diff mbox series

[FFmpeg-devel,09/26] lavu/floatdsp: RISC-V V vector_fmul

Message ID 20220920144013.4959-9-remi@remlab.net
State New
Headers show
Series [FFmpeg-devel,01/26] lavu/cpu: detect RISC-V base extensions | expand

Checks

Context Check Description
yinshiyou/make_loongarch64 success Make finished
yinshiyou/make_fate_loongarch64 success Make fate finished
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished

Commit Message

Rémi Denis-Courmont Sept. 20, 2022, 2:39 p.m. UTC 
From: Rémi Denis-Courmont <remi@remlab.net>

---
 libavutil/riscv/float_dsp_init.c |  3 +++
 libavutil/riscv/float_dsp_rvv.S  | 18 ++++++++++++++++++
 2 files changed, 21 insertions(+)
diff mbox series

Patch

diff --git a/libavutil/riscv/float_dsp_init.c b/libavutil/riscv/float_dsp_init.c
index b829c0f736..60b79bd59e 100644
--- a/libavutil/riscv/float_dsp_init.c
+++ b/libavutil/riscv/float_dsp_init.c
@@ -25,6 +25,8 @@ 
 #include "libavutil/cpu.h"
 #include "libavutil/float_dsp.h"
 
+void ff_vector_fmul_rvv(float *dst, const float *src0, const float *src1,
+                         int len);
 void ff_vector_fmul_scalar_rvv(float *dst, const float *src, float mul,
                                 int len);
 
@@ -37,6 +39,7 @@  av_cold void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp)
     int flags = av_get_cpu_flags();
 
     if (flags & AV_CPU_FLAG_RV_ZVE32F) {
+        fdsp->vector_fmul = ff_vector_fmul_rvv;
         fdsp->vector_fmul_scalar = ff_vector_fmul_scalar_rvv;
 
         if (flags & AV_CPU_FLAG_RV_ZVE64D)
diff --git a/libavutil/riscv/float_dsp_rvv.S b/libavutil/riscv/float_dsp_rvv.S
index e82d56ac15..fb2cb54081 100644
--- a/libavutil/riscv/float_dsp_rvv.S
+++ b/libavutil/riscv/float_dsp_rvv.S
@@ -21,6 +21,24 @@ 
 #include "config.h"
 #include "asm.S"
 
+// (a0) = (a1) * (a2) [0..a3-1]
+func ff_vector_fmul_rvv, zve32f
+1:
+        vsetvli  t0, a3, e32, m1, ta, ma
+        slli     t1, t0, 2
+        vle32.v  v16, (a1)
+        add      a1, a1, t1
+        vle32.v  v24, (a2)
+        add      a2, a2, t1
+        vfmul.vv v16, v16, v24
+        sub      a3, a3, t0
+        vse32.v  v16, (a0)
+        add      a0, a0, t1
+        bnez     a3, 1b
+
+        ret
+endfunc
+
 // (a0) = (a1) * fa0 [0..a2-1]
 func ff_vector_fmul_scalar_rvv, zve32f
 NOHWF   fmv.w.x  fa0, a2