[FFmpeg-devel] [PATCH 2/6] lavc/ac3dsp: RISC-V V float_to_fixed24

[Peiting Shen]

From: Shen Peiting <shenpeiting at eswincomputing.com>

Vector instructions replaces scalar options of float convert to fixed

Benchmarks on Spike(cycles):
len=16
float_to_fixed24_c: 315
float_to_fixed24_rvv: 27
len=160
float_to_fixed24_c: 2871
float_to_fixed24_rvv: 67

Co-Authored by: Yang Xiaojun <yangxiaojun at eswincomputing.com>
Co-Authored by: Huang Xing <huangxing1 at eswincomputing.com>
Co-Authored by: Zeng Fanchen <zengfanchen at eswincomputing.com>
Signed-off-by: Shen Peiting <shenpeiting at eswincomputing.com>
---
 libavcodec/riscv/ac3dsp_init.c |  5 ++++-
 libavcodec/riscv/ac3dsp_rvv.S  | 19 +++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/libavcodec/riscv/ac3dsp_init.c b/libavcodec/riscv/ac3dsp_init.c
index bb67d86998..a4e75a7541 100644
--- a/libavcodec/riscv/ac3dsp_init.c
+++ b/libavcodec/riscv/ac3dsp_init.c
@@ -25,13 +25,16 @@
 #include "config.h"
 
 void ff_ac3_exponent_min_rvv(uint8_t *exp, int num_reuse_blocks, int nb_coefs);
+void ff_float_to_fixed24_rvv(int32_t *dst, const float *src, unsigned int len);
 
 av_cold void ff_ac3dsp_init_riscv(AC3DSPContext *c)
 {
     int flags = av_get_cpu_flags();
 #if HAVE_RVV
-    if (flags & AV_CPU_FLAG_RVV_I32)
+    if (flags & AV_CPU_FLAG_RVV_I32) {
         c->ac3_exponent_min = ff_ac3_exponent_min_rvv;
+        c->float_to_fixed24 = ff_float_to_fixed24_rvv;
+    }
 #endif
 }
 
diff --git a/libavcodec/riscv/ac3dsp_rvv.S b/libavcodec/riscv/ac3dsp_rvv.S
index 879123f4a7..d98e72c12c 100644
--- a/libavcodec/riscv/ac3dsp_rvv.S
+++ b/libavcodec/riscv/ac3dsp_rvv.S
@@ -44,3 +44,22 @@ func ff_ac3_exponent_min_rvv, zve32x
 3:
     ret
 endfunc
+
+
+func ff_float_to_fixed24_rvv, zve32x
+    addi            t1, x0, 1
+    slli            t1, t1, 24
+    fcvt.s.w        f1, t1
+1:
+    vsetvli         t0, a2, e32, m8
+    vle32.v         v0, (a1)
+    vfmul.vf        v0, v0, f1
+    vfcvt.x.f.v     v16, v0
+    vse32.v         v16, (a0)
+    sub             a2, a2, t0
+    slli            t0, t0, 2
+    add             a1, a1, t0
+    add             a0, a0, t0
+    bgtz            a2, 1b
+    ret
+endfunc
-- 
2.17.1