search for: x86_celt_map

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

...arch[1] -> sse * arch[2] -> sse2 * arch[3] -> sse4.1 + * arch[4] -> avx */ -#define OPUS_ARCHMASK 3 +#define OPUS_ARCHMASK 7 int opus_select_arch(void); #else #define OPUS_ARCHMASK 0 static OPUS_INLINE int opus_select_arch(void) { return 0; diff --git a/celt/x86/x86_celt_map.c b/celt/x86/x86_celt_map.c index 1ed2acb..8e5e449 100644 --- a/celt/x86/x86_celt_map.c +++ b/celt/x86/x86_celt_map.c @@ -48,44 +48,47 @@ void (*const CELT_FIR_IMPL[OPUS_ARCHMASK + 1])( int ord, opus_val16 *mem, int arch ) = { c...

...arch[1] -> sse * arch[2] -> sse2 * arch[3] -> sse4.1 + * arch[4] -> avx */ -#define OPUS_ARCHMASK 3 +#define OPUS_ARCHMASK 7 int opus_select_arch(void); #else #define OPUS_ARCHMASK 0 static OPUS_INLINE int opus_select_arch(void) { return 0; diff --git a/celt/x86/x86_celt_map.c b/celt/x86/x86_celt_map.c index 1ed2acb..8e5e449 100644 --- a/celt/x86/x86_celt_map.c +++ b/celt/x86/x86_celt_map.c @@ -48,44 +48,47 @@ void (*const CELT_FIR_IMPL[OPUS_ARCHMASK + 1])( int ord, opus_val16 *mem, int arch ) = { c...

...include "pitch.c" diff --git a/celt/tests/test_unit_mathops.c b/celt/tests/test_unit_mathops.c index 5b446b7..fd3319d 100644 --- a/celt/tests/test_unit_mathops.c +++ b/celt/tests/test_unit_mathops.c @@ -63,8 +63,7 @@ # include "x86/celt_lpc_sse.c" # endif # include "x86/x86_celt_map.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" # if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/cel...

...include "pitch.c" diff --git a/celt/tests/test_unit_mathops.c b/celt/tests/test_unit_mathops.c index 5b446b7..fd3319d 100644 --- a/celt/tests/test_unit_mathops.c +++ b/celt/tests/test_unit_mathops.c @@ -63,8 +63,7 @@ # include "x86/celt_lpc_sse.c" # endif # include "x86/x86_celt_map.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" # if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/cel...

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

...\..\celt\x86\pitch_sse2.c" /> <ClCompile Include="..\..\celt\x86\pitch_sse4_1.c" /> + <ClCompile Include="..\..\celt\x86\vq_sse2.c" /> <ClCompile Include="..\..\celt\x86\x86cpu.c" /> <ClCompile Include="..\..\celt\x86\x86_celt_map.c" /> <ClCompile Include="..\..\silk\A2NLSF.c" /> diff --git a/win32/VS2015/opus.vcxproj.filters b/win32/VS2015/opus.vcxproj.filters index d05ef1b..3d749e0 100644 --- a/win32/VS2015/opus.vcxproj.filters +++ b/win32/VS2015/opus.vcxproj.filters @@ -213,6 +213,9 @@ &l...

..."arm/celt_neon_intr.c" > +#endif > + > +#if ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ > + || defined(OPUS_ARM_NEON_INTR)) > #include "arm/arm_celt_map.c" > #endif You should keep the #elif (the intent was to _guarantee_ that only one of x86_celt_map.c or arm_celt_map.c would be included). Instead, just move the #if defined(OPUS_ARM_NEON_INTR) block inside that #elif (both in test_unit_mathops.c and test_unit_rotation.c).

Hi all, This is Linfeng Zhang from Google. I'll work on ARM NEON optimization in the next few months. I'm submitting 2 patches in the following couple of emails, which have the new created celt_fir_neon(). I revised celt_fir_c() to not pass in argument "mem" in Patch 1. If there are concerns to this change, please let me know. Many thanks to your comments. Linfeng Zhang

...| 12 +- celt/x86/pitch_sse.c | 334 +++++++++++++------------------ celt/x86/pitch_sse.h | 256 ++++++++++------------- celt/x86/pitch_sse2.c | 95 +++++++++ celt/x86/pitch_sse4_1.c | 195 ++++++++++++++++++ celt/x86/x86_celt_map.c | 76 ++++++- celt/x86/x86cpu.c | 47 ++++- celt/x86/x86cpu.h | 26 ++- celt_sources.mk | 5 +- configure.ac | 313 ++++++++++++++++++----------- m4/opus-intrinsics.m4...

...| 12 +- celt/x86/pitch_sse.c | 334 +++++++++++++------------------ celt/x86/pitch_sse.h | 256 ++++++++++------------- celt/x86/pitch_sse2.c | 95 +++++++++ celt/x86/pitch_sse4_1.c | 195 ++++++++++++++++++ celt/x86/x86_celt_map.c | 76 ++++++- celt/x86/x86cpu.c | 47 ++++- celt/x86/x86cpu.h | 26 ++- celt_sources.mk | 5 +- configure.ac | 312 ++++++++++++++++++----------- m4/opus-intrinsics.m4...

...) #if defined(HAVE_ARM_NE10) diff --git a/celt/tests/test_unit_mathops.c b/celt/tests/test_unit_mathops.c index a1cf2f7..2e43e07 100644 --- a/celt/tests/test_unit_mathops.c +++ b/celt/tests/test_unit_mathops.c @@ -65,17 +65,18 @@ #include "x86/celt_lpc_sse.c" #endif #include "x86/x86_celt_map.c" + #elif ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ - || defined(OPUS_ARM_NEON_INTR)) -#if defined(OPUS_ARM_NEON_INTR) + || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) #include "arm/celt_neon_intr.c" +#endif #if def...

...sics was not really mapping well to what was done in celt_pitch_xcorr_arm.s - Makefile.am Removed explicit -O3 optimization - test_unit_mathops.c, test_unit_rotation.c followed recommendation to use #if #elif to guarantee that only one of "arm/arm_celt_map.c" or "x86/x86_celt_map.c" is included Viswanath Puttagunta (1): armv7: celt_pitch_xcorr: Introduce ARM neon intrinsics Makefile.am | 12 ++ celt/arm/arm_celt_map.c | 15 ++- celt/arm/celt_neon_intr.c | 249 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h...

Hi, Optimizes celt_pitch_xcorr for floating point. Changes from RFCv2: - Changes recommended by Timothy for celt_neon_intr.c everything except, left the unrolled loop still unrolled - configure.ac - use AC_LINK_IFELSE instead of AC_COMPILE_IFELSE - Moved compile flags into Makefile.am - OPUS_ARM_NEON_INR --> typo --> OPUS_ARM_NEON_INTR Viswanath Puttagunta (1): armv7:

...+#endif > > + > > +#if ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ > > + || defined(OPUS_ARM_NEON_INTR)) > > #include "arm/arm_celt_map.c" > > #endif > > You should keep the #elif (the intent was to _guarantee_ that only one > of x86_celt_map.c or arm_celt_map.c would be included). Instead, just > move the #if defined(OPUS_ARM_NEON_INTR) block inside that #elif (both > in test_unit_mathops.c and test_unit_rotation.c). Will do > _______________________________________________ > opus mailing list > opus at xiph.org > ht...

..., xcorr, len, max_pitch, arch)) diff --git a/celt/tests/test_unit_mathops.c b/celt/tests/test_unit_mathops.c index 3076bbf..cdb2939 100644 --- a/celt/tests/test_unit_mathops.c +++ b/celt/tests/test_unit_mathops.c @@ -56,7 +56,7 @@ #include "x86/celt_lpc_sse.c" #endif #include "x86/x86_celt_map.c" -#elif defined(OPUS_ARM_ASM) && defined(FIXED_POINT) +#elif defined(OPUS_ARM_ASM) #include "arm/arm_celt_map.c" #endif diff --git a/celt/tests/test_unit_rotation.c b/celt/tests/test_unit_rotation.c index 37ba74e..906fa7e 100644 --- a/celt/tests/test_unit_rotation.c +++...

...| 12 +- celt/x86/pitch_sse.c | 334 +++++++++++++------------------ celt/x86/pitch_sse.h | 261 ++++++++++-------------- celt/x86/pitch_sse2.c | 95 +++++++++ celt/x86/pitch_sse4_1.c | 195 ++++++++++++++++++ celt/x86/x86_celt_map.c | 76 ++++++- celt/x86/x86cpu.c | 47 ++++- celt/x86/x86cpu.h | 26 ++- celt_sources.mk | 5 +- configure.ac | 320 ++++++++++++++++++----------- m4/opus-intrinsics.m4...

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

...fined(FIXED_POINT) opus_val32 diff --git a/celt/tests/test_unit_mathops.c b/celt/tests/test_unit_mathops.c index 3076bbf..b9b1bcf 100644 --- a/celt/tests/test_unit_mathops.c +++ b/celt/tests/test_unit_mathops.c @@ -56,7 +56,11 @@ #include "x86/celt_lpc_sse.c" #endif #include "x86/x86_celt_map.c" -#elif defined(OPUS_ARM_ASM) && defined(FIXED_POINT) +#elif ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ + || defined(OPUS_ARM_NEON_INTR)) +#if defined(OPUS_ARM_NEON_INTR) +#include "arm/celt_neon_intr.c" +#endif #include "arm/arm_celt_map.c"...