mirrors/gnss-sdr
1
0
Fork 0
mirror of https://github.com/gnss-sdr/gnss-sdr synced 2025-10-31 15:23:04 +00:00
Code Issues Releases Wiki Activity

Fixing includes in volk functions

Browse Source
This commit is contained in:
andres
2014-10-20 16:37:49 +02:00
parent 61f6e125ea
commit d3aade34b2
22 changed files with 93 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h
View File

@@ -53,7 +53,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -262,7 +262,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_generic(lv_32fc_t* E
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!

14
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h
View File

@@ -53,7 +53,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -220,7 +220,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_first(
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -459,7 +459,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_second
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -681,7 +681,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_third(
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -912,7 +912,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_fourth
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
@@ -1076,7 +1076,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_fifth(
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -1284,7 +1284,7 @@ static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_generic(lv_32fc
#include <string.h> #include <string.h>
// //
//#ifdef LV_HAVE_SSE4_1 //#ifdef LV_HAVE_SSE4_1
//#include "smmintrin.h" //#include <smmintrin.h>
///*! ///*!
// \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation // \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
// \param input The input signal input // \param input The input signal input

4
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h
View File

@@ -57,7 +57,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -331,7 +331,7 @@ static inline void volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_generic(lv_32fc_t*
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!

2
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32f_index_max_16u.h
View File

@@ -7,7 +7,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include<smmintrin.h> #include <smmintrin.h>
static inline void volk_gnsssdr_32f_index_max_16u_a_sse4_1(unsigned int* target, const float* src0, unsigned int num_points) { static inline void volk_gnsssdr_32f_index_max_16u_a_sse4_1(unsigned int* target, const float* src0, unsigned int num_points) {
if(num_points > 0){ if(num_points > 0){

4
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x2_dot_prod_32fc.h
View File

@@ -180,7 +180,6 @@ static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse_64(lv_32fc_t* result
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <pmmintrin.h> #include <pmmintrin.h>
static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) { static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) {
@@ -237,7 +236,6 @@ static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse3(lv_32fc_t* result,
#endif /*LV_HAVE_SSE3*/ #endif /*LV_HAVE_SSE3*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include <smmintrin.h> #include <smmintrin.h>
static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) { static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_u_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) {
@@ -622,7 +620,6 @@ static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse_32(lv_32fc_t* result
#endif /*LV_HAVE_SSE*/ #endif /*LV_HAVE_SSE*/
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <pmmintrin.h> #include <pmmintrin.h>
static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) { static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) {
@@ -681,7 +678,6 @@ static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse3(lv_32fc_t* result,
#endif /*LV_HAVE_SSE3*/ #endif /*LV_HAVE_SSE3*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include <smmintrin.h> #include <smmintrin.h>
static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) { static inline void volk_gnsssdr_32fc_x2_dot_prod_32fc_a_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_points) {

4
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_64f_accumulator_64f.h
View File

@@ -79,7 +79,7 @@ static inline void volk_gnsssdr_64f_accumulator_64f_u_avx(double* result,const d
#endif /* LV_HAVE_AVX */ #endif /* LV_HAVE_AVX */
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <xmmintrin.h> #include <pmmintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result
@@ -185,7 +185,7 @@ static inline void volk_gnsssdr_64f_accumulator_64f_a_avx(double* result,const d
#endif /* LV_HAVE_AVX */ #endif /* LV_HAVE_AVX */
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <xmmintrin.h> #include <pmmintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result

4
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8i_accumulator_s8i.h
View File

@@ -40,7 +40,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <xmmintrin.h> #include <pmmintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result
@@ -105,7 +105,7 @@ static inline void volk_gnsssdr_8i_accumulator_s8i_generic(char* result, const c
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <xmmintrin.h> #include <pmmintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result

13
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8i_index_max_16u.h
View File

@@ -40,7 +40,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include "immintrin.h" #include <immintrin.h>
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0
@@ -108,7 +108,7 @@ static inline void volk_gnsssdr_8i_index_max_16u_u_avx(unsigned int* target, con
#endif /*LV_HAVE_AVX*/ #endif /*LV_HAVE_AVX*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include<smmintrin.h> #include <smmintrin.h>
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0
@@ -167,7 +167,7 @@ static inline void volk_gnsssdr_8i_index_max_16u_u_sse4_1(unsigned int* target,
#endif /*LV_HAVE_SSE4_1*/ #endif /*LV_HAVE_SSE4_1*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include<xmmintrin.h> #include<emmintrin.h>
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0
@@ -270,7 +270,7 @@ static inline void volk_gnsssdr_8i_index_max_16u_generic(unsigned int* target, c
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include "immintrin.h" #include <immintrin.h>
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0
@@ -338,8 +338,7 @@ static inline void volk_gnsssdr_8i_index_max_16u_a_avx(unsigned int* target, con
#endif /*LV_HAVE_AVX*/ #endif /*LV_HAVE_AVX*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "emmintrin.h"
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0
@@ -398,7 +397,7 @@ static inline void volk_gnsssdr_8i_index_max_16u_a_sse4_1(unsigned int* target,
#endif /*LV_HAVE_SSE4_1*/ #endif /*LV_HAVE_SSE4_1*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Returns the index of the max value in src0 \brief Returns the index of the max value in src0
\param target The index of the max value in src0 \param target The index of the max value in src0

8
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8i_max_s8i.h
View File

@@ -40,7 +40,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include<smmintrin.h> #include <smmintrin.h>
/*! /*!
\brief Returns the max value in src0 \brief Returns the max value in src0
\param target The max value in src0 \param target The max value in src0
@@ -90,7 +90,7 @@ static inline void volk_gnsssdr_8i_max_s8i_u_sse4_1(char target, const char* src
#endif /*LV_HAVE_SSE4_1*/ #endif /*LV_HAVE_SSE4_1*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include<xmmintrin.h> #include<emmintrin.h>
/*! /*!
\brief Returns the max value in src0 \brief Returns the max value in src0
\param target The max value in src0 \param target The max value in src0
@@ -186,7 +186,7 @@ static inline void volk_gnsssdr_8i_max_s8i_generic(char target, const char* src0
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Returns the max value in src0 \brief Returns the max value in src0
\param target The max value in src0 \param target The max value in src0
@@ -236,7 +236,7 @@ static inline void volk_gnsssdr_8i_max_s8i_a_sse4_1(char target, const char* src
#endif /*LV_HAVE_SSE4_1*/ #endif /*LV_HAVE_SSE4_1*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Returns the max value in src0 \brief Returns the max value in src0
\param target The max value in src0 \param target The max value in src0

8
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8i_x2_add_8i.h
View File

@@ -39,7 +39,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "pmmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Adds the two input vectors and store their results in the third vector \brief Adds the two input vectors and store their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -59,8 +59,8 @@ static inline void volk_gnsssdr_8i_x2_add_8i_u_sse2(char* cVector, const char* a
for(int number = 0; number < sse_iters; number++){ for(int number = 0; number < sse_iters; number++){
aVal = _mm_lddqu_si128((__m128i*)aPtr); aVal = _mm_load_si128((__m128i*)aPtr);
bVal = _mm_lddqu_si128((__m128i*)bPtr); bVal = _mm_load_si128((__m128i*)bPtr);
cVal = _mm_add_epi8(aVal, bVal); cVal = _mm_add_epi8(aVal, bVal);
@@ -108,7 +108,7 @@ static inline void volk_gnsssdr_8i_x2_add_8i_generic(char* cVector, const char*
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "pmmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Adds the two input vectors and store their results in the third vector \brief Adds the two input vectors and store their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored

8
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_conjugate_8ic.h
View File

@@ -41,7 +41,7 @@
#include <volk_gnsssdr/volk_gnsssdr_complex.h> #include <volk_gnsssdr/volk_gnsssdr_complex.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include "immintrin.h" #include <immintrin.h>
/*! /*!
\brief Takes the conjugate of an unsigned char vector. \brief Takes the conjugate of an unsigned char vector.
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -83,7 +83,7 @@ static inline void volk_gnsssdr_8ic_conjugate_8ic_u_avx(lv_8sc_t* cVector, const
#endif /* LV_HAVE_AVX */ #endif /* LV_HAVE_AVX */
#ifdef LV_HAVE_SSSE3 #ifdef LV_HAVE_SSSE3
#include "tmmintrin.h" #include <tmmintrin.h>
/*! /*!
\brief Takes the conjugate of an unsigned char vector. \brief Takes the conjugate of an unsigned char vector.
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -181,7 +181,7 @@ static inline void volk_gnsssdr_8ic_conjugate_8ic_generic(lv_8sc_t* cVector, con
#include <volk_gnsssdr/volk_gnsssdr_complex.h> #include <volk_gnsssdr/volk_gnsssdr_complex.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include "immintrin.h" #include <immintrin.h>
/*! /*!
\brief Takes the conjugate of an unsigned char vector. \brief Takes the conjugate of an unsigned char vector.
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -223,7 +223,7 @@ static inline void volk_gnsssdr_8ic_conjugate_8ic_a_avx(lv_8sc_t* cVector, const
#endif /* LV_HAVE_AVX */ #endif /* LV_HAVE_AVX */
#ifdef LV_HAVE_SSSE3 #ifdef LV_HAVE_SSSE3
#include "tmmintrin.h" #include <tmmintrin.h>
/*! /*!
\brief Takes the conjugate of an unsigned char vector. \brief Takes the conjugate of an unsigned char vector.
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored

13
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_magnitude_squared_8i.h
View File

@@ -41,9 +41,8 @@
#include <stdio.h> #include <stdio.h>
#include <math.h> #include <math.h>
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSSE3
#include <pmmintrin.h> #include <tmmintrin.h>
#include "tmmintrin.h"
/*! /*!
\brief Calculates the magnitude squared of complexVector and stores the results in magnitudeVector \brief Calculates the magnitude squared of complexVector and stores the results in magnitudeVector
\param complexVector The vector containing the complex input values \param complexVector The vector containing the complex input values
@@ -101,7 +100,7 @@ static inline void volk_gnsssdr_8ic_magnitude_squared_8i_u_sse3(char* magnitudeV
*magnitudeVectorPtr++ = (valReal * valReal) + (valImag * valImag); *magnitudeVectorPtr++ = (valReal * valReal) + (valImag * valImag);
} }
} }
#endif /* LV_HAVE_SSE3 */ #endif /* LV_HAVE_SSSE3 */
//#ifdef LV_HAVE_SSE //#ifdef LV_HAVE_SSE
//#include <xmmintrin.h> //#include <xmmintrin.h>
@@ -178,8 +177,8 @@ static inline void volk_gnsssdr_8ic_magnitude_squared_8i_generic(char* magnitude
#include <stdio.h> #include <stdio.h>
#include <math.h> #include <math.h>
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSSE3
#include <pmmintrin.h> #include <tmmintrin.h>
/*! /*!
\brief Calculates the magnitude squared of complexVector and stores the results in magnitudeVector \brief Calculates the magnitude squared of complexVector and stores the results in magnitudeVector
\param complexVector The vector containing the complex input values \param complexVector The vector containing the complex input values
@@ -237,7 +236,7 @@ static inline void volk_gnsssdr_8ic_magnitude_squared_8i_a_sse3(char* magnitudeV
*magnitudeVectorPtr++ = (valReal * valReal) + (valImag * valImag); *magnitudeVectorPtr++ = (valReal * valReal) + (valImag * valImag);
} }
} }
#endif /* LV_HAVE_SSE3 */ #endif /* LV_HAVE_SSSE3 */
//#ifdef LV_HAVE_SSE //#ifdef LV_HAVE_SSE
//#include <xmmintrin.h> //#include <xmmintrin.h>

12
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x2_dot_prod_8ic.h
View File

@@ -91,7 +91,7 @@ static inline void volk_gnsssdr_8ic_x2_dot_prod_8ic_generic(lv_8sc_t* result, co
#endif /*LV_HAVE_GENERIC*/ #endif /*LV_HAVE_GENERIC*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector \brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector
\param cVector The vector where the accumulated result will be stored \param cVector The vector where the accumulated result will be stored
@@ -119,8 +119,8 @@ static inline void volk_gnsssdr_8ic_x2_dot_prod_8ic_u_sse2(lv_8sc_t* result, con
for(int number = 0; number < sse_iters; number++){ for(int number = 0; number < sse_iters; number++){
x = _mm_lddqu_si128((__m128i*)a); x = _mm_load_si128((__m128i*)a);
y = _mm_lddqu_si128((__m128i*)b); y = _mm_load_si128((__m128i*)b);
imagx = _mm_srli_si128 (x, 1); imagx = _mm_srli_si128 (x, 1);
imagx = _mm_and_si128 (imagx, mult1); imagx = _mm_and_si128 (imagx, mult1);
@@ -172,7 +172,7 @@ static inline void volk_gnsssdr_8ic_x2_dot_prod_8ic_u_sse2(lv_8sc_t* result, con
#endif /*LV_HAVE_SSE2*/ #endif /*LV_HAVE_SSE2*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector \brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector
\param cVector The vector where the accumulated result will be stored \param cVector The vector where the accumulated result will be stored
@@ -312,7 +312,7 @@ static inline void volk_gnsssdr_8ic_x2_dot_prod_8ic_a_generic(lv_8sc_t* result,
#endif /*LV_HAVE_GENERIC*/ #endif /*LV_HAVE_GENERIC*/
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector \brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector
\param cVector The vector where the accumulated result will be stored \param cVector The vector where the accumulated result will be stored
@@ -393,7 +393,7 @@ static inline void volk_gnsssdr_8ic_x2_dot_prod_8ic_a_sse2(lv_8sc_t* result, con
#endif /*LV_HAVE_SSE2*/ #endif /*LV_HAVE_SSE2*/
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector \brief Multiplies the two input complex vectors and accumulates them, storing the result in the third vector
\param cVector The vector where the accumulated result will be stored \param cVector The vector where the accumulated result will be stored

12
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x2_multiply_8ic.h
View File

@@ -41,7 +41,7 @@
#include <volk_gnsssdr/volk_gnsssdr_complex.h> #include <volk_gnsssdr/volk_gnsssdr_complex.h>
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and stores their results in the third vector \brief Multiplies the two input complex vectors and stores their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -62,8 +62,8 @@ static inline void volk_gnsssdr_8ic_x2_multiply_8ic_u_sse2(lv_8sc_t* cVector, co
for(int number = 0;number < sse_iters; number++){ for(int number = 0;number < sse_iters; number++){
x = _mm_lddqu_si128((__m128i*)a); x = _mm_load_si128((__m128i*)a);
y = _mm_lddqu_si128((__m128i*)b); y = _mm_load_si128((__m128i*)b);
imagx = _mm_srli_si128 (x, 1); imagx = _mm_srli_si128 (x, 1);
imagx = _mm_and_si128 (imagx, mult1); imagx = _mm_and_si128 (imagx, mult1);
@@ -101,7 +101,7 @@ static inline void volk_gnsssdr_8ic_x2_multiply_8ic_u_sse2(lv_8sc_t* cVector, co
#endif /* LV_HAVE_SSE2 */ #endif /* LV_HAVE_SSE2 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and stores their results in the third vector \brief Multiplies the two input complex vectors and stores their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -190,7 +190,7 @@ static inline void volk_gnsssdr_8ic_x2_multiply_8ic_generic(lv_8sc_t* cVector, c
#include <volk_gnsssdr/volk_gnsssdr_complex.h> #include <volk_gnsssdr/volk_gnsssdr_complex.h>
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and stores their results in the third vector \brief Multiplies the two input complex vectors and stores their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored
@@ -250,7 +250,7 @@ static inline void volk_gnsssdr_8ic_x2_multiply_8ic_a_sse2(lv_8sc_t* cVector, co
#endif /* LV_HAVE_SSE2 */ #endif /* LV_HAVE_SSE2 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Multiplies the two input complex vectors and stores their results in the third vector \brief Multiplies the two input complex vectors and stores their results in the third vector
\param cVector The vector where the results will be stored \param cVector The vector where the results will be stored

18
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h
View File

@@ -54,7 +54,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -171,7 +171,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse4_1(lv_32fc_t* E
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -222,8 +222,8 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse2(lv_32fc_t* E_o
for(int number = 0;number < sse_iters; number++){ for(int number = 0;number < sse_iters; number++){
//Perform the carrier wipe-off //Perform the carrier wipe-off
x = _mm_lddqu_si128((__m128i*)input_ptr); x = _mm_load_si128((__m128i*)input_ptr);
y = _mm_lddqu_si128((__m128i*)carrier_ptr); y = _mm_load_si128((__m128i*)carrier_ptr);
CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx) CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy) CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
@@ -231,7 +231,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse2(lv_32fc_t* E_o
CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample) CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
//Get early values //Get early values
y = _mm_lddqu_si128((__m128i*)E_code_ptr); y = _mm_load_si128((__m128i*)E_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -239,7 +239,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse2(lv_32fc_t* E_o
E_code_acc = _mm_add_ps (E_code_acc, output_ps_2); E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
//Get prompt values //Get prompt values
y = _mm_lddqu_si128((__m128i*)P_code_ptr); y = _mm_load_si128((__m128i*)P_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -247,7 +247,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse2(lv_32fc_t* E_o
P_code_acc = _mm_add_ps (P_code_acc, output_ps_2); P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
//Get late values //Get late values
y = _mm_lddqu_si128((__m128i*)L_code_ptr); y = _mm_load_si128((__m128i*)L_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -339,7 +339,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_generic(lv_32fc_t* E_
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -456,7 +456,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_sse4_1(lv_32fc_t* E
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!

18
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h
View File

@@ -53,7 +53,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -220,7 +220,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse4_1(lv_8sc_t* E_o
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -268,8 +268,8 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse2(lv_8sc_t* E_out
for(int number = 0;number < sse_iters; number++){ for(int number = 0;number < sse_iters; number++){
//Perform the carrier wipe-off //Perform the carrier wipe-off
x = _mm_lddqu_si128((__m128i*)input_ptr); x = _mm_load_si128((__m128i*)input_ptr);
y = _mm_lddqu_si128((__m128i*)carrier_ptr); y = _mm_load_si128((__m128i*)carrier_ptr);
imagx = _mm_srli_si128 (x, 1); imagx = _mm_srli_si128 (x, 1);
imagx = _mm_and_si128 (imagx, mult1); imagx = _mm_and_si128 (imagx, mult1);
@@ -288,7 +288,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse2(lv_8sc_t* E_out
imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy); imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
//Get early values //Get early values
y = _mm_lddqu_si128((__m128i*)E_code_ptr); y = _mm_load_si128((__m128i*)E_code_ptr);
imagy = _mm_srli_si128 (y, 1); imagy = _mm_srli_si128 (y, 1);
imagy = _mm_and_si128 (imagy, mult1); imagy = _mm_and_si128 (imagy, mult1);
@@ -306,7 +306,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse2(lv_8sc_t* E_out
imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output); imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output);
//Get late values //Get late values
y = _mm_lddqu_si128((__m128i*)L_code_ptr); y = _mm_load_si128((__m128i*)L_code_ptr);
imagy = _mm_srli_si128 (y, 1); imagy = _mm_srli_si128 (y, 1);
imagy = _mm_and_si128 (imagy, mult1); imagy = _mm_and_si128 (imagy, mult1);
@@ -324,7 +324,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse2(lv_8sc_t* E_out
imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output); imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output);
//Get prompt values //Get prompt values
y = _mm_lddqu_si128((__m128i*)P_code_ptr); y = _mm_load_si128((__m128i*)P_code_ptr);
imagy = _mm_srli_si128 (y, 1); imagy = _mm_srli_si128 (y, 1);
imagy = _mm_and_si128 (imagy, mult1); imagy = _mm_and_si128 (imagy, mult1);
@@ -441,7 +441,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_generic(lv_8sc_t* E_ou
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input
@@ -608,7 +608,7 @@ static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_sse4_1(lv_8sc_t* E_o
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
\param input The input signal input \param input The input signal input

22
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h
View File

@@ -73,7 +73,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -226,7 +226,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse4_1(lv_32fc_t*
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -289,8 +289,8 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
for(int number = 0;number < sse_iters; number++){ for(int number = 0;number < sse_iters; number++){
//Perform the carrier wipe-off //Perform the carrier wipe-off
x = _mm_lddqu_si128((__m128i*)input_ptr); x = _mm_load_si128((__m128i*)input_ptr);
y = _mm_lddqu_si128((__m128i*)carrier_ptr); y = _mm_load_si128((__m128i*)carrier_ptr);
CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx) CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy) CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
@@ -298,7 +298,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample) CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
//Get very early values //Get very early values
y = _mm_lddqu_si128((__m128i*)VE_code_ptr); y = _mm_load_si128((__m128i*)VE_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -306,7 +306,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2); VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2);
//Get early values //Get early values
y = _mm_lddqu_si128((__m128i*)E_code_ptr); y = _mm_load_si128((__m128i*)E_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -314,7 +314,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
E_code_acc = _mm_add_ps (E_code_acc, output_ps_2); E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
//Get prompt values //Get prompt values
y = _mm_lddqu_si128((__m128i*)P_code_ptr); y = _mm_load_si128((__m128i*)P_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -322,7 +322,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
P_code_acc = _mm_add_ps (P_code_acc, output_ps_2); P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
//Get late values //Get late values
y = _mm_lddqu_si128((__m128i*)L_code_ptr); y = _mm_load_si128((__m128i*)L_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -330,7 +330,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE
L_code_acc = _mm_add_ps (L_code_acc, output_ps_2); L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
//Get very late values //Get very late values
y = _mm_lddqu_si128((__m128i*)VL_code_ptr); y = _mm_load_si128((__m128i*)VL_code_ptr);
CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2) CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
@@ -440,7 +440,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_generic(lv_32fc_t* V
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -593,7 +593,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_sse4_1(lv_32fc_t*
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE2 #ifdef LV_HAVE_SSE2
#include "emmintrin.h" #include <emmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!

10
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h
View File

@@ -58,7 +58,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -362,7 +362,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_first(
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -647,7 +647,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_second
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -937,7 +937,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_third(
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -1239,8 +1239,6 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_fourth
#ifdef LV_HAVE_GENERIC #ifdef LV_HAVE_GENERIC
#include <stdio.h>
#include <tmmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation

8
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h
View File

@@ -70,7 +70,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -315,8 +315,6 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_u_sse4_1(lv_32f
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_GENERIC #ifdef LV_HAVE_GENERIC
#include <stdio.h>
#include <tmmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
@@ -426,7 +424,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_generic(lv_32fc
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -671,8 +669,6 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_sse4_1(lv_32f
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_GENERIC #ifdef LV_HAVE_GENERIC
#include <stdio.h>
#include <tmmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation

8
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h
View File

@@ -70,7 +70,7 @@
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -262,8 +262,6 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_u_sse4_1(lv_3
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_GENERIC #ifdef LV_HAVE_GENERIC
#include <stdio.h>
#include <tmmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
@@ -317,7 +315,7 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_generic(lv_32
#include <string.h> #include <string.h>
#ifdef LV_HAVE_SSE4_1 #ifdef LV_HAVE_SSE4_1
#include "smmintrin.h" #include <smmintrin.h>
#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h" #include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
#include "CommonMacros/CommonMacros.h" #include "CommonMacros/CommonMacros.h"
/*! /*!
@@ -509,8 +507,6 @@ static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_sse4_1(lv_3
#endif /* LV_HAVE_SSE4_1 */ #endif /* LV_HAVE_SSE4_1 */
#ifdef LV_HAVE_GENERIC #ifdef LV_HAVE_GENERIC
#include <stdio.h>
#include <tmmintrin.h>
/*! /*!
\brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation

3
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8u_x2_multiply_8u.h
View File

@@ -40,7 +40,6 @@
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <pmmintrin.h> #include <pmmintrin.h>
#include <emmintrin.h>
/*! /*!
\brief Multiplies the two input unsigned char values and stores their results in the third unisgned char \brief Multiplies the two input unsigned char values and stores their results in the third unisgned char
\param cChar The unsigned char where the results will be stored \param cChar The unsigned char where the results will be stored
@@ -122,7 +121,7 @@ static inline void volk_gnsssdr_8u_x2_multiply_8u_generic(unsigned char* cChar,
#ifdef LV_HAVE_SSE3 #ifdef LV_HAVE_SSE3
#include <pmmintrin.h> #include <pmmintrin.h>
#include <emmintrin.h>
/*! /*!
\brief Multiplies the two input unsigned char values and stores their results in the third unisgned char \brief Multiplies the two input unsigned char values and stores their results in the third unisgned char
\param cChar The unsigned char where the results will be stored \param cChar The unsigned char where the results will be stored

6
src/algorithms/libs/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_s32f_x2_update_local_carrier_32fc.h
View File

@@ -70,7 +70,7 @@
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include <tmmintrin.h> #include <immintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result
@@ -264,7 +264,7 @@ static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_u_avx(lv_32fc_
if (num_points%8!=0) if (num_points%8!=0)
{ {
__VOLK_ATTR_ALIGNED(32) float phase_rad_store[8]; __VOLK_ATTR_ALIGNED(32) float phase_rad_store[8];
_mm256_storeu_si256 ((float*)phase_rad_store, phase_rad_array); _mm256_storeu_si256 ((__m256i*)phase_rad_store, phase_rad_array);
float phase_rad = phase_rad_store[0]; float phase_rad = phase_rad_store[0];
@@ -472,7 +472,7 @@ static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_generic(lv_32f
#include <stdio.h> #include <stdio.h>
#ifdef LV_HAVE_AVX #ifdef LV_HAVE_AVX
#include <tmmintrin.h> #include <immintrin.h>
/*! /*!
\brief Accumulates the values in the input buffer \brief Accumulates the values in the input buffer
\param result The accumulated result \param result The accumulated result