lavc/vp7dsp: add R-V V vp7_idct_dc_add4uv

This is almost the same story as vp7_idct_add4y. We just have to use
strided loads of 2 64-bit elements to account for the different data
layout in memory.

T-Head C908:
vp7_idct_dc_add4uv_c:       7.5
vp7_idct_dc_add4uv_rvv_i64: 2.0
vp8_idct_dc_add4uv_c:       6.2
vp8_idct_dc_add4uv_rvv_i32: 2.2 (before)
vp8_idct_dc_add4uv_rvv_i64: 2.0

SpacemiT X60:
vp7_idct_dc_add4uv_c:       6.7
vp7_idct_dc_add4uv_rvv_i64: 2.2
vp8_idct_dc_add4uv_c:       5.7
vp8_idct_dc_add4uv_rvv_i32: 2.5 (before)
vp8_idct_dc_add4uv_rvv_i64: 2.0

libavcodec/riscv/vp7dsp_init.c

@@ -29,6 +29,7 @@ void ff_vp7_luma_dc_wht_rvv(int16_t block[4][4][16], int16_t dc[16]);
 void ff_vp7_idct_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
 void ff_vp78_idct_dc_add_rvv(uint8_t *, int16_t block[16], ptrdiff_t, int dc);
 void ff_vp7_idct_dc_add4y_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t);
+void ff_vp7_idct_dc_add4uv_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t);
 
 static void ff_vp7_idct_dc_add_rvv(uint8_t *dst, int16_t block[16],
                                    ptrdiff_t stride)
@@ -51,6 +52,8 @@ av_cold void ff_vp7dsp_init_riscv(VP8DSPContext *c)
 #endif
         c->vp8_idct_dc_add = ff_vp7_idct_dc_add_rvv;
         c->vp8_idct_dc_add4y  = ff_vp7_idct_dc_add4y_rvv;
+        if (flags & AV_CPU_FLAG_RVV_I64)
+            c->vp8_idct_dc_add4uv = ff_vp7_idct_dc_add4uv_rvv;
     }
 #endif
 }

libavcodec/riscv/vp7dsp_rvv.S

@@ -128,7 +128,8 @@ func ff_vp7_idct_add_rvv, zve32x
 endfunc
 #endif
 
-func ff_vp7_idct_dc_add4y_rvv, zve32x
+.irp type, y, uv
+func ff_vp7_idct_dc_add4\type\()_rvv, zve32x
         li       t0, 32
         vsetivli zero, 4, e16, mf2, ta, ma
         li       t1, 23170
@@ -141,5 +142,6 @@ func ff_vp7_idct_dc_add4y_rvv, zve32x
         vadd.vx  v0, v0, t2
         vsetvli  zero, zero, e16, mf2, ta, ma
         vnsra.wi v8, v0, 18   # 4x DC
-        tail     ff_vp78_idct_dc_add4y_rvv
+        tail     ff_vp78_idct_dc_add4\type\()_rvv
 endfunc
+.endr

libavcodec/riscv/vp8dsp_init.c

@@ -131,9 +131,8 @@ av_cold void ff_vp8dsp_init_riscv(VP8DSPContext *c)
 #endif
         c->vp8_idct_dc_add = ff_vp8_idct_dc_add_rvv;
         c->vp8_idct_dc_add4y = ff_vp8_idct_dc_add4y_rvv;
-        if (flags & AV_CPU_FLAG_RVB_ADDR) {
+        if (flags & AV_CPU_FLAG_RVV_I64)
             c->vp8_idct_dc_add4uv = ff_vp8_idct_dc_add4uv_rvv;
-        }
     }
 #endif
 }

libavcodec/riscv/vp8dsp_rvv.S

@@ -157,6 +157,43 @@ func ff_vp78_idct_dc_add4y_rvv, zve32x
         ret
 endfunc
 
+func ff_vp8_idct_dc_add4uv_rvv, zve32x
+        li       t0, 32
+        vsetivli zero, 4, e16, mf2, ta, ma
+        li       t1, 4 - (128 << 3)
+        vlse16.v v8, (a1), t0
+        vadd.vx  v8, v8, t1
+        vsra.vi  v8, v8, 3
+        # fall through
+endfunc
+
+        .variant_cc ff_vp78_idct_dc_add4uv_rvv
+func ff_vp78_idct_dc_add4uv_rvv, zve64x
+        vsetivli    zero, 16, e16, m2, ta, ma
+        vid.v       v4
+        li          a4, 4
+        vsrl.vi     v4, v4, 2
+        li          t1, 128
+        vrgather.vv v0, v8, v4 # replicate each DC four times
+        slli        t2, a2, 2
+        vsetivli    zero, 2, e64, m1, ta, ma
+1:
+        vlse64.v    v8, (a0), t2
+        addi        a4, a4, -1
+        vsetivli    zero, 16, e8, m1, ta, ma
+        vwaddu.wv   v16, v0, v8
+        sh          zero, (a1)
+        vnclip.wi   v8, v16, 0
+        addi        a1, a1, 32
+        vxor.vx     v8, v8, t1
+        vsetivli    zero, 2, e64, m1, ta, ma
+        vsse64.v    v8, (a0), t2
+        add         a0, a0, a2
+        bnez        a4, 1b
+
+        ret
+endfunc
+
 .macro vp8_idct_dc_add
         vlse32.v      v0, (a0), a2
         lh            a5, 0(a1)
@@ -179,19 +216,6 @@ endfunc
         addi          a1, a1, 32
 .endm
 
-func ff_vp8_idct_dc_add4uv_rvv, zve32x
-        vsetivli      zero, 4, e8, mf4, ta, ma
-        vp8_idct_dc_addy
-        vp8_idct_dc_add
-        addi          a0, a0, -4
-        sh2add        a0, a2, a0
-        addi          a1, a1, 32
-        vp8_idct_dc_addy
-        vp8_idct_dc_add
-
-        ret
-endfunc
-
 .macro bilin_load dst type mn
 .ifc \type,v
         add             t5, a2, a3