search for: opus_x86_may_have_sse2

...files changed, 4 insertions(+), 2 deletions(-) diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 133abbf..68fc606 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -45,7 +45,8 @@ #elif (defined(OPUS_X86_MAY_HAVE_SSE) && !defined(OPUS_X86_PRESUME_SSE)) || \ (defined(OPUS_X86_MAY_HAVE_SSE2) && !defined(OPUS_X86_PRESUME_SSE2)) || \ - (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) + (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) || \ + (defined(OPUS_X86_MAY_HAVE_AVX) && !defined(OPUS_X86_PRESUME_AVX)...

...PUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) + #include "arm/armcpu.h" /* We currently support 4 ARM variants: @@ -43,14 +44,16 @@ */ #define OPUS_ARCHMASK 3 -#elif defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) +#elif (defined(OPUS_X86_MAY_HAVE_SSE) && !defined(OPUS_X86_PRESUME_SSE)) || \ + (defined(OPUS_X86_MAY_HAVE_SSE2) && !defined(OPUS_X86_PRESUME_SSE2)) || \ + (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) #i...

...PUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) + #include "arm/armcpu.h" /* We currently support 4 ARM variants: @@ -43,14 +44,16 @@ */ #define OPUS_ARCHMASK 3 -#elif defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) +#elif (defined(OPUS_X86_MAY_HAVE_SSE) && !defined(OPUS_X86_PRESUME_SSE)) || \ + (defined(OPUS_X86_MAY_HAVE_SSE2) && !defined(OPUS_X86_PRESUME_SSE2)) || \ + (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) #i...

...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"yes"],[ [OPUS_X86_MAY_HAVE_SSE2], [OPUS_X86_PRESUME_SSE2], [[#include <emmintrin.h> + #include <time.h> ]], [[ - static __m128i mtest; - mtest = _mm_setzero_si128(); + __m128i mtest; + mtest = _mm_set1_epi32((int)time(NULL)...

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

Yes, Thank you. I'll follow up with the AVX code and tests for pitch code. Radu -----Original Message----- From: opus-bounces at xiph.org [mailto:opus-bounces at xiph.org] On Behalf Of Timothy B. Terriberry Sent: Thursday, November 5, 2015 10:31 AM To: opus at xiph.org Subject: Re: [opus] AVX Optimizations Velea, Radu wrote: > I've created a pull request[1] to enable configuration

...| 3 +-- celt/tests/test_unit_rotation.c | 3 +-- 4 files changed, 4 insertions(+), 8 deletions(-) diff --git a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index bcee440..484dc57 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -47,8 +47,7 @@ #if defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) # include "x86/x86cpu.c" -#elif defined(OPUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#elif defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/armcpu.c" #...

...| 3 +-- celt/tests/test_unit_rotation.c | 3 +-- 4 files changed, 4 insertions(+), 8 deletions(-) diff --git a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index bcee440..484dc57 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -47,8 +47,7 @@ #if defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) # include "x86/x86cpu.c" -#elif defined(OPUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#elif defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/armcpu.c" #...

...e changes. diff --git a/celt/cpu_support.h b/celt/cpu_support.h index db1cb58..133abbf 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -43,23 +43,24 @@ */ #define OPUS_ARCHMASK 3 #elif (defined(OPUS_X86_MAY_HAVE_SSE) && !defined(OPUS_X86_PRESUME_SSE)) || \ (defined(OPUS_X86_MAY_HAVE_SSE2) && !defined(OPUS_X86_PRESUME_SSE2)) || \ (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) #include "x86/x86cpu.h" -/* We currently support 4 x86 variants: +/* We currently support 5 x86 variants: * arch[0] -> non-sse * arch[1] -&gt...

Fixes build failure on platforms with MAY_HAVE_SSE4_1 (but not PRESUME_SSE4_1) with --enable-intrinsics. --- silk/fixed/main_FIX.h | 11 +++++++++++ silk/x86/x86_silk_map.c | 2 ++ 2 files changed, 13 insertions(+) diff --git a/silk/fixed/main_FIX.h b/silk/fixed/main_FIX.h index ffeb4f3..375b5eb 100644 --- a/silk/fixed/main_FIX.h +++ b/silk/fixed/main_FIX.h @@ -97,6 +97,17 @@ void

Fixes build failure on platforms with MAY_HAVE_SSE4_1 (but not PRESUME_SSE4_1) with --enable-intrinsics. --- silk/fixed/main_FIX.h | 11 +++++++++++ silk/x86/x86_silk_map.c | 2 ++ 2 files changed, 13 insertions(+) diff --git a/silk/fixed/main_FIX.h b/silk/fixed/main_FIX.h index ffeb4f3..375b5eb 100644 --- a/silk/fixed/main_FIX.h +++ b/silk/fixed/main_FIX.h @@ -97,6 +97,17 @@ void

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:

...se changes. diff --git a/celt/cpu_support.h b/celt/cpu_support.h index db1cb58..133abbf 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -43,23 +43,24 @@ */ #define OPUS_ARCHMASK 3 #elif (defined(OPUS_X86_MAY_HAVE_SSE) && !defined(OPUS_X86_PRESUME_SSE)) || \ (defined(OPUS_X86_MAY_HAVE_SSE2) && !defined(OPUS_X86_PRESUME_SSE2)) || \ (defined(OPUS_X86_MAY_HAVE_SSE4_1) && !defined(OPUS_X86_PRESUME_SSE4_1)) #include "x86/x86cpu.h" -/* We currently support 4 x86 variants: +/* We currently support 5 x86 variants: * arch[0] -> non-sse * arch[1] -&gt...

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]

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

...t;arm/celt_ne10_mdct.c" #endif +#if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) +#include "arm/celt_neon_intr.c" +#endif #include "celt_lpc.c" #include "pitch.c" -#include "arm/celt_neon_intr.c" #include "arm/arm_celt_map.c" -#endif #elif defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) #include "x86/x86cpu.c" #include "celt/x86/pitch_sse.c" diff --git a/celt/tests/test_unit_mdct.c b/celt/tests/test_unit_mdct.c index 53258fe..5d9a8f5 100644 --- a/celt/tests/test_unit_mdct.c +++ b/celt/tests/test_unit_mdct.c @@ -49,16 +49,...

...PUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if defined(HAVE_ARM_NE10) +#include "arm/celt_ne10_fft.c" +#include "arm/celt_ne10_mdct.c" +#include "arm/celt_neon_intr.c" +#include "arm/arm_celt_map.c" +#endif +#elif defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) +#include "x86/x86cpu.c" +#endif #ifndef M_PI #define M_PI 3.141592653 @@ -93,13 +109,13 @@ void check(kiss_fft_cpx * in,kiss_fft_cpx * out,int nfft,int isinverse) } } -void test1d(int nfft,int isinverse) +void test1d(int nfft,int isinve...

...PUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if defined(HAVE_ARM_NE10) +#include "arm/celt_ne10_fft.c" +#include "arm/celt_ne10_mdct.c" +#endif +#include "arm/celt_neon_intr.c" +#include "arm/arm_celt_map.c" +#elif defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) +#include "x86/x86cpu.c" +#endif #ifndef M_PI #define M_PI 3.141592653 @@ -93,13 +109,13 @@ void check(kiss_fft_cpx * in,kiss_fft_cpx * out,int nfft,int isinverse) } } -void test1d(int nfft,int isinverse) +void test1d(int nfft,int isinve...