search for: _mm_mul_ps

...t j; __m128 xsum1 = _mm_loadu_ps(sum); __m128 xsum2 = _mm_setzero_ps(); for (j = 0; j < len-3; j += 4) { const __m128 x0 = _mm_loadu_ps(x+j); const __m128 y0 = _mm_loadu_ps(y+j); const __m128 y3 = _mm_loadu_ps(y+j+3); xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),y0)); xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55),_mm_shuffle_ps(y0,y3,0x49))); xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa),_mm_shuffle_ps(y0,y3,0x9e))); xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps...

...gt; __m128 xsum2 = _mm_setzero_ps(); > > for (j = 0; j < len-3; j += 4) { > const __m128 x0 = _mm_loadu_ps(x+j); > const __m128 y0 = _mm_loadu_ps(y+j); > const __m128 y3 = _mm_loadu_ps(y+j+3); > > xsum1 = > _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),y0)); > xsum2 = > _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55),_mm_shuffle_ps(y0,y3,0x49))); > xsum1 = > _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa),_mm_shuffle_ps(y0,y3,0x9e))); > xsum2 = > _mm_add_ps(x...

...*/ xx = _mm_load_ps1(x+i); yy = _mm_add_ss(xx, mem[0]); _mm_store_ss(y+i, yy); yy = _mm_shuffle_ps(yy, yy, 0); /* Update memory */ mem[0] = _mm_move_ss(mem[0], mem[1]); mem[0] = _mm_shuffle_ps(mem[0], mem[0], 0x39); mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0])); mem[0] = _mm_sub_ps(mem[0], _mm_mul_ps(yy, den[0])); mem[1] = _mm_move_ss(mem[1], mem[2]); mem[1] = _mm_shuffle_ps(mem[1], mem[1], 0x39); mem[1] = _mm_add_ps(mem[1], _mm_mul_ps(xx, num[1])); mem[1] = _mm_sub_ps(mem[1], _mm_mul_ps(yy, den[1])); me...

> Personally, I don't think much of PNI. The complex arithmetic stuff they > added sets you up for a lot of permute overhead that is inefficient -- > especially on a processor that is already weak on permute. In my opinion, Actually, the new instructions make it possible to do complex multiplies without the need to permute and separate the add and subtract. The really useful

...en) +{ + int j; + __m128 xsum1, xsum2; + xsum1 = _mm_loadu_ps(sum); + xsum2 = _mm_setzero_ps(); + + for (j = 0; j < len-3; j += 4) + { + __m128 x0 = _mm_loadu_ps(x+j); + __m128 yj = _mm_loadu_ps(y+j); + __m128 y3 = _mm_loadu_ps(y+j+3); + + xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),yj)); + xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55), + _mm_shuffle_ps(yj,y3,0x49))); + xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa), + _mm_shuf...

...en) +{ + int j; + __m128 xsum1, xsum2; + xsum1 = _mm_loadu_ps(sum); + xsum2 = _mm_setzero_ps(); + + for (j = 0; j < len-3; j += 4) + { + __m128 x0 = _mm_loadu_ps(x+j); + __m128 yj = _mm_loadu_ps(y+j); + __m128 y3 = _mm_loadu_ps(y+j+3); + + xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),yj)); + xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55), + _mm_shuffle_ps(yj,y3,0x49))); + xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa), + _mm_shuf...

The attached patch cleans up Opus's x86 intrinsics configury. It: * Makes ?enable-intrinsics work with clang and other non-GCC compilers * Enables RTCD for the floating-point-mode SSE code in Celt. * Disables use of RTCD in cases where the compiler targets an instruction set by default. * Enables the SSE4.1 Silk optimizations that apply to the common parts of Silk when Opus is built in

...GE. +*/ + +#include <xmmintrin.h> + +#define OVERRIDE_INNER_PRODUCT_SINGLE +static inline float inner_product_single(const float *a, const float *b, unsigned int len) +{ + int i; + float ret; + __m128 sum = _mm_setzero_ps(); + for (i=0;i<len;i+=8) + { + sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i))); + sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4))); + } + sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum)); + sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55)); + _mm_store_ss(&ret, sum); + return ret; +} + +#de...

...GE. +*/ + +#include <xmmintrin.h> + +#define OVERRIDE_INNER_PRODUCT_SINGLE +static inline float inner_product_single(const float *a, const float *b, unsigned int len) +{ + int i; + float ret; + __m128 sum = _mm_setzero_ps(); + for (i=0;i<len;i+=8) + { + sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i))); + sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4))); + } + sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum)); + sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55)); + _mm_store_ss(&ret, sum); + return ret; +} + +#de...

...86_PRESUME_SSE], [[#include <xmmintrin.h> + #include <time.h> ]], [[ - static __m128 mtest; - mtest = _mm_setzero_ps(); + __m128 mtest; + mtest = _mm_set1_ps((float)time(NULL)); + mtest = _mm_mul_ps(mtest, mtest); + return _mm_cvtss_si32(mtest); ]] ) AS_IF([test x"$OPUS_X86_MAY_HAVE_SSE" = x"1" && test x"$OPUS_X86_PRESUME_SSE" != x"1"], @@ -539,10 +543,13 @@ AS_IF([test x"$enable_intrinsics" = x"...

...or xout2 that go to INF. That is the main issue- I have also seen the IIR filter go wonky occasionally, which is what is corrupting st->mem_sp. Usually this is just because there are some odd values in st->interp_qlpc. However it seems like it can also just happen sometimes as output of the _mm_mul_ps multiply goes to INF (this can also happen in the non-sse code). I am working on figuring out why this is happening. With the new changes also filter_ratio went to 0 in one of my tests, in part because rh was INF. This is around the section where I think you made changes to how you calculate st-...

Hi All, Since I continue to base my work on top of Jonathan's patch, and my previous Ne10 fft/ifft/mdct_forward/backward patches, I thought it would be better to just post all new patches as a patch series. Please let me know if anyone disagrees with this approach. You can see wip branch of all latest patches at https://git.linaro.org/people/viswanath.puttagunta/opus.git Branch:

Hi Timothy, As I mentioned earlier [1], I now fixed compile issues with fixed point and resubmitting the patch. I also have new patch that does intrinsics optimizations for celt_pitch_xcorr targetting aarch64. You can find my latest work-in-progress branch at [2] For reference, you can use the Ne10 pre-built libraries at [3] Note that I am working with Phil at ARM to get my patch at [4]

...0h],xmm1 266: mem[0] = _mm_shuffle_ps(mem[0], mem[0], 0x39); 004134E8 movaps xmm0,xmmword ptr [ebp-60h] 004134EC movaps xmm1,xmmword ptr [ebp-60h] 004134F0 shufps xmm1,xmm0,39h 004134F4 movaps xmmword ptr [ebp-60h],xmm1 267: 268: mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0])); 004134F8 movaps xmm0,xmmword ptr [ebp-30h] 004134FC movaps xmm1,xmmword ptr [xx] 00413500 mulps xmm1,xmm0 00413503 movaps xmm0,xmmword ptr [ebp-60h] 00413507 addps xmm0,xmm1 0041350A movaps xmmword ptr [ebp-60h],xmm0 269: 270: mem[1]...

Hi All, As per Timothy's suggestion, disabling mdct_forward for fixed point. Only effects armv7,armv8: Extend fixed fft NE10 optimizations to mdct Rest of patches are same as in [1] For reference, latest wip code for opus is at [2] Still working with NE10 team at ARM to get corner cases of mdct_forward. Will update with another patch when issue in NE10 gets fixed. Regards, Vish [1]:

Hi All, Changes from RFC v2 [1] armv7,armv8: Extend fixed fft NE10 optimizations to mdct - Overflow issue fixed by Phil at ARM. Ne10 wip at [2]. Should be upstream soon. - So, re-enabled using fixed fft for mdct_forward which was disabled in RFCv2 armv7,armv8: Optimize fixed point fft using NE10 library - Thanks to Jonathan Lennox, fixed some build fixes on iOS and some copy-paste errors Rest

Hello Timothy / Jean-Marc / opus-dev, This patch series is follow up on work I posted on [1]. In addition to what was posted on [1], this patch series mainly integrates Fixed point FFT implementations in NE10 library into opus. You can view my opus wip code at [2]. Note that while I found some issues both with the NE10 library(fixed fft) and with Linaro toolchain (armv8 intrinsics), the work

...at *b, unsigned int len, const spx_uint32_t oversample, float *frac) { int i; - float ret; __m128 sum = _mm_setzero_ps(); __m128 f = _mm_loadu_ps(frac); for(i=0;i<len;i+=2) @@ -67,18 +64,16 @@ static inline float interpolate_product_single(const float *a, const float *b, u sum = _mm_mul_ps(f, sum); sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum)); sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55)); - _mm_store_ss(&ret, sum); - return ret; + _mm_store_ss(ret, sum); } #ifdef _USE_SSE2 #include <emmintrin.h> #define OVERRIDE_INNER_PRODUCT_DOUBLE -static...

...o wonky > occasionally, which is what is corrupting st->mem_sp. Well, they would if the filter is bad (read unstable). > Usually > this is just because there are some odd values in st->interp_qlpc. > However it seems like it can also just happen sometimes as > output of the _mm_mul_ps multiply goes to INF (this can also > happen in the non-sse code). I am working on figuring out why > this is happening. Can you leave SSE out of that for now? > With the new changes also filter_ratio went to 0 in one of my > tests, in part because rh was INF. This is around the sec...

A little more info on this: I backtracked deeper into this and it looks like excBuf is corrupted, which is corrupted by low_innov_alias being invalid. However it is not entirely clear where that gets initialized (in sb_celp it is set to out+st->frame_size) Tom