[FFmpeg-cvslog] lavc/vp8dsp: avoid one multiplication on RISC-V

[Rémi Denis-Courmont]

ffmpeg | branch: master | Rémi Denis-Courmont <remi at remlab.net> | Sat May 25 13:41:04 2024 +0300| [4e56455d3672beccd63f922cdc5052aa48f088bd] | committer: Rémi Denis-Courmont

lavc/vp8dsp: avoid one multiplication on RISC-V

Use shifts rather than multiply, and save one instruction.

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=4e56455d3672beccd63f922cdc5052aa48f088bd
---

 libavcodec/riscv/vp8dsp_init.c | 50 ++++++++++++++++++++++--------------------
 libavcodec/riscv/vp8dsp_rvv.S  |  7 +++---
 2 files changed, 29 insertions(+), 28 deletions(-)

diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c
index 92e3366290..a272058801 100644
--- a/libavcodec/riscv/vp8dsp_init.c
+++ b/libavcodec/riscv/vp8dsp_init.c
@@ -84,33 +84,35 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
         c->put_vp8_bilinear_pixels_tab[2][2][1] = ff_put_vp8_bilin4_hv_rvv;
         c->put_vp8_bilinear_pixels_tab[2][2][2] = ff_put_vp8_bilin4_hv_rvv;
 
-        c->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_rvv;
-        c->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_rvv;
-        c->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_rvv;
-        c->put_vp8_epel_pixels_tab[0][0][1] = ff_put_vp8_epel16_h4_rvv;
-        c->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_rvv;
-        c->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_rvv;
+        if (flags & AV_CPU_FLAG_RVB_ADDR) {
+            c->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_rvv;
+            c->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_rvv;
+            c->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_rvv;
+            c->put_vp8_epel_pixels_tab[0][0][1] = ff_put_vp8_epel16_h4_rvv;
+            c->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_rvv;
+            c->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_rvv;
 
-        c->put_vp8_epel_pixels_tab[0][2][0] = ff_put_vp8_epel16_v6_rvv;
-        c->put_vp8_epel_pixels_tab[1][2][0] = ff_put_vp8_epel8_v6_rvv;
-        c->put_vp8_epel_pixels_tab[2][2][0] = ff_put_vp8_epel4_v6_rvv;
-        c->put_vp8_epel_pixels_tab[0][1][0] = ff_put_vp8_epel16_v4_rvv;
-        c->put_vp8_epel_pixels_tab[1][1][0] = ff_put_vp8_epel8_v4_rvv;
-        c->put_vp8_epel_pixels_tab[2][1][0] = ff_put_vp8_epel4_v4_rvv;
+            c->put_vp8_epel_pixels_tab[0][2][0] = ff_put_vp8_epel16_v6_rvv;
+            c->put_vp8_epel_pixels_tab[1][2][0] = ff_put_vp8_epel8_v6_rvv;
+            c->put_vp8_epel_pixels_tab[2][2][0] = ff_put_vp8_epel4_v6_rvv;
+            c->put_vp8_epel_pixels_tab[0][1][0] = ff_put_vp8_epel16_v4_rvv;
+            c->put_vp8_epel_pixels_tab[1][1][0] = ff_put_vp8_epel8_v4_rvv;
+            c->put_vp8_epel_pixels_tab[2][1][0] = ff_put_vp8_epel4_v4_rvv;
 #if __riscv_xlen <= 64
-        c->put_vp8_epel_pixels_tab[0][2][2] = ff_put_vp8_epel16_h6v6_rvv;
-        c->put_vp8_epel_pixels_tab[1][2][2] = ff_put_vp8_epel8_h6v6_rvv;
-        c->put_vp8_epel_pixels_tab[2][2][2] = ff_put_vp8_epel4_h6v6_rvv;
-        c->put_vp8_epel_pixels_tab[0][2][1] = ff_put_vp8_epel16_h4v6_rvv;
-        c->put_vp8_epel_pixels_tab[1][2][1] = ff_put_vp8_epel8_h4v6_rvv;
-        c->put_vp8_epel_pixels_tab[2][2][1] = ff_put_vp8_epel4_h4v6_rvv;
-        c->put_vp8_epel_pixels_tab[0][1][1] = ff_put_vp8_epel16_h4v4_rvv;
-        c->put_vp8_epel_pixels_tab[1][1][1] = ff_put_vp8_epel8_h4v4_rvv;
-        c->put_vp8_epel_pixels_tab[2][1][1] = ff_put_vp8_epel4_h4v4_rvv;
-        c->put_vp8_epel_pixels_tab[0][1][2] = ff_put_vp8_epel16_h6v4_rvv;
-        c->put_vp8_epel_pixels_tab[1][1][2] = ff_put_vp8_epel8_h6v4_rvv;
-        c->put_vp8_epel_pixels_tab[2][1][2] = ff_put_vp8_epel4_h6v4_rvv;
+            c->put_vp8_epel_pixels_tab[0][2][2] = ff_put_vp8_epel16_h6v6_rvv;
+            c->put_vp8_epel_pixels_tab[1][2][2] = ff_put_vp8_epel8_h6v6_rvv;
+            c->put_vp8_epel_pixels_tab[2][2][2] = ff_put_vp8_epel4_h6v6_rvv;
+            c->put_vp8_epel_pixels_tab[0][2][1] = ff_put_vp8_epel16_h4v6_rvv;
+            c->put_vp8_epel_pixels_tab[1][2][1] = ff_put_vp8_epel8_h4v6_rvv;
+            c->put_vp8_epel_pixels_tab[2][2][1] = ff_put_vp8_epel4_h4v6_rvv;
+            c->put_vp8_epel_pixels_tab[0][1][1] = ff_put_vp8_epel16_h4v4_rvv;
+            c->put_vp8_epel_pixels_tab[1][1][1] = ff_put_vp8_epel8_h4v4_rvv;
+            c->put_vp8_epel_pixels_tab[2][1][1] = ff_put_vp8_epel4_h4v4_rvv;
+            c->put_vp8_epel_pixels_tab[0][1][2] = ff_put_vp8_epel16_h6v4_rvv;
+            c->put_vp8_epel_pixels_tab[1][1][2] = ff_put_vp8_epel8_h6v4_rvv;
+            c->put_vp8_epel_pixels_tab[2][1][2] = ff_put_vp8_epel4_h6v4_rvv;
 #endif
+        }
     }
 #endif
 #endif
diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
index ba0b131c74..dc48197cf1 100644
--- a/libavcodec/riscv/vp8dsp_rvv.S
+++ b/libavcodec/riscv/vp8dsp_rvv.S
@@ -182,15 +182,14 @@ const subpel_filters
 endconst
 
 .macro epel_filter size type regtype
-        lla             \regtype\()2, subpel_filters
 .ifc \type,v
         addi            \regtype\()0, a6, -1
 .else
         addi            \regtype\()0, a5, -1
 .endif
-        li              \regtype\()1, 6
-        mul             \regtype\()0, \regtype\()0, \regtype\()1
-        add             \regtype\()0, \regtype\()0, \regtype\()2
+        lla             \regtype\()2, subpel_filters
+        sh1add          \regtype\()0, \regtype\()0, \regtype\()0
+        sh1add          \regtype\()0, \regtype\()0, \regtype\()2
         .irp n,1,2,3,4
         lb              \regtype\n, \n(\regtype\()0)
         .endr