[FFmpeg-devel] [PATCH 3/3] avfilter/vf_convolution: add X86 SIMD for filter_column()

[Song, Ruiling]

> -----Original Message-----
> From: ffmpeg-devel <ffmpeg-devel-bounces at ffmpeg.org> On Behalf Of
> chen
> Sent: Tuesday, December 3, 2019 4:59 PM
> To: FFmpeg development discussions and patches <ffmpeg-
> devel at ffmpeg.org>
> Subject: Re: [FFmpeg-devel] [PATCH 3/3] avfilter/vf_convolution: add X86
> SIMD for filter_column()
> 
> comments inline in code
> 
> 
> At 2019-12-03 15:52:07, xujunzz at sjtu.edu.cn wrote:
> >From: Xu Jun <xujunzz at sjtu.edu.cn>
[...]
> >+
> >+        cvtdq2ps m4, m4
> >+        mulps m4, m0     ; sum *= rdiv
> >+        addps m4, m1     ; sum += bias
> 
> >+        addps m4, m5     ; sum += 0.5
> I don't know how about precision mismatch if we pre-compute (bias+0.5)
I think it is hard to prove it is safe to do pre-compute.

> 
> 
> >+        cvttps2dq m4, m4
> >+        packssdw m4, m4
> >+        packuswb m4, m4
> >+        movss [dstq + dst_offq], m4
> >+        add c_offq, mmsize/4
> >+        add dst_offq, mmsize/4
> >+
> >+        add off16q, mmsize/4
> >+        cmp off16q, widthq
> >+        jl .loop16
> >+
> >+    add widthq, rq
> >+    cmp off16q, widthq
> >+    jge .paraend
> >+
> 
> >+    .loopr:
> no idea about this loop, if we can read beyond, we can reuse above SIMD
> code
Reuse above SIMD code may write to the memory that does not belong to this slice-thread.
IMO, the code to handle remainder columns is still necessary.

Ruiling
> 
> 
> >+        xor sumd, sumd
> >+        xor iq, iq
> >+        .loopr_i:
> >+            mov ciq, [ptrq + iq * gprsize]
> >+            movzx rd, byte [ciq + c_offq]
> >+            imul rd, [matrixq + 4*iq]
> >+            add sumd, rd
> >+
> >+            add iq, 1
> >+            cmp iq, radq
> >+            jl .loopr_i
> >+
> >+        pxor m4, m4
> >+        cvtsi2ss m4, sumd
> >+        mulss m4, m0     ; sum *= rdiv
> >+        addss m4, m1     ; sum += bias
> >+        addss m4, m5     ; sum += 0.5
> >+        cvttps2dq m4, m4
> >+        packssdw m4, m4
> >+        packuswb m4, m4
> >+        movd sumd, m4
> >+        mov [dstq + dst_offq], sumb
> >+        add c_offq, 1
> >+        add dst_offq, 1
> >+        add off16q, 1
> >+        cmp off16q, widthq
> >+        jl .loopr
> >+
> >+    .paraend:
> >+    sub c_offq, widthq
> >+    sub dst_offq, widthq
> >+    add c_offq, strideq
> >+    add dst_offq, dstrideq
> >+
> >+    sub heightq, 1
> >+    cmp heightq, 0
> >+    jg .loopy
> >+
> >+.end:
> >+    RET
> 
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".