Skip to content

Commit

Permalink
huff0: Assembler improvements (#736)
Browse files Browse the repository at this point in the history 
Main changes:

* Compute out[id * dstEvery + i] statically. This shaves four
  instructions off the main loops. (It also frees up a register.)

* Track "exhausted" by addition instead or OR. This gets rid of an
  additional instruction. The variable is now also zeroed inside the
  loop as a dependency hint.

Benchmark results show small speedups on some datasets:

```
name                                           old speed      new speed      delta
Decompress1XTable/digits-8                      350MB/s ± 0%   350MB/s ± 1%    ~     (p=0.764 n=10+9)
Decompress1XTable/gettysburg-8                  270MB/s ± 1%   268MB/s ± 1%  -0.72%  (p=0.001 n=10+10)
Decompress1XTable/twain-8                       329MB/s ± 1%   328MB/s ± 0%    ~     (p=0.035 n=10+9)
Decompress1XTable/low-ent.10k-8                 387MB/s ± 1%   386MB/s ± 0%    ~     (p=0.027 n=10+8)
Decompress1XTable/superlow-ent-10k-8            377MB/s ± 0%   375MB/s ± 0%  -0.48%  (p=0.000 n=10+10)
Decompress1XTable/crash2-8                     17.0MB/s ± 0%  16.9MB/s ± 0%  -0.36%  (p=0.004 n=9+10)
Decompress1XTable/endzerobits-8                53.3MB/s ± 0%  53.0MB/s ± 0%  -0.55%  (p=0.000 n=10+9)
Decompress1XTable/endnonzero-8                 11.3MB/s ± 0%  11.3MB/s ± 1%    ~     (p=0.060 n=10+10)
Decompress1XTable/case1-8                      22.0MB/s ± 0%  21.9MB/s ± 1%    ~     (p=0.015 n=9+9)
Decompress1XTable/case2-8                      18.1MB/s ± 1%  18.1MB/s ± 1%    ~     (p=0.202 n=10+9)
Decompress1XTable/case3-8                      19.1MB/s ± 1%  19.2MB/s ± 1%    ~     (p=0.056 n=9+10)
Decompress1XTable/pngdata.001-8                 374MB/s ± 0%   374MB/s ± 0%    ~     (p=0.148 n=10+10)
Decompress1XTable/normcount2-8                 54.4MB/s ± 1%  54.4MB/s ± 1%    ~     (p=0.617 n=10+10)
Decompress1XNoTable/digits/100-8                280MB/s ± 0%   280MB/s ± 1%    ~     (p=0.951 n=9+10)
Decompress1XNoTable/digits/10000-8              366MB/s ± 1%   367MB/s ± 0%    ~     (p=0.090 n=10+9)
Decompress1XNoTable/digits/262143-8             348MB/s ± 1%   349MB/s ± 0%    ~     (p=0.043 n=10+10)
Decompress1XNoTable/gettysburg/100-8            276MB/s ± 0%   277MB/s ± 1%  +0.44%  (p=0.009 n=10+10)
Decompress1XNoTable/gettysburg/10000-8          363MB/s ± 1%   363MB/s ± 0%    ~     (p=0.041 n=10+7)
Decompress1XNoTable/gettysburg/262143-8         349MB/s ± 1%   350MB/s ± 0%    ~     (p=0.123 n=10+10)
Decompress1XNoTable/twain/100-8                 267MB/s ± 0%   268MB/s ± 0%    ~     (p=0.052 n=10+10)
Decompress1XNoTable/twain/10000-8               357MB/s ± 3%   363MB/s ± 0%  +1.74%  (p=0.000 n=10+10)
Decompress1XNoTable/twain/262143-8              320MB/s ± 2%   329MB/s ± 0%  +3.09%  (p=0.000 n=10+10)
Decompress1XNoTable/low-ent.10k/100-8           183MB/s ± 1%   184MB/s ± 0%    ~     (p=0.211 n=9+10)
Decompress1XNoTable/low-ent.10k/10000-8         377MB/s ± 3%   385MB/s ± 1%  +2.14%  (p=0.000 n=10+10)
Decompress1XNoTable/low-ent.10k/262143-8        386MB/s ± 1%   389MB/s ± 1%  +0.84%  (p=0.005 n=10+10)
Decompress1XNoTable/superlow-ent-10k/262143-8   382MB/s ± 2%   389MB/s ± 1%  +1.89%  (p=0.001 n=10+10)
Decompress1XNoTable/crash2/100-8                276MB/s ± 2%   278MB/s ± 0%    ~     (p=0.180 n=10+8)
Decompress1XNoTable/crash2/10000-8              373MB/s ± 1%   374MB/s ± 1%    ~     (p=0.315 n=10+10)
Decompress1XNoTable/crash2/262143-8             373MB/s ± 1%   375MB/s ± 0%    ~     (p=0.165 n=10+8)
Decompress1XNoTable/endzerobits/100-8           184MB/s ± 0%   184MB/s ± 1%    ~     (p=0.845 n=9+9)
Decompress1XNoTable/endzerobits/10000-8         384MB/s ± 1%   386MB/s ± 0%  +0.61%  (p=0.007 n=10+10)
Decompress1XNoTable/endzerobits/262143-8        387MB/s ± 2%   389MB/s ± 0%    ~     (p=0.963 n=9+8)
Decompress1XNoTable/endnonzero/100-8            181MB/s ± 2%   183MB/s ± 0%    ~     (p=0.017 n=9+10)
Decompress1XNoTable/endnonzero/10000-8          385MB/s ± 0%   382MB/s ± 1%  -0.88%  (p=0.001 n=8+10)
Decompress1XNoTable/endnonzero/262143-8         387MB/s ± 1%   385MB/s ± 2%    ~     (p=0.143 n=10+10)
Decompress1XNoTable/case1/100-8                 278MB/s ± 2%   282MB/s ± 1%    ~     (p=0.013 n=10+9)
Decompress1XNoTable/case1/10000-8               373MB/s ± 1%   373MB/s ± 0%    ~     (p=0.274 n=10+8)
Decompress1XNoTable/case1/262143-8              374MB/s ± 1%   374MB/s ± 0%    ~     (p=0.589 n=10+9)
Decompress1XNoTable/case2/100-8                 274MB/s ± 0%   274MB/s ± 0%  -0.26%  (p=0.002 n=10+9)
Decompress1XNoTable/case2/10000-8               378MB/s ± 0%   377MB/s ± 0%    ~     (p=0.093 n=10+10)
Decompress1XNoTable/case2/262143-8              377MB/s ± 1%   376MB/s ± 1%    ~     (p=0.225 n=10+10)
Decompress1XNoTable/case3/100-8                 266MB/s ± 0%   265MB/s ± 0%  -0.20%  (p=0.007 n=10+9)
Decompress1XNoTable/case3/10000-8               371MB/s ± 0%   372MB/s ± 0%    ~     (p=0.211 n=10+9)
Decompress1XNoTable/case3/262143-8              373MB/s ± 0%   374MB/s ± 0%    ~     (p=0.073 n=10+10)
Decompress1XNoTable/pngdata.001/100-8           239MB/s ± 0%   239MB/s ± 0%    ~     (p=0.889 n=9+10)
Decompress1XNoTable/pngdata.001/10000-8         384MB/s ± 0%   384MB/s ± 0%    ~     (p=0.228 n=10+8)
Decompress1XNoTable/pngdata.001/262143-8        377MB/s ± 0%   379MB/s ± 0%  +0.56%  (p=0.000 n=10+10)
Decompress1XNoTable/normcount2/100-8            281MB/s ± 1%   282MB/s ± 1%    ~     (p=0.015 n=10+10)
Decompress1XNoTable/normcount2/10000-8          368MB/s ± 0%   370MB/s ± 0%  +0.37%  (p=0.004 n=10+10)
Decompress1XNoTable/normcount2/262143-8         371MB/s ± 0%   371MB/s ± 0%    ~     (p=0.034 n=8+10)
Decompress4XNoTable/digits/100-8                200MB/s ± 1%   201MB/s ± 0%    ~     (p=0.274 n=8+10)
Decompress4XNoTable/digits/10000-8              603MB/s ± 0%   622MB/s ± 1%  +3.20%  (p=0.000 n=8+10)
Decompress4XNoTable/digits/262143-8             578MB/s ± 0%   595MB/s ± 1%  +2.87%  (p=0.000 n=8+10)
Decompress4XNoTable/gettysburg/100-8            260MB/s ± 0%   260MB/s ± 1%    ~     (p=0.011 n=8+10)
Decompress4XNoTable/gettysburg/10000-8          643MB/s ± 0%   657MB/s ± 1%  +2.19%  (p=0.000 n=10+9)
Decompress4XNoTable/gettysburg/262143-8         572MB/s ± 0%   589MB/s ± 0%  +2.93%  (p=0.000 n=8+10)
Decompress4XNoTable/twain/100-8                 206MB/s ± 1%   206MB/s ± 1%    ~     (p=0.436 n=10+10)
Decompress4XNoTable/twain/10000-8               639MB/s ± 1%   653MB/s ± 1%  +2.25%  (p=0.000 n=10+10)
Decompress4XNoTable/twain/262143-8              516MB/s ± 0%   522MB/s ± 1%  +1.09%  (p=0.004 n=10+10)
Decompress4XNoTable/low-ent.10k/100-8           207MB/s ± 1%   207MB/s ± 0%    ~     (p=1.000 n=10+9)
Decompress4XNoTable/low-ent.10k/10000-8         631MB/s ± 0%   653MB/s ± 0%  +3.42%  (p=0.000 n=10+9)
Decompress4XNoTable/low-ent.10k/262143-8        685MB/s ± 1%   696MB/s ± 0%  +1.61%  (p=0.000 n=10+10)
Decompress4XNoTable/superlow-ent-10k/262143-8   684MB/s ± 1%   695MB/s ± 1%  +1.51%  (p=0.000 n=9+10)
Decompress4XNoTable/case1/100-8                 208MB/s ± 1%   207MB/s ± 0%    ~     (p=0.353 n=10+10)
Decompress4XNoTable/case1/10000-8               601MB/s ± 0%   621MB/s ± 1%  +3.22%  (p=0.000 n=10+10)
Decompress4XNoTable/case1/262143-8              613MB/s ± 1%   632MB/s ± 0%  +3.14%  (p=0.000 n=10+10)
Decompress4XNoTable/case2/100-8                 210MB/s ± 2%   208MB/s ± 2%    ~     (p=0.315 n=10+9)
Decompress4XNoTable/case2/10000-8               618MB/s ± 0%   636MB/s ± 0%  +2.95%  (p=0.000 n=10+10)
Decompress4XNoTable/case2/262143-8              635MB/s ± 0%   651MB/s ± 0%  +2.56%  (p=0.000 n=7+10)
Decompress4XNoTable/case3/100-8                 199MB/s ± 1%   200MB/s ± 1%    ~     (p=0.055 n=10+10)
Decompress4XNoTable/case3/10000-8               615MB/s ± 0%   633MB/s ± 1%  +2.94%  (p=0.000 n=10+10)
Decompress4XNoTable/case3/262143-8              620MB/s ± 0%   639MB/s ± 1%  +3.00%  (p=0.000 n=10+10)
Decompress4XNoTable/pngdata.001/100-8           212MB/s ± 0%   211MB/s ± 1%    ~     (p=0.211 n=10+9)
Decompress4XNoTable/pngdata.001/10000-8         649MB/s ± 0%   667MB/s ± 1%  +2.76%  (p=0.000 n=10+10)
Decompress4XNoTable/pngdata.001/262143-8        646MB/s ± 0%   660MB/s ± 0%  +2.28%  (p=0.000 n=9+10)
Decompress4XNoTable/normcount2/100-8            261MB/s ± 1%   262MB/s ± 1%    ~     (p=0.031 n=9+9)
Decompress4XNoTable/normcount2/10000-8          589MB/s ± 1%   613MB/s ± 0%  +3.99%  (p=0.000 n=10+9)
Decompress4XNoTable/normcount2/262143-8         585MB/s ± 3%   617MB/s ± 1%  +5.57%  (p=0.000 n=10+10)
Decompress4XNoTableTableLog8/digits-8           579MB/s ± 2%   610MB/s ± 0%  +5.33%  (p=0.000 n=10+10)
Decompress4XTable/digits-8                      584MB/s ± 1%   607MB/s ± 1%  +3.89%  (p=0.000 n=10+10)
Decompress4XTable/gettysburg-8                  370MB/s ± 0%   373MB/s ± 1%  +0.67%  (p=0.009 n=10+10)
Decompress4XTable/twain-8                       512MB/s ± 2%   523MB/s ± 1%  +2.08%  (p=0.000 n=9+10)
Decompress4XTable/low-ent.10k-8                 656MB/s ± 1%   677MB/s ± 1%  +3.21%  (p=0.000 n=10+10)
Decompress4XTable/superlow-ent-10k-8            603MB/s ± 4%   626MB/s ± 1%  +3.91%  (p=0.000 n=9+10)
Decompress4XTable/case1-8                      21.1MB/s ± 0%  21.0MB/s ± 0%  -0.55%  (p=0.000 n=9+9)
Decompress4XTable/case2-8                      17.6MB/s ± 0%  17.6MB/s ± 1%    ~     (p=0.736 n=9+10)
Decompress4XTable/case3-8                      18.7MB/s ± 1%  18.7MB/s ± 1%    ~     (p=0.642 n=10+10)
Decompress4XTable/pngdata.001-8                 648MB/s ± 0%   657MB/s ± 0%  +1.50%  (p=0.000 n=10+8)
Decompress4XTable/normcount2-8                 49.7MB/s ± 1%  49.7MB/s ± 1%    ~     (p=0.839 n=10+10)
[Geo mean]                                      271MB/s        274MB/s       +0.96%
```
  • Loading branch information
@greatroar
greatroar authored Jan 9, 2023
1 parent 272358c commit 60e376b
Show file tree
Hide file tree
Showing 2 changed files with 340 additions and 350 deletions.
106 changes: 56 additions & 50 deletions huff0/_generate/gen.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -47,14 +47,11 @@ func (d decompress4x) generateProcedure(name string) {
Doc(name+" is an x86 assembler implementation of Decompress4X when tablelog > 8.decodes a sequence", "")
Pragma("noescape")

exhausted := GP64()
XORQ(exhausted.As64(), exhausted.As64()) // exhausted = false

exhausted := GP8()
buffer := GP64()
limit := GP64()

bufferOrigin := GP64()
peekBits := GP64()
buffer := GP64()
dstEvery := GP64()
table := GP64()

Expand All @@ -64,7 +61,7 @@ func (d decompress4x) generateProcedure(name string) {
{
ctx := Dereference(Param("ctx"))
Load(ctx.Field("peekBits"), peekBits)
Load(ctx.Field("out"), bufferOrigin)
Load(ctx.Field("out"), buffer)
Load(ctx.Field("limit"), limit)
Load(ctx.Field("dstEvery"), dstEvery)
Load(ctx.Field("tbl"), table)
Expand All @@ -74,27 +71,26 @@ func (d decompress4x) generateProcedure(name string) {
Comment("Main loop")
Label("main_loop")

MOVQ(bufferOrigin, buffer)
// Check if we have space
// Check if we have space. We could zero exhausted outside the loop,
// but doing it here is a hint to the CPU that there's no dependency
// on the previous iteration's value.
XORL(exhausted.As32(), exhausted.As32())
CMPQ(buffer, limit)
SETGE(exhausted.As8())
d.decodeTwoValues(0, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeTwoValues(1, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeTwoValues(2, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeTwoValues(3, br, peekBits, table, buffer, exhausted)
d.decodeTwoValues(0, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeTwoValues(1, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeTwoValues(2, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeTwoValues(3, br, peekBits, table, buffer, dstEvery, exhausted)

ADDQ(U8(2), bufferOrigin) // off += 2
ADDQ(U8(2), buffer) // off += 2

TESTB(exhausted.As8(), exhausted.As8()) // any br[i].ofs < 4?
TESTB(exhausted, exhausted) // any br[i].ofs < 4?
JZ(LabelRef("main_loop"))

{
ctx := Dereference(Param("ctx"))
ctxout, _ := ctx.Field("out").Resolve()
decoded := bufferOrigin
decoded := buffer
SUBQ(ctxout.Addr, decoded)
SHLQ(U8(2), decoded) // decoded *= 4

Expand All @@ -105,15 +101,14 @@ func (d decompress4x) generateProcedure(name string) {
}

// TODO [wmu]: I believe it's doable in avo, but can't figure out how to deal
//
// with arbitrary pointers to a given type
// with arbitrary pointers to a given type
const bitReader_in = 0
const bitReader_off = bitReader_in + 3*8 // {ptr, len, cap}
const bitReader_value = bitReader_off + 8
const bitReader_bitsRead = bitReader_value + 8
const bitReader__size = bitReader_bitsRead + 8

func (d decompress4x) decodeTwoValues(id int, br, peekBits, table, buffer, exhausted reg.GPVirtual) {
func (d decompress4x) decodeTwoValues(id int, br, peekBits, table, buffer, dstEvery, exhausted reg.GPVirtual) {
brValue, brBitsRead := d.fillFast32(id, 32, br, exhausted)

val := GP64()
Expand Down Expand Up @@ -149,7 +144,7 @@ func (d decompress4x) decodeTwoValues(id int, br, peekBits, table, buffer, exhau
Comment("these two writes get coalesced")
Comment("out[id * dstEvery + 0] = uint8(v0.entry >> 8)")
Comment("out[id * dstEvery + 1] = uint8(v1.entry >> 8)")
MOVW(out.As16(), Mem{Base: buffer})
MOVW(out.As16(), bufferIndex(id, buffer, dstEvery))

Comment("update the bitreader structure")
offset := id * bitReader__size
Expand All @@ -163,14 +158,11 @@ func (d decompress4x) generateProcedure4x8bit(name string) {
Doc(name+" is an x86 assembler implementation of Decompress4X when tablelog > 8.decodes a sequence", "")
Pragma("noescape")

exhausted := GP64() // Fixed since we need 8H
XORQ(exhausted.As64(), exhausted.As64()) // exhausted = false

bufferOrigin := GP64()
exhausted := GP8()
buffer := GP64()
limit := GP64()

peekBits := GP64()
buffer := GP64()
dstEvery := GP64()
table := GP64()

Expand All @@ -180,7 +172,7 @@ func (d decompress4x) generateProcedure4x8bit(name string) {
{
ctx := Dereference(Param("ctx"))
Load(ctx.Field("peekBits"), peekBits)
Load(ctx.Field("out"), bufferOrigin)
Load(ctx.Field("out"), buffer)
Load(ctx.Field("limit"), limit)
Load(ctx.Field("dstEvery"), dstEvery)
Load(ctx.Field("tbl"), table)
Expand All @@ -190,27 +182,26 @@ func (d decompress4x) generateProcedure4x8bit(name string) {
Comment("Main loop")
Label("main_loop")

MOVQ(bufferOrigin, buffer)
// Check if we have space
// Check if we have space. We could zero exhausted outside the loop,
// but doing it here is a hint to the CPU that there's no dependency
// on the previous iteration's value.
XORL(exhausted.As32(), exhausted.As32())
CMPQ(buffer, limit)
SETGE(exhausted.As8())
d.decodeFourValues(0, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeFourValues(1, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeFourValues(2, br, peekBits, table, buffer, exhausted)
ADDQ(dstEvery, buffer)
d.decodeFourValues(3, br, peekBits, table, buffer, exhausted)
SETGE(exhausted)
d.decodeFourValues(0, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeFourValues(1, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeFourValues(2, br, peekBits, table, buffer, dstEvery, exhausted)
d.decodeFourValues(3, br, peekBits, table, buffer, dstEvery, exhausted)

ADDQ(U8(4), bufferOrigin) // off += 4
ADDQ(U8(4), buffer) // off += 4

TESTB(exhausted.As8(), exhausted.As8()) // any br[i].ofs < 4?
TESTB(exhausted, exhausted) // any br[i].ofs < 4?
JZ(LabelRef("main_loop"))

{
ctx := Dereference(Param("ctx"))
ctxout, _ := ctx.Field("out").Resolve()
decoded := bufferOrigin
decoded := buffer
SUBQ(ctxout.Addr, decoded)
SHLQ(U8(2), decoded) // decoded *= 4

Expand All @@ -219,7 +210,7 @@ func (d decompress4x) generateProcedure4x8bit(name string) {
RET()
}

func (d decompress4x) decodeFourValues(id int, br, peekBits, table, buffer, exhausted reg.GPVirtual) {
func (d decompress4x) decodeFourValues(id int, br, peekBits, table, buffer, dstEvery, exhausted reg.GPVirtual) {
brValue, brBitsRead := d.fillFast32(id, 32, br, exhausted)

decompress := func(valID int, outByte reg.Register) {
Expand Down Expand Up @@ -253,14 +244,29 @@ func (d decompress4x) decodeFourValues(id int, br, peekBits, table, buffer, exha
Comment("out[id * dstEvery + 1] = uint8(v1.entry >> 8)")
Comment("out[id * dstEvery + 3] = uint8(v2.entry >> 8)")
Comment("out[id * dstEvery + 4] = uint8(v3.entry >> 8)")
MOVL(out.As32(), Mem{Base: buffer})
MOVL(out.As32(), bufferIndex(id, buffer, dstEvery))

Comment("update the bitreader structure")
offset := id * bitReader__size
MOVQ(brValue, Mem{Base: br, Disp: offset + bitReader_value})
MOVB(brBitsRead.As8(), Mem{Base: br, Disp: offset + bitReader_bitsRead})
}

func bufferIndex(id int, buffer, dstEvery reg.GPVirtual) Mem {
switch id {
case 0:
return Mem{Base: buffer}
case 1, 2:
return Mem{Base: buffer, Index: dstEvery, Scale: byte(id)}
case 3:
stride3 := GP64() // stride3 := 3*dstEvery
LEAQ(Mem{Base: dstEvery, Index: dstEvery, Scale: 2}, stride3)
return Mem{Base: buffer, Index: stride3, Scale: 1}
default:
panic("id must be >=0, <4")
}
}

func (d decompress4x) fillFast32(id, atLeast int, br, exhausted reg.GPVirtual) (brValue, brBitsRead reg.GPVirtual) {
if atLeast > 32 {
panic(fmt.Sprintf("at least (%d) cannot be >32", atLeast))
Expand Down Expand Up @@ -297,11 +303,11 @@ func (d decompress4x) fillFast32(id, atLeast int, br, exhausted reg.GPVirtual) (
MOVQ(brOffset, Mem{Base: br, Disp: offset + bitReader_off})
ORQ(tmp.As64(), brValue)
{
Commentf("exhausted = exhausted || (br%d.off < 4)", id)
Commentf("exhausted += (br%d.off < 4)", id)
CMPQ(brOffset, U8(4))
tmp = GP64()
SETLT(tmp.As8())
ORB(tmp.As8(), exhausted.As8())
// Add carry from brOffset-4. We do this at most four times per iteration,
// and every iteration resets exhausted's lower byte, so it doesn't overflow.
ADCB(I8(0), exhausted)
}

Label("skip_fill" + strconv.Itoa(id))
Expand Down Expand Up @@ -409,7 +415,7 @@ func (d decompress1x) generateProcedure(name string) {
outCap := GP64()
Load(ctx.Field("outCap"), outCap)
CMPQ(outCap, U8(4))
JB(LabelRef("error_max_decoded_size_exeeded"))
JB(LabelRef("error_max_decoded_size_exceeded"))

LEAQ(Mem{Base: buffer, Index: outCap, Scale: 1}, bufferEnd)

Expand All @@ -432,7 +438,7 @@ func (d decompress1x) generateProcedure(name string) {
tmp := GP64()
LEAQ(Mem{Base: buffer, Disp: 4}, tmp)
CMPQ(tmp, bufferEnd)
JGE(LabelRef("error_max_decoded_size_exeeded"))
JGE(LabelRef("error_max_decoded_size_exceeded"))
}

decompress := func(id int, out reg.Register) {
Expand Down Expand Up @@ -474,7 +480,7 @@ func (d decompress1x) generateProcedure(name string) {
RET()

Comment("Report error")
Label("error_max_decoded_size_exeeded")
Label("error_max_decoded_size_exceeded")
{
ctx := Dereference(Param("ctx"))
tmp := GP64()
Expand Down
Loading

0 comments on commit 60e376b

Please sign in to comment.