (R13), R0 + ADD R12, R13, R15 + MOVD -8(R15), R1 + MOVD R0, (R9) + ADD R12, R9, R15 + MOVD R1, -8(R15) + ADD R12, R13, R13 + ADD R12, R9, R9 + +copy_4_end: + ADD R12, R11, R11 + JMP handle_loop + JMP loop_finished + +copy_all_from_history: + MOVD R0, R14 + SUBS $0x10, R14, R14 + BLO copy_5_small + +copy_5_loop: + VLD1 (R13), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R13, R13 + ADD $0x10, R9, R9 + SUBS $0x10, R14, R14 + BHS copy_5_loop + ADD R14, R13, R13 + ADD $16, R13, R13 + ADD R14, R9, R9 + ADD $16, R9, R9 + ADD $-16, R13, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_5_end + +copy_5_small: + CMP $0x03, R0 + BEQ copy_5_move_3 + BLO copy_5_move_1or2 + CMP $0x08, R0 + BLO copy_5_move_4through7 + JMP copy_5_move_8through16 + +copy_5_move_1or2: + MOVBU (R13), R16 + BFI $0, R16, $8, R14 + ADD R0, R13, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R4 + MOVB R14, (R9) + ADD R0, R9, R15 + MOVB R4, -1(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_3: + MOVHU (R13), R14 + MOVBU 2(R13), R16 + BFI $0, R16, $8, R4 + MOVH R14, (R9) + MOVB R4, 2(R9) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_4through7: + MOVWU (R13), R14 + ADD R0, R13, R15 + MOVWU -4(R15), R4 + MOVW R14, (R9) + ADD R0, R9, R15 + MOVW R4, -4(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + JMP copy_5_end + +copy_5_move_8through16: + MOVD (R13), R14 + ADD R0, R13, R15 + MOVD -8(R15), R4 + MOVD R14, (R9) + ADD R0, R9, R15 + MOVD R4, -8(R15) + ADD R0, R13, R13 + ADD R0, R9, R9 + +copy_5_end: + ADD R0, R11, R11 + SUB R0, R12, R12 + + // Copy match from the current buffer +copy_match: + MOVD R9, R0 + SUB R1, R0, R0 + + // ml <= mo + CMP R1, R12 + BHI copy_overlapping_match + + // Copy non-overlapping match + ADD R12, R11, R11 + MOVD R12, R1 + SUBS $0x10, R1, R1 + BLO copy_2_small + +copy_2_loop: + VLD1 (R0), [V0.B16] + VST1 [V0.B16], (R9) + ADD $0x10, R0, R0 + ADD $0x10, R9, R9 + SUBS $0x10, R1, R1 + BHS copy_2_loop + ADD R1, R0, R0 + ADD $16, R0, R0 + ADD R1, R9, R9 + ADD $16, R9, R9 + ADD $-16, R0, R15 + VLD1 (R15), [V0.B16] + ADD $-16, R9, R15 + VST1 [V0.B16], (R15) + JMP copy_2_end + +copy_2_small: + CMP $0x03, R12 + BEQ copy_2_move_3 + BLO copy_2_move_1or2 + CMP $0x08, R12 + BLO copy_2_move_4through7 + JMP copy_2_move_8through16 + +copy_2_move_1or2: + MOVBU (R0), R16 + BFI $0, R16, $8, R1 + ADD R12, R0, R15 + MOVBU -1(R15), R16 + BFI $0, R16, $8, R13 + MOVB R1, (R9) + ADD R12, R9, R15 + MOVB R13, -1(R15) + ADD R12, R0, R0 + ADD R12, R9, R9 + JMP copy_2_end + +copy_2_move_3: + MOVHU (R0), R1 + MOVBU 2(R0), R16 + BFI $0, R16, $8, R13 + MOVH R1, (R9) + MOVB R13, 2(R9) + ADD R12, R0, R0 + ADD R12, R9, R9 + JMP copy_2_end + +copy_2_move_4through7: + MOVWU (R0), R1 + ADD R12, R0, R15 + MOVWU -4(R15), R13 + MOVW R1, (R9) + ADD R12, R9, R15 + MOVW R13, -4(R15) + ADD R12, R0, R0 + ADD R12, R9, R9 + JMP copy_2_end + +copy_2_move_8through16: + MOVD (R0), R1 + ADD R12, R0, R15 + MOVD -8(R15), R13 + MOVD R1, (R9) + ADD R12, R9, R15 + MOVD R13, -8(R15) + ADD R12, R0, R0 + ADD R12, R9, R9 + +copy_2_end: + JMP handle_loop + + // Copy overlapping match +copy_overlapping_match: + ADD R12, R11, R11 + +copy_slow_3: + MOVBU (R0), R16 + BFI $0, R16, $8, R1 + MOVB R1, (R9) + ADD $1, R0, R0 + ADD $1, R9, R9 + SUBS $1, R12, R12 + BNE copy_slow_3 + +handle_loop: + MOVD ctx+16(FP), R0 + MOVD 96(R0), R16 + SUBS $1, R16, R16 + MOVD R16, 96(R0) + BPL sequenceDecs_decodeSync_safe_amd64_main_loop + +loop_finished: + MOVD br+8(FP), R0 + MOVD R2, 24(R0) + MOVB R3, 40(R0) + MOVD R5, 32(R0) + + // Update the context + MOVD ctx+16(FP), R0 + MOVD R11, 136(R0) + MOVD 144(R0), R1 + SUB R1, R10, R10 + MOVD R10, 168(R0) + + // Return success + MOVD $0x00000000, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match length error +sequenceDecs_decodeSync_safe_amd64_error_match_len_ofs_mismatch: + MOVD 24(RSP), R0 + MOVD ctx+16(FP), R1 + MOVD R0, 216(R1) + MOVD $0x00000001, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match too long error +sequenceDecs_decodeSync_safe_amd64_error_match_len_too_big: + MOVD ctx+16(FP), R0 + MOVD 24(RSP), R1 + MOVD R1, 216(R0) + MOVD $0x00000002, R16 + MOVD R16, ret+24(FP) + RET + + // Return with match offset too long error +error_match_off_too_big: + MOVD ctx+16(FP), R0 + MOVD 16(RSP), R1 + MOVD R1, 224(R0) + MOVD R11, 136(R0) + MOVD $0x00000003, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough literals error +error_not_enough_literals: + MOVD ctx+16(FP), R0 + MOVD 32(RSP), R1 + MOVD R1, 208(R0) + MOVD $0x00000004, R16 + MOVD R16, ret+24(FP) + RET + + // Return with overread error +error_overread: + MOVD $0x00000006, R16 + MOVD R16, ret+24(FP) + RET + + // Return with not enough output space error +error_not_enough_space: + MOVD ctx+16(FP), R0 + MOVD 32(RSP), R1 + MOVD R1, 208(R0) + MOVD 24(RSP), R1 + MOVD R1, 216(R0) + MOVD R11, 136(R0) + MOVD $0x00000005, R16 + MOVD R16, ret+24(FP) + RET + +// skipped sequenceDecs_decodeSync_safe_bmi2 (generic twin preferred on arm64) diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_asm.go b/vendor/github.com/klauspost/compress/zstd/seqdec_asm.go new file mode 100644 index 000000000000..42ce5de71636 --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_asm.go @@ -0,0 +1,316 @@ +//go:build (amd64 || arm64) && !appengine && !noasm && gc + +package zstd + +import ( + "fmt" + "io" +) + +// This file holds the parts of the assembly sequence decoder that are identical +// across architectures: the context structs exchanged with the asm, the error +// codes, and the decode/decodeSync/executeSimple wrappers. Each architecture +// supplies the small dispatch helpers (decodeAsm, decodeSyncAsm, +// executeSimpleAsm) that select the concrete asm routine — amd64 also chooses a +// BMI2 variant, arm64 has a single implementation. + +type decodeSyncAsmContext struct { + llTable []decSymbol + mlTable []decSymbol + ofTable []decSymbol + llState uint64 + mlState uint64 + ofState uint64 + iteration int + litRemain int + out []byte + outPosition int + literals []byte + litPosition int + history []byte + windowSize int + ll int // set on error (not for all errors, please refer to _generate/gen.go) + ml int // set on error (not for all errors, please refer to _generate/gen.go) + mo int // set on error (not for all errors, please refer to _generate/gen.go) +} + +type decodeAsmContext struct { + llTable []decSymbol + mlTable []decSymbol + ofTable []decSymbol + llState uint64 + mlState uint64 + ofState uint64 + iteration int + seqs []seqVals + litRemain int +} + +type executeAsmContext struct { + seqs []seqVals + seqIndex int + out []byte + history []byte + literals []byte + outPosition int + litPosition int + windowSize int +} + +const noError = 0 + +// error reported when mo == 0 && ml > 0 +const errorMatchLenOfsMismatch = 1 + +// error reported when ml > maxMatchLen +const errorMatchLenTooBig = 2 + +// error reported when mo > available history or mo > s.windowSize +const errorMatchOffTooBig = 3 + +// error reported when the sum of literal lengths exeeceds the literal buffer size +const errorNotEnoughLiterals = 4 + +// error reported when capacity of `out` is too small +const errorNotEnoughSpace = 5 + +// error reported when bits are overread. +const errorOverread = 6 + +// useSafeDecodeSync reports whether decodeSyncSimple must use the bounds-exact +// ("safe") copy variants for the current buffer geometry. +// +// When the output and literal buffers have compressedBlockOverAlloc (16) +// bytes of slack past their logical use, the assembly may use extended +// memory copies that read and write in 16-byte blocks, overrunning the end +// of a literal run or match by up to 15 bytes. Otherwise it must use the +// bounds-exact ("safe") copies. This mirrors the analogous, always-dynamic +// selection in executeSimple below. +// +// The unsafe copies were disabled in #644 (2022) as a mitigation for a +// crash, but that crash's root cause — an unguarded bitReader overread that +// produced out-of-range match offsets/lengths — was fixed three days later +// in #645, which also added the fuzz corpus that has guarded this path since. +// See #1168. An asan-instrumented fuzz job (see .github/workflows/go.yml) +// covers the extended-copy path, which -race and plain fuzzing cannot. +func (s *sequenceDecs) useSafeDecodeSync() bool { + if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSizeAlloc { + return true + } + if s.maxSyncLen > 0 && cap(s.out)-len(s.out)-compressedBlockOverAlloc < int(s.maxSyncLen) { + return true + } + if cap(s.literals) < len(s.literals)+compressedBlockOverAlloc { + return true + } + return false +} + +// decode sequences from the stream with the provided history but without a dictionary. +func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) { + if len(s.dict) > 0 { + return false, nil + } + if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSize { + return false, nil + } + + useSafe := s.useSafeDecodeSync() + + br := s.br + + maxBlockSize := min(s.windowSize, maxCompressedBlockSize) + + ctx := decodeSyncAsmContext{ + llTable: s.litLengths.fse.dt[:maxTablesize], + mlTable: s.matchLengths.fse.dt[:maxTablesize], + ofTable: s.offsets.fse.dt[:maxTablesize], + llState: uint64(s.litLengths.state.state), + mlState: uint64(s.matchLengths.state.state), + ofState: uint64(s.offsets.state.state), + iteration: s.nSeqs - 1, + litRemain: len(s.literals), + out: s.out, + outPosition: len(s.out), + literals: s.literals, + windowSize: s.windowSize, + history: hist, + } + + s.seqSize = 0 + startSize := len(s.out) + + errCode := decodeSyncAsm(s, br, &ctx, useSafe) + switch errCode { + case noError: + break + + case errorMatchLenOfsMismatch: + return true, fmt.Errorf("zero matchoff and matchlen (%d) > 0", ctx.ml) + + case errorMatchLenTooBig: + return true, fmt.Errorf("match len (%d) bigger than max allowed length", ctx.ml) + + case errorMatchOffTooBig: + return true, fmt.Errorf("match offset (%d) bigger than current history (%d)", + ctx.mo, ctx.outPosition+len(hist)-startSize) + + case errorNotEnoughLiterals: + return true, fmt.Errorf("unexpected literal count, want %d bytes, but only %d is available", + ctx.ll, ctx.litRemain+ctx.ll) + + case errorOverread: + return true, io.ErrUnexpectedEOF + + case errorNotEnoughSpace: + size := ctx.outPosition + ctx.ll + ctx.ml + if debugDecoder { + println("msl:", s.maxSyncLen, "cap", cap(s.out), "bef:", startSize, "sz:", size-startSize, "mbs:", maxBlockSize, "outsz:", cap(s.out)-startSize) + } + return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) + + default: + return true, fmt.Errorf("sequenceDecs_decode returned erroneous code %d", errCode) + } + + s.seqSize += ctx.litRemain + if s.seqSize > maxBlockSize { + return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) + } + err := br.close() + if err != nil { + printf("Closing sequences: %v, %+v\n", err, *br) + return true, err + } + + s.literals = s.literals[ctx.litPosition:] + t := ctx.outPosition + s.out = s.out[:t] + + // Add final literals + s.out = append(s.out, s.literals...) + if debugDecoder { + t += len(s.literals) + if t != len(s.out) { + panic(fmt.Errorf("length mismatch, want %d, got %d", len(s.out), t)) + } + } + + return true, nil +} + +// decode sequences from the stream without the provided history. +func (s *sequenceDecs) decode(seqs []seqVals) error { + br := s.br + + maxBlockSize := min(s.windowSize, maxCompressedBlockSize) + + ctx := decodeAsmContext{ + llTable: s.litLengths.fse.dt[:maxTablesize], + mlTable: s.matchLengths.fse.dt[:maxTablesize], + ofTable: s.offsets.fse.dt[:maxTablesize], + llState: uint64(s.litLengths.state.state), + mlState: uint64(s.matchLengths.state.state), + ofState: uint64(s.offsets.state.state), + seqs: seqs, + iteration: len(seqs) - 1, + litRemain: len(s.literals), + } + + if debugDecoder { + println("decode: decoding", len(seqs), "sequences", br.remain(), "bits remain on stream") + } + + s.seqSize = 0 + lte56bits := s.maxBits+s.offsets.fse.actualTableLog+s.matchLengths.fse.actualTableLog+s.litLengths.fse.actualTableLog <= 56 + errCode := decodeAsm(s, br, &ctx, lte56bits) + if errCode != 0 { + i := len(seqs) - ctx.iteration - 1 + switch errCode { + case errorMatchLenOfsMismatch: + ml := ctx.seqs[i].ml + return fmt.Errorf("zero matchoff and matchlen (%d) > 0", ml) + + case errorMatchLenTooBig: + ml := ctx.seqs[i].ml + return fmt.Errorf("match len (%d) bigger than max allowed length", ml) + + case errorNotEnoughLiterals: + ll := ctx.seqs[i].ll + return fmt.Errorf("unexpected literal count, want %d bytes, but only %d is available", ll, ctx.litRemain+ll) + case errorOverread: + return io.ErrUnexpectedEOF + } + + return fmt.Errorf("sequenceDecs_decode_amd64 returned erroneous code %d", errCode) + } + + if ctx.litRemain < 0 { + return fmt.Errorf("literal count is too big: total available %d, total requested %d", + len(s.literals), len(s.literals)-ctx.litRemain) + } + + s.seqSize += ctx.litRemain + if s.seqSize > maxBlockSize { + return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) + } + if debugDecoder { + println("decode: ", br.remain(), "bits remain on stream. code:", errCode) + } + err := br.close() + if err != nil { + printf("Closing sequences: %v, %+v\n", err, *br) + } + return err +} + +// executeSimple handles cases when dictionary is not used. +func (s *sequenceDecs) executeSimple(seqs []seqVals, hist []byte) error { + // Ensure we have enough output size... + if len(s.out)+s.seqSize+compressedBlockOverAlloc > cap(s.out) { + addBytes := s.seqSize + len(s.out) + compressedBlockOverAlloc + s.out = append(s.out, make([]byte, addBytes)...) + s.out = s.out[:len(s.out)-addBytes] + } + + if debugDecoder { + printf("Execute %d seqs with literals: %d into %d bytes\n", len(seqs), len(s.literals), s.seqSize) + } + + var t = len(s.out) + out := s.out[:t+s.seqSize] + + ctx := executeAsmContext{ + seqs: seqs, + seqIndex: 0, + out: out, + history: hist, + outPosition: t, + litPosition: 0, + literals: s.literals, + windowSize: s.windowSize, + } + // useSafe avoids overwriting the output buffer when the literals slice has + // not been allocated with the required over-allocation slack. + useSafe := cap(s.literals) < len(s.literals)+compressedBlockOverAlloc + + ok := executeSimpleAsm(&ctx, useSafe) + if !ok { + return fmt.Errorf("match offset (%d) bigger than current history (%d)", + seqs[ctx.seqIndex].mo, ctx.outPosition+len(hist)) + } + s.literals = s.literals[ctx.litPosition:] + t = ctx.outPosition + + // Add final literals + copy(out[t:], s.literals) + if debugDecoder { + t += len(s.literals) + if t != len(out) { + panic(fmt.Errorf("length mismatch, want %d, got %d, ss: %d", len(out), t, s.seqSize)) + } + } + s.out = out + + return nil +} diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_generic.go b/vendor/github.com/klauspost/compress/zstd/seqdec_generic.go index 516cd9b07013..8a3db6ba22f1 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_generic.go +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_generic.go @@ -1,4 +1,4 @@ -//go:build !amd64 || appengine || !gc || noasm +//go:build (!amd64 && !arm64) || appengine || !gc || noasm package zstd diff --git a/vendor/github.com/klauspost/compress/zstd/snappy.go b/vendor/github.com/klauspost/compress/zstd/snappy.go index 336c28893045..36c56f36d771 100644 --- a/vendor/github.com/klauspost/compress/zstd/snappy.go +++ b/vendor/github.com/klauspost/compress/zstd/snappy.go @@ -334,9 +334,10 @@ func decodeSnappy(blk *blockEnc, src []byte) error { return errUnsupportedLiteralLength } - //if length > snappyMaxBlockSize-d || uint32(length) > len(src)-s { - // return ErrSnappyCorrupt - //} + if length > len(src)-s { + println("length > len(src)-s", length, len(src)-s) + return ErrSnappyCorrupt + } blk.literals = append(blk.literals, src[s:s+length]...) //println(length, "litLen") diff --git a/vendor/modules.txt b/vendor/modules.txt index 1cebccd6194d..1fbb530bde94 100644 --- a/vendor/modules.txt +++ b/vendor/modules.txt @@ -146,7 +146,7 @@ github.com/grpc-ecosystem/grpc-gateway/v2/utilities # github.com/inconshreveable/mousetrap v1.1.0 ## explicit; go 1.18 github.com/inconshreveable/mousetrap -# github.com/klauspost/compress v1.18.7 +# github.com/klauspost/compress v1.19.2 ## explicit; go 1.24 github.com/klauspost/compress github.com/klauspost/compress/fse