[FFmpeg-devel] [PATCH 6/6] lavc/takdsp: R-V V decorrelate_sm

[flow gg <hlefthleft@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 59 bytes --]

C908:
decorrelate_sm_c: 130.0
decorrelate_sm_rvv_i32: 43.7

[-- Attachment #2: 0006-lavc-takdsp-R-V-V-decorrelate_sm.patch --]
[-- Type: text/x-patch, Size: 1901 bytes --]

From 3dc613feaa6c38a7df47a3fc385e2140716e0ae2 Mon Sep 17 00:00:00 2001
From: sunyuechi <sunyuechi@iscas.ac.cn>
Date: Mon, 18 Dec 2023 22:53:39 +0800
Subject: [PATCH 6/6] lavc/takdsp: R-V V decorrelate_sm

C908:
decorrelate_sm_c: 130.0
decorrelate_sm_rvv_i32: 43.7
---
 libavcodec/riscv/takdsp_init.c |  2 ++
 libavcodec/riscv/takdsp_rvv.S  | 17 +++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/libavcodec/riscv/takdsp_init.c b/libavcodec/riscv/takdsp_init.c
index 0b4ec18086..85634d6db6 100644
--- a/libavcodec/riscv/takdsp_init.c
+++ b/libavcodec/riscv/takdsp_init.c
@@ -27,6 +27,7 @@
 
 void ff_decorrelate_ls_rvv(int32_t *p1, int32_t *p2, int length);
 void ff_decorrelate_sr_rvv(int32_t *p1, 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 65c79e1aa9..816e765039 100644
--- a/libavcodec/riscv/takdsp_rvv.S
+++ b/libavcodec/riscv/takdsp_rvv.S
@@ -47,3 +47,20 @@ 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  v0, (a0)
+        sub a2,  a2, t0
+        vle32.v  v8, (a1)
+        vsra.vi  v16, v8, 1
+        vsub.vv  v0, v0, v16
+        vse32.v  v0, (a0)
+        sh2add   a0, t0, a0
+        vadd.vv  v0, v0, v8
+        vse32.v  v0, (a1)
+        sh2add   a1, t0, a1
+        bnez     a2, 1b
+        ret
+endfunc
-- 
2.43.0


[-- Attachment #3: Type: text/plain, Size: 251 bytes --]

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".