ceph-csi/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go
dependabot[bot] b044363a31 rebase: bump the github-dependencies group across 1 directory with 4 updates
Bumps the github-dependencies group with 4 updates in the / directory: [github.com/aws/aws-sdk-go-v2/service/sts](https://github.com/aws/aws-sdk-go-v2), [github.com/kubernetes-csi/csi-lib-utils](https://github.com/kubernetes-csi/csi-lib-utils), [github.com/onsi/ginkgo/v2](https://github.com/onsi/ginkgo) and [github.com/prometheus/client_golang](https://github.com/prometheus/client_golang).


Updates `github.com/aws/aws-sdk-go-v2/service/sts` from 1.30.3 to 1.30.4
- [Release notes](https://github.com/aws/aws-sdk-go-v2/releases)
- [Commits](https://github.com/aws/aws-sdk-go-v2/compare/v1.30.3...v1.30.4)

Updates `github.com/kubernetes-csi/csi-lib-utils` from 0.18.1 to 0.19.0
- [Release notes](https://github.com/kubernetes-csi/csi-lib-utils/releases)
- [Commits](https://github.com/kubernetes-csi/csi-lib-utils/compare/v0.18.1...v0.19.0)

Updates `github.com/onsi/ginkgo/v2` from 2.19.1 to 2.20.0
- [Release notes](https://github.com/onsi/ginkgo/releases)
- [Changelog](https://github.com/onsi/ginkgo/blob/master/CHANGELOG.md)
- [Commits](https://github.com/onsi/ginkgo/compare/v2.19.1...v2.20.0)

Updates `github.com/prometheus/client_golang` from 1.19.1 to 1.20.1
- [Release notes](https://github.com/prometheus/client_golang/releases)
- [Changelog](https://github.com/prometheus/client_golang/blob/v1.20.1/CHANGELOG.md)
- [Commits](https://github.com/prometheus/client_golang/compare/v1.19.1...v1.20.1)

---
updated-dependencies:
- dependency-name: github.com/aws/aws-sdk-go-v2/service/sts
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: github-dependencies
- dependency-name: github.com/kubernetes-csi/csi-lib-utils
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: github-dependencies
- dependency-name: github.com/onsi/ginkgo/v2
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: github-dependencies
- dependency-name: github.com/prometheus/client_golang
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: github-dependencies
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-08-22 10:52:39 +00:00

227 lines
5.7 KiB
Go

//go:build amd64 && !appengine && !noasm && gc
// +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.
package huff0
import (
"errors"
"fmt"
"github.com/klauspost/compress/internal/cpuinfo"
)
// decompress4x_main_loop_x86 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
// 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 := 0; i < 3; i++ {
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 := offset + remainBytes
if endsAt > len(out) {
endsAt = 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
// 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
// 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
}
// 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]
}
// 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()
}