diff options
| author | Greentime Hu <greentime.hu@sifive.com> | 2024-01-15 08:59:22 +0300 |
|---|---|---|
| committer | Palmer Dabbelt <palmer@rivosinc.com> | 2024-01-16 18:13:55 +0300 |
| commit | c5674d00cacdb1c47c72e19a552fbae401bc3532 (patch) | |
| tree | 0d4817448829b9d5eeb5e2458f9faa4efbf34616 /arch/riscv/lib | |
| parent | 956895b9d8f74df015636288a81872c07c4fded3 (diff) | |
| download | linux-c5674d00cacdb1c47c72e19a552fbae401bc3532.tar.xz | |
riscv: Add vector extension XOR implementation
This patch adds support for vector optimized XOR and it is tested in
qemu.
Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-4-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch/riscv/lib')
| -rw-r--r-- | arch/riscv/lib/Makefile | 1 | ||||
| -rw-r--r-- | arch/riscv/lib/xor.S | 81 |
2 files changed, 82 insertions, 0 deletions
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 26cb2502ecf8..494f9cd1a00c 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -11,3 +11,4 @@ lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +lib-$(CONFIG_RISCV_ISA_V) += xor.o diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S new file mode 100644 index 000000000000..b28f2430e52f --- /dev/null +++ b/arch/riscv/lib/xor.S @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 SiFive + */ +#include <linux/linkage.h> +#include <linux/export.h> +#include <asm/asm.h> + +SYM_FUNC_START(xor_regs_2_) + vsetvli a3, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a3 + vxor.vv v16, v0, v8 + add a2, a2, a3 + vse8.v v16, (a1) + add a1, a1, a3 + bnez a0, xor_regs_2_ + ret +SYM_FUNC_END(xor_regs_2_) +EXPORT_SYMBOL(xor_regs_2_) + +SYM_FUNC_START(xor_regs_3_) + vsetvli a4, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a4 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a4 + vxor.vv v16, v0, v16 + add a3, a3, a4 + vse8.v v16, (a1) + add a1, a1, a4 + bnez a0, xor_regs_3_ + ret +SYM_FUNC_END(xor_regs_3_) +EXPORT_SYMBOL(xor_regs_3_) + +SYM_FUNC_START(xor_regs_4_) + vsetvli a5, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a5 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a5 + vxor.vv v0, v0, v16 + vle8.v v24, (a4) + add a3, a3, a5 + vxor.vv v16, v0, v24 + add a4, a4, a5 + vse8.v v16, (a1) + add a1, a1, a5 + bnez a0, xor_regs_4_ + ret +SYM_FUNC_END(xor_regs_4_) +EXPORT_SYMBOL(xor_regs_4_) + +SYM_FUNC_START(xor_regs_5_) + vsetvli a6, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a6 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a6 + vxor.vv v0, v0, v16 + vle8.v v24, (a4) + add a3, a3, a6 + vxor.vv v0, v0, v24 + vle8.v v8, (a5) + add a4, a4, a6 + vxor.vv v16, v0, v8 + add a5, a5, a6 + vse8.v v16, (a1) + add a1, a1, a6 + bnez a0, xor_regs_5_ + ret +SYM_FUNC_END(xor_regs_5_) +EXPORT_SYMBOL(xor_regs_5_) |