// Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT.

//go:build amd64 && !appengine && !noasm && gc

// func decompress4x_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_main_loop_amd64(SB), $0-8
	XORQ DX, DX

	// Preload values
	MOVQ    ctx+0(FP), AX
	MOVBQZX 8(AX), DI
	MOVQ    16(AX), SI
	MOVQ    48(AX), BX
	MOVQ    24(AX), R9
	MOVQ    32(AX), R10
	MOVQ    (AX), R11

	// Main loop
main_loop:
	MOVQ  SI, R8
	CMPQ  R8, BX
	SETGE DL

	// br0.fillFast32()
	MOVQ    32(R11), R12
	MOVBQZX 40(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill0
	MOVQ    24(R11), AX
	SUBQ    $0x20, R13
	SUBQ    $0x04, AX
	MOVQ    (R11), R14

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(R14*1), R14
	MOVQ R13, CX
	SHLQ CL, R14
	MOVQ AX, 24(R11)
	ORQ  R14, R12

	// exhausted = exhausted || (br0.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill0:
	// val0 := br0.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br0.peekTopBits(peekBits)
	MOVQ DI, CX
	MOVQ R12, R14
	SHRQ CL, R14

	// v1 := table[val1&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (R8)

	// update the bitreader structure
	MOVQ R12, 32(R11)
	MOVB R13, 40(R11)
	ADDQ R9, R8

	// br1.fillFast32()
	MOVQ    80(R11), R12
	MOVBQZX 88(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill1
	MOVQ    72(R11), AX
	SUBQ    $0x20, R13
	SUBQ    $0x04, AX
	MOVQ    48(R11), R14

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(R14*1), R14
	MOVQ R13, CX
	SHLQ CL, R14
	MOVQ AX, 72(R11)
	ORQ  R14, R12

	// exhausted = exhausted || (br1.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1:
	// val0 := br1.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br1.peekTopBits(peekBits)
	MOVQ DI, CX
	MOVQ R12, R14
	SHRQ CL, R14

	// v1 := table[val1&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (R8)

	// update the bitreader structure
	MOVQ R12, 80(R11)
	MOVB R13, 88(R11)
	ADDQ R9, R8

	// br2.fillFast32()
	MOVQ    128(R11), R12
	MOVBQZX 136(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill2
	MOVQ    120(R11), AX
	SUBQ    $0x20, R13
	SUBQ    $0x04, AX
	MOVQ    96(R11), R14

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(R14*1), R14
	MOVQ R13, CX
	SHLQ CL, R14
	MOVQ AX, 120(R11)
	ORQ  R14, R12

	// exhausted = exhausted || (br2.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill2:
	// val0 := br2.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br2.peekTopBits(peekBits)
	MOVQ DI, CX
	MOVQ R12, R14
	SHRQ CL, R14

	// v1 := table[val1&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (R8)

	// update the bitreader structure
	MOVQ R12, 128(R11)
	MOVB R13, 136(R11)
	ADDQ R9, R8

	// br3.fillFast32()
	MOVQ    176(R11), R12
	MOVBQZX 184(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill3
	MOVQ    168(R11), AX
	SUBQ    $0x20, R13
	SUBQ    $0x04, AX
	MOVQ    144(R11), R14

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(R14*1), R14
	MOVQ R13, CX
	SHLQ CL, R14
	MOVQ AX, 168(R11)
	ORQ  R14, R12

	// exhausted = exhausted || (br3.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill3:
	// val0 := br3.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br3.peekTopBits(peekBits)
	MOVQ DI, CX
	MOVQ R12, R14
	SHRQ CL, R14

	// v1 := table[val1&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (R8)

	// update the bitreader structure
	MOVQ  R12, 176(R11)
	MOVB  R13, 184(R11)
	ADDQ  $0x02, SI
	TESTB DL, DL
	JZ    main_loop
	MOVQ  ctx+0(FP), AX
	SUBQ  16(AX), SI
	SHLQ  $0x02, SI
	MOVQ  SI, 40(AX)
	RET

// func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_8b_main_loop_amd64(SB), $0-8
	XORQ DX, DX

	// Preload values
	MOVQ    ctx+0(FP), CX
	MOVBQZX 8(CX), DI
	MOVQ    16(CX), BX
	MOVQ    48(CX), SI
	MOVQ    24(CX), R9
	MOVQ    32(CX), R10
	MOVQ    (CX), R11

	// Main loop
main_loop:
	MOVQ  BX, R8
	CMPQ  R8, SI
	SETGE DL

	// br0.fillFast32()
	MOVQ    32(R11), R12
	MOVBQZX 40(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill0
	MOVQ    24(R11), R14
	SUBQ    $0x20, R13
	SUBQ    $0x04, R14
	MOVQ    (R11), R15

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R14)(R15*1), R15
	MOVQ R13, CX
	SHLQ CL, R15
	MOVQ R14, 24(R11)
	ORQ  R15, R12

	// exhausted = exhausted || (br0.off < 4)
	CMPQ  R14, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill0:
	// val0 := br0.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br0.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v1 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// val2 := br0.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v2 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// val3 := br0.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v3 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br0.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// 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)
	MOVL AX, (R8)

	// update the bitreader structure
	MOVQ R12, 32(R11)
	MOVB R13, 40(R11)
	ADDQ R9, R8

	// br1.fillFast32()
	MOVQ    80(R11), R12
	MOVBQZX 88(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill1
	MOVQ    72(R11), R14
	SUBQ    $0x20, R13
	SUBQ    $0x04, R14
	MOVQ    48(R11), R15

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R14)(R15*1), R15
	MOVQ R13, CX
	SHLQ CL, R15
	MOVQ R14, 72(R11)
	ORQ  R15, R12

	// exhausted = exhausted || (br1.off < 4)
	CMPQ  R14, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1:
	// val0 := br1.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br1.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v1 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// val2 := br1.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v2 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// val3 := br1.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v3 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br1.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// 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)
	MOVL AX, (R8)

	// update the bitreader structure
	MOVQ R12, 80(R11)
	MOVB R13, 88(R11)
	ADDQ R9, R8

	// br2.fillFast32()
	MOVQ    128(R11), R12
	MOVBQZX 136(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill2
	MOVQ    120(R11), R14
	SUBQ    $0x20, R13
	SUBQ    $0x04, R14
	MOVQ    96(R11), R15

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R14)(R15*1), R15
	MOVQ R13, CX
	SHLQ CL, R15
	MOVQ R14, 120(R11)
	ORQ  R15, R12

	// exhausted = exhausted || (br2.off < 4)
	CMPQ  R14, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill2:
	// val0 := br2.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br2.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v1 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// val2 := br2.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v2 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// val3 := br2.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v3 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br2.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// 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)
	MOVL AX, (R8)

	// update the bitreader structure
	MOVQ R12, 128(R11)
	MOVB R13, 136(R11)
	ADDQ R9, R8

	// br3.fillFast32()
	MOVQ    176(R11), R12
	MOVBQZX 184(R11), R13
	CMPQ    R13, $0x20
	JBE     skip_fill3
	MOVQ    168(R11), R14
	SUBQ    $0x20, R13
	SUBQ    $0x04, R14
	MOVQ    144(R11), R15

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R14)(R15*1), R15
	MOVQ R13, CX
	SHLQ CL, R15
	MOVQ R14, 168(R11)
	ORQ  R15, R12

	// exhausted = exhausted || (br3.off < 4)
	CMPQ  R14, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill3:
	// val0 := br3.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v0 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R12
	ADDB CL, R13

	// val1 := br3.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v1 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// val2 := br3.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v2 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R12
	ADDB CL, R13

	// val3 := br3.peekTopBits(peekBits)
	MOVQ R12, R14
	MOVQ DI, CX
	SHRQ CL, R14

	// v3 := table[val0&mask]
	MOVW (R10)(R14*2), CX

	// br3.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R12
	ADDB   CL, R13
	BSWAPL AX

	// 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)
	MOVL AX, (R8)

	// update the bitreader structure
	MOVQ  R12, 176(R11)
	MOVB  R13, 184(R11)
	ADDQ  $0x04, BX
	TESTB DL, DL
	JZ    main_loop
	MOVQ  ctx+0(FP), AX
	SUBQ  16(AX), BX
	SHLQ  $0x02, BX
	MOVQ  BX, 40(AX)
	RET

// func decompress1x_main_loop_amd64(ctx *decompress1xContext)
TEXT ·decompress1x_main_loop_amd64(SB), $0-8
	MOVQ    ctx+0(FP), CX
	MOVQ    16(CX), DX
	MOVQ    24(CX), BX
	CMPQ    BX, $0x04
	JB      error_max_decoded_size_exeeded
	LEAQ    (DX)(BX*1), BX
	MOVQ    (CX), SI
	MOVQ    (SI), R8
	MOVQ    24(SI), R9
	MOVQ    32(SI), R10
	MOVBQZX 40(SI), R11
	MOVQ    32(CX), SI
	MOVBQZX 8(CX), DI
	JMP     loop_condition

main_loop:
	// Check if we have room for 4 bytes in the output buffer
	LEAQ 4(DX), CX
	CMPQ CX, BX
	JGE  error_max_decoded_size_exeeded

	// Decode 4 values
	CMPQ R11, $0x20
	JL   bitReader_fillFast_1_end
	SUBQ $0x20, R11
	SUBQ $0x04, R9
	MOVL (R8)(R9*1), R12
	MOVQ R11, CX
	SHLQ CL, R12
	ORQ  R12, R10

bitReader_fillFast_1_end:
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	BSWAPL  AX
	CMPQ    R11, $0x20
	JL      bitReader_fillFast_2_end
	SUBQ    $0x20, R11
	SUBQ    $0x04, R9
	MOVL    (R8)(R9*1), R12
	MOVQ    R11, CX
	SHLQ    CL, R12
	ORQ     R12, R10

bitReader_fillFast_2_end:
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	BSWAPL  AX

	// Store the decoded values
	MOVL AX, (DX)
	ADDQ $0x04, DX

loop_condition:
	CMPQ R9, $0x08
	JGE  main_loop

	// Update ctx structure
	MOVQ ctx+0(FP), AX
	SUBQ 16(AX), DX
	MOVQ DX, 40(AX)
	MOVQ (AX), AX
	MOVQ R9, 24(AX)
	MOVQ R10, 32(AX)
	MOVB R11, 40(AX)
	RET

	// Report error
error_max_decoded_size_exeeded:
	MOVQ ctx+0(FP), AX
	MOVQ $-1, CX
	MOVQ CX, 40(AX)
	RET

// func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
// Requires: BMI2
TEXT ·decompress1x_main_loop_bmi2(SB), $0-8
	MOVQ    ctx+0(FP), CX
	MOVQ    16(CX), DX
	MOVQ    24(CX), BX
	CMPQ    BX, $0x04
	JB      error_max_decoded_size_exeeded
	LEAQ    (DX)(BX*1), BX
	MOVQ    (CX), SI
	MOVQ    (SI), R8
	MOVQ    24(SI), R9
	MOVQ    32(SI), R10
	MOVBQZX 40(SI), R11
	MOVQ    32(CX), SI
	MOVBQZX 8(CX), DI
	JMP     loop_condition

main_loop:
	// Check if we have room for 4 bytes in the output buffer
	LEAQ 4(DX), CX
	CMPQ CX, BX
	JGE  error_max_decoded_size_exeeded

	// Decode 4 values
	CMPQ  R11, $0x20
	JL    bitReader_fillFast_1_end
	SUBQ  $0x20, R11
	SUBQ  $0x04, R9
	MOVL  (R8)(R9*1), CX
	SHLXQ R11, CX, CX
	ORQ   CX, R10

bitReader_fillFast_1_end:
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	BSWAPL  AX
	CMPQ    R11, $0x20
	JL      bitReader_fillFast_2_end
	SUBQ    $0x20, R11
	SUBQ    $0x04, R9
	MOVL    (R8)(R9*1), CX
	SHLXQ   R11, CX, CX
	ORQ     CX, R10

bitReader_fillFast_2_end:
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	BSWAPL  AX

	// Store the decoded values
	MOVL AX, (DX)
	ADDQ $0x04, DX

loop_condition:
	CMPQ R9, $0x08
	JGE  main_loop

	// Update ctx structure
	MOVQ ctx+0(FP), AX
	SUBQ 16(AX), DX
	MOVQ DX, 40(AX)
	MOVQ (AX), AX
	MOVQ R9, 24(AX)
	MOVQ R10, 32(AX)
	MOVB R11, 40(AX)
	RET

	// Report error
error_max_decoded_size_exeeded:
	MOVQ ctx+0(FP), AX
	MOVQ $-1, CX
	MOVQ CX, 40(AX)
	RET