VictoriaMetrics/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s
2023-01-23 18:43:43 -08:00

831 lines
15 KiB
ArmAsm

// 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
// Preload values
MOVQ ctx+0(FP), AX
MOVBQZX 8(AX), DI
MOVQ 16(AX), BX
MOVQ 48(AX), SI
MOVQ 24(AX), R8
MOVQ 32(AX), R9
MOVQ (AX), R10
// Main loop
main_loop:
XORL DX, DX
CMPQ BX, SI
SETGE DL
// br0.fillFast32()
MOVQ 32(R10), R11
MOVBQZX 40(R10), R12
CMPQ R12, $0x20
JBE skip_fill0
MOVQ 24(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ (R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 24(R10)
ORQ R13, R11
// exhausted += (br0.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill0:
// val0 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br0.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)
// update the bitreader structure
MOVQ R11, 32(R10)
MOVB R12, 40(R10)
// br1.fillFast32()
MOVQ 80(R10), R11
MOVBQZX 88(R10), R12
CMPQ R12, $0x20
JBE skip_fill1
MOVQ 72(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 48(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 72(R10)
ORQ R13, R11
// exhausted += (br1.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill1:
// val0 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br1.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)(R8*1)
// update the bitreader structure
MOVQ R11, 80(R10)
MOVB R12, 88(R10)
// br2.fillFast32()
MOVQ 128(R10), R11
MOVBQZX 136(R10), R12
CMPQ R12, $0x20
JBE skip_fill2
MOVQ 120(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 96(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 120(R10)
ORQ R13, R11
// exhausted += (br2.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill2:
// val0 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br2.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)(R8*2)
// update the bitreader structure
MOVQ R11, 128(R10)
MOVB R12, 136(R10)
// br3.fillFast32()
MOVQ 176(R10), R11
MOVBQZX 184(R10), R12
CMPQ R12, $0x20
JBE skip_fill3
MOVQ 168(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 144(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 168(R10)
ORQ R13, R11
// exhausted += (br3.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill3:
// val0 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br3.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
LEAQ (R8)(R8*2), CX
MOVW AX, (BX)(CX*1)
// update the bitreader structure
MOVQ R11, 176(R10)
MOVB R12, 184(R10)
ADDQ $0x02, 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 decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_8b_main_loop_amd64(SB), $0-8
// Preload values
MOVQ ctx+0(FP), CX
MOVBQZX 8(CX), DI
MOVQ 16(CX), BX
MOVQ 48(CX), SI
MOVQ 24(CX), R8
MOVQ 32(CX), R9
MOVQ (CX), R10
// Main loop
main_loop:
XORL DX, DX
CMPQ BX, SI
SETGE DL
// br0.fillFast32()
MOVQ 32(R10), R11
MOVBQZX 40(R10), R12
CMPQ R12, $0x20
JBE skip_fill0
MOVQ 24(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ (R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 24(R10)
ORQ R14, R11
// exhausted += (br0.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill0:
// val0 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
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, (BX)
// update the bitreader structure
MOVQ R11, 32(R10)
MOVB R12, 40(R10)
// br1.fillFast32()
MOVQ 80(R10), R11
MOVBQZX 88(R10), R12
CMPQ R12, $0x20
JBE skip_fill1
MOVQ 72(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 48(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 72(R10)
ORQ R14, R11
// exhausted += (br1.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill1:
// val0 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
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, (BX)(R8*1)
// update the bitreader structure
MOVQ R11, 80(R10)
MOVB R12, 88(R10)
// br2.fillFast32()
MOVQ 128(R10), R11
MOVBQZX 136(R10), R12
CMPQ R12, $0x20
JBE skip_fill2
MOVQ 120(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 96(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 120(R10)
ORQ R14, R11
// exhausted += (br2.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill2:
// val0 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
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, (BX)(R8*2)
// update the bitreader structure
MOVQ R11, 128(R10)
MOVB R12, 136(R10)
// br3.fillFast32()
MOVQ 176(R10), R11
MOVBQZX 184(R10), R12
CMPQ R12, $0x20
JBE skip_fill3
MOVQ 168(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 144(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 168(R10)
ORQ R14, R11
// exhausted += (br3.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill3:
// val0 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
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)
LEAQ (R8)(R8*2), CX
MOVL AX, (BX)(CX*1)
// update the bitreader structure
MOVQ R11, 176(R10)
MOVB R12, 184(R10)
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_exceeded
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_exceeded
// 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_exceeded:
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_exceeded
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_exceeded
// 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_exceeded:
MOVQ ctx+0(FP), AX
MOVQ $-1, CX
MOVQ CX, 40(AX)
RET