This saves one instruction and frees up A5, which will be repurposed in
later changes. Unfortunately, we need to add quite a lot of alternative
code for this.
---
libavcodec/riscv/vp8dsp_rvv.S | 24 ++++++++++++++++--------
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
index 545c2e9728..a4fcd158a5 100644
--- a/libavcodec/riscv/vp8dsp_rvv.S
+++ b/libavcodec/riscv/vp8dsp_rvv.S
@@ -202,23 +202,31 @@ func ff_put_vp8_epel\len\()_\type\()\size\()_rvv, zve32x
1:
addi a4, a4, -1
.ifc \type,v
- mv a5, a3
+ sub t6, a2, a3
+ add a7, a2, a3
.else
- li a5, 1
+ addi t6, a2, -1
+ addi a7, a2, 1
.endif
- sub t6, a2, a5
- add a7, a2, a5
-
vle8.v v24, (a2)
vle8.v v22, (t6)
vle8.v v26, (a7)
- add a7, a7, a5
+.ifc \type,v
+ add a7, a7, a3
+.else
+ addi a7, a7, 1
+.endif
vle8.v v28, (a7)
vwmulu.vx v16, v24, t2
vwmulu.vx v20, v26, t3
.ifc \size,6
- sub t6, t6, a5
- add a7, a7, a5
+.ifc \type,v
+ sub t6, t6, a3
+ add a7, a7, a3
+.else
+ addi t6, t6, -1
+ addi a7, a7, 1
+.endif
vle8.v v24, (t6)
vle8.v v26, (a7)
vwmaccu.vx v16, t0, v24
--
2.45.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
