mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-09-04 20:19:47 +08:00
e7c9d66e31
Detect if vector misaligned accesses are faster or slower than equivalent vector byte accesses. This is useful for usermode to know whether vector byte accesses or vector misaligned accesses have a better bandwidth for operations like memcpy. Signed-off-by: Jesse Taube <jesse@rivosinc.com> Reviewed-by: Charlie Jenkins <charlie@rivosinc.com> Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-5-5b33500160f8@rivosinc.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
59 lines
1.4 KiB
ArmAsm
59 lines
1.4 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright (C) 2024 Rivos Inc. */
|
|
|
|
#include <linux/args.h>
|
|
#include <linux/linkage.h>
|
|
#include <asm/asm.h>
|
|
|
|
.text
|
|
|
|
#define WORD_EEW 32
|
|
|
|
#define WORD_SEW CONCATENATE(e, WORD_EEW)
|
|
#define VEC_L CONCATENATE(vle, WORD_EEW).v
|
|
#define VEC_S CONCATENATE(vle, WORD_EEW).v
|
|
|
|
/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */
|
|
/* Performs a memcpy without aligning buffers, using word loads and stores. */
|
|
/* Note: The size is truncated to a multiple of WORD_EEW */
|
|
SYM_FUNC_START(__riscv_copy_vec_words_unaligned)
|
|
andi a4, a2, ~(WORD_EEW-1)
|
|
beqz a4, 2f
|
|
add a3, a1, a4
|
|
.option push
|
|
.option arch, +zve32x
|
|
1:
|
|
vsetivli t0, 8, WORD_SEW, m8, ta, ma
|
|
VEC_L v0, (a1)
|
|
VEC_S v0, (a0)
|
|
addi a0, a0, WORD_EEW
|
|
addi a1, a1, WORD_EEW
|
|
bltu a1, a3, 1b
|
|
|
|
2:
|
|
.option pop
|
|
ret
|
|
SYM_FUNC_END(__riscv_copy_vec_words_unaligned)
|
|
|
|
/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */
|
|
/* Performs a memcpy without aligning buffers, using only byte accesses. */
|
|
/* Note: The size is truncated to a multiple of 8 */
|
|
SYM_FUNC_START(__riscv_copy_vec_bytes_unaligned)
|
|
andi a4, a2, ~(8-1)
|
|
beqz a4, 2f
|
|
add a3, a1, a4
|
|
.option push
|
|
.option arch, +zve32x
|
|
1:
|
|
vsetivli t0, 8, e8, m8, ta, ma
|
|
vle8.v v0, (a1)
|
|
vse8.v v0, (a0)
|
|
addi a0, a0, 8
|
|
addi a1, a1, 8
|
|
bltu a1, a3, 1b
|
|
|
|
2:
|
|
.option pop
|
|
ret
|
|
SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned)
|