lavc/h264dsp: R-V V high-depth h264_idct_add

T-Head C908 (cycles):
h264_idct4_add_9bpp_c:        248.2
h264_idct4_add_9bpp_rvv_i32:  128.7
h264_idct4_add_10bpp_c:       256.7
h264_idct4_add_10bpp_rvv_i32: 128.7
h264_idct4_add_12bpp_c:       252.5
h264_idct4_add_12bpp_rvv_i32: 129.7
h264_idct4_add_14bpp_c:       258.0
h264_idct4_add_14bpp_rvv_i32: 129.7

libavcodec/riscv/h264dsp_init.c

@@ -52,6 +52,11 @@ void ff_h264_idct8_add4_8_rvv(uint8_t *dst, const int *blockoffset,
                               int16_t *block, int stride,
                               const uint8_t nnzc[5 * 8]);
 
+void ff_h264_idct_add_9_rvv(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct_add_10_rvv(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct_add_12_rvv(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct_add_14_rvv(uint8_t *dst, int16_t *block, int stride);
+
 extern int ff_startcode_find_candidate_rvb(const uint8_t *, int);
 extern int ff_startcode_find_candidate_rvv(const uint8_t *, int);
 
@@ -65,7 +70,9 @@ av_cold void ff_h264dsp_init_riscv(H264DSPContext *dsp, const int bit_depth,
         dsp->startcode_find_candidate = ff_startcode_find_candidate_rvb;
 # if HAVE_RVV
     if (flags & AV_CPU_FLAG_RVV_I32) {
-        if (bit_depth == 8 && ff_rv_vlen_least(128)) {
+        const bool zvl128b = ff_rv_vlen_least(128);
+
+        if (bit_depth == 8 && zvl128b) {
             for (int i = 0; i < 4; i++) {
                 dsp->weight_h264_pixels_tab[i] =
                     ff_h264_weight_funcs_8_rvv[i].weight;
@@ -86,6 +93,16 @@ av_cold void ff_h264dsp_init_riscv(H264DSPContext *dsp, const int bit_depth,
             dsp->h264_idct8_add4 = ff_h264_idct8_add4_8_rvv;
 #  endif
         }
+
+        if (bit_depth == 9 && zvl128b)
+            dsp->h264_idct_add = ff_h264_idct_add_9_rvv;
+        if (bit_depth == 10 && zvl128b)
+            dsp->h264_idct_add = ff_h264_idct_add_10_rvv;
+        if (bit_depth == 12 && zvl128b)
+            dsp->h264_idct_add = ff_h264_idct_add_12_rvv;
+        if (bit_depth == 14 && zvl128b)
+            dsp->h264_idct_add = ff_h264_idct_add_14_rvv;
+
         dsp->startcode_find_candidate = ff_startcode_find_candidate_rvv;
     }
 # endif

libavcodec/riscv/h264idct_rvv.S

@@ -105,6 +105,69 @@ func ff_h264_idct_add_8_rvv, zve32x
         ret
 endfunc
 
+func ff_h264_idct_add_16_rvv, zve32x
+        csrwi       vxrm, 0
+        vsetivli    zero, 4, e32, m1, ta, ma
+        addi        t1, a1, 1 * 4 * 4
+        vle32.v     v0, (a1)
+        addi        t2, a1, 2 * 4 * 4
+        vle32.v     v1, (t1)
+        addi        t3, a1, 3 * 4 * 4
+        vle32.v     v2, (t2)
+        vle32.v     v3, (t3)
+        jal         t0, ff_h264_idct4_rvv
+        vse32.v     v0, (a1)
+        vse32.v     v1, (t1)
+        vse32.v     v2, (t2)
+        vse32.v     v3, (t3)
+        vlseg4e32.v v0, (a1)
+        .equ    offset, 0
+        .rept   512 / __riscv_xlen
+        sx      zero, offset(a1)
+        .equ    offset, offset + (__riscv_xlen / 8)
+        .endr
+        jal         t0, ff_h264_idct4_rvv
+        add         t1, a0, a2
+        vle16.v     v4, (a0)
+        add         t2, t1, a2
+        vle16.v     v5, (t1)
+        add         t3, t2, a2
+        vle16.v     v6, (t2)
+        vle16.v     v7, (t3)
+        .irp    n,0,1,2,3
+        vssra.vi    v\n, v\n, 6
+        .endr
+        vsetvli     zero, zero, e16, mf2, ta, ma
+        vwaddu.wv   v0, v0, v4
+        vwaddu.wv   v1, v1, v5
+        vwaddu.wv   v2, v2, v6
+        vwaddu.wv   v3, v3, v7
+        vsetvli     zero, zero, e32, m1, ta, ma
+        .irp    n,0,1,2,3
+        vmax.vx     v\n, v\n, zero
+        .endr
+        .irp    n,0,1,2,3
+        vmin.vx     v\n, v\n, a3
+        .endr
+        vsetvli     zero, zero, e16, mf2, ta, ma
+        vncvt.x.x.w v4, v0
+        vncvt.x.x.w v5, v1
+        vncvt.x.x.w v6, v2
+        vncvt.x.x.w v7, v3
+        vse16.v     v4, (a0)
+        vse16.v     v5, (t1)
+        vse16.v     v6, (t2)
+        vse16.v     v7, (t3)
+        ret
+endfunc
+
+.irp    depth, 9, 10, 12, 14
+func ff_h264_idct_add_\depth\()_rvv, zve32x
+        li      a3, (1 << \depth) - 1
+        j       ff_h264_idct_add_16_rvv
+endfunc
+.endr
+
         .variant_cc ff_h264_idct8_rvv
 func ff_h264_idct8_rvv, zve32x
         vsra.vi v9, v7, 1