[FFmpeg-devel] [PATCH 3/7] lavc/idctdsp: RISC-V V add_pixels_clamped function

[remi at remlab.net]

From: Rémi Denis-Courmont <remi at remlab.net>

---
 libavcodec/riscv/idctdsp_init.c |  6 +++++-
 libavcodec/riscv/idctdsp_rvv.S  | 16 ++++++++++++++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/libavcodec/riscv/idctdsp_init.c b/libavcodec/riscv/idctdsp_init.c
index 1a6add80da..58b8a6c97a 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_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,
                                    unsigned high_bit_depth)
@@ -35,7 +37,9 @@ av_cold void ff_idctdsp_init_riscv(IDCTDSPContext *c, AVCodecContext *avctx,
 #if HAVE_RVV
     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->add_pixels_clamped = ff_add_pixels_clamped_rvv;
+    }
 #endif
 }
diff --git a/libavcodec/riscv/idctdsp_rvv.S b/libavcodec/riscv/idctdsp_rvv.S
index a59edd0a83..e6cb53bd6f 100644
--- a/libavcodec/riscv/idctdsp_rvv.S
+++ b/libavcodec/riscv/idctdsp_rvv.S
@@ -24,6 +24,7 @@
 func ff_put_pixels_clamped_rvv, zve32x
         vsetivli    zero, 8, e16, m1, ta, ma
         vlseg8e16.v v24, (a0)
+1:
         /* RVV only has signed-signed and unsigned-unsigned clipping.
          * We need two steps for signed-to-unsigned clipping. */
         vsetvli     t0, zero, e16, m8, ta, ma
@@ -41,3 +42,18 @@ func ff_put_pixels_clamped_rvv, zve32x
         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)
+        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
-- 
2.37.2