[FFmpeg-cvslog] lavc/takdsp: R-V V decorrelate_sf

[Rémi Denis-Courmont]

ffmpeg | branch: master | Rémi Denis-Courmont <remi at remlab.net> | Fri Dec 22 18:12:57 2023 +0200| [278b4b60d636ac0673524471a8ae35108d31f3d7] | committer: Rémi Denis-Courmont

lavc/takdsp: R-V V decorrelate_sf

decorrelate_sf_c:      259.2
decorrelate_sf_rvv_i32: 45.5

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=278b4b60d636ac0673524471a8ae35108d31f3d7
---

 libavcodec/riscv/takdsp_init.c |  2 ++
 libavcodec/riscv/takdsp_rvv.S  | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/libavcodec/riscv/takdsp_init.c b/libavcodec/riscv/takdsp_init.c
index 4312c8d99d..58be83860b 100644
--- a/libavcodec/riscv/takdsp_init.c
+++ b/libavcodec/riscv/takdsp_init.c
@@ -28,6 +28,7 @@
 void ff_decorrelate_ls_rvv(const int32_t *p1, int32_t *p2, int length);
 void ff_decorrelate_sr_rvv(int32_t *p1, const int32_t *p2, int length);
 void ff_decorrelate_sm_rvv(int32_t *p1, int32_t *p2, int length);
+void ff_decorrelate_sf_rvv(int32_t *p1, const int32_t *p2, int len, int, int);
 
 av_cold void ff_takdsp_init_riscv(TAKDSPContext *dsp)
 {
@@ -38,6 +39,7 @@ av_cold void ff_takdsp_init_riscv(TAKDSPContext *dsp)
         dsp->decorrelate_ls = ff_decorrelate_ls_rvv;
         dsp->decorrelate_sr = ff_decorrelate_sr_rvv;
         dsp->decorrelate_sm = ff_decorrelate_sm_rvv;
+        dsp->decorrelate_sf = ff_decorrelate_sf_rvv;
     }
 #endif
 }
diff --git a/libavcodec/riscv/takdsp_rvv.S b/libavcodec/riscv/takdsp_rvv.S
index b593d9139a..fa942a3be6 100644
--- a/libavcodec/riscv/takdsp_rvv.S
+++ b/libavcodec/riscv/takdsp_rvv.S
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2023 Institue of Software Chinese Academy of Sciences (ISCAS).
+ * Copyright (c) 2023 Rémi Denis-Courmont
  *
  * This file is part of FFmpeg.
  *
@@ -65,3 +66,23 @@ func ff_decorrelate_sm_rvv, zve32x
 
         ret
 endfunc
+
+func ff_decorrelate_sf_rvv, zve32x
+        csrwi    vxrm, 0
+1:
+        vsetvli  t0, a2, e32, m8, ta, ma
+        vle32.v  v8, (a1)
+        sub      a2, a2, t0
+        vsra.vx  v8, v8, a3
+        sh2add   a1, t0, a1
+        vle32.v  v0, (a0)
+        vmul.vx  v8, v8, a4
+        vssra.vi v8, v8, 8
+        vsll.vx  v8, v8, a3
+        vsub.vv  v0, v8, v0
+        vse32.v  v0, (a0)
+        sh2add   a0, t0, a0
+        bnez     a2, 1b
+
+        ret
+endfunc