diff --git a/libavcodec/flacdsp.c b/libavcodec/flacdsp.c index 42e231db53..71b4ac44aa 100644 --- a/libavcodec/flacdsp.c +++ b/libavcodec/flacdsp.c @@ -121,6 +121,8 @@ av_cold void ff_flacdsp_init(FLACDSPContext *c, enum AVSampleFormat fmt, int cha #if ARCH_ARM ff_flacdsp_init_arm(c, fmt, channels); +#elif ARCH_RISCV + ff_flacdsp_init_riscv(c, fmt, channels); #elif ARCH_X86 ff_flacdsp_init_x86(c, fmt, channels); #endif diff --git a/libavcodec/flacdsp.h b/libavcodec/flacdsp.h index 9f8ed38b66..15149c026e 100644 --- a/libavcodec/flacdsp.h +++ b/libavcodec/flacdsp.h @@ -38,6 +38,7 @@ typedef struct FLACDSPContext { void ff_flacdsp_init(FLACDSPContext *c, enum AVSampleFormat fmt, int channels); void ff_flacdsp_init_arm(FLACDSPContext *c, enum AVSampleFormat fmt, int channels); +void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt, int channels); void ff_flacdsp_init_x86(FLACDSPContext *c, enum AVSampleFormat fmt, int channels); #endif /* AVCODEC_FLACDSP_H */ diff --git a/libavcodec/riscv/Makefile b/libavcodec/riscv/Makefile index 57c1708dbb..d34dc77458 100644 --- a/libavcodec/riscv/Makefile +++ b/libavcodec/riscv/Makefile @@ -12,6 +12,8 @@ OBJS-$(CONFIG_BSWAPDSP) += riscv/bswapdsp_init.o \ RVV-OBJS-$(CONFIG_BSWAPDSP) += riscv/bswapdsp_rvv.o OBJS-$(CONFIG_EXR_DECODER) += riscv/exrdsp_init.o RVV-OBJS-$(CONFIG_EXR_DECODER) += riscv/exrdsp_rvv.o +OBJS-$(CONFIG_FLAC_DECODER) += riscv/flacdsp_init.o +RVV-OBJS-$(CONFIG_FLAC_DECODER) += riscv/flacdsp_rvv.o OBJS-$(CONFIG_FMTCONVERT) += riscv/fmtconvert_init.o RVV-OBJS-$(CONFIG_FMTCONVERT) += riscv/fmtconvert_rvv.o OBJS-$(CONFIG_G722DSP) += riscv/g722dsp_init.o diff --git a/libavcodec/riscv/flacdsp_init.c b/libavcodec/riscv/flacdsp_init.c new file mode 100644 index 0000000000..9734805979 --- /dev/null +++ b/libavcodec/riscv/flacdsp_init.c @@ -0,0 +1,55 @@ +/* + * Copyright © 2023 Rémi Denis-Courmont. + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "config.h" + +#include "libavutil/attributes.h" +#include "libavutil/cpu.h" +#include "libavcodec/flacdsp.h" + +void ff_flac_decorrelate_ls_16_rvv(uint8_t **out, int32_t **in, + int channels, int len, int shift); +void ff_flac_decorrelate_rs_16_rvv(uint8_t **out, int32_t **in, + int channels, int len, int shift); +void ff_flac_decorrelate_ls_32_rvv(uint8_t **out, int32_t **in, + int channels, int len, int shift); +void ff_flac_decorrelate_rs_32_rvv(uint8_t **out, int32_t **in, + int channels, int len, int shift); + +av_cold void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt, + int channels) +{ +#if HAVE_RVV && (__riscv_xlen >= 64) + int flags = av_get_cpu_flags(); + + if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) { + switch (fmt) { + case AV_SAMPLE_FMT_S16: + c->decorrelate[1] = ff_flac_decorrelate_ls_16_rvv; + c->decorrelate[2] = ff_flac_decorrelate_rs_16_rvv; + break; + case AV_SAMPLE_FMT_S32: + c->decorrelate[1] = ff_flac_decorrelate_ls_32_rvv; + c->decorrelate[2] = ff_flac_decorrelate_rs_32_rvv; + break; + } + } +#endif +} diff --git a/libavcodec/riscv/flacdsp_rvv.S b/libavcodec/riscv/flacdsp_rvv.S new file mode 100644 index 0000000000..c70ad8fcb0 --- /dev/null +++ b/libavcodec/riscv/flacdsp_rvv.S @@ -0,0 +1,113 @@ +/* + * Copyright © 2023 Rémi Denis-Courmont. + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/riscv/asm.S" + +#if (__riscv_xlen == 64) +func ff_flac_decorrelate_ls_16_rvv, zve32x + ld a0, (a0) + ld a2, 8(a1) + ld a1, (a1) +1: + vsetvli t0, a3, e32, m8, ta, ma + vle32.v v0, (a1) + sub a3, a3, t0 + vle32.v v8, (a2) + sh2add a1, t0, a1 + vsll.vx v0, v0, a4 + sh2add a2, t0, a2 + vsll.vx v8, v8, a4 + vsub.vv v8, v0, v8 + vsetvli zero, zero, e16, m4, ta, ma + vncvt.x.x.w v16, v0 + vncvt.x.x.w v20, v8 + vsseg2e16.v v16, (a0) + sh2add a0, t0, a0 + bnez a3, 1b + + ret +endfunc + +func ff_flac_decorrelate_rs_16_rvv, zve32x + ld a0, (a0) + ld a2, 8(a1) + ld a1, (a1) +1: + vsetvli t0, a3, e32, m8, ta, ma + vle32.v v0, (a1) + sub a3, a3, t0 + vle32.v v8, (a2) + sh2add a1, t0, a1 + vsll.vx v0, v0, a4 + sh2add a2, t0, a2 + vsll.vx v8, v8, a4 + vadd.vv v0, v0, v8 + vsetvli zero, zero, e16, m4, ta, ma + vncvt.x.x.w v16, v0 + vncvt.x.x.w v20, v8 + vsseg2e16.v v16, (a0) + sh2add a0, t0, a0 + bnez a3, 1b + + ret +endfunc + +func ff_flac_decorrelate_ls_32_rvv, zve32x + ld a0, (a0) + ld a2, 8(a1) + ld a1, (a1) +1: + vsetvli t0, a3, e32, m4, ta, ma + vle32.v v0, (a1) + sub a3, a3, t0 + vle32.v v4, (a2) + sh2add a1, t0, a1 + vsll.vx v0, v0, a4 + sh2add a2, t0, a2 + vsll.vx v4, v4, a4 + vsub.vv v4, v0, v4 + vsseg2e32.v v0, (a0) + sh3add a0, t0, a0 + bnez a3, 1b + + ret +endfunc + +func ff_flac_decorrelate_rs_32_rvv, zve32x + ld a0, (a0) + ld a2, 8(a1) + ld a1, (a1) +1: + vsetvli t0, a3, e32, m4, ta, ma + vle32.v v0, (a1) + sub a3, a3, t0 + vle32.v v4, (a2) + sh2add a1, t0, a1 + vsll.vx v0, v0, a4 + sh2add a2, t0, a2 + vsll.vx v4, v4, a4 + vadd.vv v0, v0, v4 + vsseg2e32.v v0, (a0) + sh3add a0, t0, a0 + bnez a3, 1b + + ret +endfunc +#endif