Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-06 Thread Henrik Gramner
On Sat, Aug 5, 2017 at 12:58 AM, Ivan Kalvachev wrote: > 8 packed, 8 scalar. > > Unless I miss something (and as I've said before, > I'm not confident enough to mess with that code.) > > (AVX does extend to 32 variants, but they are not > SSE compatible, so no need to

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-05 Thread Ivan Kalvachev
On 8/5/17, Hendrik Leppkes wrote: > On Sat, Aug 5, 2017 at 12:21 PM, Ivan Kalvachev > wrote: >> On 8/5/17, Rostislav Pehlivanov wrote: >>> On 4 August 2017 at 23:58, Ivan Kalvachev wrote: >>> >> I

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-05 Thread Hendrik Leppkes
On Sat, Aug 5, 2017 at 12:21 PM, Ivan Kalvachev wrote: > On 8/5/17, Rostislav Pehlivanov wrote: >> On 4 August 2017 at 23:58, Ivan Kalvachev wrote: >> >>> >>> >> I had it mixed before, but I changed it to be consistent. >>> >>

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-05 Thread Ivan Kalvachev
On 8/5/17, Rostislav Pehlivanov wrote: > On 4 August 2017 at 23:58, Ivan Kalvachev wrote: > >> >> >> I had it mixed before, but I changed it to be consistent. >> >> Some new avx instruction are not overloaded or >> >> available without their "v-"

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-04 Thread Rostislav Pehlivanov
On 4 August 2017 at 23:58, Ivan Kalvachev wrote: > > >> I had it mixed before, but I changed it to be consistent. > >> Some new avx instruction are not overloaded or > >> available without their "v-" prefix. > >> e.g. x86util uses vpbroadcastw in SPLATW. > > > > Every

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-04 Thread Ivan Kalvachev
On 8/4/17, Henrik Gramner wrote: > On Thu, Aug 3, 2017 at 11:36 PM, Ivan Kalvachev > wrote: >>> 1234_1234_1234_123 >>> VBROADCASTSS ym1, xm1 >>> BLENDVPS m1, m2, m3 >>> >>> is the most commonly used alignment. >> >> I see that a

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-04 Thread Henrik Gramner
On Thu, Aug 3, 2017 at 11:36 PM, Ivan Kalvachev wrote: >> 1234_1234_1234_123 >> VBROADCASTSS ym1, xm1 >> BLENDVPS m1, m2, m3 >> >> is the most commonly used alignment. > > I see that a lot of .asm files use different alignments. > I'll try to pick

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-03 Thread Ivan Kalvachev
On 8/2/17, Henrik Gramner wrote: > On Tue, Aug 1, 2017 at 11:46 PM, Ivan Kalvachev > wrote: >> On 7/31/17, Henrik Gramner wrote: >>> Use rN instead of rNq for numbered registers (q suffix is used for >>> named args only due to

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-02 Thread Henrik Gramner
On Tue, Aug 1, 2017 at 11:46 PM, Ivan Kalvachev wrote: > On 7/31/17, Henrik Gramner wrote: >> Use rN instead of rNq for numbered registers (q suffix is used for >> named args only due to preprocessor limitations). > > Is this documented? Not sure, but

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-08-01 Thread Ivan Kalvachev
On 7/31/17, Henrik Gramner wrote: > On Wed, Jul 26, 2017 at 4:56 PM, Ivan Kalvachev > wrote: >> +++ b/libavcodec/x86/opus_pvq_search.asm > > Generic minor stuff: > > Use rN instead of rNq for numbered registers (q suffix is used for > named args only due

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-07-31 Thread Henrik Gramner
On Wed, Jul 26, 2017 at 4:56 PM, Ivan Kalvachev wrote: > +++ b/libavcodec/x86/opus_pvq_search.asm Generic minor stuff: Use rN instead of rNq for numbered registers (q suffix is used for named args only due to preprocessor limitations). Use the same "standard" vertical

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-07-27 Thread Ivan Kalvachev
On 7/27/17, Rostislav Pehlivanov wrote: > On 27 July 2017 at 09:38, Ivan Kalvachev wrote: > >> On 7/27/17, Rostislav Pehlivanov wrote: >> > On 26 July 2017 at 15:56, Ivan Kalvachev wrote: >> > >> >> +if

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-07-27 Thread Rostislav Pehlivanov
On 27 July 2017 at 09:38, Ivan Kalvachev wrote: > On 7/27/17, Rostislav Pehlivanov wrote: > > On 26 July 2017 at 15:56, Ivan Kalvachev wrote: > > > >> +if (ARCH_X86 && CONFIG_OPUS_ENCODER) > >> +

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-07-27 Thread Ivan Kalvachev
On 7/27/17, Rostislav Pehlivanov wrote: > On 26 July 2017 at 15:56, Ivan Kalvachev wrote: > >> +if (ARCH_X86 && CONFIG_OPUS_ENCODER) >> +ff_opus_dsp_init_x86(s); >> > > Just change it to > +if (ARCH_X86) > > The init function is named

Re: [FFmpeg-devel] [PATCH]v6 Opus Pyramid Vector Quantization Search in x86 SIMD asm

2017-07-26 Thread Rostislav Pehlivanov
On 26 July 2017 at 15:56, Ivan Kalvachev wrote: > +if (ARCH_X86 && CONFIG_OPUS_ENCODER) > +ff_opus_dsp_init_x86(s); > Just change it to +if (ARCH_X86) The init function is named opus_dsp, so it'll get used to other opus things, not just the encoder. The