diff mbox series

[FFmpeg-devel,12/29] lavu/floatdsp: RISC-V V vector_dmac_scalar

Message ID 20220922183726.38624-12-remi@remlab.net
State New
Headers show
Series [FFmpeg-devel,01/29] lavu/cpu: detect RISC-V base extensions | expand

Checks

Context Check Description
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished

Commit Message

Rémi Denis-Courmont Sept. 22, 2022, 6:37 p.m. UTC
From: Rémi Denis-Courmont <remi@remlab.net>

---
 libavutil/riscv/float_dsp_init.c |  3 +++
 libavutil/riscv/float_dsp_rvv.S  | 19 +++++++++++++++++++
 2 files changed, 22 insertions(+)
diff mbox series

Patch

diff --git a/libavutil/riscv/float_dsp_init.c b/libavutil/riscv/float_dsp_init.c
index c2d93e0cd7..d17d0f66c5 100644
--- a/libavutil/riscv/float_dsp_init.c
+++ b/libavutil/riscv/float_dsp_init.c
@@ -34,6 +34,8 @@  void ff_vector_fmul_scalar_rvv(float *dst, const float *src, float mul,
 
 void ff_vector_dmul_rvv(double *dst, const double *src0, const double *src1,
                          int len);
+void ff_vector_dmac_scalar_rvv(double *dst, const double *src, double mul,
+                                int len);
 void ff_vector_dmul_scalar_rvv(double *dst, const double *src, double mul,
                                 int len);
 
@@ -49,6 +51,7 @@  av_cold void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp)
 
         if (flags & AV_CPU_FLAG_RV_ZVE64D) {
             fdsp->vector_dmul = ff_vector_dmul_rvv;
+            fdsp->vector_dmac_scalar = ff_vector_dmac_scalar_rvv;
             fdsp->vector_dmul_scalar = ff_vector_dmul_scalar_rvv;
         }
     }
diff --git a/libavutil/riscv/float_dsp_rvv.S b/libavutil/riscv/float_dsp_rvv.S
index 1c1fa906e6..0d6fffe235 100644
--- a/libavutil/riscv/float_dsp_rvv.S
+++ b/libavutil/riscv/float_dsp_rvv.S
@@ -94,6 +94,25 @@  func ff_vector_dmul_rvv, zve64d
         ret
 endfunc
 
+// (a0) += (a1) * fa0 [0..a2-1]
+func ff_vector_dmac_scalar_rvv, zve64d
+NOHWD   fmv.d.x   fa0, a2
+NOHWD   mv        a2, a3
+1:
+        vsetvli   t0, a2, e64, m1, ta, ma
+        slli      t1, t0, 3
+        vle64.v   v24, (a1)
+        add       a1, a1, t1
+        vle64.v   v16, (a0)
+        vfmacc.vf v16, fa0, v24
+        sub       a2, a2, t0
+        vse64.v   v16, (a0)
+        add       a0, a0, t1
+        bnez      a2, 1b
+
+        ret
+endfunc
+
 // (a0) = (a1) * fa0 [0..a2-1]
 func ff_vector_dmul_scalar_rvv, zve64d
 NOHWD   fmv.d.x  fa0, a2