virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2025-08-15 14:13:16 +02:00
Code Issues Releases Activity

lavc/idctdsp: RISC-V V add_pixels_clamped function

Browse Source
This commit is contained in:
Rémi Denis-Courmont
2022-09-27 23:04:23 +03:00
committed by Lynne
parent b29ee63a1b
commit fa983b5656
2 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
libavcodec/riscv/idctdsp_init.c
View File

@@ -28,6 +28,8 @@
void ff_put_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels, void ff_put_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels,
ptrdiff_t stride); ptrdiff_t stride);
void ff_add_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels,
ptrdiff_t stride);
av_cold void ff_idctdsp_init_riscv(IDCTDSPContext *c, AVCodecContext *avctx, av_cold void ff_idctdsp_init_riscv(IDCTDSPContext *c, AVCodecContext *avctx,
unsigned high_bit_depth) unsigned high_bit_depth)
@@ -35,7 +37,9 @@ av_cold void ff_idctdsp_init_riscv(IDCTDSPContext *c, AVCodecContext *avctx,
#if HAVE_RVV #if HAVE_RVV
int flags = av_get_cpu_flags(); int flags = av_get_cpu_flags();
if ((flags & AV_CPU_FLAG_RVV_I32) && ff_get_rv_vlenb() >= 16) if ((flags & AV_CPU_FLAG_RVV_I32) && ff_get_rv_vlenb() >= 16) {
c->put_pixels_clamped = ff_put_pixels_clamped_rvv; c->put_pixels_clamped = ff_put_pixels_clamped_rvv;
c->add_pixels_clamped = ff_add_pixels_clamped_rvv;
}
#endif #endif
} }

16
libavcodec/riscv/idctdsp_rvv.S
View File

@@ -24,6 +24,7 @@
func ff_put_pixels_clamped_rvv, zve32x func ff_put_pixels_clamped_rvv, zve32x
vsetivli zero, 8, e16, m1, ta, ma vsetivli zero, 8, e16, m1, ta, ma
vlseg8e16.v v24, (a0) vlseg8e16.v v24, (a0)
1:
/* RVV only has signed-signed and unsigned-unsigned clipping. /* RVV only has signed-signed and unsigned-unsigned clipping.
* We need two steps for signed-to-unsigned clipping. */ * We need two steps for signed-to-unsigned clipping. */
vsetvli t0, zero, e16, m8, ta, ma vsetvli t0, zero, e16, m8, ta, ma
@@ -41,3 +42,18 @@ func ff_put_pixels_clamped_rvv, zve32x
vssseg8e8.v v16, (a1), a2 vssseg8e8.v v16, (a1), a2
ret ret
endfunc endfunc
func ff_add_pixels_clamped_rvv, zve32x
vsetivli zero, 8, e8, mf2, ta, ma
vlseg8e16.v v24, (a0)
vlsseg8e8.v v16, (a1), a2
vwaddu.wv v24, v24, v16
vwaddu.wv v25, v25, v17
vwaddu.wv v26, v26, v18
vwaddu.wv v27, v27, v19
vwaddu.wv v28, v28, v20
vwaddu.wv v29, v29, v21
vwaddu.wv v30, v30, v22
vwaddu.wv v31, v31, v23
j 1b
endfunc