.text
SYM_FUNC_START(crc32c_x86_3way)
cmp $SMALL_SIZE, len
jb .Lsmall
mov bufp_d, n_misaligned
neg n_misaligned
and $7, n_misaligned
je .Laligned
.Ldo_align:
movq (bufp), %rax
add n_misaligned_q, bufp
sub n_misaligned_q, len
.Lalign_loop:
crc32b %al, crc0
shr $8, %rax
dec n_misaligned
jne .Lalign_loop
.Laligned:
cmp $128*24, len
jae .Lfull_block
.Lpartial_block:
imul $2731, len_dw, %eax
shr $16, %eax
jmp .Lcrc_3lanes
.Lfull_block:
mov $128, %eax
.Lcrc_3lanes:
xor crc1,crc1
xor crc2,crc2
mov %eax, chunk_bytes
shl $3, chunk_bytes
sub $5, %eax
jl .Lcrc_3lanes_4x_done
.Lcrc_3lanes_4x_loop:
crc32q (bufp), crc0_q
crc32q (bufp,chunk_bytes_q), crc1
crc32q (bufp,chunk_bytes_q,2), crc2
crc32q 8(bufp), crc0_q
crc32q 8(bufp,chunk_bytes_q), crc1
crc32q 8(bufp,chunk_bytes_q,2), crc2
crc32q 16(bufp), crc0_q
crc32q 16(bufp,chunk_bytes_q), crc1
crc32q 16(bufp,chunk_bytes_q,2), crc2
crc32q 24(bufp), crc0_q
crc32q 24(bufp,chunk_bytes_q), crc1
crc32q 24(bufp,chunk_bytes_q,2), crc2
add $32, bufp
sub $4, %eax
jge .Lcrc_3lanes_4x_loop
.Lcrc_3lanes_4x_done:
add $4, %eax
jz .Lcrc_3lanes_last_qword
.Lcrc_3lanes_1x_loop:
crc32q (bufp), crc0_q
crc32q (bufp,chunk_bytes_q), crc1
crc32q (bufp,chunk_bytes_q,2), crc2
add $8, bufp
dec %eax
jnz .Lcrc_3lanes_1x_loop
.Lcrc_3lanes_last_qword:
crc32q (bufp), crc0_q
crc32q (bufp,chunk_bytes_q), crc1
lea (K_table-8)(%rip), %rax
pmovzxdq (%rax,chunk_bytes_q), %xmm0
lea (chunk_bytes,chunk_bytes,2), %eax
sub %rax, len
movq crc0_q, %xmm1
pclmulqdq $0x00, %xmm0, %xmm1
movq crc1, %xmm2
pclmulqdq $0x10, %xmm0, %xmm2
pxor %xmm2,%xmm1
movq %xmm1, %rax
xor (bufp,chunk_bytes_q,2), %rax
mov crc2, crc0_q
crc32 %rax, crc0_q
lea 8(bufp,chunk_bytes_q,2), bufp
cmp $128*24, len
jae .Lfull_block
cmp $SMALL_SIZE, len
jae .Lpartial_block
.Lsmall:
test len_dw, len_dw
jz .Ldone
mov len_dw, %eax
shr $3, %eax
jz .Ldo_dword
.Ldo_qwords:
crc32q (bufp), crc0_q
add $8, bufp
dec %eax
jnz .Ldo_qwords
.Ldo_dword:
test $4, len_dw
jz .Ldo_word
crc32l (bufp), crc0
add $4, bufp
.Ldo_word:
test $2, len_dw
jz .Ldo_byte
crc32w (bufp), crc0
add $2, bufp
.Ldo_byte:
test $1, len_dw
jz .Ldone
crc32b (bufp), crc0
.Ldone:
mov crc0, %eax
RET
SYM_FUNC_END(crc32c_x86_3way)
.section .rodata, "a", @progbits
.align 8
K_table:
.long 0x493c7d27, 0x00000001
.long 0xba4fc28e, 0x493c7d27
.long 0xddc0152b, 0xf20c0dfe
.long 0x9e4addf8, 0xba4fc28e
.long 0x39d3b296, 0x3da6d0cb
.long 0x0715ce53, 0xddc0152b
.long 0x47db8317, 0x1c291d04
.long 0x0d3b6092, 0x9e4addf8
.long 0xc96cfdc0, 0x740eef02
.long 0x878a92a7, 0x39d3b296
.long 0xdaece73e, 0x083a6eec
.long 0xab7aff2a, 0x0715ce53
.long 0x2162d385, 0xc49f4f67
.long 0x83348832, 0x47db8317
.long 0x299847d5, 0x2ad91c30
.long 0xb9e02b86, 0x0d3b6092
.long 0x18b33a4e, 0x6992cea2
.long 0xb6dd949b, 0xc96cfdc0
.long 0x78d9ccb7, 0x7e908048
.long 0xbac2fd7b, 0x878a92a7
.long 0xa60ce07b, 0x1b3d8f29
.long 0xce7f39f4, 0xdaece73e
.long 0x61d82e56, 0xf1d0f55e
.long 0xd270f1a2, 0xab7aff2a
.long 0xc619809d, 0xa87ab8a8
.long 0x2b3cac5d, 0x2162d385
.long 0x65863b64, 0x8462d800
.long 0x1b03397f, 0x83348832
.long 0xebb883bd, 0x71d111a8
.long 0xb3e32c28, 0x299847d5
.long 0x064f7f26, 0xffd852c6
.long 0xdd7e3b0c, 0xb9e02b86
.long 0xf285651c, 0xdcb17aa4
.long 0x10746f3c, 0x18b33a4e
.long 0xc7a68855, 0xf37c5aee
.long 0x271d9844, 0xb6dd949b
.long 0x8e766a0c, 0x6051d5a2
.long 0x93a5f730, 0x78d9ccb7
.long 0x6cb08e5c, 0x18b0d4ff
.long 0x6b749fb2, 0xbac2fd7b
.long 0x1393e203, 0x21f3d99c
.long 0xcec3662e, 0xa60ce07b
.long 0x96c515bb, 0x8f158014
.long 0xe6fc4e6a, 0xce7f39f4
.long 0x8227bb8a, 0xa00457f7
.long 0xb0cd4768, 0x61d82e56
.long 0x39c7ff35, 0x8d6d2c43
.long 0xd7a4825c, 0xd270f1a2
.long 0x0ab3844b, 0x00ac29cf
.long 0x0167d312, 0xc619809d
.long 0xf6076544, 0xe9adf796
.long 0x26f6a60a, 0x2b3cac5d
.long 0xa741c1bf, 0x96638b34
.long 0x98d8d9cb, 0x65863b64
.long 0x49c3cc9c, 0xe0e9f351
.long 0x68bce87a, 0x1b03397f
.long 0x57a3d037, 0x9af01f2d
.long 0x6956fc3b, 0xebb883bd
.long 0x42d98888, 0x2cff42cf
.long 0x3771e98f, 0xb3e32c28
.long 0xb42ae3d9, 0x88f25a3a
.long 0x2178513a, 0x064f7f26
.long 0xe0ac139e, 0x4e36f0b0
.long 0x170076fa, 0xdd7e3b0c
.long 0x444dd413, 0xbd6f81f8
.long 0x6f345e45, 0xf285651c
.long 0x41d17b64, 0x91c9bd4b
.long 0xff0dba97, 0x10746f3c
.long 0xa2b73df1, 0x885f087b
.long 0xf872e54c, 0xc7a68855
.long 0x1e41e9fc, 0x4c144932
.long 0x86d8e4d2, 0x271d9844
.long 0x651bd98b, 0x52148f02
.long 0x5bb8f1bc, 0x8e766a0c
.long 0xa90fd27a, 0xa3c6f37a
.long 0xb3af077a, 0x93a5f730
.long 0x4984d782, 0xd7c0557f
.long 0xca6ef3ac, 0x6cb08e5c
.long 0x234e0b26, 0x63ded06a
.long 0xdd66cbbb, 0x6b749fb2
.long 0x4597456a, 0x4d56973c
.long 0xe9e28eb4, 0x1393e203
.long 0x7b3ff57a, 0x9669c9df
.long 0xc9c8b782, 0xcec3662e
.long 0x3f70cc6f, 0xe417f38a
.long 0x93e106a4, 0x96c515bb
.long 0x62ec6c6d, 0x4b9e0f71
.long 0xd813b325, 0xe6fc4e6a
.long 0x0df04680, 0xd104b8fc
.long 0x2342001e, 0x8227bb8a
.long 0x0a2a8d7e, 0x5b397730
.long 0x6d9a4957, 0xb0cd4768
.long 0xe8b6368b, 0xe78eb416
.long 0xd2c3ed1a, 0x39c7ff35
.long 0x995a5724, 0x61ff0e01
.long 0x9ef68d35, 0xd7a4825c
.long 0x0c139b31, 0x8d96551c
.long 0xf2271e60, 0x0ab3844b
.long 0x0b0bf8ca, 0x0bf80dd2
.long 0x2664fd8b, 0x0167d312
.long 0xed64812d, 0x8821abed
.long 0x02ee03b2, 0xf6076544
.long 0x8604ae0f, 0x6a45d2b2
.long 0x363bd6b3, 0x26f6a60a
.long 0x135c83fd, 0xd8d26619
.long 0x5fabe670, 0xa741c1bf
.long 0x35ec3279, 0xde87806c
.long 0x00bcf5f6, 0x98d8d9cb
.long 0x8ae00689, 0x14338754
.long 0x17f27698, 0x49c3cc9c
.long 0x58ca5f00, 0x5bd2011f
.long 0xaa7c7ad5, 0x68bce87a
.long 0xb5cfca28, 0xdd07448e
.long 0xded288f8, 0x57a3d037
.long 0x59f229bc, 0xdde8f5b9
.long 0x6d390dec, 0x6956fc3b
.long 0x37170390, 0xa3e3e02c
.long 0x6353c1cc, 0x42d98888
.long 0xc4584f5c, 0xd73c7bea
.long 0xf48642e9, 0x3771e98f
.long 0x531377e2, 0x80ff0093
.long 0xdd35bc8d, 0xb42ae3d9
.long 0xb25b29f2, 0x8fe4c34d
.long 0x9a5ede41, 0x2178513a
.long 0xa563905d, 0xdf99fc11
.long 0x45cddf4e, 0xe0ac139e
.long 0xacfa3103, 0x6c23e841
.long 0xa51b6135, 0x170076fa