Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
* [FFmpeg-devel] [PATCH 12/18] lavu/riscv: float vector multiply-accumulate with RVV
@ 2022-09-09 15:48 remi
  0 siblings, 0 replies; 2+ messages in thread
From: remi @ 2022-09-09 15:48 UTC (permalink / raw)
  To: ffmpeg-devel

From: Rémi Denis-Courmont <remi@remlab.net>

---
 libavutil/riscv/float_dsp_init.c |  6 +++++
 libavutil/riscv/float_dsp_rvv.S  | 38 ++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/libavutil/riscv/float_dsp_init.c b/libavutil/riscv/float_dsp_init.c
index 49a4c95a0b..b63da72acd 100644
--- a/libavutil/riscv/float_dsp_init.c
+++ b/libavutil/riscv/float_dsp_init.c
@@ -24,11 +24,15 @@
 
 void ff_vector_fmul_rvv(float *dst, const float *src0, const float *src1,
                          int len);
+void ff_vector_fmac_scalar_rvv(float *dst, const float *src, float mul,
+                                int len);
 void ff_vector_fmul_scalar_rvv(float *dst, const float *src, float mul,
                                 int len);
 
 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);
 
@@ -39,10 +43,12 @@ av_cold void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp)
 
     if (flags & AV_CPU_FLAG_ZVE32F) {
         fdsp->vector_fmul = ff_vector_fmul_rvv;
+        fdsp->vector_fmac_scalar = ff_vector_fmac_scalar_rvv;
         fdsp->vector_fmul_scalar = ff_vector_fmul_scalar_rvv;
 
         if (flags & AV_CPU_FLAG_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 65c3a77b01..5a7d92abd6 100644
--- a/libavutil/riscv/float_dsp_rvv.S
+++ b/libavutil/riscv/float_dsp_rvv.S
@@ -36,6 +36,25 @@ func ff_vector_fmul_rvv, zve32f
         ret
 endfunc
 
+// (a0) += (a1) * fa0 [0..a2-1]
+func ff_vector_fmac_scalar_rvv, zve32f
+NOHWF   fmv.w.x   fa0, a2
+NOHWF   mv        a2, a3
+
+1:      vsetvli   t0, a2, e32, m8, ta, ma
+        slli      t1, t0, 2
+        vle32.v   v24, (a1)
+        add       a1, a1, t1
+        vle32.v   v16, (a0)
+        vfmacc.vf v16, fa0, v24
+        sub       a2, a2, t0
+        vse32.v   v16, (a0)
+        add       a0, a0, t1
+        bnez      a2, 1b
+
+        ret
+endfunc
+
 // (a0) = (a1) * fa0 [0..a2-1]
 func ff_vector_fmul_scalar_rvv, zve32f
 NOHWF   fmv.w.x  fa0, a2
@@ -71,6 +90,25 @@ 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, m8, 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
-- 
2.37.2

_______________________________________________
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".

^ permalink raw reply	[flat|nested] 2+ messages in thread
[parent not found: <2652141.mvXUDI8C0e@basile.remlab.net>]
end of thread, other threads:[~2022-09-12 15:55 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-09-09 15:48 [FFmpeg-devel] [PATCH 12/18] lavu/riscv: float vector multiply-accumulate with RVV remi
     [not found] <2652141.mvXUDI8C0e@basile.remlab.net>
2022-09-12 15:53 ` remi

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git