diff options
| author | Rémi Denis-Courmont <remi@remlab.net> | 2022-09-27 23:04:24 +0300 |
|---|---|---|
| committer | Lynne <dev@lynne.ee> | 2022-09-28 12:46:11 +0300 |
| commit | 2746329ce25fb3d30bbf2aab187e90e21ae98064 (patch) | |
| tree | 19ce4f78e436340070781d9308deeae7bb67379d /libavcodec/riscv | |
| parent | fa983b56560ede2d9e3e3e21c80bbe0352b8794d (diff) | |
lavc/idctdsp: RISC-V V put_signed_pixels_clamped function
Diffstat (limited to 'libavcodec/riscv')
| -rw-r--r-- | libavcodec/riscv/idctdsp_init.c | 3 | ||||
| -rw-r--r-- | libavcodec/riscv/idctdsp_rvv.S | 21 |
2 files changed, 24 insertions, 0 deletions
diff --git a/libavcodec/riscv/idctdsp_init.c b/libavcodec/riscv/idctdsp_init.c index 58b8a6c97a..e6e616a555 100644 --- a/libavcodec/riscv/idctdsp_init.c +++ b/libavcodec/riscv/idctdsp_init.c @@ -28,6 +28,8 @@ void ff_put_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels, ptrdiff_t stride); +void ff_put_signed_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels, + ptrdiff_t stride); void ff_add_pixels_clamped_rvv(const int16_t *block, uint8_t *pixels, ptrdiff_t stride); @@ -39,6 +41,7 @@ av_cold void ff_idctdsp_init_riscv(IDCTDSPContext *c, AVCodecContext *avctx, if ((flags & AV_CPU_FLAG_RVV_I32) && ff_get_rv_vlenb() >= 16) { c->put_pixels_clamped = ff_put_pixels_clamped_rvv; + c->put_signed_pixels_clamped = ff_put_signed_pixels_clamped_rvv; c->add_pixels_clamped = ff_add_pixels_clamped_rvv; } #endif diff --git a/libavcodec/riscv/idctdsp_rvv.S b/libavcodec/riscv/idctdsp_rvv.S index 3b504f5866..f5e1165eee 100644 --- a/libavcodec/riscv/idctdsp_rvv.S +++ b/libavcodec/riscv/idctdsp_rvv.S @@ -43,6 +43,27 @@ func ff_put_pixels_clamped_rvv, zve32x ret endfunc +func ff_put_signed_pixels_clamped_rvv, zve32x + vsetivli zero, 8, e16, m1, ta, ma + vlseg8e16.v v24, (a0) + + li t1, 128 + vsetivli zero, 8, e8, mf2, ta, ma + vnclip.wi v16, v24, 0 + vnclip.wi v17, v25, 0 + vnclip.wi v18, v26, 0 + vnclip.wi v19, v27, 0 + vnclip.wi v20, v28, 0 + vnclip.wi v21, v29, 0 + vnclip.wi v22, v30, 0 + vnclip.wi v23, v31, 0 + vsetvli t0, zero, e8, m8, ta, ma + vadd.vx v16, v16, t1 + vsetivli zero, 8, e8, mf2, ta, ma + vssseg8e8.v v16, (a1), a2 + ret +endfunc + func ff_add_pixels_clamped_rvv, zve32x vsetivli zero, 8, e8, mf2, ta, ma vlseg8e16.v v24, (a0) |