This does not make much difference with the Device Under Test, but since
we can:
Before:
ps_add_squares_rvv_f32: 11973.7
After:
ps_add_squares_rvv_f32: 11958.2
---
libavcodec/riscv/aacpsdsp_rvv.S | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/libavcodec/riscv/aacpsdsp_rvv.S b/libavcodec/riscv/aacpsdsp_rvv.S
index b7ea314fc3..bd8f905334 100644
--- a/libavcodec/riscv/aacpsdsp_rvv.S
+++ b/libavcodec/riscv/aacpsdsp_rvv.S
@@ -23,15 +23,15 @@
func ff_ps_add_squares_rvv, zve32f
li t1, 32
1:
- vsetvli t0, a2, e32, m1, ta, ma
+ vsetvli t0, a2, e32, m4, ta, ma
vle64.v v8, (a1)
vnsrl.wx v24, v8, zero
vle32.v v16, (a0)
sub a2, a2, t0
- vnsrl.wx v25, v8, t1
+ vnsrl.wx v28, v8, t1
vfmacc.vv v16, v24, v24
sh3add a1, t0, a1
- vfmacc.vv v16, v25, v25
+ vfmacc.vv v16, v28, v28
vse32.v v16, (a0)
sh2add a0, t0, a0
bnez a2, 1b
--
2.40.1
_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".