On Wed, Oct 05, 2016 at 02:04:31PM +0200, Alexandra Hájková wrote:
> --- a/libavcodec/x86/hevc_idct.asm
> +++ b/libavcodec/x86/hevc_idct.asm
> @@ -74,34 +286,578 @@ cglobal hevc_idct_%1x%1_dc_%2, 1, 2, 1, coeff, tmp
>
> INIT_XMM sse2
> +IDCT_DC_NL 8, %1
> +IDCT_DC 16, 4, %1
> +IDCT_DC 32, 16, %1
> +%if %1 == 8
> +TRANSPOSE_8x8
> +%if ARCH_X86_64
> +TRANSPOSE_16x16
> +TRANSPOSE_32x32
> +%endif
> +%endif
> +%define transpose_8x8 hevc_idct_transpose_8x8_sse2
> +%if ARCH_X86_64
> +%define transpose_16x16 hevc_idct_transpose_16x16_sse2
> +%define transpose_32x32 hevc_idct_transpose_32x32_sse2
> +IDCT_32x32 %1
> +IDCT_16x16 %1
> +%endif
There should be no need to redefine the transpose functions, just call
the right one with the help of the cpuname macro.
> --- a/libavcodec/x86/hevcdsp_init.c
> +++ b/libavcodec/x86/hevcdsp_init.c
> @@ -329,6 +361,11 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int
> bit_depth)
> #if HAVE_AVX_EXTERNAL
> SET_QPEL_FUNCS(1, 1, 8, avx, hevc_qpel_hv);
> SET_EPEL_FUNCS(1, 1, 8, avx, hevc_epel_hv);
> +
> + c->idct[0] = ff_hevc_idct_4x4_8_avx;
> + c->idct[1] = ff_hevc_idct_8x8_8_avx;
> + c->idct[2] = ff_hevc_idct_16x16_8_avx;
> + c->idct[3] = ff_hevc_idct_32x32_8_avx;
> #endif /* HAVE_AVX_EXTERNAL */
> }
Only the parts that are explicitly ifdeffed above within this very file
should be ifdeffed here. Add these below the ifdef.
> @@ -354,6 +397,12 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int
> bit_depth)
> SET_EPEL_FUNCS(0, 1, 10, avx, ff_hevc_epel_h);
> SET_EPEL_FUNCS(1, 0, 10, avx, ff_hevc_epel_v);
> SET_EPEL_FUNCS(1, 1, 10, avx, hevc_epel_hv);
> +
> + c->idct[0] = ff_hevc_idct_4x4_10_avx;
> + c->idct[1] = ff_hevc_idct_8x8_10_avx;
> + c->idct[2] = ff_hevc_idct_16x16_10_avx;
> + c->idct[3] = ff_hevc_idct_32x32_10_avx;
> +
> #endif /* HAVE_AVX_EXTERNAL */
> }
> if (EXTERNAL_AVX2(cpu_flags)) {
same
Diego
_______________________________________________
libav-devel mailing list
libav-devel@libav.org
https://lists.libav.org/mailman/listinfo/libav-devel
