isa-l/igzip/aarch64/encode_df.S
Zhiyuan Zhu 683364c47b igzip: implement encode_deflate_icf with assembly
Change-Id: I90b12da2d2a96bfdb47d29ab329648247a756585
Signed-off-by: Zhiyuan Zhu <zhiyuan.zhu@arm.com>
2019-11-29 14:45:45 -07:00

160 lines
5.4 KiB
ArmAsm

/**********************************************************************
Copyright(c) 2019 Arm 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 Arm 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.
**********************************************************************/
.arch armv8-a+crc
.text
.align 2
#include "lz0a_const_aarch64.h"
#include "data_struct_aarch64.h"
#include "huffman_aarch64.h"
#include "bitbuf2_aarch64.h"
#include "stdmac_aarch64.h"
/*
declare Macros
*/
.macro declare_generic_reg name:req,reg:req,default:req
\name .req \default\reg
w_\name .req w\reg
x_\name .req x\reg
.endm
.global encode_deflate_icf_aarch64
.type encode_deflate_icf_aarch64, %function
/*
struct deflate_icf *encode_deflate_icf_base(struct deflate_icf *next_in,
struct deflate_icf *end_in, struct BitBuf2 *bb,
struct hufftables_icf *hufftables)
*/
// parameters
declare_generic_reg next_in, 0,x
declare_generic_reg end_in, 1,x
declare_generic_reg bb, 2,x
declare_generic_reg hufftables, 3,x
// local variable
declare_generic_reg bb_out_end, 4,x
declare_generic_reg bb_bit_count, 5,w
declare_generic_reg dist_extra, 6,x
declare_generic_reg dist_lit_table, 7,x
declare_generic_reg code_and_extra, 8,x
declare_generic_reg bb_out_buf, 9,x
declare_generic_reg bb_bits, 10,x
declare_generic_reg d_length, 11,x
declare_generic_reg l_length, 12,x
declare_generic_reg d_extra_bit_count, 13,x
declare_generic_reg code_sum, 4,x
declare_generic_reg count_sum, 7,x
declare_generic_reg tmp0, 14,x
declare_generic_reg tmp1, 15,x
// bit buffer offset
.equ offset_m_bits, 0
.equ offset_m_bit_count, 8
.equ offset_m_out_buf, 16
.equ offset_m_out_end, 24
encode_deflate_icf_aarch64:
cmp next_in, end_in
bcs .done
ldp bb_out_buf, bb_out_end, [bb, offset_m_out_buf]
cmp bb_out_end, bb_out_buf
bcc .done
ldr bb_bit_count, [bb, offset_m_bit_count]
ldr bb_bits, [bb, offset_m_bits]
b .loop_start
.align 3
.loop:
ldr bb_out_end, [bb, offset_m_out_end]
cmp bb_out_end, bb_out_buf
bcc .done
.loop_start:
ldrh w_code_and_extra, [next_in]
add next_in, next_in, 4
ldr w_dist_lit_table, [next_in, -4]
and code_and_extra, code_and_extra, 1023
ldrh w_dist_extra, [next_in, -2]
add code_and_extra, code_and_extra, 31
ubfx x_dist_lit_table, x_dist_lit_table, 10, 9
add x_tmp0, hufftables, code_and_extra, lsl 2
ubfx x_dist_extra, x_dist_extra, 3, 13
lsl x_dist_lit_table, x_dist_lit_table, 2
ldr w_code_and_extra, [hufftables, code_and_extra, lsl 2]
add x_d_extra_bit_count, hufftables, x_dist_lit_table
ldrb w_l_length, [x_tmp0, 3]
and code_and_extra, code_and_extra, 0xffffff
ldrh w_code_sum, [hufftables, x_dist_lit_table]
ldrb w_d_length, [x_d_extra_bit_count, 3]
add w_l_length, w_l_length, bb_bit_count
ldrb w_d_extra_bit_count, [x_d_extra_bit_count, 2]
lsl x_tmp0, code_and_extra, x_bb_bit_count
add bb_bit_count, w_d_length, w_l_length
lsl x_code_sum, x_code_sum, x_l_length
orr x_code_sum, x_code_sum, x_tmp0
add w_count_sum, w_d_extra_bit_count, bb_bit_count
lsl x_bb_bit_count, x_dist_extra, x_bb_bit_count
orr x_bb_bit_count, x_bb_bit_count, bb_bits
orr x_tmp0, x_code_sum, x_bb_bit_count // me->m_bits => x_tmp0
str x_tmp0, [bb, offset_m_bits] // me->m_bits => x_tmp0
str w_count_sum, [bb, offset_m_bit_count]
str x_tmp0, [bb_out_buf] // me->m_bits => x_tmp0
ldr bb_bit_count, [bb, offset_m_bit_count]
ldr bb_bits, [bb, offset_m_bits]
and w_tmp0, bb_bit_count, -8 // bits => w_tmp0
ldr bb_out_buf, [bb, offset_m_out_buf]
lsr w_tmp1, bb_bit_count, 3 // bits/8 => w_tmp1
lsr bb_bits, bb_bits, x_tmp0 // bits => x_tmp0
sub bb_bit_count, bb_bit_count, w_tmp0 // bits => w_tmp0
add bb_out_buf, bb_out_buf, x_tmp1 // bits/8 => x_tmp1
str bb_bits, [bb,offset_m_bits]
str bb_bit_count, [bb, offset_m_bit_count]
str bb_out_buf, [bb, offset_m_out_buf]
cmp end_in, next_in
bhi .loop
.done:
ret
.size encode_deflate_icf_aarch64, .-encode_deflate_icf_aarch64