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

[sunyuechi]

ffmpeg | branch: master | sunyuechi <sunyuechi at iscas.ac.cn> | Mon Dec 18 22:53:39 2023 +0800| [3d39b8d4e7ca43baafa3b4cd5784dd64197dd232] | committer: Rémi Denis-Courmont

lavc/takdsp: R-V V decorrelate_sm

C908:
decorrelate_sm_c: 130.0
decorrelate_sm_rvv_i32: 43.2

Signed-off-by: Rémi Denis-Courmont <remi at remlab.net>
(with minor changes)

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=3d39b8d4e7ca43baafa3b4cd5784dd64197dd232
---

 libavcodec/riscv/takdsp_init.c |  2 ++
 libavcodec/riscv/takdsp_rvv.S  | 18 ++++++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/libavcodec/riscv/takdsp_init.c b/libavcodec/riscv/takdsp_init.c
index 2d5c974459..4312c8d99d 100644
--- a/libavcodec/riscv/takdsp_init.c
+++ b/libavcodec/riscv/takdsp_init.c
@@ -27,6 +27,7 @@
 
 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);
 
 av_cold void ff_takdsp_init_riscv(TAKDSPContext *dsp)
 {
@@ -36,6 +37,7 @@ av_cold void ff_takdsp_init_riscv(TAKDSPContext *dsp)
     if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) {
         dsp->decorrelate_ls = ff_decorrelate_ls_rvv;
         dsp->decorrelate_sr = ff_decorrelate_sr_rvv;
+        dsp->decorrelate_sm = ff_decorrelate_sm_rvv;
     }
 #endif
 }
diff --git a/libavcodec/riscv/takdsp_rvv.S b/libavcodec/riscv/takdsp_rvv.S
index 65672cdfb8..b593d9139a 100644
--- a/libavcodec/riscv/takdsp_rvv.S
+++ b/libavcodec/riscv/takdsp_rvv.S
@@ -47,3 +47,21 @@ func ff_decorrelate_sr_rvv, zve32x
         bnez     a2, 1b
         ret
 endfunc
+
+func ff_decorrelate_sm_rvv, zve32x
+1:
+        vsetvli  t0, a2, e32, m8, ta, ma
+        vle32.v  v8, (a1)
+        sub      a2, a2, t0
+        vle32.v  v0, (a0)
+        vsra.vi  v16, v8, 1
+        vsub.vv  v0, v0, v16
+        vse32.v  v0, (a0)
+        sh2add   a0, t0, a0
+        vadd.vv  v8, v0, v8
+        vse32.v  v8, (a1)
+        sh2add   a1, t0, a1
+        bnez     a2, 1b
+
+        ret
+endfunc