aleesa-bot/aleesa-webapp-go
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update dependencies

Browse Source
This commit is contained in:
eleksir
2026-02-10 20:54:39 +03:00
parent f2fc168abe
commit 170d0d0ed4
559 changed files with 66718 additions and 72415 deletions
Download Patch File Download Diff File Expand all files Collapse all files

380
vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s generated vendored
View File

@@ -5,11 +5,11 @@
// func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
// Requires: CMOV
TEXT ·sequenceDecs_decode_amd64(SB), $8-32
MOVQ br+8(FP), AX
MOVQ 32(AX), DX
MOVBQZX 40(AX), BX
MOVQ 24(AX), SI
MOVQ (AX), AX
MOVQ br+8(FP), CX
MOVQ 24(CX), DX
MOVBQZX 40(CX), BX
MOVQ (CX), AX
MOVQ 32(CX), SI
ADDQ SI, AX
MOVQ AX, (SP)
MOVQ ctx+16(FP), AX
@@ -38,7 +38,7 @@ sequenceDecs_decode_amd64_main_loop:
sequenceDecs_decode_amd64_fill_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decode_amd64_fill_end
JLE sequenceDecs_decode_amd64_fill_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decode_amd64_fill_end
SHLQ $0x08, DX
@@ -49,6 +49,10 @@ sequenceDecs_decode_amd64_fill_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decode_amd64_fill_byte_by_byte
sequenceDecs_decode_amd64_fill_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decode_amd64_fill_end:
// Update offset
MOVQ R9, AX
@@ -105,7 +109,7 @@ sequenceDecs_decode_amd64_ml_update_zero:
sequenceDecs_decode_amd64_fill_2_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decode_amd64_fill_2_end
JLE sequenceDecs_decode_amd64_fill_2_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decode_amd64_fill_2_end
SHLQ $0x08, DX
@@ -116,6 +120,10 @@ sequenceDecs_decode_amd64_fill_2_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decode_amd64_fill_2_byte_by_byte
sequenceDecs_decode_amd64_fill_2_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decode_amd64_fill_2_end:
// Update literal length
MOVQ DI, AX
@@ -149,8 +157,7 @@ sequenceDecs_decode_amd64_ll_update_zero:
// Update Literal Length State
MOVBQZX DI, R14
SHRQ $0x10, DI
MOVWQZX DI, DI
SHRL $0x10, DI
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -169,8 +176,7 @@ sequenceDecs_decode_amd64_ll_update_zero:
// Update Match Length State
MOVBQZX R8, R14
SHRQ $0x10, R8
MOVWQZX R8, R8
SHRL $0x10, R8
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -189,8 +195,7 @@ sequenceDecs_decode_amd64_ll_update_zero:
// Update Offset State
MOVBQZX R9, R14
SHRQ $0x10, R9
MOVWQZX R9, R9
SHRL $0x10, R9
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -293,9 +298,9 @@ sequenceDecs_decode_amd64_match_len_ofs_ok:
MOVQ R12, 152(AX)
MOVQ R13, 160(AX)
MOVQ br+8(FP), AX
MOVQ DX, 32(AX)
MOVQ DX, 24(AX)
MOVB BL, 40(AX)
MOVQ SI, 24(AX)
MOVQ SI, 32(AX)
// Return success
MOVQ $0x00000000, ret+24(FP)
@@ -320,14 +325,19 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// func sequenceDecs_decode_56_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
// Requires: CMOV
TEXT ·sequenceDecs_decode_56_amd64(SB), $8-32
MOVQ br+8(FP), AX
MOVQ 32(AX), DX
MOVBQZX 40(AX), BX
MOVQ 24(AX), SI
MOVQ (AX), AX
MOVQ br+8(FP), CX
MOVQ 24(CX), DX
MOVBQZX 40(CX), BX
MOVQ (CX), AX
MOVQ 32(CX), SI
ADDQ SI, AX
MOVQ AX, (SP)
MOVQ ctx+16(FP), AX
@@ -356,7 +366,7 @@ sequenceDecs_decode_56_amd64_main_loop:
sequenceDecs_decode_56_amd64_fill_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decode_56_amd64_fill_end
JLE sequenceDecs_decode_56_amd64_fill_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decode_56_amd64_fill_end
SHLQ $0x08, DX
@@ -367,6 +377,10 @@ sequenceDecs_decode_56_amd64_fill_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decode_56_amd64_fill_byte_by_byte
sequenceDecs_decode_56_amd64_fill_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decode_56_amd64_fill_end:
// Update offset
MOVQ R9, AX
@@ -442,8 +456,7 @@ sequenceDecs_decode_56_amd64_ll_update_zero:
// Update Literal Length State
MOVBQZX DI, R14
SHRQ $0x10, DI
MOVWQZX DI, DI
SHRL $0x10, DI
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -462,8 +475,7 @@ sequenceDecs_decode_56_amd64_ll_update_zero:
// Update Match Length State
MOVBQZX R8, R14
SHRQ $0x10, R8
MOVWQZX R8, R8
SHRL $0x10, R8
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -482,8 +494,7 @@ sequenceDecs_decode_56_amd64_ll_update_zero:
// Update Offset State
MOVBQZX R9, R14
SHRQ $0x10, R9
MOVWQZX R9, R9
SHRL $0x10, R9
LEAQ (BX)(R14*1), CX
MOVQ DX, R15
MOVQ CX, BX
@@ -586,9 +597,9 @@ sequenceDecs_decode_56_amd64_match_len_ofs_ok:
MOVQ R12, 152(AX)
MOVQ R13, 160(AX)
MOVQ br+8(FP), AX
MOVQ DX, 32(AX)
MOVQ DX, 24(AX)
MOVB BL, 40(AX)
MOVQ SI, 24(AX)
MOVQ SI, 32(AX)
// Return success
MOVQ $0x00000000, ret+24(FP)
@@ -613,14 +624,19 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// func sequenceDecs_decode_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
// Requires: BMI, BMI2, CMOV
TEXT ·sequenceDecs_decode_bmi2(SB), $8-32
MOVQ br+8(FP), CX
MOVQ 32(CX), AX
MOVBQZX 40(CX), DX
MOVQ 24(CX), BX
MOVQ (CX), CX
MOVQ br+8(FP), BX
MOVQ 24(BX), AX
MOVBQZX 40(BX), DX
MOVQ (BX), CX
MOVQ 32(BX), BX
ADDQ BX, CX
MOVQ CX, (SP)
MOVQ ctx+16(FP), CX
@@ -649,7 +665,7 @@ sequenceDecs_decode_bmi2_main_loop:
sequenceDecs_decode_bmi2_fill_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decode_bmi2_fill_end
JLE sequenceDecs_decode_bmi2_fill_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decode_bmi2_fill_end
SHLQ $0x08, AX
@@ -660,6 +676,10 @@ sequenceDecs_decode_bmi2_fill_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decode_bmi2_fill_byte_by_byte
sequenceDecs_decode_bmi2_fill_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decode_bmi2_fill_end:
// Update offset
MOVQ $0x00000808, CX
@@ -700,7 +720,7 @@ sequenceDecs_decode_bmi2_fill_end:
sequenceDecs_decode_bmi2_fill_2_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decode_bmi2_fill_2_end
JLE sequenceDecs_decode_bmi2_fill_2_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decode_bmi2_fill_2_end
SHLQ $0x08, AX
@@ -711,6 +731,10 @@ sequenceDecs_decode_bmi2_fill_2_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decode_bmi2_fill_2_byte_by_byte
sequenceDecs_decode_bmi2_fill_2_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decode_bmi2_fill_2_end:
// Update literal length
MOVQ $0x00000808, CX
@@ -742,11 +766,10 @@ sequenceDecs_decode_bmi2_fill_2_end:
BZHIQ R14, R15, R15
// Update Offset State
BZHIQ R8, R15, CX
SHRXQ R8, R15, R15
MOVQ $0x00001010, R14
BEXTRQ R14, R8, R8
ADDQ CX, R8
BZHIQ R8, R15, CX
SHRXQ R8, R15, R15
SHRL $0x10, R8
ADDQ CX, R8
// Load ctx.ofTable
MOVQ ctx+16(FP), CX
@@ -754,11 +777,10 @@ sequenceDecs_decode_bmi2_fill_2_end:
MOVQ (CX)(R8*8), R8
// Update Match Length State
BZHIQ DI, R15, CX
SHRXQ DI, R15, R15
MOVQ $0x00001010, R14
BEXTRQ R14, DI, DI
ADDQ CX, DI
BZHIQ DI, R15, CX
SHRXQ DI, R15, R15
SHRL $0x10, DI
ADDQ CX, DI
// Load ctx.mlTable
MOVQ ctx+16(FP), CX
@@ -766,10 +788,9 @@ sequenceDecs_decode_bmi2_fill_2_end:
MOVQ (CX)(DI*8), DI
// Update Literal Length State
BZHIQ SI, R15, CX
MOVQ $0x00001010, R14
BEXTRQ R14, SI, SI
ADDQ CX, SI
BZHIQ SI, R15, CX
SHRL $0x10, SI
ADDQ CX, SI
// Load ctx.llTable
MOVQ ctx+16(FP), CX
@@ -862,9 +883,9 @@ sequenceDecs_decode_bmi2_match_len_ofs_ok:
MOVQ R11, 152(CX)
MOVQ R12, 160(CX)
MOVQ br+8(FP), CX
MOVQ AX, 32(CX)
MOVQ AX, 24(CX)
MOVB DL, 40(CX)
MOVQ BX, 24(CX)
MOVQ BX, 32(CX)
// Return success
MOVQ $0x00000000, ret+24(FP)
@@ -889,14 +910,19 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// func sequenceDecs_decode_56_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
// Requires: BMI, BMI2, CMOV
TEXT ·sequenceDecs_decode_56_bmi2(SB), $8-32
MOVQ br+8(FP), CX
MOVQ 32(CX), AX
MOVBQZX 40(CX), DX
MOVQ 24(CX), BX
MOVQ (CX), CX
MOVQ br+8(FP), BX
MOVQ 24(BX), AX
MOVBQZX 40(BX), DX
MOVQ (BX), CX
MOVQ 32(BX), BX
ADDQ BX, CX
MOVQ CX, (SP)
MOVQ ctx+16(FP), CX
@@ -925,7 +951,7 @@ sequenceDecs_decode_56_bmi2_main_loop:
sequenceDecs_decode_56_bmi2_fill_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decode_56_bmi2_fill_end
JLE sequenceDecs_decode_56_bmi2_fill_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decode_56_bmi2_fill_end
SHLQ $0x08, AX
@@ -936,6 +962,10 @@ sequenceDecs_decode_56_bmi2_fill_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decode_56_bmi2_fill_byte_by_byte
sequenceDecs_decode_56_bmi2_fill_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decode_56_bmi2_fill_end:
// Update offset
MOVQ $0x00000808, CX
@@ -993,11 +1023,10 @@ sequenceDecs_decode_56_bmi2_fill_end:
BZHIQ R14, R15, R15
// Update Offset State
BZHIQ R8, R15, CX
SHRXQ R8, R15, R15
MOVQ $0x00001010, R14
BEXTRQ R14, R8, R8
ADDQ CX, R8
BZHIQ R8, R15, CX
SHRXQ R8, R15, R15
SHRL $0x10, R8
ADDQ CX, R8
// Load ctx.ofTable
MOVQ ctx+16(FP), CX
@@ -1005,11 +1034,10 @@ sequenceDecs_decode_56_bmi2_fill_end:
MOVQ (CX)(R8*8), R8
// Update Match Length State
BZHIQ DI, R15, CX
SHRXQ DI, R15, R15
MOVQ $0x00001010, R14
BEXTRQ R14, DI, DI
ADDQ CX, DI
BZHIQ DI, R15, CX
SHRXQ DI, R15, R15
SHRL $0x10, DI
ADDQ CX, DI
// Load ctx.mlTable
MOVQ ctx+16(FP), CX
@@ -1017,10 +1045,9 @@ sequenceDecs_decode_56_bmi2_fill_end:
MOVQ (CX)(DI*8), DI
// Update Literal Length State
BZHIQ SI, R15, CX
MOVQ $0x00001010, R14
BEXTRQ R14, SI, SI
ADDQ CX, SI
BZHIQ SI, R15, CX
SHRL $0x10, SI
ADDQ CX, SI
// Load ctx.llTable
MOVQ ctx+16(FP), CX
@@ -1113,9 +1140,9 @@ sequenceDecs_decode_56_bmi2_match_len_ofs_ok:
MOVQ R11, 152(CX)
MOVQ R12, 160(CX)
MOVQ br+8(FP), CX
MOVQ AX, 32(CX)
MOVQ AX, 24(CX)
MOVB DL, 40(CX)
MOVQ BX, 24(CX)
MOVQ BX, 32(CX)
// Return success
MOVQ $0x00000000, ret+24(FP)
@@ -1140,6 +1167,11 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// func sequenceDecs_executeSimple_amd64(ctx *executeAsmContext) bool
// Requires: SSE
TEXT ·sequenceDecs_executeSimple_amd64(SB), $8-9
@@ -1753,11 +1785,11 @@ empty_seqs:
// func sequenceDecs_decodeSync_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
// Requires: CMOV, SSE
TEXT ·sequenceDecs_decodeSync_amd64(SB), $64-32
MOVQ br+8(FP), AX
MOVQ 32(AX), DX
MOVBQZX 40(AX), BX
MOVQ 24(AX), SI
MOVQ (AX), AX
MOVQ br+8(FP), CX
MOVQ 24(CX), DX
MOVBQZX 40(CX), BX
MOVQ (CX), AX
MOVQ 32(CX), SI
ADDQ SI, AX
MOVQ AX, (SP)
MOVQ ctx+16(FP), AX
@@ -1782,7 +1814,7 @@ TEXT ·sequenceDecs_decodeSync_amd64(SB), $64-32
MOVQ 40(SP), AX
ADDQ AX, 48(SP)
// Calculate poiter to s.out[cap(s.out)] (a past-end pointer)
// Calculate pointer to s.out[cap(s.out)] (a past-end pointer)
ADDQ R10, 32(SP)
// outBase += outPosition
@@ -1804,7 +1836,7 @@ sequenceDecs_decodeSync_amd64_main_loop:
sequenceDecs_decodeSync_amd64_fill_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decodeSync_amd64_fill_end
JLE sequenceDecs_decodeSync_amd64_fill_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decodeSync_amd64_fill_end
SHLQ $0x08, DX
@@ -1815,6 +1847,10 @@ sequenceDecs_decodeSync_amd64_fill_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decodeSync_amd64_fill_byte_by_byte
sequenceDecs_decodeSync_amd64_fill_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decodeSync_amd64_fill_end:
// Update offset
MOVQ R9, AX
@@ -1871,7 +1907,7 @@ sequenceDecs_decodeSync_amd64_ml_update_zero:
sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decodeSync_amd64_fill_2_end
JLE sequenceDecs_decodeSync_amd64_fill_2_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decodeSync_amd64_fill_2_end
SHLQ $0x08, DX
@@ -1882,6 +1918,10 @@ sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decodeSync_amd64_fill_2_byte_by_byte
sequenceDecs_decodeSync_amd64_fill_2_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decodeSync_amd64_fill_2_end:
// Update literal length
MOVQ DI, AX
@@ -1915,8 +1955,7 @@ sequenceDecs_decodeSync_amd64_ll_update_zero:
// Update Literal Length State
MOVBQZX DI, R13
SHRQ $0x10, DI
MOVWQZX DI, DI
SHRL $0x10, DI
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -1935,8 +1974,7 @@ sequenceDecs_decodeSync_amd64_ll_update_zero:
// Update Match Length State
MOVBQZX R8, R13
SHRQ $0x10, R8
MOVWQZX R8, R8
SHRL $0x10, R8
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -1955,8 +1993,7 @@ sequenceDecs_decodeSync_amd64_ll_update_zero:
// Update Offset State
MOVBQZX R9, R13
SHRQ $0x10, R9
MOVWQZX R9, R9
SHRL $0x10, R9
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -2243,9 +2280,9 @@ handle_loop:
loop_finished:
MOVQ br+8(FP), AX
MOVQ DX, 32(AX)
MOVQ DX, 24(AX)
MOVB BL, 40(AX)
MOVQ SI, 24(AX)
MOVQ SI, 32(AX)
// Update the context
MOVQ ctx+16(FP), AX
@@ -2291,6 +2328,11 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// Return with not enough output space error
error_not_enough_space:
MOVQ ctx+16(FP), AX
@@ -2305,11 +2347,11 @@ error_not_enough_space:
// func sequenceDecs_decodeSync_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
// Requires: BMI, BMI2, CMOV, SSE
TEXT ·sequenceDecs_decodeSync_bmi2(SB), $64-32
MOVQ br+8(FP), CX
MOVQ 32(CX), AX
MOVBQZX 40(CX), DX
MOVQ 24(CX), BX
MOVQ (CX), CX
MOVQ br+8(FP), BX
MOVQ 24(BX), AX
MOVBQZX 40(BX), DX
MOVQ (BX), CX
MOVQ 32(BX), BX
ADDQ BX, CX
MOVQ CX, (SP)
MOVQ ctx+16(FP), CX
@@ -2334,7 +2376,7 @@ TEXT ·sequenceDecs_decodeSync_bmi2(SB), $64-32
MOVQ 40(SP), CX
ADDQ CX, 48(SP)
// Calculate poiter to s.out[cap(s.out)] (a past-end pointer)
// Calculate pointer to s.out[cap(s.out)] (a past-end pointer)
ADDQ R9, 32(SP)
// outBase += outPosition
@@ -2356,7 +2398,7 @@ sequenceDecs_decodeSync_bmi2_main_loop:
sequenceDecs_decodeSync_bmi2_fill_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decodeSync_bmi2_fill_end
JLE sequenceDecs_decodeSync_bmi2_fill_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decodeSync_bmi2_fill_end
SHLQ $0x08, AX
@@ -2367,6 +2409,10 @@ sequenceDecs_decodeSync_bmi2_fill_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decodeSync_bmi2_fill_byte_by_byte
sequenceDecs_decodeSync_bmi2_fill_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decodeSync_bmi2_fill_end:
// Update offset
MOVQ $0x00000808, CX
@@ -2407,7 +2453,7 @@ sequenceDecs_decodeSync_bmi2_fill_end:
sequenceDecs_decodeSync_bmi2_fill_2_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decodeSync_bmi2_fill_2_end
JLE sequenceDecs_decodeSync_bmi2_fill_2_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decodeSync_bmi2_fill_2_end
SHLQ $0x08, AX
@@ -2418,6 +2464,10 @@ sequenceDecs_decodeSync_bmi2_fill_2_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decodeSync_bmi2_fill_2_byte_by_byte
sequenceDecs_decodeSync_bmi2_fill_2_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decodeSync_bmi2_fill_2_end:
// Update literal length
MOVQ $0x00000808, CX
@@ -2449,11 +2499,10 @@ sequenceDecs_decodeSync_bmi2_fill_2_end:
BZHIQ R13, R14, R14
// Update Offset State
BZHIQ R8, R14, CX
SHRXQ R8, R14, R14
MOVQ $0x00001010, R13
BEXTRQ R13, R8, R8
ADDQ CX, R8
BZHIQ R8, R14, CX
SHRXQ R8, R14, R14
SHRL $0x10, R8
ADDQ CX, R8
// Load ctx.ofTable
MOVQ ctx+16(FP), CX
@@ -2461,11 +2510,10 @@ sequenceDecs_decodeSync_bmi2_fill_2_end:
MOVQ (CX)(R8*8), R8
// Update Match Length State
BZHIQ DI, R14, CX
SHRXQ DI, R14, R14
MOVQ $0x00001010, R13
BEXTRQ R13, DI, DI
ADDQ CX, DI
BZHIQ DI, R14, CX
SHRXQ DI, R14, R14
SHRL $0x10, DI
ADDQ CX, DI
// Load ctx.mlTable
MOVQ ctx+16(FP), CX
@@ -2473,10 +2521,9 @@ sequenceDecs_decodeSync_bmi2_fill_2_end:
MOVQ (CX)(DI*8), DI
// Update Literal Length State
BZHIQ SI, R14, CX
MOVQ $0x00001010, R13
BEXTRQ R13, SI, SI
ADDQ CX, SI
BZHIQ SI, R14, CX
SHRL $0x10, SI
ADDQ CX, SI
// Load ctx.llTable
MOVQ ctx+16(FP), CX
@@ -2753,9 +2800,9 @@ handle_loop:
loop_finished:
MOVQ br+8(FP), CX
MOVQ AX, 32(CX)
MOVQ AX, 24(CX)
MOVB DL, 40(CX)
MOVQ BX, 24(CX)
MOVQ BX, 32(CX)
// Update the context
MOVQ ctx+16(FP), AX
@@ -2801,6 +2848,11 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// Return with not enough output space error
error_not_enough_space:
MOVQ ctx+16(FP), AX
@@ -2815,11 +2867,11 @@ error_not_enough_space:
// func sequenceDecs_decodeSync_safe_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
// Requires: CMOV, SSE
TEXT ·sequenceDecs_decodeSync_safe_amd64(SB), $64-32
MOVQ br+8(FP), AX
MOVQ 32(AX), DX
MOVBQZX 40(AX), BX
MOVQ 24(AX), SI
MOVQ (AX), AX
MOVQ br+8(FP), CX
MOVQ 24(CX), DX
MOVBQZX 40(CX), BX
MOVQ (CX), AX
MOVQ 32(CX), SI
ADDQ SI, AX
MOVQ AX, (SP)
MOVQ ctx+16(FP), AX
@@ -2844,7 +2896,7 @@ TEXT ·sequenceDecs_decodeSync_safe_amd64(SB), $64-32
MOVQ 40(SP), AX
ADDQ AX, 48(SP)
// Calculate poiter to s.out[cap(s.out)] (a past-end pointer)
// Calculate pointer to s.out[cap(s.out)] (a past-end pointer)
ADDQ R10, 32(SP)
// outBase += outPosition
@@ -2866,7 +2918,7 @@ sequenceDecs_decodeSync_safe_amd64_main_loop:
sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decodeSync_safe_amd64_fill_end
JLE sequenceDecs_decodeSync_safe_amd64_fill_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decodeSync_safe_amd64_fill_end
SHLQ $0x08, DX
@@ -2877,6 +2929,10 @@ sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decodeSync_safe_amd64_fill_byte_by_byte
sequenceDecs_decodeSync_safe_amd64_fill_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decodeSync_safe_amd64_fill_end:
// Update offset
MOVQ R9, AX
@@ -2933,7 +2989,7 @@ sequenceDecs_decodeSync_safe_amd64_ml_update_zero:
sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte:
CMPQ SI, $0x00
JLE sequenceDecs_decodeSync_safe_amd64_fill_2_end
JLE sequenceDecs_decodeSync_safe_amd64_fill_2_check_overread
CMPQ BX, $0x07
JLE sequenceDecs_decodeSync_safe_amd64_fill_2_end
SHLQ $0x08, DX
@@ -2944,6 +3000,10 @@ sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte:
ORQ AX, DX
JMP sequenceDecs_decodeSync_safe_amd64_fill_2_byte_by_byte
sequenceDecs_decodeSync_safe_amd64_fill_2_check_overread:
CMPQ BX, $0x40
JA error_overread
sequenceDecs_decodeSync_safe_amd64_fill_2_end:
// Update literal length
MOVQ DI, AX
@@ -2977,8 +3037,7 @@ sequenceDecs_decodeSync_safe_amd64_ll_update_zero:
// Update Literal Length State
MOVBQZX DI, R13
SHRQ $0x10, DI
MOVWQZX DI, DI
SHRL $0x10, DI
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -2997,8 +3056,7 @@ sequenceDecs_decodeSync_safe_amd64_ll_update_zero:
// Update Match Length State
MOVBQZX R8, R13
SHRQ $0x10, R8
MOVWQZX R8, R8
SHRL $0x10, R8
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -3017,8 +3075,7 @@ sequenceDecs_decodeSync_safe_amd64_ll_update_zero:
// Update Offset State
MOVBQZX R9, R13
SHRQ $0x10, R9
MOVWQZX R9, R9
SHRL $0x10, R9
LEAQ (BX)(R13*1), CX
MOVQ DX, R14
MOVQ CX, BX
@@ -3407,9 +3464,9 @@ handle_loop:
loop_finished:
MOVQ br+8(FP), AX
MOVQ DX, 32(AX)
MOVQ DX, 24(AX)
MOVB BL, 40(AX)
MOVQ SI, 24(AX)
MOVQ SI, 32(AX)
// Update the context
MOVQ ctx+16(FP), AX
@@ -3455,6 +3512,11 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// Return with not enough output space error
error_not_enough_space:
MOVQ ctx+16(FP), AX
@@ -3469,11 +3531,11 @@ error_not_enough_space:
// func sequenceDecs_decodeSync_safe_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
// Requires: BMI, BMI2, CMOV, SSE
TEXT ·sequenceDecs_decodeSync_safe_bmi2(SB), $64-32
MOVQ br+8(FP), CX
MOVQ 32(CX), AX
MOVBQZX 40(CX), DX
MOVQ 24(CX), BX
MOVQ (CX), CX
MOVQ br+8(FP), BX
MOVQ 24(BX), AX
MOVBQZX 40(BX), DX
MOVQ (BX), CX
MOVQ 32(BX), BX
ADDQ BX, CX
MOVQ CX, (SP)
MOVQ ctx+16(FP), CX
@@ -3498,7 +3560,7 @@ TEXT ·sequenceDecs_decodeSync_safe_bmi2(SB), $64-32
MOVQ 40(SP), CX
ADDQ CX, 48(SP)
// Calculate poiter to s.out[cap(s.out)] (a past-end pointer)
// Calculate pointer to s.out[cap(s.out)] (a past-end pointer)
ADDQ R9, 32(SP)
// outBase += outPosition
@@ -3520,7 +3582,7 @@ sequenceDecs_decodeSync_safe_bmi2_main_loop:
sequenceDecs_decodeSync_safe_bmi2_fill_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decodeSync_safe_bmi2_fill_end
JLE sequenceDecs_decodeSync_safe_bmi2_fill_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decodeSync_safe_bmi2_fill_end
SHLQ $0x08, AX
@@ -3531,6 +3593,10 @@ sequenceDecs_decodeSync_safe_bmi2_fill_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decodeSync_safe_bmi2_fill_byte_by_byte
sequenceDecs_decodeSync_safe_bmi2_fill_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decodeSync_safe_bmi2_fill_end:
// Update offset
MOVQ $0x00000808, CX
@@ -3571,7 +3637,7 @@ sequenceDecs_decodeSync_safe_bmi2_fill_end:
sequenceDecs_decodeSync_safe_bmi2_fill_2_byte_by_byte:
CMPQ BX, $0x00
JLE sequenceDecs_decodeSync_safe_bmi2_fill_2_end
JLE sequenceDecs_decodeSync_safe_bmi2_fill_2_check_overread
CMPQ DX, $0x07
JLE sequenceDecs_decodeSync_safe_bmi2_fill_2_end
SHLQ $0x08, AX
@@ -3582,6 +3648,10 @@ sequenceDecs_decodeSync_safe_bmi2_fill_2_byte_by_byte:
ORQ CX, AX
JMP sequenceDecs_decodeSync_safe_bmi2_fill_2_byte_by_byte
sequenceDecs_decodeSync_safe_bmi2_fill_2_check_overread:
CMPQ DX, $0x40
JA error_overread
sequenceDecs_decodeSync_safe_bmi2_fill_2_end:
// Update literal length
MOVQ $0x00000808, CX
@@ -3613,11 +3683,10 @@ sequenceDecs_decodeSync_safe_bmi2_fill_2_end:
BZHIQ R13, R14, R14
// Update Offset State
BZHIQ R8, R14, CX
SHRXQ R8, R14, R14
MOVQ $0x00001010, R13
BEXTRQ R13, R8, R8
ADDQ CX, R8
BZHIQ R8, R14, CX
SHRXQ R8, R14, R14
SHRL $0x10, R8
ADDQ CX, R8
// Load ctx.ofTable
MOVQ ctx+16(FP), CX
@@ -3625,11 +3694,10 @@ sequenceDecs_decodeSync_safe_bmi2_fill_2_end:
MOVQ (CX)(R8*8), R8
// Update Match Length State
BZHIQ DI, R14, CX
SHRXQ DI, R14, R14
MOVQ $0x00001010, R13
BEXTRQ R13, DI, DI
ADDQ CX, DI
BZHIQ DI, R14, CX
SHRXQ DI, R14, R14
SHRL $0x10, DI
ADDQ CX, DI
// Load ctx.mlTable
MOVQ ctx+16(FP), CX
@@ -3637,10 +3705,9 @@ sequenceDecs_decodeSync_safe_bmi2_fill_2_end:
MOVQ (CX)(DI*8), DI
// Update Literal Length State
BZHIQ SI, R14, CX
MOVQ $0x00001010, R13
BEXTRQ R13, SI, SI
ADDQ CX, SI
BZHIQ SI, R14, CX
SHRL $0x10, SI
ADDQ CX, SI
// Load ctx.llTable
MOVQ ctx+16(FP), CX
@@ -4019,9 +4086,9 @@ handle_loop:
loop_finished:
MOVQ br+8(FP), CX
MOVQ AX, 32(CX)
MOVQ AX, 24(CX)
MOVB DL, 40(CX)
MOVQ BX, 24(CX)
MOVQ BX, 32(CX)
// Update the context
MOVQ ctx+16(FP), AX
@@ -4067,6 +4134,11 @@ error_not_enough_literals:
MOVQ $0x00000004, ret+24(FP)
RET
// Return with overread error
error_overread:
MOVQ $0x00000006, ret+24(FP)
RET
// Return with not enough output space error
error_not_enough_space:
MOVQ ctx+16(FP), AX