isa-l/raid/riscv64/raid_xor_gen_rvv.S
sunyuechi 0de3661ec0 raid: R-V V xor_gen
banana_f3:
        new: xor_gen_warm: runtime =    3006459 usecs, bandwidth 10685 MB in 3.0065 sec = 3554.17 MB/s
        old: xor_gen_warm: runtime =    3060970 usecs, bandwidth 514 MB in 3.0610 sec = 168.21 MB/s

Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
2025-04-29 12:16:01 +00:00

83 lines
3.2 KiB
ArmAsm

/**********************************************************************
Copyright (c) 2025 Institute of Software Chinese Academy of Sciences (ISCAS).
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 ISCAS 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.
**********************************************************************/
#if HAVE_RVV
.option arch, +v
.global xor_gen_rvv
.type xor_gen_rvv, %function
xor_gen_rvv:
beqz a1, ret0 # len <= 0, return 0
addi t1, a0, -2 # vects - 3
blez t1, ret1 # vects < 3, return 1
slli t0, a0, 3 # t0 = vects * 8
add t0, a2, t0 # array + vects * 8
ld a4, 0(a2) # src[0]
ld a3, -8(t0) # dest = array[vects - 1]
mv t5, a3 # save dest
mv t6, a1 # save len
init_dest:
vsetvli t4, t6, e8, m8, ta, ma
vle8.v v0, (a4) # load src[0]
vse8.v v0, (a3) # dest
sub t6, t6, t4
add a4, a4, t4
add a3, a3, t4
bnez t6, init_dest
outer_j:
mv a3, t5 # restore dest
mv t6, a1 # restore length
ld a4, -16(t0)
inner_len:
vsetvli t4, t6, e8, m8, ta, ma
vle8.v v0, (a4) # src[j]
vle8.v v8, (a3) # dest
vxor.vv v8, v8, v0 # dest ^= src[j]
vse8.v v8, (a3)
sub t6, t6, t4
add a4, a4, t4
add a3, a3, t4
bnez t6, inner_len
addi t1, t1, -1
addi t0, t0, -8
bnez t1, outer_j
ret0:
li a0, 0
ret
ret1:
li a0, 1
ret
#endif