[FFmpeg-cvslog] lavc/blockdsp: R-V V fill_block

[sunyuechi]

ffmpeg | branch: master | sunyuechi <sunyuechi at iscas.ac.cn> | Wed Mar  6 12:46:03 2024 +0800| [7d0673db7eb285ffe6da51fa2ab981b38a6f7542] | committer: Rémi Denis-Courmont

lavc/blockdsp: R-V V fill_block

C908:
blockdsp.fill_block_tab[0]_c: 549.7
blockdsp.fill_block_tab[0]_rvv_i64: 48.2
blockdsp.fill_block_tab[1]_c: 77.0
blockdsp.fill_block_tab[1]_rvv_i64: 19.7

Signed-off-by: Rémi Denis-Courmont <remi at remlab.net>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=7d0673db7eb285ffe6da51fa2ab981b38a6f7542
---

 libavcodec/riscv/blockdsp_init.c |  6 ++++++
 libavcodec/riscv/blockdsp_rvv.S  | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/libavcodec/riscv/blockdsp_init.c b/libavcodec/riscv/blockdsp_init.c
index 59b2f9d47b..42c8e87fa7 100644
--- a/libavcodec/riscv/blockdsp_init.c
+++ b/libavcodec/riscv/blockdsp_init.c
@@ -27,6 +27,10 @@
 
 void ff_clear_block_rvv(int16_t *block);
 void ff_clear_blocks_rvv(int16_t *block);
+void ff_fill_block16_rvv(uint8_t *block, uint8_t value, ptrdiff_t line_size,
+                           int h);
+void ff_fill_block8_rvv(uint8_t *block, uint8_t value, ptrdiff_t line_size,
+                           int h);
 
 av_cold void ff_blockdsp_init_riscv(BlockDSPContext *c)
 {
@@ -36,6 +40,8 @@ av_cold void ff_blockdsp_init_riscv(BlockDSPContext *c)
     if (flags & AV_CPU_FLAG_RVV_I64 && ff_get_rv_vlenb() >= 16) {
         c->clear_block = ff_clear_block_rvv;
         c->clear_blocks = ff_clear_blocks_rvv;
+        c->fill_block_tab[0] = ff_fill_block16_rvv;
+        c->fill_block_tab[1] = ff_fill_block8_rvv;
     }
 #endif
 }
diff --git a/libavcodec/riscv/blockdsp_rvv.S b/libavcodec/riscv/blockdsp_rvv.S
index 8bb00bb467..18ab17da00 100644
--- a/libavcodec/riscv/blockdsp_rvv.S
+++ b/libavcodec/riscv/blockdsp_rvv.S
@@ -40,3 +40,24 @@ func ff_clear_blocks_rvv, zve64x
 
         ret
 endfunc
+
+func ff_fill_block16_rvv, zve32x
+        vsetivli      t0, 16, e8, m1, ta, ma
+        vmv.v.x       v8, a1
+1:
+        addi          a3, a3, -1
+        vse8.v        v8, (a0)
+        add           a0, a0, a2
+        bnez          a3, 1b
+
+        ret
+endfunc
+
+func ff_fill_block8_rvv, zve64x
+        vsetvli       t0, zero, e8, m4, ta, ma
+        vmv.v.x       v8, a1
+        vsetvli       t0, a3, e64, m4, ta, ma
+        vsse64.v      v8, (a0), a2
+
+        ret
+endfunc