mirror of
https://github.com/intel/isa-l.git
synced 2025-09-18 19:09:32 +02:00
igzip: Remove igzip copy of crc32_gzip
Change-Id: I859ed904effa0a8bd7462b77b13e359014912639 Signed-off-by: Roy Oursler <roy.j.oursler@intel.com>
This commit is contained in:
Roy Oursler
parent
7205c23647
commit
9689ba7e13
@ -91,7 +91,6 @@ objs = \
|
||||
bin\crc16_t10dif_01.obj \
|
||||
bin\crc16_t10dif_by4.obj \
|
||||
bin\crc16_t10dif_copy_by4.obj \
|
||||
bin\crc32_gzip.obj \
|
||||
bin\crc32_ieee_01.obj \
|
||||
bin\crc32_ieee_by4.obj \
|
||||
bin\crc32_iscsi_00.obj \
|
||||
@ -105,7 +104,7 @@ objs = \
|
||||
bin\crc64_jones_refl_by8.obj \
|
||||
bin\crc64_multibinary.obj \
|
||||
bin\crc_base.obj \
|
||||
bin\crc32_gzip_base.obj \
|
||||
bin\adler32_base.obj \
|
||||
bin\crc_multibinary.obj \
|
||||
bin\huff_codes.obj \
|
||||
bin\hufftables_c.obj \
|
||||
|
||||
@ -31,6 +31,12 @@ units = erasure_code raid crc igzip programs
|
||||
|
||||
default: lib
|
||||
|
||||
ifeq (,$(findstring crc,$(units)))
|
||||
ifneq (,$(findstring igzip,$(units)))
|
||||
override units += crc
|
||||
endif
|
||||
endif
|
||||
|
||||
include $(foreach unit,$(units), $(unit)/Makefile.am)
|
||||
|
||||
ifneq (,$(findstring igzip,$(units)))
|
||||
|
||||
@ -31,7 +31,7 @@ lsrc += igzip/igzip.c \
|
||||
igzip/hufftables_c.c \
|
||||
igzip/igzip_base.c \
|
||||
igzip/igzip_icf_base.c \
|
||||
igzip/crc32_gzip_base.c \
|
||||
igzip/adler32_base.c \
|
||||
igzip/flatten_ll.c \
|
||||
igzip/encode_df.c \
|
||||
igzip/igzip_icf_body.c
|
||||
@ -44,7 +44,6 @@ lsrc_x86_64 += igzip/igzip_body.asm \
|
||||
igzip/igzip_icf_body_h1_gr_bt.asm \
|
||||
igzip/igzip_icf_finish.asm \
|
||||
igzip/rfc1951_lookup.asm \
|
||||
igzip/crc32_gzip.asm \
|
||||
igzip/adler32_sse.asm \
|
||||
igzip/adler32_avx2_4.asm \
|
||||
igzip/igzip_multibinary.asm \
|
||||
|
||||
63
igzip/adler32_base.c
Normal file
63
igzip/adler32_base.c
Normal file
@ -0,0 +1,63 @@
|
||||
/**********************************************************************
|
||||
Copyright(c) 2011-2017 Intel Corporation All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions
|
||||
are met:
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in
|
||||
the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Intel Corporation nor the names of its
|
||||
contributors may be used to endorse or promote products derived
|
||||
from this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
**********************************************************************/
|
||||
|
||||
#include <stdint.h>
|
||||
#include "igzip_checksums.h"
|
||||
|
||||
uint32_t adler32_base(uint32_t adler32, uint8_t * start, uint32_t length)
|
||||
{
|
||||
uint8_t *end, *next = start;
|
||||
uint64_t A, B;
|
||||
|
||||
A = adler32 & 0xffff;
|
||||
B = adler32 >> 16;
|
||||
|
||||
while (length > MAX_ADLER_BUF) {
|
||||
end = next + MAX_ADLER_BUF;
|
||||
for (; next < end; next++) {
|
||||
A += *next;
|
||||
B += A;
|
||||
}
|
||||
|
||||
A = A % ADLER_MOD;
|
||||
B = B % ADLER_MOD;
|
||||
length -= MAX_ADLER_BUF;
|
||||
}
|
||||
|
||||
end = next + length;
|
||||
for (; next < end; next++) {
|
||||
A += *next;
|
||||
B += A;
|
||||
}
|
||||
|
||||
A = A % ADLER_MOD;
|
||||
B = B % ADLER_MOD;
|
||||
|
||||
return B << 16 | A;
|
||||
}
|
||||
@ -51,7 +51,6 @@ typedef struct func_case {
|
||||
|
||||
func_case_t test_funcs[] = {
|
||||
{"checksum32_adler", isal_adler32, adler_ref},
|
||||
{"crc32_gzip_refl", crc32_gzip, crc32_gzip_refl_ref}
|
||||
};
|
||||
|
||||
// Generates pseudo-random data
|
||||
|
||||
@ -1,617 +0,0 @@
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
; Copyright(c) 2011-2016 Intel Corporation All rights reserved.
|
||||
;
|
||||
; Redistribution and use in source and binary forms, with or without
|
||||
; modification, are permitted provided that the following conditions
|
||||
; are met:
|
||||
; * Redistributions of source code must retain the above copyright
|
||||
; notice, this list of conditions and the following disclaimer.
|
||||
; * Redistributions in binary form must reproduce the above copyright
|
||||
; notice, this list of conditions and the following disclaimer in
|
||||
; the documentation and/or other materials provided with the
|
||||
; distribution.
|
||||
; * Neither the name of Intel Corporation nor the names of its
|
||||
; contributors may be used to endorse or promote products derived
|
||||
; from this software without specific prior written permission.
|
||||
;
|
||||
; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
; "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
; LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
; A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
; OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
; SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
; LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
; DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
; THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
; (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
; OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
; Function API:
|
||||
; UINT32 crc32_gzip(
|
||||
; UINT32 init_crc, //initial CRC value, 32 bits
|
||||
; const unsigned char *buf, //buffer pointer to calculate CRC on
|
||||
; UINT64 len //buffer length in bytes (64-bit data)
|
||||
; );
|
||||
;
|
||||
; Authors:
|
||||
; Erdinc Ozturk
|
||||
; Vinodh Gopal
|
||||
; James Guilford
|
||||
;
|
||||
; Reference paper titled "Fast CRC Computation for Generic Polynomials Using PCLMULQDQ Instruction"
|
||||
; URL: http://download.intel.com/design/intarch/papers/323102.pdf
|
||||
;
|
||||
;
|
||||
; sample yasm command line:
|
||||
; yasm -f x64 -f elf64 -X gnu -g dwarf2 crc32_gzip
|
||||
;
|
||||
; As explained here:
|
||||
; http://docs.oracle.com/javase/7/docs/api/java/util/zip/package-summary.html
|
||||
; CRC-32 checksum is described in RFC 1952
|
||||
; Implementing RFC 1952 CRC:
|
||||
; http://www.ietf.org/rfc/rfc1952.txt
|
||||
|
||||
%include "reg_sizes.asm"
|
||||
|
||||
[bits 64]
|
||||
default rel
|
||||
|
||||
section .text
|
||||
|
||||
|
||||
%ifidn __OUTPUT_FORMAT__, win64
|
||||
%xdefine arg1 rcx
|
||||
%xdefine arg2 rdx
|
||||
%xdefine arg3 r8
|
||||
|
||||
%xdefine arg1_low32 ecx
|
||||
%else
|
||||
%xdefine arg1 rdi
|
||||
%xdefine arg2 rsi
|
||||
%xdefine arg3 rdx
|
||||
|
||||
%xdefine arg1_low32 edi
|
||||
%endif
|
||||
|
||||
%define TMP 16*0
|
||||
%ifidn __OUTPUT_FORMAT__, win64
|
||||
%define XMM_SAVE 16*2
|
||||
%define VARIABLE_OFFSET 16*10+8
|
||||
%else
|
||||
%define VARIABLE_OFFSET 16*2+8
|
||||
%endif
|
||||
|
||||
align 16
|
||||
global crc32_gzip_01
|
||||
crc32_gzip_01:
|
||||
|
||||
; unsigned long c = crc ^ 0xffffffffL;
|
||||
not arg1_low32 ;
|
||||
|
||||
|
||||
sub rsp, VARIABLE_OFFSET
|
||||
%ifidn __OUTPUT_FORMAT__, win64
|
||||
; push the xmm registers into the stack to maintain
|
||||
movdqa [rsp + XMM_SAVE + 16*0], xmm6
|
||||
movdqa [rsp + XMM_SAVE + 16*1], xmm7
|
||||
movdqa [rsp + XMM_SAVE + 16*2], xmm8
|
||||
movdqa [rsp + XMM_SAVE + 16*3], xmm9
|
||||
movdqa [rsp + XMM_SAVE + 16*4], xmm10
|
||||
movdqa [rsp + XMM_SAVE + 16*5], xmm11
|
||||
movdqa [rsp + XMM_SAVE + 16*6], xmm12
|
||||
movdqa [rsp + XMM_SAVE + 16*7], xmm13
|
||||
%endif
|
||||
|
||||
; check if smaller than 256B
|
||||
cmp arg3, 256
|
||||
|
||||
; for sizes less than 256, we can't fold 128B at a time...
|
||||
jl _less_than_256
|
||||
|
||||
|
||||
; load the initial crc value
|
||||
movd xmm10, arg1_low32 ; initial crc
|
||||
|
||||
; receive the initial 64B data, xor the initial crc value
|
||||
movdqu xmm0, [arg2+16*0]
|
||||
movdqu xmm1, [arg2+16*1]
|
||||
movdqu xmm2, [arg2+16*2]
|
||||
movdqu xmm3, [arg2+16*3]
|
||||
movdqu xmm4, [arg2+16*4]
|
||||
movdqu xmm5, [arg2+16*5]
|
||||
movdqu xmm6, [arg2+16*6]
|
||||
movdqu xmm7, [arg2+16*7]
|
||||
|
||||
; XOR the initial_crc value
|
||||
pxor xmm0, xmm10
|
||||
movdqa xmm10, [rk3] ;xmm10 has rk3 and rk4
|
||||
;imm value of pclmulqdq instruction will determine which constant to use
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
; we subtract 256 instead of 128 to save one instruction from the loop
|
||||
sub arg3, 256
|
||||
|
||||
; at this section of the code, there is 128*x+y (0<=y<128) bytes of buffer. The _fold_128_B_loop
|
||||
; loop will fold 128B at a time until we have 128+y Bytes of buffer
|
||||
|
||||
|
||||
; fold 128B at a time. This section of the code folds 8 xmm registers in parallel
|
||||
_fold_128_B_loop:
|
||||
|
||||
; update the buffer pointer
|
||||
add arg2, 128
|
||||
|
||||
movdqu xmm9, [arg2+16*0]
|
||||
movdqu xmm12, [arg2+16*1]
|
||||
movdqa xmm8, xmm0
|
||||
movdqa xmm13, xmm1
|
||||
pclmulqdq xmm0, xmm10, 0x10
|
||||
pclmulqdq xmm8, xmm10 , 0x1
|
||||
pclmulqdq xmm1, xmm10, 0x10
|
||||
pclmulqdq xmm13, xmm10 , 0x1
|
||||
pxor xmm0, xmm9
|
||||
xorps xmm0, xmm8
|
||||
pxor xmm1, xmm12
|
||||
xorps xmm1, xmm13
|
||||
|
||||
movdqu xmm9, [arg2+16*2]
|
||||
movdqu xmm12, [arg2+16*3]
|
||||
movdqa xmm8, xmm2
|
||||
movdqa xmm13, xmm3
|
||||
pclmulqdq xmm2, xmm10, 0x10
|
||||
pclmulqdq xmm8, xmm10 , 0x1
|
||||
pclmulqdq xmm3, xmm10, 0x10
|
||||
pclmulqdq xmm13, xmm10 , 0x1
|
||||
pxor xmm2, xmm9
|
||||
xorps xmm2, xmm8
|
||||
pxor xmm3, xmm12
|
||||
xorps xmm3, xmm13
|
||||
|
||||
movdqu xmm9, [arg2+16*4]
|
||||
movdqu xmm12, [arg2+16*5]
|
||||
movdqa xmm8, xmm4
|
||||
movdqa xmm13, xmm5
|
||||
pclmulqdq xmm4, xmm10, 0x10
|
||||
pclmulqdq xmm8, xmm10 , 0x1
|
||||
pclmulqdq xmm5, xmm10, 0x10
|
||||
pclmulqdq xmm13, xmm10 , 0x1
|
||||
pxor xmm4, xmm9
|
||||
xorps xmm4, xmm8
|
||||
pxor xmm5, xmm12
|
||||
xorps xmm5, xmm13
|
||||
|
||||
movdqu xmm9, [arg2+16*6]
|
||||
movdqu xmm12, [arg2+16*7]
|
||||
movdqa xmm8, xmm6
|
||||
movdqa xmm13, xmm7
|
||||
pclmulqdq xmm6, xmm10, 0x10
|
||||
pclmulqdq xmm8, xmm10 , 0x1
|
||||
pclmulqdq xmm7, xmm10, 0x10
|
||||
pclmulqdq xmm13, xmm10 , 0x1
|
||||
pxor xmm6, xmm9
|
||||
xorps xmm6, xmm8
|
||||
pxor xmm7, xmm12
|
||||
xorps xmm7, xmm13
|
||||
|
||||
sub arg3, 128
|
||||
|
||||
; check if there is another 128B in the buffer to be able to fold
|
||||
jge _fold_128_B_loop
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
|
||||
|
||||
add arg2, 128
|
||||
; at this point, the buffer pointer is pointing at the last y Bytes of the buffer, where 0 <= y < 128
|
||||
; the 128B of folded data is in 8 of the xmm registers: xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7
|
||||
|
||||
|
||||
; fold the 8 xmm registers to 1 xmm register with different constants
|
||||
|
||||
movdqa xmm10, [rk9]
|
||||
movdqa xmm8, xmm0
|
||||
pclmulqdq xmm0, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
xorps xmm7, xmm0
|
||||
|
||||
movdqa xmm10, [rk11]
|
||||
movdqa xmm8, xmm1
|
||||
pclmulqdq xmm1, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
xorps xmm7, xmm1
|
||||
|
||||
movdqa xmm10, [rk13]
|
||||
movdqa xmm8, xmm2
|
||||
pclmulqdq xmm2, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
pxor xmm7, xmm2
|
||||
|
||||
movdqa xmm10, [rk15]
|
||||
movdqa xmm8, xmm3
|
||||
pclmulqdq xmm3, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
xorps xmm7, xmm3
|
||||
|
||||
movdqa xmm10, [rk17]
|
||||
movdqa xmm8, xmm4
|
||||
pclmulqdq xmm4, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
pxor xmm7, xmm4
|
||||
|
||||
movdqa xmm10, [rk19]
|
||||
movdqa xmm8, xmm5
|
||||
pclmulqdq xmm5, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
xorps xmm7, xmm5
|
||||
|
||||
movdqa xmm10, [rk1]
|
||||
movdqa xmm8, xmm6
|
||||
pclmulqdq xmm6, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
pxor xmm7, xmm6
|
||||
|
||||
|
||||
; instead of 128, we add 128-16 to the loop counter to save 1 instruction from the loop
|
||||
; instead of a cmp instruction, we use the negative flag with the jl instruction
|
||||
add arg3, 128-16
|
||||
jl _final_reduction_for_128
|
||||
|
||||
; now we have 16+y bytes left to reduce. 16 Bytes is in register xmm7 and the rest is in memory
|
||||
; we can fold 16 bytes at a time if y>=16
|
||||
; continue folding 16B at a time
|
||||
|
||||
_16B_reduction_loop:
|
||||
movdqa xmm8, xmm7
|
||||
pclmulqdq xmm7, xmm10, 0x1
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
movdqu xmm0, [arg2]
|
||||
pxor xmm7, xmm0
|
||||
add arg2, 16
|
||||
sub arg3, 16
|
||||
; instead of a cmp instruction, we utilize the flags with the jge instruction
|
||||
; equivalent of: cmp arg3, 16-16
|
||||
; check if there is any more 16B in the buffer to be able to fold
|
||||
jge _16B_reduction_loop
|
||||
|
||||
;now we have 16+z bytes left to reduce, where 0<= z < 16.
|
||||
;first, we reduce the data in the xmm7 register
|
||||
|
||||
|
||||
_final_reduction_for_128:
|
||||
add arg3, 16
|
||||
je _128_done
|
||||
|
||||
; here we are getting data that is less than 16 bytes.
|
||||
; since we know that there was data before the pointer, we can offset the input pointer before the actual point, to receive exactly 16 bytes.
|
||||
; after that the registers need to be adjusted.
|
||||
_get_last_two_xmms:
|
||||
|
||||
|
||||
movdqa xmm2, xmm7
|
||||
movdqu xmm1, [arg2 - 16 + arg3]
|
||||
|
||||
; get rid of the extra data that was loaded before
|
||||
; load the shift constant
|
||||
lea rax, [pshufb_shf_table]
|
||||
add rax, arg3
|
||||
movdqu xmm0, [rax]
|
||||
|
||||
|
||||
pshufb xmm7, xmm0
|
||||
pxor xmm0, [mask3]
|
||||
pshufb xmm2, xmm0
|
||||
|
||||
pblendvb xmm2, xmm1 ;xmm0 is implicit
|
||||
;;;;;;;;;;
|
||||
movdqa xmm8, xmm7
|
||||
pclmulqdq xmm7, xmm10, 0x1
|
||||
|
||||
pclmulqdq xmm8, xmm10, 0x10
|
||||
pxor xmm7, xmm8
|
||||
pxor xmm7, xmm2
|
||||
|
||||
_128_done:
|
||||
; compute crc of a 128-bit value
|
||||
movdqa xmm10, [rk5]
|
||||
movdqa xmm0, xmm7
|
||||
|
||||
;64b fold
|
||||
pclmulqdq xmm7, xmm10, 0
|
||||
psrldq xmm0, 8
|
||||
pxor xmm7, xmm0
|
||||
|
||||
;32b fold
|
||||
movdqa xmm0, xmm7
|
||||
pslldq xmm7, 4
|
||||
pclmulqdq xmm7, xmm10, 0x10
|
||||
|
||||
pxor xmm7, xmm0
|
||||
|
||||
|
||||
;barrett reduction
|
||||
_barrett:
|
||||
pand xmm7, [mask2]
|
||||
movdqa xmm1, xmm7
|
||||
movdqa xmm2, xmm7
|
||||
movdqa xmm10, [rk7]
|
||||
|
||||
pclmulqdq xmm7, xmm10, 0
|
||||
pxor xmm7, xmm2
|
||||
pand xmm7, [mask]
|
||||
movdqa xmm2, xmm7
|
||||
pclmulqdq xmm7, xmm10, 0x10
|
||||
pxor xmm7, xmm2
|
||||
pxor xmm7, xmm1
|
||||
pextrd eax, xmm7, 2
|
||||
|
||||
_cleanup:
|
||||
; return c ^ 0xffffffffL;
|
||||
not eax
|
||||
|
||||
|
||||
%ifidn __OUTPUT_FORMAT__, win64
|
||||
movdqa xmm6, [rsp + XMM_SAVE + 16*0]
|
||||
movdqa xmm7, [rsp + XMM_SAVE + 16*1]
|
||||
movdqa xmm8, [rsp + XMM_SAVE + 16*2]
|
||||
movdqa xmm9, [rsp + XMM_SAVE + 16*3]
|
||||
movdqa xmm10, [rsp + XMM_SAVE + 16*4]
|
||||
movdqa xmm11, [rsp + XMM_SAVE + 16*5]
|
||||
movdqa xmm12, [rsp + XMM_SAVE + 16*6]
|
||||
movdqa xmm13, [rsp + XMM_SAVE + 16*7]
|
||||
%endif
|
||||
add rsp, VARIABLE_OFFSET
|
||||
ret
|
||||
|
||||
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
|
||||
align 16
|
||||
_less_than_256:
|
||||
|
||||
; check if there is enough buffer to be able to fold 16B at a time
|
||||
cmp arg3, 32
|
||||
jl _less_than_32
|
||||
|
||||
; if there is, load the constants
|
||||
movdqa xmm10, [rk1] ; rk1 and rk2 in xmm10
|
||||
|
||||
movd xmm0, arg1_low32 ; get the initial crc value
|
||||
movdqu xmm7, [arg2] ; load the plaintext
|
||||
pxor xmm7, xmm0
|
||||
|
||||
; update the buffer pointer
|
||||
add arg2, 16
|
||||
|
||||
; update the counter. subtract 32 instead of 16 to save one instruction from the loop
|
||||
sub arg3, 32
|
||||
|
||||
jmp _16B_reduction_loop
|
||||
|
||||
|
||||
align 16
|
||||
_less_than_32:
|
||||
; mov initial crc to the return value. this is necessary for zero-length buffers.
|
||||
mov eax, arg1_low32
|
||||
test arg3, arg3
|
||||
je _cleanup
|
||||
|
||||
movd xmm0, arg1_low32 ; get the initial crc value
|
||||
|
||||
cmp arg3, 16
|
||||
je _exact_16_left
|
||||
jl _less_than_16_left
|
||||
|
||||
movdqu xmm7, [arg2] ; load the plaintext
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
add arg2, 16
|
||||
sub arg3, 16
|
||||
movdqa xmm10, [rk1] ; rk1 and rk2 in xmm10
|
||||
jmp _get_last_two_xmms
|
||||
|
||||
|
||||
align 16
|
||||
_less_than_16_left:
|
||||
; use stack space to load data less than 16 bytes, zero-out the 16B in memory first.
|
||||
|
||||
pxor xmm1, xmm1
|
||||
mov r11, rsp
|
||||
movdqa [r11], xmm1
|
||||
|
||||
cmp arg3, 4
|
||||
jl _only_less_than_4
|
||||
|
||||
; backup the counter value
|
||||
mov r9, arg3
|
||||
cmp arg3, 8
|
||||
jl _less_than_8_left
|
||||
|
||||
; load 8 Bytes
|
||||
mov rax, [arg2]
|
||||
mov [r11], rax
|
||||
add r11, 8
|
||||
sub arg3, 8
|
||||
add arg2, 8
|
||||
_less_than_8_left:
|
||||
|
||||
cmp arg3, 4
|
||||
jl _less_than_4_left
|
||||
|
||||
; load 4 Bytes
|
||||
mov eax, [arg2]
|
||||
mov [r11], eax
|
||||
add r11, 4
|
||||
sub arg3, 4
|
||||
add arg2, 4
|
||||
_less_than_4_left:
|
||||
|
||||
cmp arg3, 2
|
||||
jl _less_than_2_left
|
||||
|
||||
; load 2 Bytes
|
||||
mov ax, [arg2]
|
||||
mov [r11], ax
|
||||
add r11, 2
|
||||
sub arg3, 2
|
||||
add arg2, 2
|
||||
_less_than_2_left:
|
||||
cmp arg3, 1
|
||||
jl _zero_left
|
||||
|
||||
; load 1 Byte
|
||||
mov al, [arg2]
|
||||
mov [r11], al
|
||||
|
||||
_zero_left:
|
||||
movdqa xmm7, [rsp]
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
|
||||
lea rax,[pshufb_shf_table]
|
||||
movdqu xmm0, [rax + r9]
|
||||
pshufb xmm7,xmm0
|
||||
|
||||
|
||||
|
||||
jmp _128_done
|
||||
|
||||
align 16
|
||||
_exact_16_left:
|
||||
movdqu xmm7, [arg2]
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
|
||||
jmp _128_done
|
||||
|
||||
_only_less_than_4:
|
||||
cmp arg3, 3
|
||||
jl _only_less_than_3
|
||||
|
||||
; load 3 Bytes
|
||||
mov al, [arg2]
|
||||
mov [r11], al
|
||||
|
||||
mov al, [arg2+1]
|
||||
mov [r11+1], al
|
||||
|
||||
mov al, [arg2+2]
|
||||
mov [r11+2], al
|
||||
|
||||
movdqa xmm7, [rsp]
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
|
||||
pslldq xmm7, 5
|
||||
|
||||
jmp _barrett
|
||||
_only_less_than_3:
|
||||
cmp arg3, 2
|
||||
jl _only_less_than_2
|
||||
|
||||
; load 2 Bytes
|
||||
mov al, [arg2]
|
||||
mov [r11], al
|
||||
|
||||
mov al, [arg2+1]
|
||||
mov [r11+1], al
|
||||
|
||||
movdqa xmm7, [rsp]
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
|
||||
pslldq xmm7, 6
|
||||
|
||||
jmp _barrett
|
||||
_only_less_than_2:
|
||||
|
||||
; load 1 Byte
|
||||
mov al, [arg2]
|
||||
mov [r11], al
|
||||
|
||||
movdqa xmm7, [rsp]
|
||||
pxor xmm7, xmm0 ; xor the initial crc value
|
||||
|
||||
pslldq xmm7, 7
|
||||
|
||||
jmp _barrett
|
||||
|
||||
section .data
|
||||
|
||||
; precomputed constants
|
||||
align 16
|
||||
rk1 :
|
||||
DQ 0x00000000ccaa009e
|
||||
rk2 :
|
||||
DQ 0x00000001751997d0
|
||||
rk3 :
|
||||
DQ 0x000000014a7fe880
|
||||
rk4 :
|
||||
DQ 0x00000001e88ef372
|
||||
rk5 :
|
||||
DQ 0x00000000ccaa009e
|
||||
rk6 :
|
||||
DQ 0x0000000163cd6124
|
||||
rk7 :
|
||||
DQ 0x00000001f7011640
|
||||
rk8 :
|
||||
DQ 0x00000001db710640
|
||||
rk9 :
|
||||
DQ 0x00000001d7cfc6ac
|
||||
rk10 :
|
||||
DQ 0x00000001ea89367e
|
||||
rk11 :
|
||||
DQ 0x000000018cb44e58
|
||||
rk12 :
|
||||
DQ 0x00000000df068dc2
|
||||
rk13 :
|
||||
DQ 0x00000000ae0b5394
|
||||
rk14 :
|
||||
DQ 0x00000001c7569e54
|
||||
rk15 :
|
||||
DQ 0x00000001c6e41596
|
||||
rk16 :
|
||||
DQ 0x0000000154442bd4
|
||||
rk17 :
|
||||
DQ 0x0000000174359406
|
||||
rk18 :
|
||||
DQ 0x000000003db1ecdc
|
||||
rk19 :
|
||||
DQ 0x000000015a546366
|
||||
rk20 :
|
||||
DQ 0x00000000f1da05aa
|
||||
|
||||
|
||||
pshufb_shf_table:
|
||||
; use these values for shift constants for the pshufb instruction
|
||||
; different alignments result in values as shown:
|
||||
; dq 0x8887868584838281, 0x008f8e8d8c8b8a89 ; shl 15 (16-1) / shr1
|
||||
; dq 0x8988878685848382, 0x01008f8e8d8c8b8a ; shl 14 (16-3) / shr2
|
||||
; dq 0x8a89888786858483, 0x0201008f8e8d8c8b ; shl 13 (16-4) / shr3
|
||||
; dq 0x8b8a898887868584, 0x030201008f8e8d8c ; shl 12 (16-4) / shr4
|
||||
; dq 0x8c8b8a8988878685, 0x04030201008f8e8d ; shl 11 (16-5) / shr5
|
||||
; dq 0x8d8c8b8a89888786, 0x0504030201008f8e ; shl 10 (16-6) / shr6
|
||||
; dq 0x8e8d8c8b8a898887, 0x060504030201008f ; shl 9 (16-7) / shr7
|
||||
; dq 0x8f8e8d8c8b8a8988, 0x0706050403020100 ; shl 8 (16-8) / shr8
|
||||
; dq 0x008f8e8d8c8b8a89, 0x0807060504030201 ; shl 7 (16-9) / shr9
|
||||
; dq 0x01008f8e8d8c8b8a, 0x0908070605040302 ; shl 6 (16-10) / shr10
|
||||
; dq 0x0201008f8e8d8c8b, 0x0a09080706050403 ; shl 5 (16-11) / shr11
|
||||
; dq 0x030201008f8e8d8c, 0x0b0a090807060504 ; shl 4 (16-12) / shr12
|
||||
; dq 0x04030201008f8e8d, 0x0c0b0a0908070605 ; shl 3 (16-13) / shr13
|
||||
; dq 0x0504030201008f8e, 0x0d0c0b0a09080706 ; shl 2 (16-14) / shr14
|
||||
; dq 0x060504030201008f, 0x0e0d0c0b0a090807 ; shl 1 (16-15) / shr15
|
||||
dq 0x8786858483828100, 0x8f8e8d8c8b8a8988
|
||||
dq 0x0706050403020100, 0x000e0d0c0b0a0908
|
||||
|
||||
|
||||
mask:
|
||||
dq 0xFFFFFFFFFFFFFFFF, 0x0000000000000000
|
||||
mask2:
|
||||
dq 0xFFFFFFFF00000000, 0xFFFFFFFFFFFFFFFF
|
||||
mask3:
|
||||
dq 0x8080808080808080, 0x8080808080808080
|
||||
@ -1,139 +0,0 @@
|
||||
/**********************************************************************
|
||||
Copyright(c) 2011-2017 Intel Corporation All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions
|
||||
are met:
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in
|
||||
the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Intel Corporation nor the names of its
|
||||
contributors may be used to endorse or promote products derived
|
||||
from this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
**********************************************************************/
|
||||
|
||||
#include <stdint.h>
|
||||
#include "igzip_checksums.h"
|
||||
|
||||
uint32_t crc32_table_gzip_base[256] = {
|
||||
0x00000000, 0x77073096, 0xee0e612c, 0x990951ba,
|
||||
0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3,
|
||||
0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
|
||||
0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91,
|
||||
0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
|
||||
0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
|
||||
0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec,
|
||||
0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5,
|
||||
0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
|
||||
0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
|
||||
0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940,
|
||||
0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
|
||||
0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116,
|
||||
0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f,
|
||||
0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
|
||||
0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d,
|
||||
0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a,
|
||||
0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
|
||||
0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818,
|
||||
0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
|
||||
0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
|
||||
0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457,
|
||||
0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c,
|
||||
0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
|
||||
0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
|
||||
0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb,
|
||||
0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
|
||||
0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9,
|
||||
0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086,
|
||||
0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
|
||||
0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4,
|
||||
0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad,
|
||||
0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
|
||||
0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683,
|
||||
0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
|
||||
0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
|
||||
0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe,
|
||||
0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7,
|
||||
0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
|
||||
0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
|
||||
0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252,
|
||||
0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
|
||||
0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60,
|
||||
0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79,
|
||||
0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
|
||||
0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f,
|
||||
0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04,
|
||||
0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
|
||||
0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a,
|
||||
0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
|
||||
0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
|
||||
0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21,
|
||||
0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e,
|
||||
0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
|
||||
0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
|
||||
0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45,
|
||||
0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
|
||||
0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db,
|
||||
0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0,
|
||||
0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
|
||||
0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6,
|
||||
0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf,
|
||||
0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
|
||||
0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,
|
||||
};
|
||||
|
||||
uint32_t crc32_gzip_base(uint32_t crc, uint8_t * start, uint32_t length)
|
||||
{
|
||||
uint8_t *end = start + length;
|
||||
crc = ~crc;
|
||||
while (start < end)
|
||||
crc = (crc >> 8) ^ crc32_table_gzip_base[(crc & 0xff) ^ *start++];
|
||||
return ~crc;
|
||||
}
|
||||
|
||||
uint32_t adler32_base(uint32_t adler32, uint8_t * start, uint32_t length)
|
||||
{
|
||||
uint8_t *end, *next = start;
|
||||
uint64_t A, B;
|
||||
|
||||
A = adler32 & 0xffff;
|
||||
B = adler32 >> 16;
|
||||
|
||||
while (length > MAX_ADLER_BUF) {
|
||||
end = next + MAX_ADLER_BUF;
|
||||
for (; next < end; next++) {
|
||||
A += *next;
|
||||
B += A;
|
||||
}
|
||||
|
||||
A = A % ADLER_MOD;
|
||||
B = B % ADLER_MOD;
|
||||
length -= MAX_ADLER_BUF;
|
||||
}
|
||||
|
||||
end = next + length;
|
||||
for (; next < end; next++) {
|
||||
A += *next;
|
||||
B += A;
|
||||
}
|
||||
|
||||
A = A % ADLER_MOD;
|
||||
B = B % ADLER_MOD;
|
||||
|
||||
return B << 16 | A;
|
||||
}
|
||||
@ -44,6 +44,7 @@
|
||||
#include "huffman.h"
|
||||
#include "bitbuf2.h"
|
||||
#include "igzip_lib.h"
|
||||
#include "crc.h"
|
||||
#include "repeated_char_result.h"
|
||||
#include "huff_codes.h"
|
||||
#include "encode_df.h"
|
||||
@ -158,7 +159,7 @@ static void update_checksum(struct isal_zstream *stream, uint8_t * start_in, uin
|
||||
switch (stream->gzip_flag) {
|
||||
case IGZIP_GZIP:
|
||||
case IGZIP_GZIP_NO_HDR:
|
||||
state->crc = crc32_gzip(state->crc, start_in, length);
|
||||
state->crc = crc32_gzip_refl(state->crc, start_in, length);
|
||||
break;
|
||||
case IGZIP_ZLIB:
|
||||
case IGZIP_ZLIB_NO_HDR:
|
||||
@ -1085,7 +1086,7 @@ uint32_t isal_write_gzip_header(struct isal_zstream *stream, struct isal_gzip_he
|
||||
}
|
||||
|
||||
if (flags & HCRC_FLAG) {
|
||||
hcrc = crc32_gzip(0, out_buf_start, out_buf - out_buf_start);
|
||||
hcrc = crc32_gzip_refl(0, out_buf_start, out_buf - out_buf_start);
|
||||
*(uint16_t *) out_buf = hcrc;
|
||||
out_buf += GZIP_HCRC_LEN;
|
||||
}
|
||||
|
||||
@ -43,7 +43,6 @@ void isal_update_histogram_base(uint8_t * start_stream, int length,
|
||||
struct deflate_icf *encode_deflate_icf_base(struct deflate_icf *next_in,
|
||||
struct deflate_icf *end_in, struct BitBuf2 *bb,
|
||||
struct hufftables_icf *hufftables);
|
||||
uint32_t crc32_gzip_base(uint32_t init_crc, const unsigned char *buf, uint64_t len);
|
||||
uint32_t adler32_base(uint32_t init, const unsigned char *buf, uint64_t len);
|
||||
int decode_huffman_code_block_stateless_base(struct inflate_state *s);
|
||||
|
||||
@ -107,11 +106,6 @@ struct deflate_icf *encode_deflate_icf(struct deflate_icf *next_in,
|
||||
return encode_deflate_icf_base(next_in, end_in, bb, hufftables);
|
||||
}
|
||||
|
||||
uint32_t crc32_gzip(uint32_t init_crc, const unsigned char *buf, uint64_t len)
|
||||
{
|
||||
return crc32_gzip_base(init_crc, buf, len);
|
||||
}
|
||||
|
||||
uint32_t isal_adler32(uint32_t init, const unsigned char *buf, uint64_t len)
|
||||
{
|
||||
return adler32_base(init, buf, len);
|
||||
|
||||
@ -6,7 +6,6 @@
|
||||
#define MAX_ADLER_BUF (1 << 28)
|
||||
#define ADLER_MOD 65521
|
||||
|
||||
uint32_t crc32_gzip(uint32_t init_crc, const unsigned char *buf, uint64_t len);
|
||||
uint32_t isal_adler32(uint32_t init_crc, const unsigned char *buf, uint64_t len);
|
||||
uint32_t isal_adler32_bam1(uint32_t init_crc, const unsigned char *buf, uint64_t len);
|
||||
|
||||
|
||||
@ -29,6 +29,7 @@
|
||||
|
||||
#include <stdint.h>
|
||||
#include "igzip_lib.h"
|
||||
#include "crc.h"
|
||||
#include "huff_codes.h"
|
||||
#include "igzip_checksums.h"
|
||||
#include "igzip_wrapper.h"
|
||||
@ -175,7 +176,7 @@ static void update_checksum(struct inflate_state *state, uint8_t * start_in, uin
|
||||
case ISAL_GZIP:
|
||||
case ISAL_GZIP_NO_HDR:
|
||||
case ISAL_GZIP_NO_HDR_VER:
|
||||
state->crc = crc32_gzip(state->crc, start_in, length);
|
||||
state->crc = crc32_gzip_refl(state->crc, start_in, length);
|
||||
break;
|
||||
case ISAL_ZLIB:
|
||||
case ISAL_ZLIB_NO_HDR:
|
||||
@ -2037,7 +2038,7 @@ int isal_read_gzip_header(struct inflate_state *state, struct isal_gzip_header *
|
||||
}
|
||||
|
||||
if (flags & HCRC_FLAG) {
|
||||
hcrc = crc32_gzip(hcrc, start_in, state->next_in - start_in);
|
||||
hcrc = crc32_gzip_refl(hcrc, start_in, state->next_in - start_in);
|
||||
gz_hdr->hcrc = hcrc;
|
||||
|
||||
case ISAL_GZIP_HCRC:
|
||||
@ -2057,7 +2058,7 @@ int isal_read_gzip_header(struct inflate_state *state, struct isal_gzip_header *
|
||||
}
|
||||
|
||||
if (flags & HCRC_FLAG)
|
||||
gz_hdr->hcrc = crc32_gzip(hcrc, start_in, state->next_in - start_in);
|
||||
gz_hdr->hcrc = crc32_gzip_refl(hcrc, start_in, state->next_in - start_in);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
@ -67,9 +67,6 @@ extern set_long_icf_fg_06
|
||||
extern gen_icf_map_lh1_06
|
||||
%endif
|
||||
|
||||
extern crc32_gzip_base
|
||||
extern crc32_gzip_01
|
||||
|
||||
extern adler32_base
|
||||
extern adler32_avx2_4
|
||||
extern adler32_sse
|
||||
@ -132,9 +129,6 @@ mbin_interface gen_icf_map_lh1
|
||||
mbin_dispatch_init5 gen_icf_map_lh1, gen_icf_map_h1_base, gen_icf_map_h1_base, gen_icf_map_h1_base, gen_icf_map_lh1_04
|
||||
%endif
|
||||
|
||||
mbin_interface crc32_gzip
|
||||
mbin_dispatch_init_clmul crc32_gzip, crc32_gzip_base, crc32_gzip_01
|
||||
|
||||
mbin_interface isal_adler32
|
||||
mbin_dispatch_init5 isal_adler32, adler32_base, adler32_sse, adler32_sse, adler32_avx2_4
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user