87 files changed, 562 insertions, 539 deletions

diff --git a/volk/include/volk/Makefile.am b/volk/include/volk/Makefile.am
index aef1d7ba8..43c8ae9df 100644
--- a/volk/include/volk/Makefile.am
+++ b/volk/include/volk/Makefile.am
@@ -41,93 +41,93 @@ volkinclude_HEADERS = \
 	volk.h \
 	volk_cpu.h \
 	volk_environment_init.h \
-	volk_16s_add_quad_a16.h \
-	volk_16s_branch_4_state_8_a16.h \
-	volk_16sc_deinterleave_16s_16s_a16.h \
-	volk_16sc_s32f_deinterleave_32f_32f_a16.h \
-	volk_16sc_deinterleave_real_16s_a16.h \
-	volk_16sc_s32f_deinterleave_real_32f_a16.h \
-	volk_16sc_deinterleave_real_8s_a16.h \
-	volk_16sc_magnitude_16s_a16.h \
-	volk_16sc_s32f_magnitude_32f_a16.h \
-	volk_16s_s32f_convert_32f_a16.h \
-	volk_16s_s32f_convert_32f_ua16.h \
-	volk_16s_convert_8s_a16.h \
-	volk_16s_convert_8s_ua16.h \
-	volk_16s_max_star_16s_a16.h \
-	volk_16s_max_star_horizontal_16s_a16.h \
-	volk_16s_permute_and_scalar_add_a16.h \
-	volk_16s_quad_max_star_16s_a16.h \
+	volk_16i_x5_add_quad_16i_x4_a16.h \
+	volk_16i_branch_4_state_8_a16.h \
+	volk_16ic_deinterleave_16i_x2_a16.h \
+	volk_16ic_s32f_deinterleave_32f_x2_a16.h \
+	volk_16ic_deinterleave_real_16i_a16.h \
+	volk_16ic_s32f_deinterleave_real_32f_a16.h \
+	volk_16ic_deinterleave_real_8i_a16.h \
+	volk_16ic_magnitude_16i_a16.h \
+	volk_16ic_s32f_magnitude_32f_a16.h \
+	volk_16i_s32f_convert_32f_a16.h \
+	volk_16i_s32f_convert_32f_u.h \
+	volk_16i_convert_8i_a16.h \
+	volk_16i_convert_8i_u.h \
+	volk_16i_max_star_16i_a16.h \
+	volk_16i_max_star_horizontal_16i_a16.h \
+	volk_16i_permute_and_scalar_add_a16.h \
+	volk_16i_x4_quad_max_star_16i_a16.h \
 	volk_16u_byteswap_a16.h \
 	volk_32f_accumulator_s32f_a16.h \
-	volk_32f_32f_add_32f_a16.h \
+	volk_32f_x2_add_32f_a16.h \
 	volk_32fc_32f_multiply_32fc_a16.h \
 	volk_32fc_32f_power_32fc_a16.h \
 	volk_32f_calc_spectral_noise_floor_a16.h \
 	volk_32fc_s32f_atan2_32f_a16.h \
-	volk_32fc_32fc_conjugate_dot_prod_32fc_a16.h \
-	volk_32fc_deinterleave_32f_32f_a16.h \
-	volk_32fc_deinterleave_64f_64f_a16.h \
-	volk_32fc_deinterleave_real_16s_a16.h \
+	volk_32fc_x2_conjugate_dot_prod_32fc_a16.h \
+	volk_32fc_deinterleave_32f_x2_a16.h \
+	volk_32fc_deinterleave_64f_x2_a16.h \
+	volk_32fc_deinterleave_real_16i_a16.h \
 	volk_32fc_deinterleave_real_32f_a16.h \
 	volk_32fc_deinterleave_real_64f_a16.h \
-	volk_32fc_32fc_dot_prod_32fc_a16.h \
+	volk_32fc_x2_dot_prod_32fc_a16.h \
 	volk_32fc_index_max_16u_a16.h \
-	volk_32fc_s32f_magnitude_16s_a16.h \
+	volk_32fc_s32f_magnitude_16i_a16.h \
 	volk_32fc_magnitude_32f_a16.h \
-	volk_32fc_32fc_multiply_32fc_a16.h \
-	volk_32f_s32f_convert_16s_a16.h \
-	volk_32f_s32f_convert_16s_ua16.h \
-	volk_32f_s32f_convert_32s_a16.h \
-	volk_32f_s32f_convert_32s_ua16.h \
+	volk_32fc_x2_multiply_32fc_a16.h \
+	volk_32f_s32f_convert_16i_a16.h \
+	volk_32f_s32f_convert_16i_u.h \
+	volk_32f_s32f_convert_32i_a16.h \
+	volk_32f_s32f_convert_32i_u.h \
 	volk_32f_convert_64f_a16.h \
-	volk_32f_convert_64f_ua16.h \
-	volk_32f_s32f_convert_8s_a16.h \
-	volk_32f_s32f_convert_8s_ua16.h \
-	volk_32fc_s32f_s32f_power_spectral_density_32f_a16.h \
+	volk_32f_convert_64f_u.h \
+	volk_32f_s32f_convert_8i_a16.h \
+	volk_32f_s32f_convert_8i_u.h \
+	volk_32fc_s32f_x2_power_spectral_density_32f_a16.h \
 	volk_32fc_s32f_power_spectrum_32f_a16.h \
-	volk_32fc_32fc_square_dist_32f_a16.h \
-	volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16.h \
-	volk_32f_32f_divide_32f_a16.h \
-	volk_32f_32f_dot_prod_32f_a16.h \
-	volk_32f_32f_dot_prod_32f_ua16.h \
+	volk_32fc_x2_square_dist_32f_a16.h \
+	volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16.h \
+	volk_32f_x2_divide_32f_a16.h \
+	volk_32f_x2_dot_prod_32f_a16.h \
+	volk_32f_x2_dot_prod_32f_u.h \
 	volk_32f_s32f_32f_fm_detect_32f_a16.h \
 	volk_32f_index_max_16u_a16.h \
-	volk_32f_32f_s32f_interleave_16sc_a16.h \
-	volk_32f_32f_interleave_32fc_a16.h \
-	volk_32f_32f_max_32f_a16.h \
-	volk_32f_32f_min_32f_a16.h \
-	volk_32f_32f_multiply_32f_a16.h \
+	volk_32f_x2_s32f_interleave_16ic_a16.h \
+	volk_32f_x2_interleave_32fc_a16.h \
+	volk_32f_x2_max_32f_a16.h \
+	volk_32f_x2_min_32f_a16.h \
+	volk_32f_x2_multiply_32f_a16.h \
 	volk_32f_s32f_normalize_a16.h \
 	volk_32f_s32f_power_32f_a16.h \
 	volk_32f_sqrt_32f_a16.h \
 	volk_32f_s32f_stddev_32f_a16.h \
-	volk_32f_stddev_and_mean_32f_32f_a16.h \
-	volk_32f_32f_subtract_32f_a16.h \
-	volk_32f_32f_32f_sum_of_poly_32f_a16.h \
-	volk_32s_32s_and_32s_a16.h \
-	volk_32s_s32f_convert_32f_a16.h \
-	volk_32s_s32f_convert_32f_ua16.h \
-	volk_32s_32s_or_32s_a16.h \
+	volk_32f_stddev_and_mean_32f_x2_a16.h \
+	volk_32f_x2_subtract_32f_a16.h \
+	volk_32f_x3_sum_of_poly_32f_a16.h \
+	volk_32i_x2_and_32i_a16.h \
+	volk_32i_s32f_convert_32f_a16.h \
+	volk_32i_s32f_convert_32f_u.h \
+	volk_32i_x2_or_32i_a16.h \
 	volk_32u_byteswap_a16.h \
 	volk_32u_popcnt_a16.h \
 	volk_64f_convert_32f_a16.h \
-	volk_64f_convert_32f_ua16.h \
-	volk_64f_64f_max_64f_a16.h \
-	volk_64f_64f_min_64f_a16.h \
+	volk_64f_convert_32f_u.h \
+	volk_64f_x2_max_64f_a16.h \
+	volk_64f_x2_min_64f_a16.h \
 	volk_64u_byteswap_a16.h \
 	volk_64u_popcnt_a16.h \
-	volk_8sc_deinterleave_16s_16s_a16.h \
-	volk_8sc_s32f_deinterleave_32f_32f_a16.h \
-	volk_8sc_deinterleave_real_16s_a16.h \
-	volk_8sc_s32f_deinterleave_real_32f_a16.h \
-	volk_8sc_deinterleave_real_8s_a16.h \
-	volk_8sc_8sc_multiply_conjugate_16sc_a16.h \
-	volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16.h \
-	volk_8s_convert_16s_a16.h \
-	volk_8s_convert_16s_ua16.h \
-	volk_8s_s32f_convert_32f_a16.h \
-	volk_8s_s32f_convert_32f_ua16.h 
+	volk_8ic_deinterleave_16i_x2_a16.h \
+	volk_8ic_s32f_deinterleave_32f_x2_a16.h \
+	volk_8ic_deinterleave_real_16i_a16.h \
+	volk_8ic_s32f_deinterleave_real_32f_a16.h \
+	volk_8ic_deinterleave_real_8i_a16.h \
+	volk_8ic_x2_multiply_conjugate_16ic_a16.h \
+	volk_8ic_x2_s32f_multiply_conjugate_32fc_a16.h \
+	volk_8i_convert_16i_a16.h \
+	volk_8i_convert_16i_u.h \
+	volk_8i_s32f_convert_32f_a16.h \
+	volk_8i_s32f_convert_32f_u.h 
 
 VOLK_MKTABLES_SOURCES = \
 	$(top_srcdir)/lib/volk_rank_archs.c \
diff --git a/volk/include/volk/make_c.py b/volk/include/volk/make_c.py
index f708ba7d0..6e75067d0 100644
--- a/volk/include/volk/make_c.py
+++ b/volk/include/volk/make_c.py
@@ -24,7 +24,7 @@ def make_c(funclist, taglist, arched_arglist, retlist, my_arglist, fcountlist) :
     tempstring = tempstring + "    }\n"
     tempstring = tempstring + "    return 0;\n"
     tempstring = tempstring + "}\n"
-    
+
     for i in range(len(funclist)): 
         tempstring = tempstring + "static const " + replace_volk.sub("p", funclist[i]) + " " + funclist[i] + "_archs[] = {\n";
         
diff --git a/volk/include/volk/volk_16s_branch_4_state_8_a16.h b/volk/include/volk/volk_16i_branch_4_state_8_a16.h
index 4c1af8729..3437c1a6b 100644
--- a/volk/include/volk/volk_16s_branch_4_state_8_a16.h
+++ b/volk/include/volk/volk_16i_branch_4_state_8_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_branch_4_state_8_a16_H
-#define INCLUDED_volk_16s_branch_4_state_8_a16_H
+#ifndef INCLUDED_volk_16i_branch_4_state_8_a16_H
+#define INCLUDED_volk_16i_branch_4_state_8_a16_H
 
 
 #include<inttypes.h>
@@ -14,7 +14,7 @@
 #include<emmintrin.h>
 #include<tmmintrin.h>
 
-static inline  void volk_16s_branch_4_state_8_a16_ssse3(short* target,  short* src0, char** permuters, short* cntl2, short* cntl3, short* scalars) {
+static inline  void volk_16i_branch_4_state_8_a16_ssse3(short* target,  short* src0, char** permuters, short* cntl2, short* cntl3, short* scalars) {
 	
   
   __m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8, xmm9, xmm10, xmm11;
@@ -138,7 +138,7 @@ static inline  void volk_16s_branch_4_state_8_a16_ssse3(short* target,  short* s
 #endif /*LV_HAVE_SSEs*/
 
 #if LV_HAVE_GENERIC
-static inline  void volk_16s_branch_4_state_8_a16_generic(short* target,  short* src0, char** permuters, short* cntl2, short* cntl3, short* scalars) {
+static inline  void volk_16i_branch_4_state_8_a16_generic(short* target,  short* src0, char** permuters, short* cntl2, short* cntl3, short* scalars) {
 	int i = 0;
 	
 	int bound = 4;
@@ -191,4 +191,4 @@ static inline  void volk_16s_branch_4_state_8_a16_generic(short* target,  short*
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_16s_branch_4_state_8_a16_H*/
+#endif /*INCLUDED_volk_16i_branch_4_state_8_a16_H*/
diff --git a/volk/include/volk/volk_16s_convert_8s_a16.h b/volk/include/volk/volk_16i_convert_8i_a16.h
index 13db435de..73e45ad63 100644
--- a/volk/include/volk/volk_16s_convert_8s_a16.h
+++ b/volk/include/volk/volk_16i_convert_8i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_convert_8s_a16_H
-#define INCLUDED_volk_16s_convert_8s_a16_H
+#ifndef INCLUDED_volk_16i_convert_8i_a16_H
+#define INCLUDED_volk_16i_convert_8i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
   \param outputVector The 8 bit output data buffer
   \param num_points The number of data values to be converted
 */
-static inline void volk_16s_convert_8s_a16_sse2(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
+static inline void volk_16i_convert_8i_a16_sse2(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
     
@@ -52,7 +52,7 @@ static inline void volk_16s_convert_8s_a16_sse2(int8_t* outputVector, const int1
   \param outputVector The 8 bit output data buffer
   \param num_points The number of data values to be converted
 */
-static inline void volk_16s_convert_8s_a16_generic(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
+static inline void volk_16i_convert_8i_a16_generic(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
   int8_t* outputVectorPtr = outputVector;
   const int16_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -66,4 +66,4 @@ static inline void volk_16s_convert_8s_a16_generic(int8_t* outputVector, const i
 
 
 
-#endif /* INCLUDED_volk_16s_convert_8s_a16_H */
+#endif /* INCLUDED_volk_16i_convert_8i_a16_H */
diff --git a/volk/include/volk/volk_16s_convert_8s_ua16.h b/volk/include/volk/volk_16i_convert_8i_u.h
index 9941118ae..5fc792b56 100644
--- a/volk/include/volk/volk_16s_convert_8s_ua16.h
+++ b/volk/include/volk/volk_16i_convert_8i_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_convert_8s_ua16_H
-#define INCLUDED_volk_16s_convert_8s_ua16_H
+#ifndef INCLUDED_volk_16i_convert_8i_u_H
+#define INCLUDED_volk_16i_convert_8i_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param num_points The number of data values to be converted
   \note Input and output buffers do NOT need to be properly aligned
 */
-static inline void volk_16s_convert_8s_ua16_sse2(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
+static inline void volk_16i_convert_8i_u_sse2(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
     
@@ -54,7 +54,7 @@ static inline void volk_16s_convert_8s_ua16_sse2(int8_t* outputVector, const int
   \param num_points The number of data values to be converted
   \note Input and output buffers do NOT need to be properly aligned
 */
-static inline void volk_16s_convert_8s_ua16_generic(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
+static inline void volk_16i_convert_8i_u_generic(int8_t* outputVector, const int16_t* inputVector, unsigned int num_points){
   int8_t* outputVectorPtr = outputVector;
   const int16_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -68,4 +68,4 @@ static inline void volk_16s_convert_8s_ua16_generic(int8_t* outputVector, const
 
 
 
-#endif /* INCLUDED_volk_16s_convert_8s_ua16_H */
+#endif /* INCLUDED_volk_16i_convert_8i_u_H */
diff --git a/volk/include/volk/volk_16s_max_star_16s_a16.h b/volk/include/volk/volk_16i_max_star_16i_a16.h
index b2ec90552..ff57bd2a1 100644
--- a/volk/include/volk/volk_16s_max_star_16s_a16.h
+++ b/volk/include/volk/volk_16i_max_star_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_max_star_16s_a16_H
-#define INCLUDED_volk_16s_max_star_16s_a16_H
+#ifndef INCLUDED_volk_16i_max_star_16i_a16_H
+#define INCLUDED_volk_16i_max_star_16i_a16_H
 
 
 #include<inttypes.h>
@@ -12,7 +12,7 @@
 #include<emmintrin.h>
 #include<tmmintrin.h>
 
-static inline  void volk_16s_max_star_16s_a16_ssse3(short* target, short* src0, unsigned int num_bytes) {
+static inline  void volk_16i_max_star_16i_a16_ssse3(short* target, short* src0, unsigned int num_bytes) {
 
 
   
@@ -87,7 +87,7 @@ static inline  void volk_16s_max_star_16s_a16_ssse3(short* target, short* src0,
 
 #if LV_HAVE_GENERIC
 
-static inline void volk_16s_max_star_16s_a16_generic(short* target, short* src0, unsigned int num_bytes) {
+static inline void volk_16i_max_star_16i_a16_generic(short* target, short* src0, unsigned int num_bytes) {
 	
 	int i = 0;
 	
@@ -105,4 +105,4 @@ static inline void volk_16s_max_star_16s_a16_generic(short* target, short* src0,
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_16s_max_star_16s_a16_H*/
+#endif /*INCLUDED_volk_16i_max_star_16i_a16_H*/
diff --git a/volk/include/volk/volk_16s_max_star_horizontal_16s_a16.h b/volk/include/volk/volk_16i_max_star_horizontal_16i_a16.h
index 68994593b..695e08dbf 100644
--- a/volk/include/volk/volk_16s_max_star_horizontal_16s_a16.h
+++ b/volk/include/volk/volk_16i_max_star_horizontal_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_max_star_horizontal_16s_a16_H
-#define INCLUDED_volk_16s_max_star_horizontal_16s_a16_H
+#ifndef INCLUDED_volk_16i_max_star_horizontal_16i_a16_H
+#define INCLUDED_volk_16i_max_star_horizontal_16i_a16_H
 
 
 #include<inttypes.h>
@@ -12,7 +12,7 @@
 #include<emmintrin.h>
 #include<tmmintrin.h>
 
-static inline  void volk_16s_max_star_horizontal_16s_a16_ssse3(int16_t* target, int16_t* src0, unsigned int num_bytes) {
+static inline  void volk_16i_max_star_horizontal_16i_a16_ssse3(int16_t* target, int16_t* src0, unsigned int num_bytes) {
 
   const static uint8_t shufmask0[16] = {0x00, 0x01, 0x04, 0x05, 0x08, 0x09, 0x0c, 0x0d, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
   const static uint8_t shufmask1[16] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x01, 0x04, 0x05, 0x08, 0x09, 0x0c, 0x0d};
@@ -110,7 +110,7 @@ static inline  void volk_16s_max_star_horizontal_16s_a16_ssse3(int16_t* target,
 
 
 #if LV_HAVE_GENERIC
-static inline void volk_16s_max_star_horizontal_16s_a16_generic(int16_t* target, int16_t* src0, unsigned int num_bytes) {
+static inline void volk_16i_max_star_horizontal_16i_a16_generic(int16_t* target, int16_t* src0, unsigned int num_bytes) {
 	
 	int i = 0;
 	
@@ -127,4 +127,4 @@ static inline void volk_16s_max_star_horizontal_16s_a16_generic(int16_t* target,
 
 #endif /*LV_HAVE_GENERIC*/
 
-#endif /*INCLUDED_volk_16s_max_star_horizontal_16s_a16_H*/
+#endif /*INCLUDED_volk_16i_max_star_horizontal_16i_a16_H*/
diff --git a/volk/include/volk/volk_16s_permute_and_scalar_add_a16.h b/volk/include/volk/volk_16i_permute_and_scalar_add_a16.h
index 2e7586b57..e52a949fb 100644
--- a/volk/include/volk/volk_16s_permute_and_scalar_add_a16.h
+++ b/volk/include/volk/volk_16i_permute_and_scalar_add_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_permute_and_scalar_add_a16_H
-#define INCLUDED_volk_16s_permute_and_scalar_add_a16_H
+#ifndef INCLUDED_volk_16i_permute_and_scalar_add_a16_H
+#define INCLUDED_volk_16i_permute_and_scalar_add_a16_H
 
 
 #include<inttypes.h>
@@ -13,7 +13,7 @@
 #include<xmmintrin.h>
 #include<emmintrin.h>
 
-static inline  void volk_16s_permute_and_scalar_add_a16_sse2(short* target,  short* src0, short* permute_indexes, short* cntl0, short* cntl1, short* cntl2, short* cntl3, short* scalars, unsigned int num_bytes) {
+static inline  void volk_16i_permute_and_scalar_add_a16_sse2(short* target,  short* src0, short* permute_indexes, short* cntl0, short* cntl1, short* cntl2, short* cntl3, short* scalars, unsigned int num_bytes) {
 	
 
   __m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7;
@@ -117,7 +117,7 @@ static inline  void volk_16s_permute_and_scalar_add_a16_sse2(short* target,  sho
 
 
 #if LV_HAVE_GENERIC
-static inline void volk_16s_permute_and_scalar_add_a16_generic(short* target, short* src0, short* permute_indexes, short* cntl0, short* cntl1, short* cntl2, short* cntl3, short* scalars, unsigned int num_bytes) {
+static inline void volk_16i_permute_and_scalar_add_a16_generic(short* target, short* src0, short* permute_indexes, short* cntl0, short* cntl1, short* cntl2, short* cntl3, short* scalars, unsigned int num_bytes) {
 	
 	int i = 0;
 	
@@ -136,4 +136,4 @@ static inline void volk_16s_permute_and_scalar_add_a16_generic(short* target, sh
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_16s_permute_and_scalar_add_a16_H*/
+#endif /*INCLUDED_volk_16i_permute_and_scalar_add_a16_H*/
diff --git a/volk/include/volk/volk_16s_s32f_convert_32f_a16.h b/volk/include/volk/volk_16i_s32f_convert_32f_a16.h
index 8f9b44478..83fd26ff9 100644
--- a/volk/include/volk/volk_16s_s32f_convert_32f_a16.h
+++ b/volk/include/volk/volk_16i_s32f_convert_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_s32f_convert_32f_a16_H
-#define INCLUDED_volk_16s_s32f_convert_32f_a16_H
+#ifndef INCLUDED_volk_16i_s32f_convert_32f_a16_H
+#define INCLUDED_volk_16i_s32f_convert_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_16s_s32f_convert_32f_a16_sse4_1(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_a16_sse4_1(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int eighthPoints = num_points / 8;
     
@@ -68,7 +68,7 @@ static inline void volk_16s_s32f_convert_32f_a16_sse4_1(float* outputVector, con
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_16s_s32f_convert_32f_a16_sse(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_a16_sse(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
     
@@ -102,7 +102,7 @@ static inline void volk_16s_s32f_convert_32f_a16_sse(float* outputVector, const
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_16s_s32f_convert_32f_a16_generic(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_a16_generic(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int16_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -116,4 +116,4 @@ static inline void volk_16s_s32f_convert_32f_a16_generic(float* outputVector, co
 
 
 
-#endif /* INCLUDED_volk_16s_s32f_convert_32f_a16_H */
+#endif /* INCLUDED_volk_16i_s32f_convert_32f_a16_H */
diff --git a/volk/include/volk/volk_16s_s32f_convert_32f_ua16.h b/volk/include/volk/volk_16i_s32f_convert_32f_u.h
index ad52aea1a..8f0dd0083 100644
--- a/volk/include/volk/volk_16s_s32f_convert_32f_ua16.h
+++ b/volk/include/volk/volk_16i_s32f_convert_32f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_s32f_convert_32f_ua16_H
-#define INCLUDED_volk_16s_s32f_convert_32f_ua16_H
+#ifndef INCLUDED_volk_16i_s32f_convert_32f_u_H
+#define INCLUDED_volk_16i_s32f_convert_32f_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -15,7 +15,7 @@
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_16s_s32f_convert_32f_ua16_sse4_1(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_u_sse4_1(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int eighthPoints = num_points / 8;
     
@@ -70,7 +70,7 @@ static inline void volk_16s_s32f_convert_32f_ua16_sse4_1(float* outputVector, co
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_16s_s32f_convert_32f_ua16_sse(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_u_sse(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
     
@@ -105,7 +105,7 @@ static inline void volk_16s_s32f_convert_32f_ua16_sse(float* outputVector, const
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_16s_s32f_convert_32f_ua16_generic(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_16i_s32f_convert_32f_u_generic(float* outputVector, const int16_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int16_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -119,4 +119,4 @@ static inline void volk_16s_s32f_convert_32f_ua16_generic(float* outputVector, c
 
 
 
-#endif /* INCLUDED_volk_16s_s32f_convert_32f_ua16_H */
+#endif /* INCLUDED_volk_16i_s32f_convert_32f_u_H */
diff --git a/volk/include/volk/volk_16s_quad_max_star_16s_a16.h b/volk/include/volk/volk_16i_x4_quad_max_star_16i_a16.h
index 3e89ff963..e4ec5ab4e 100644
--- a/volk/include/volk/volk_16s_quad_max_star_16s_a16.h
+++ b/volk/include/volk/volk_16i_x4_quad_max_star_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_quad_max_star_16s_a16_H
-#define INCLUDED_volk_16s_quad_max_star_16s_a16_H
+#ifndef INCLUDED_volk_16i_x4_quad_max_star_16i_a16_H
+#define INCLUDED_volk_16i_x4_quad_max_star_16i_a16_H
 
 
 #include<inttypes.h>
@@ -13,7 +13,7 @@
 
 #include<emmintrin.h>
 
-static inline  void volk_16s_quad_max_star_16s_a16_sse2(short* target, short* src0, short* src1, short* src2, short* src3, unsigned int num_bytes) {
+static inline  void volk_16i_x4_quad_max_star_16i_a16_sse2(short* target, short* src0, short* src1, short* src2, short* src3, unsigned int num_bytes) {
 	
 
 
@@ -96,9 +96,9 @@ static inline  void volk_16s_quad_max_star_16s_a16_sse2(short* target, short* sr
 
 	/*asm volatile
 		(
-		 "volk_16s_quad_max_star_16s_a16_sse2_L1:\n\t"
+		 "volk_16i_x4_quad_max_star_16i_a16_sse2_L1:\n\t"
 		 "cmp $0, %[bound]\n\t"
-		 "je volk_16s_quad_max_star_16s_a16_sse2_END\n\t"
+		 "je volk_16i_x4_quad_max_star_16i_a16_sse2_END\n\t"
 
 		 "movaps (%[src0]), %%xmm1\n\t"
 		 "movaps (%[src1]), %%xmm2\n\t"
@@ -143,9 +143,9 @@ static inline  void volk_16s_quad_max_star_16s_a16_sse2(short* target, short* sr
 
 		 "movaps %%xmm1, (%[target])\n\t"
 		 "addw $16, %[target]\n\t"
-		 "jmp volk_16s_quad_max_star_16s_a16_sse2_L1\n\t"
+		 "jmp volk_16i_x4_quad_max_star_16i_a16_sse2_L1\n\t"
 		 
-		 "volk_16s_quad_max_star_16s_a16_sse2_END:\n\t"
+		 "volk_16i_x4_quad_max_star_16i_a16_sse2_END:\n\t"
 		 :
 		 :[bound]"r"(bound), [src0]"r"(src0), [src1]"r"(src1), [src2]"r"(src2), [src3]"r"(src3), [target]"r"(target)
 		 :
@@ -168,7 +168,7 @@ static inline  void volk_16s_quad_max_star_16s_a16_sse2(short* target, short* sr
 
 
 #if LV_HAVE_GENERIC
-static inline void volk_16s_quad_max_star_16s_a16_generic(short* target, short* src0, short* src1, short* src2, short* src3, unsigned int num_bytes) {
+static inline void volk_16i_x4_quad_max_star_16i_a16_generic(short* target, short* src0, short* src1, short* src2, short* src3, unsigned int num_bytes) {
 	
 	int i = 0;
 	
@@ -188,4 +188,4 @@ static inline void volk_16s_quad_max_star_16s_a16_generic(short* target, short*
 
 #endif /*LV_HAVE_GENERIC*/
 
-#endif /*INCLUDED_volk_16s_quad_max_star_16s_a16_H*/
+#endif /*INCLUDED_volk_16i_x4_quad_max_star_16i_a16_H*/
diff --git a/volk/include/volk/volk_16s_add_quad_a16.h b/volk/include/volk/volk_16i_x5_add_quad_16i_x4_a16.h
index 67d0c55a3..5744ca3a6 100644
--- a/volk/include/volk/volk_16s_add_quad_a16.h
+++ b/volk/include/volk/volk_16i_x5_add_quad_16i_x4_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16s_add_quad_a16_H
-#define INCLUDED_volk_16s_add_quad_a16_H
+#ifndef INCLUDED_volk_16i_x5_add_quad_16i_x4_a16_H
+#define INCLUDED_volk_16i_x5_add_quad_16i_x4_a16_H
 
 
 #include<inttypes.h>
@@ -13,7 +13,7 @@
 #include<xmmintrin.h>
 #include<emmintrin.h>
 
-static inline  void volk_16s_add_quad_a16_sse2(short* target0, short* target1, short* target2, short* target3, short* src0, short* src1, short* src2, short* src3, short* src4, unsigned int num_bytes) {
+static inline  void volk_16i_x5_add_quad_16i_x4_a16_sse2(short* target0, short* target1, short* target2, short* target3, short* src0, short* src1, short* src2, short* src3, short* src4, unsigned int num_bytes) {
   
   __m128i xmm0, xmm1, xmm2, xmm3, xmm4;
   __m128i *p_target0, *p_target1, *p_target2, *p_target3,  *p_src0, *p_src1, *p_src2, *p_src3, *p_src4;
@@ -65,9 +65,9 @@ static inline  void volk_16s_add_quad_a16_sse2(short* target0, short* target1, s
   }
     /*asm volatile
 		(
-		 ".%=volk_16s_add_quad_a16_sse2_L1:\n\t"
+		 ".%=volk_16i_x5_add_quad_16i_x4_a16_sse2_L1:\n\t"
 		 "cmp $0, %[bound]\n\t"
-		 "je .%=volk_16s_add_quad_a16_sse2_END\n\t"
+		 "je .%=volk_16i_x5_add_quad_16i_x4_a16_sse2_END\n\t"
 		 "movaps (%[src0]), %%xmm1\n\t"
 		 "movaps (%[src1]), %%xmm2\n\t"
 		 "movaps (%[src2]), %%xmm3\n\t"
@@ -91,8 +91,8 @@ static inline  void volk_16s_add_quad_a16_sse2(short* target0, short* target1, s
 		 "add $16, %[target1]\n\t"
 		 "add $16, %[target2]\n\t"
 		 "add $16, %[target3]\n\t"
-		 "jmp .%=volk_16s_add_quad_a16_sse2_L1\n\t"
-		 ".%=volk_16s_add_quad_a16_sse2_END:\n\t"
+		 "jmp .%=volk_16i_x5_add_quad_16i_x4_a16_sse2_L1\n\t"
+		 ".%=volk_16i_x5_add_quad_16i_x4_a16_sse2_END:\n\t"
 		 :
 		 :[bound]"r"(bound), [src0]"r"(src0), [src1]"r"(src1), [src2]"r"(src2), [src3]"r"(src3), [src4]"r"(src4), [target0]"r"(target0), [target1]"r"(target1), [target2]"r"(target2), [target3]"r"(target3)
 		 :"xmm1", "xmm2", "xmm3", "xmm4", "xmm5"
@@ -113,7 +113,7 @@ static inline  void volk_16s_add_quad_a16_sse2(short* target0, short* target1, s
 
 #if LV_HAVE_GENERIC
 
-static inline void volk_16s_add_quad_a16_generic(short* target0, short* target1, short* target2, short* target3, short* src0, short* src1, short* src2, short* src3, short* src4, unsigned int num_bytes) {
+static inline void volk_16i_x5_add_quad_16i_x4_a16_generic(short* target0, short* target1, short* target2, short* target3, short* src0, short* src1, short* src2, short* src3, short* src4, unsigned int num_bytes) {
 	
 	int i = 0;
 	
@@ -133,4 +133,4 @@ static inline void volk_16s_add_quad_a16_generic(short* target0, short* target1,
 
 
 
-#endif /*INCLUDED_volk_16s_add_quad_a16_H*/
+#endif /*INCLUDED_volk_16i_x5_add_quad_16i_x4_a16_H*/
diff --git a/volk/include/volk/volk_16sc_deinterleave_16s_16s_a16.h b/volk/include/volk/volk_16ic_deinterleave_16i_x2_a16.h
index 8e5da24ec..7e08bf182 100644
--- a/volk/include/volk/volk_16sc_deinterleave_16s_16s_a16.h
+++ b/volk/include/volk/volk_16ic_deinterleave_16i_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_deinterleave_16s_16s_a16_H
-#define INCLUDED_volk_16sc_deinterleave_16s_16s_a16_H
+#ifndef INCLUDED_volk_16ic_deinterleave_16i_x2_a16_H
+#define INCLUDED_volk_16ic_deinterleave_16i_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_16s_16s_a16_ssse3(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_16i_x2_a16_ssse3(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -61,7 +61,7 @@ static inline void volk_16sc_deinterleave_16s_16s_a16_ssse3(int16_t* iBuffer, in
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_16s_16s_a16_sse2(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_16i_x2_a16_sse2(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (int16_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -128,7 +128,7 @@ static inline void volk_16sc_deinterleave_16s_16s_a16_sse2(int16_t* iBuffer, int
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_16s_16s_a16_generic(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_16i_x2_a16_generic(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   const int16_t* complexVectorPtr = (const int16_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
   int16_t* qBufferPtr = qBuffer;
@@ -148,11 +148,11 @@ static inline void volk_16sc_deinterleave_16s_16s_a16_generic(int16_t* iBuffer,
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-extern void volk_16sc_deinterleave_16s_16s_a16_orc_impl(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points);
-static inline void volk_16sc_deinterleave_16s_16s_a16_orc(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
-    volk_16sc_deinterleave_16s_16s_a16_orc_impl(iBuffer, qBuffer, complexVector, num_points);
+extern void volk_16ic_deinterleave_16i_x2_a16_orc_impl(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points);
+static inline void volk_16ic_deinterleave_16i_x2_a16_orc(int16_t* iBuffer, int16_t* qBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+    volk_16ic_deinterleave_16i_x2_a16_orc_impl(iBuffer, qBuffer, complexVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_16sc_deinterleave_16s_16s_a16_H */
+#endif /* INCLUDED_volk_16ic_deinterleave_16i_x2_a16_H */
diff --git a/volk/include/volk/volk_16sc_deinterleave_real_16s_a16.h b/volk/include/volk/volk_16ic_deinterleave_real_16i_a16.h
index 068c1350c..388c00592 100644
--- a/volk/include/volk/volk_16sc_deinterleave_real_16s_a16.h
+++ b/volk/include/volk/volk_16ic_deinterleave_real_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_deinterleave_real_16s_a16_H
-#define INCLUDED_volk_16sc_deinterleave_real_16s_a16_H
+#ifndef INCLUDED_volk_16ic_deinterleave_real_16i_a16_H
+#define INCLUDED_volk_16ic_deinterleave_real_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_real_16s_a16_ssse3(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_real_16i_a16_ssse3(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (int16_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -55,7 +55,7 @@ static inline void volk_16sc_deinterleave_real_16s_a16_ssse3(int16_t* iBuffer, c
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_real_16s_a16_sse2(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_real_16i_a16_sse2(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (int16_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -103,7 +103,7 @@ static inline void volk_16sc_deinterleave_real_16s_a16_sse2(int16_t* iBuffer, co
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_real_16s_a16_generic(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_real_16i_a16_generic(int16_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (int16_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -117,4 +117,4 @@ static inline void volk_16sc_deinterleave_real_16s_a16_generic(int16_t* iBuffer,
 
 
 
-#endif /* INCLUDED_volk_16sc_deinterleave_real_16s_a16_H */
+#endif /* INCLUDED_volk_16ic_deinterleave_real_16i_a16_H */
diff --git a/volk/include/volk/volk_16sc_deinterleave_real_8s_a16.h b/volk/include/volk/volk_16ic_deinterleave_real_8i_a16.h
index afa21ebc4..437d5ab6b 100644
--- a/volk/include/volk/volk_16sc_deinterleave_real_8s_a16.h
+++ b/volk/include/volk/volk_16ic_deinterleave_real_8i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_deinterleave_real_8s_a16_H
-#define INCLUDED_volk_16sc_deinterleave_real_8s_a16_H
+#ifndef INCLUDED_volk_16ic_deinterleave_real_8i_a16_H
+#define INCLUDED_volk_16ic_deinterleave_real_8i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_real_8s_a16_ssse3(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_real_8i_a16_ssse3(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int8_t* iBufferPtr = iBuffer;
@@ -66,7 +66,7 @@ static inline void volk_16sc_deinterleave_real_8s_a16_ssse3(int8_t* iBuffer, con
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_deinterleave_real_8s_a16_generic(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_deinterleave_real_8i_a16_generic(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (int16_t*)complexVector;
   int8_t* iBufferPtr = iBuffer;
@@ -84,11 +84,11 @@ static inline void volk_16sc_deinterleave_real_8s_a16_generic(int8_t* iBuffer, c
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-extern void volk_16sc_deinterleave_real_8s_a16_orc_impl(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points);
-static inline void volk_16sc_deinterleave_real_8s_a16_orc(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
-    volk_16sc_deinterleave_real_8s_a16_orc_impl(iBuffer, complexVector, num_points);
+extern void volk_16ic_deinterleave_real_8i_a16_orc_impl(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points);
+static inline void volk_16ic_deinterleave_real_8i_a16_orc(int8_t* iBuffer, const lv_16sc_t* complexVector, unsigned int num_points){
+    volk_16ic_deinterleave_real_8i_a16_orc_impl(iBuffer, complexVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_16sc_deinterleave_real_8s_a16_H */
+#endif /* INCLUDED_volk_16ic_deinterleave_real_8i_a16_H */
diff --git a/volk/include/volk/volk_16sc_magnitude_16s_a16.h b/volk/include/volk/volk_16ic_magnitude_16i_a16.h
index d832de5fe..bdcace750 100644
--- a/volk/include/volk/volk_16sc_magnitude_16s_a16.h
+++ b/volk/include/volk/volk_16ic_magnitude_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_magnitude_16s_a16_H
-#define INCLUDED_volk_16sc_magnitude_16s_a16_H
+#ifndef INCLUDED_volk_16ic_magnitude_16i_a16_H
+#define INCLUDED_volk_16ic_magnitude_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_magnitude_16s_a16_sse3(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_magnitude_16i_a16_sse3(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
    
@@ -84,7 +84,7 @@ static inline void volk_16sc_magnitude_16s_a16_sse3(int16_t* magnitudeVector, co
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_magnitude_16s_a16_sse(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_magnitude_16i_a16_sse(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -160,7 +160,7 @@ static inline void volk_16sc_magnitude_16s_a16_sse(int16_t* magnitudeVector, con
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_magnitude_16s_a16_generic(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
+static inline void volk_16ic_magnitude_16i_a16_generic(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
   const int16_t* complexVectorPtr = (const int16_t*)complexVector;
   int16_t* magnitudeVectorPtr = magnitudeVector;
   unsigned int number = 0;
@@ -180,11 +180,11 @@ static inline void volk_16sc_magnitude_16s_a16_generic(int16_t* magnitudeVector,
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-extern void volk_16sc_magnitude_16s_a16_orc_impl(int16_t* magnitudeVector, const lv_16sc_t* complexVector, float scalar, unsigned int num_points);
-static inline void volk_16sc_magnitude_16s_a16_orc(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
-    volk_16sc_magnitude_16s_a16_orc_impl(magnitudeVector, complexVector, 32768.0, num_points);
+extern void volk_16ic_magnitude_16i_a16_orc_impl(int16_t* magnitudeVector, const lv_16sc_t* complexVector, float scalar, unsigned int num_points);
+static inline void volk_16ic_magnitude_16i_a16_orc(int16_t* magnitudeVector, const lv_16sc_t* complexVector, unsigned int num_points){
+    volk_16ic_magnitude_16i_a16_orc_impl(magnitudeVector, complexVector, 32768.0, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_16sc_magnitude_16s_a16_H */
+#endif /* INCLUDED_volk_16ic_magnitude_16i_a16_H */
diff --git a/volk/include/volk/volk_16sc_s32f_deinterleave_32f_32f_a16.h b/volk/include/volk/volk_16ic_s32f_deinterleave_32f_x2_a16.h
index 53e4253c4..606de2fc5 100644
--- a/volk/include/volk/volk_16sc_s32f_deinterleave_32f_32f_a16.h
+++ b/volk/include/volk/volk_16ic_s32f_deinterleave_32f_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_s32f_deinterleave_32f_32f_a16_H
-#define INCLUDED_volk_16sc_s32f_deinterleave_32f_32f_a16_H
+#ifndef INCLUDED_volk_16ic_s32f_deinterleave_32f_x2_a16_H
+#define INCLUDED_volk_16ic_s32f_deinterleave_32f_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param scalar The data value to be divided against each input data value of the input complex vector
     \param num_points The number of complex data values to be deinterleaved
   */
-static inline void volk_16sc_s32f_deinterleave_32f_32f_a16_sse(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_deinterleave_32f_x2_a16_sse(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
     float* iBufferPtr = iBuffer;
     float* qBufferPtr = qBuffer;
 
@@ -77,7 +77,7 @@ static inline void volk_16sc_s32f_deinterleave_32f_32f_a16_sse(float* iBuffer, f
     \param scalar The data value to be divided against each input data value of the input complex vector
     \param num_points The number of complex data values to be deinterleaved
   */
-static inline void volk_16sc_s32f_deinterleave_32f_32f_a16_generic(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_deinterleave_32f_x2_a16_generic(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   const int16_t* complexVectorPtr = (const int16_t*)complexVector;
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
@@ -98,11 +98,11 @@ static inline void volk_16sc_s32f_deinterleave_32f_32f_a16_generic(float* iBuffe
     \param scalar The data value to be divided against each input data value of the input complex vector
     \param num_points The number of complex data values to be deinterleaved
   */
-extern void volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points);
-static inline void volk_16sc_s32f_deinterleave_32f_32f_a16_orc(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
-    volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl(iBuffer, qBuffer, complexVector, scalar, num_points);
+extern void volk_16ic_s32f_deinterleave_32f_x2_a16_orc_impl(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points);
+static inline void volk_16ic_s32f_deinterleave_32f_x2_a16_orc(float* iBuffer, float* qBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+    volk_16ic_s32f_deinterleave_32f_x2_a16_orc_impl(iBuffer, qBuffer, complexVector, scalar, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_16sc_s32f_deinterleave_32f_32f_a16_H */
+#endif /* INCLUDED_volk_16ic_s32f_deinterleave_32f_x2_a16_H */
diff --git a/volk/include/volk/volk_16sc_s32f_deinterleave_real_32f_a16.h b/volk/include/volk/volk_16ic_s32f_deinterleave_real_32f_a16.h
index 7320db368..62331e496 100644
--- a/volk/include/volk/volk_16sc_s32f_deinterleave_real_32f_a16.h
+++ b/volk/include/volk/volk_16ic_s32f_deinterleave_real_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_s32f_deinterleave_real_32f_a16_H
-#define INCLUDED_volk_16sc_s32f_deinterleave_real_32f_a16_H
+#ifndef INCLUDED_volk_16ic_s32f_deinterleave_real_32f_a16_H
+#define INCLUDED_volk_16ic_s32f_deinterleave_real_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
 
   unsigned int number = 0;
@@ -61,7 +61,7 @@ static inline void volk_16sc_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffe
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_s32f_deinterleave_real_32f_a16_sse(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_deinterleave_real_32f_a16_sse(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
 
   unsigned int number = 0;
@@ -107,7 +107,7 @@ static inline void volk_16sc_s32f_deinterleave_real_32f_a16_sse(float* iBuffer,
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_16sc_s32f_deinterleave_real_32f_a16_generic(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_deinterleave_real_32f_a16_generic(float* iBuffer, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const int16_t* complexVectorPtr = (const int16_t*)complexVector;
   float* iBufferPtr = iBuffer;
@@ -122,4 +122,4 @@ static inline void volk_16sc_s32f_deinterleave_real_32f_a16_generic(float* iBuff
 
 
 
-#endif /* INCLUDED_volk_16sc_s32f_deinterleave_real_32f_a16_H */
+#endif /* INCLUDED_volk_16ic_s32f_deinterleave_real_32f_a16_H */
diff --git a/volk/include/volk/volk_16sc_s32f_magnitude_32f_a16.h b/volk/include/volk/volk_16ic_s32f_magnitude_32f_a16.h
index 649b5cc96..ae64efbeb 100644
--- a/volk/include/volk/volk_16sc_s32f_magnitude_32f_a16.h
+++ b/volk/include/volk/volk_16ic_s32f_magnitude_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_16sc_s32f_magnitude_32f_a16_H
-#define INCLUDED_volk_16sc_s32f_magnitude_32f_a16_H
+#ifndef INCLUDED_volk_16ic_s32f_magnitude_32f_a16_H
+#define INCLUDED_volk_16ic_s32f_magnitude_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param scalar The data value to be divided against each input data value of the input complex vector
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_s32f_magnitude_32f_a16_sse3(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_magnitude_32f_a16_sse3(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
   
@@ -79,7 +79,7 @@ static inline void volk_16sc_s32f_magnitude_32f_a16_sse3(float* magnitudeVector,
   \param scalar The data value to be divided against each input data value of the input complex vector
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_s32f_magnitude_32f_a16_sse(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_magnitude_32f_a16_sse(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -148,7 +148,7 @@ static inline void volk_16sc_s32f_magnitude_32f_a16_sse(float* magnitudeVector,
   \param scalar The data value to be divided against each input data value of the input complex vector
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_16sc_s32f_magnitude_32f_a16_generic(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_16ic_s32f_magnitude_32f_a16_generic(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
   const int16_t* complexVectorPtr = (const int16_t*)complexVector;
   float* magnitudeVectorPtr = magnitudeVector;
   unsigned int number = 0;
@@ -169,11 +169,11 @@ static inline void volk_16sc_s32f_magnitude_32f_a16_generic(float* magnitudeVect
   \param scalar The data value to be divided against each input data value of the input complex vector
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-extern void volk_16sc_s32f_magnitude_32f_a16_orc_impl(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points);
-static inline void volk_16sc_s32f_magnitude_32f_a16_orc(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
-    volk_16sc_s32f_magnitude_32f_a16_orc_impl(magnitudeVector, complexVector, scalar, num_points);
+extern void volk_16ic_s32f_magnitude_32f_a16_orc_impl(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points);
+static inline void volk_16ic_s32f_magnitude_32f_a16_orc(float* magnitudeVector, const lv_16sc_t* complexVector, const float scalar, unsigned int num_points){
+    volk_16ic_s32f_magnitude_32f_a16_orc_impl(magnitudeVector, complexVector, scalar, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_16sc_s32f_magnitude_32f_a16_H */
+#endif /* INCLUDED_volk_16ic_s32f_magnitude_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_convert_64f_ua16.h b/volk/include/volk/volk_32f_convert_64f_u.h
index c8de768dc..a825767de 100644
--- a/volk/include/volk/volk_32f_convert_64f_ua16.h
+++ b/volk/include/volk/volk_32f_convert_64f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_convert_64f_ua16_H
-#define INCLUDED_volk_32f_convert_64f_ua16_H
+#ifndef INCLUDED_volk_32f_convert_64f_u_H
+#define INCLUDED_volk_32f_convert_64f_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
     \param fVector The float vector values to be converted
     \param num_points The number of points in the two vectors to be converted
   */
-static inline void volk_32f_convert_64f_ua16_sse2(double* outputVector, const float* inputVector, unsigned int num_points){
+static inline void volk_32f_convert_64f_u_sse2(double* outputVector, const float* inputVector, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -53,7 +53,7 @@ static inline void volk_32f_convert_64f_ua16_sse2(double* outputVector, const fl
   \param fVector The float vector values to be converted
   \param num_points The number of points in the two vectors to be converted
 */
-static inline void volk_32f_convert_64f_ua16_generic(double* outputVector, const float* inputVector, unsigned int num_points){
+static inline void volk_32f_convert_64f_u_generic(double* outputVector, const float* inputVector, unsigned int num_points){
   double* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -67,4 +67,4 @@ static inline void volk_32f_convert_64f_ua16_generic(double* outputVector, const
 
 
 
-#endif /* INCLUDED_volk_32f_convert_64f_ua16_H */
+#endif /* INCLUDED_volk_32f_convert_64f_u_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_16s_a16.h b/volk/include/volk/volk_32f_s32f_convert_16i_a16.h
index cf51cf9c5..d6b16e336 100644
--- a/volk/include/volk/volk_32f_s32f_convert_16s_a16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_16s_a16_H
-#define INCLUDED_volk_32f_s32f_convert_16s_a16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_16i_a16_H
+#define INCLUDED_volk_32f_s32f_convert_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_16s_a16_sse2(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_a16_sse2(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int eighthPoints = num_points / 8;
@@ -53,7 +53,7 @@ static inline void volk_32f_s32f_convert_16s_a16_sse2(int16_t* outputVector, con
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_16s_a16_sse(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_a16_sse(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -93,7 +93,7 @@ static inline void volk_32f_s32f_convert_16s_a16_sse(int16_t* outputVector, cons
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_16s_a16_generic(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_a16_generic(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int16_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -107,4 +107,4 @@ static inline void volk_32f_s32f_convert_16s_a16_generic(int16_t* outputVector,
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_16s_a16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_16i_a16_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_16s_ua16.h b/volk/include/volk/volk_32f_s32f_convert_16i_u.h
index 53d159f82..4d306e53c 100644
--- a/volk/include/volk/volk_32f_s32f_convert_16s_ua16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_16i_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_16s_ua16_H
-#define INCLUDED_volk_32f_s32f_convert_16s_ua16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_16i_u_H
+#define INCLUDED_volk_32f_s32f_convert_16i_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_16s_ua16_sse2(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_u_sse2(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int eighthPoints = num_points / 8;
@@ -55,7 +55,7 @@ static inline void volk_32f_s32f_convert_16s_ua16_sse2(int16_t* outputVector, co
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_16s_ua16_sse(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_u_sse(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -96,7 +96,7 @@ static inline void volk_32f_s32f_convert_16s_ua16_sse(int16_t* outputVector, con
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_16s_ua16_generic(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_16i_u_generic(int16_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int16_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -110,4 +110,4 @@ static inline void volk_32f_s32f_convert_16s_ua16_generic(int16_t* outputVector,
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_16s_ua16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_16i_u_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_32s_a16.h b/volk/include/volk/volk_32f_s32f_convert_32i_a16.h
index 0be649418..ae874fd7b 100644
--- a/volk/include/volk/volk_32f_s32f_convert_32s_a16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_32i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_32s_a16_H
-#define INCLUDED_volk_32f_s32f_convert_32s_a16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_32i_a16_H
+#define INCLUDED_volk_32f_s32f_convert_32i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_32s_a16_sse2(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_a16_sse2(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -49,7 +49,7 @@ static inline void volk_32f_s32f_convert_32s_a16_sse2(int32_t* outputVector, con
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_32s_a16_sse(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_a16_sse(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -89,7 +89,7 @@ static inline void volk_32f_s32f_convert_32s_a16_sse(int32_t* outputVector, cons
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_32s_a16_generic(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_a16_generic(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int32_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -103,4 +103,4 @@ static inline void volk_32f_s32f_convert_32s_a16_generic(int32_t* outputVector,
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_32s_a16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_32i_a16_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_32s_ua16.h b/volk/include/volk/volk_32f_s32f_convert_32i_u.h
index efb2c3a20..561fcd800 100644
--- a/volk/include/volk/volk_32f_s32f_convert_32s_ua16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_32i_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_32s_ua16_H
-#define INCLUDED_volk_32f_s32f_convert_32s_ua16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_32i_u_H
+#define INCLUDED_volk_32f_s32f_convert_32i_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_32s_ua16_sse2(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_u_sse2(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -51,7 +51,7 @@ static inline void volk_32f_s32f_convert_32s_ua16_sse2(int32_t* outputVector, co
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_32s_ua16_sse(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_u_sse(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -92,7 +92,7 @@ static inline void volk_32f_s32f_convert_32s_ua16_sse(int32_t* outputVector, con
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_32s_ua16_generic(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_32i_u_generic(int32_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int32_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -106,4 +106,4 @@ static inline void volk_32f_s32f_convert_32s_ua16_generic(int32_t* outputVector,
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_32s_ua16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_32i_u_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_8s_a16.h b/volk/include/volk/volk_32f_s32f_convert_8i_a16.h
index 69ccec5c6..c91448951 100644
--- a/volk/include/volk/volk_32f_s32f_convert_8s_a16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_8i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_8s_a16_H
-#define INCLUDED_volk_32f_s32f_convert_8s_a16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_8i_a16_H
+#define INCLUDED_volk_32f_s32f_convert_8i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_8s_a16_sse2(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_a16_sse2(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int sixteenthPoints = num_points / 16;
@@ -60,7 +60,7 @@ static inline void volk_32f_s32f_convert_8s_a16_sse2(int8_t* outputVector, const
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_8s_a16_sse(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_a16_sse(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -100,7 +100,7 @@ static inline void volk_32f_s32f_convert_8s_a16_sse(int8_t* outputVector, const
     \param scalar The value multiplied against each point in the input buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32f_s32f_convert_8s_a16_generic(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_a16_generic(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int8_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -114,4 +114,4 @@ static inline void volk_32f_s32f_convert_8s_a16_generic(int8_t* outputVector, co
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_8s_a16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_8i_a16_H */
diff --git a/volk/include/volk/volk_32f_s32f_convert_8s_ua16.h b/volk/include/volk/volk_32f_s32f_convert_8i_u.h
index af1652b19..420693571 100644
--- a/volk/include/volk/volk_32f_s32f_convert_8s_ua16.h
+++ b/volk/include/volk/volk_32f_s32f_convert_8i_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_s32f_convert_8s_ua16_H
-#define INCLUDED_volk_32f_s32f_convert_8s_ua16_H
+#ifndef INCLUDED_volk_32f_s32f_convert_8i_u_H
+#define INCLUDED_volk_32f_s32f_convert_8i_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_8s_ua16_sse2(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_u_sse2(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int sixteenthPoints = num_points / 16;
@@ -62,7 +62,7 @@ static inline void volk_32f_s32f_convert_8s_ua16_sse2(int8_t* outputVector, cons
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_8s_ua16_sse(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_u_sse(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -103,7 +103,7 @@ static inline void volk_32f_s32f_convert_8s_ua16_sse(int8_t* outputVector, const
     \param num_points The number of data values to be converted
     \note Input buffer does NOT need to be properly aligned
   */
-static inline void volk_32f_s32f_convert_8s_ua16_generic(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32f_s32f_convert_8i_u_generic(int8_t* outputVector, const float* inputVector, const float scalar, unsigned int num_points){
   int8_t* outputVectorPtr = outputVector;
   const float* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -117,4 +117,4 @@ static inline void volk_32f_s32f_convert_8s_ua16_generic(int8_t* outputVector, c
 
 
 
-#endif /* INCLUDED_volk_32f_s32f_convert_8s_ua16_H */
+#endif /* INCLUDED_volk_32f_s32f_convert_8i_u_H */
diff --git a/volk/include/volk/volk_32f_stddev_and_mean_32f_32f_a16.h b/volk/include/volk/volk_32f_stddev_and_mean_32f_x2_a16.h
index 2ba809845..278089841 100644
--- a/volk/include/volk/volk_32f_stddev_and_mean_32f_32f_a16.h
+++ b/volk/include/volk/volk_32f_stddev_and_mean_32f_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_stddev_and_mean_32f_32f_a16_H
-#define INCLUDED_volk_32f_stddev_and_mean_32f_32f_a16_H
+#ifndef INCLUDED_volk_32f_stddev_and_mean_32f_x2_a16_H
+#define INCLUDED_volk_32f_stddev_and_mean_32f_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param inputBuffer The buffer of points to calculate the std deviation for
   \param num_points The number of values in input buffer to used in the stddev and mean calculations
 */
-static inline void volk_32f_stddev_and_mean_32f_32f_a16_sse4_1(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
+static inline void volk_32f_stddev_and_mean_32f_x2_a16_sse4_1(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
   float returnValue = 0;
   float newMean = 0;
   if(num_points > 0){
@@ -87,7 +87,7 @@ static inline void volk_32f_stddev_and_mean_32f_32f_a16_sse4_1(float* stddev, fl
   \param inputBuffer The buffer of points to calculate the std deviation for
   \param num_points The number of values in input buffer to used in the stddev and mean calculations
 */
-static inline void volk_32f_stddev_and_mean_32f_32f_a16_sse(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
+static inline void volk_32f_stddev_and_mean_32f_x2_a16_sse(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
   float returnValue = 0;
   float newMean = 0;
   if(num_points > 0){
@@ -142,7 +142,7 @@ static inline void volk_32f_stddev_and_mean_32f_32f_a16_sse(float* stddev, float
   \param inputBuffer The buffer of points to calculate the std deviation for
   \param num_points The number of values in input buffer to used in the stddev and mean calculations
 */
-static inline void volk_32f_stddev_and_mean_32f_32f_a16_generic(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
+static inline void volk_32f_stddev_and_mean_32f_x2_a16_generic(float* stddev, float* mean, const float* inputBuffer, unsigned int num_points){
   float returnValue = 0;
   float newMean = 0;
   if(num_points > 0){
@@ -166,4 +166,4 @@ static inline void volk_32f_stddev_and_mean_32f_32f_a16_generic(float* stddev, f
 
 
 
-#endif /* INCLUDED_volk_32f_stddev_and_mean_32f_32f_a16_H */
+#endif /* INCLUDED_volk_32f_stddev_and_mean_32f_x2_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_add_32f_a16.h b/volk/include/volk/volk_32f_x2_add_32f_a16.h
index ba38c310f..d0d0e0a0e 100644
--- a/volk/include/volk/volk_32f_32f_add_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_add_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_add_32f_a16_H
-#define INCLUDED_volk_32f_32f_add_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_add_32f_a16_H
+#define INCLUDED_volk_32f_x2_add_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector One of the vectors to be added
   \param num_points The number of values in aVector and bVector to be added together and stored into cVector
 */
-static inline void volk_32f_32f_add_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_add_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32f_32f_add_32f_a16_sse(float* cVector, const float* aVe
   \param bVector One of the vectors to be added
   \param num_points The number of values in aVector and bVector to be added together and stored into cVector
 */
-static inline void volk_32f_32f_add_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_add_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -71,11 +71,11 @@ static inline void volk_32f_32f_add_32f_a16_generic(float* cVector, const float*
   \param bVector One of the vectors to be added
   \param num_points The number of values in aVector and bVector to be added together and stored into cVector
 */
-extern void volk_32f_32f_add_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_add_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_add_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_add_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_add_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_add_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32f_32f_add_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_add_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_divide_32f_a16.h b/volk/include/volk/volk_32f_x2_divide_32f_a16.h
index a0995e631..d844e25b0 100644
--- a/volk/include/volk/volk_32f_32f_divide_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_divide_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_divide_32f_a16_H
-#define INCLUDED_volk_32f_32f_divide_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_divide_32f_a16_H
+#define INCLUDED_volk_32f_x2_divide_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The divisor vector
   \param num_points The number of values in aVector and bVector to be divideed together and stored into cVector
 */
-static inline void volk_32f_32f_divide_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_divide_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32f_32f_divide_32f_a16_sse(float* cVector, const float*
   \param bVector The divisor vector
   \param num_points The number of values in aVector and bVector to be divideed together and stored into cVector
 */
-static inline void volk_32f_32f_divide_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_divide_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -71,12 +71,12 @@ static inline void volk_32f_32f_divide_32f_a16_generic(float* cVector, const flo
   \param bVector The divisor vector
   \param num_points The number of values in aVector and bVector to be divideed together and stored into cVector
 */
-extern void volk_32f_32f_divide_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_divide_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_divide_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_divide_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_divide_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_divide_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
 
-#endif /* INCLUDED_volk_32f_32f_divide_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_divide_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_dot_prod_32f_a16.h b/volk/include/volk/volk_32f_x2_dot_prod_32f_a16.h
index 63f5221d3..61aa56815 100644
--- a/volk/include/volk/volk_32f_32f_dot_prod_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_dot_prod_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_dot_prod_32f_a16_H
-#define INCLUDED_volk_32f_32f_dot_prod_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_dot_prod_32f_a16_H
+#define INCLUDED_volk_32f_x2_dot_prod_32f_a16_H
 
 #include<stdio.h>
 
@@ -7,7 +7,7 @@
 #if LV_HAVE_GENERIC
 
 
-static inline void volk_32f_32f_dot_prod_32f_a16_generic(float * result, const float * input, const float * taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_a16_generic(float * result, const float * input, const float * taps, unsigned int num_points) {
 
   float dotProduct = 0;
   const float* aPtr = input;
@@ -27,7 +27,7 @@ static inline void volk_32f_32f_dot_prod_32f_a16_generic(float * result, const f
 #if LV_HAVE_SSE
 
 
-static inline void volk_32f_32f_dot_prod_32f_a16_sse( float* result, const  float* input, const  float* taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_a16_sse( float* result, const  float* input, const  float* taps, unsigned int num_points) {
   
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
@@ -77,7 +77,7 @@ static inline void volk_32f_32f_dot_prod_32f_a16_sse( float* result, const  floa
 
 #include <pmmintrin.h>
 
-static inline void volk_32f_32f_dot_prod_32f_a16_sse3(float * result, const float * input, const float * taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_a16_sse3(float * result, const float * input, const float * taps, unsigned int num_points) {
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -124,7 +124,7 @@ static inline void volk_32f_32f_dot_prod_32f_a16_sse3(float * result, const floa
 
 #include <smmintrin.h>
 
-static inline void volk_32f_32f_dot_prod_32f_a16_sse4_1(float * result, const float * input, const float* taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_a16_sse4_1(float * result, const float * input, const float* taps, unsigned int num_points) {
   unsigned int number = 0;
   const unsigned int sixteenthPoints = num_points / 16;
 
@@ -181,4 +181,4 @@ static inline void volk_32f_32f_dot_prod_32f_a16_sse4_1(float * result, const fl
 
 #endif /*LV_HAVE_SSE4_1*/
 
-#endif /*INCLUDED_volk_32f_32f_dot_prod_32f_a16_H*/
+#endif /*INCLUDED_volk_32f_x2_dot_prod_32f_a16_H*/
diff --git a/volk/include/volk/volk_32f_32f_dot_prod_32f_ua16.h b/volk/include/volk/volk_32f_x2_dot_prod_32f_u.h
index b5fa7d7a4..8469a3cea 100644
--- a/volk/include/volk/volk_32f_32f_dot_prod_32f_ua16.h
+++ b/volk/include/volk/volk_32f_x2_dot_prod_32f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_dot_prod_32f_ua16_H
-#define INCLUDED_volk_32f_32f_dot_prod_32f_ua16_H
+#ifndef INCLUDED_volk_32f_x2_dot_prod_32f_u_H
+#define INCLUDED_volk_32f_x2_dot_prod_32f_u_H
 
 #include<stdio.h>
 
@@ -7,7 +7,7 @@
 #if LV_HAVE_GENERIC
 
 
-static inline void volk_32f_32f_dot_prod_32f_ua16_generic(float * result, const float * input, const float * taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_u_generic(float * result, const float * input, const float * taps, unsigned int num_points) {
 
   float dotProduct = 0;
   const float* aPtr = input;
@@ -27,7 +27,7 @@ static inline void volk_32f_32f_dot_prod_32f_ua16_generic(float * result, const
 #if LV_HAVE_SSE
 
 
-static inline void volk_32f_32f_dot_prod_32f_ua16_sse( float* result, const  float* input, const  float* taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_u_sse( float* result, const  float* input, const  float* taps, unsigned int num_points) {
   
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
@@ -77,7 +77,7 @@ static inline void volk_32f_32f_dot_prod_32f_ua16_sse( float* result, const  flo
 
 #include <pmmintrin.h>
 
-static inline void volk_32f_32f_dot_prod_32f_ua16_sse3(float * result, const float * input, const float * taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_u_sse3(float * result, const float * input, const float * taps, unsigned int num_points) {
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -124,7 +124,7 @@ static inline void volk_32f_32f_dot_prod_32f_ua16_sse3(float * result, const flo
 
 #include <smmintrin.h>
 
-static inline void volk_32f_32f_dot_prod_32f_ua16_sse4_1(float * result, const float * input, const float* taps, unsigned int num_points) {
+static inline void volk_32f_x2_dot_prod_32f_u_sse4_1(float * result, const float * input, const float* taps, unsigned int num_points) {
   unsigned int number = 0;
   const unsigned int sixteenthPoints = num_points / 16;
 
@@ -181,4 +181,4 @@ static inline void volk_32f_32f_dot_prod_32f_ua16_sse4_1(float * result, const f
 
 #endif /*LV_HAVE_SSE4_1*/
 
-#endif /*INCLUDED_volk_32f_32f_dot_prod_32f_ua16_H*/
+#endif /*INCLUDED_volk_32f_x2_dot_prod_32f_u_H*/
diff --git a/volk/include/volk/volk_32f_32f_interleave_32fc_a16.h b/volk/include/volk/volk_32f_x2_interleave_32fc_a16.h
index 34ea93349..29c9392df 100644
--- a/volk/include/volk/volk_32f_32f_interleave_32fc_a16.h
+++ b/volk/include/volk/volk_32f_x2_interleave_32fc_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_interleave_32fc_a16_H
-#define INCLUDED_volk_32f_32f_interleave_32fc_a16_H
+#ifndef INCLUDED_volk_32f_x2_interleave_32fc_a16_H
+#define INCLUDED_volk_32f_x2_interleave_32fc_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param complexVector The complex output vector
   \param num_points The number of complex data values to be interleaved
 */
-static inline void volk_32f_32f_interleave_32fc_a16_sse(lv_32fc_t* complexVector, const float* iBuffer, const float* qBuffer, unsigned int num_points){
+static inline void volk_32f_x2_interleave_32fc_a16_sse(lv_32fc_t* complexVector, const float* iBuffer, const float* qBuffer, unsigned int num_points){
   unsigned int number = 0;
   float* complexVectorPtr = (float*)complexVector;
   const float* iBufferPtr = iBuffer;
@@ -56,7 +56,7 @@ static inline void volk_32f_32f_interleave_32fc_a16_sse(lv_32fc_t* complexVector
   \param complexVector The complex output vector
   \param num_points The number of complex data values to be interleaved
 */
-static inline void volk_32f_32f_interleave_32fc_a16_generic(lv_32fc_t* complexVector, const float* iBuffer, const float* qBuffer, unsigned int num_points){
+static inline void volk_32f_x2_interleave_32fc_a16_generic(lv_32fc_t* complexVector, const float* iBuffer, const float* qBuffer, unsigned int num_points){
   float* complexVectorPtr = (float*)complexVector;
   const float* iBufferPtr = iBuffer;
   const float* qBufferPtr = qBuffer;
@@ -72,4 +72,4 @@ static inline void volk_32f_32f_interleave_32fc_a16_generic(lv_32fc_t* complexVe
 
 
 
-#endif /* INCLUDED_volk_32f_32f_interleave_32fc_a16_H */
+#endif /* INCLUDED_volk_32f_x2_interleave_32fc_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_max_32f_a16.h b/volk/include/volk/volk_32f_x2_max_32f_a16.h
index 8ca7a5ba8..26e7f1246 100644
--- a/volk/include/volk/volk_32f_32f_max_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_max_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_max_32f_a16_H
-#define INCLUDED_volk_32f_32f_max_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_max_32f_a16_H
+#define INCLUDED_volk_32f_x2_max_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_32f_32f_max_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_max_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -53,7 +53,7 @@ static inline void volk_32f_32f_max_32f_a16_sse(float* cVector, const float* aVe
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_32f_32f_max_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_max_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -75,11 +75,11 @@ static inline void volk_32f_32f_max_32f_a16_generic(float* cVector, const float*
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-extern void volk_32f_32f_max_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_max_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_max_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_max_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_max_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_max_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32f_32f_max_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_max_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_min_32f_a16.h b/volk/include/volk/volk_32f_x2_min_32f_a16.h
index dd05988be..23bae044c 100644
--- a/volk/include/volk/volk_32f_32f_min_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_min_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_min_32f_a16_H
-#define INCLUDED_volk_32f_32f_min_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_min_32f_a16_H
+#define INCLUDED_volk_32f_x2_min_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_32f_32f_min_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_min_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -53,7 +53,7 @@ static inline void volk_32f_32f_min_32f_a16_sse(float* cVector, const float* aVe
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_32f_32f_min_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_min_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -75,11 +75,11 @@ static inline void volk_32f_32f_min_32f_a16_generic(float* cVector, const float*
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-extern void volk_32f_32f_min_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_min_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_min_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_min_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_min_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_min_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32f_32f_min_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_min_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_multiply_32f_a16.h b/volk/include/volk/volk_32f_x2_multiply_32f_a16.h
index 2d004db10..a0dcfa86e 100644
--- a/volk/include/volk/volk_32f_32f_multiply_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_multiply_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_multiply_32f_a16_H
-#define INCLUDED_volk_32f_32f_multiply_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_multiply_32f_a16_H
+#define INCLUDED_volk_32f_x2_multiply_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector One of the vectors to be multiplied
   \param num_points The number of values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_32f_32f_multiply_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_multiply_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32f_32f_multiply_32f_a16_sse(float* cVector, const float
   \param bVector One of the vectors to be multiplied
   \param num_points The number of values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_32f_32f_multiply_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_multiply_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -71,11 +71,11 @@ static inline void volk_32f_32f_multiply_32f_a16_generic(float* cVector, const f
   \param bVector One of the vectors to be multiplied
   \param num_points The number of values in aVector and bVector to be multiplied together and stored into cVector
 */
-extern void volk_32f_32f_multiply_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_multiply_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_multiply_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_multiply_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_multiply_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_multiply_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32f_32f_multiply_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_multiply_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_s32f_interleave_16sc_a16.h b/volk/include/volk/volk_32f_x2_s32f_interleave_16ic_a16.h
index 207382a19..30306774d 100644
--- a/volk/include/volk/volk_32f_32f_s32f_interleave_16sc_a16.h
+++ b/volk/include/volk/volk_32f_x2_s32f_interleave_16ic_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_s32f_interleave_16sc_a16_H
-#define INCLUDED_volk_32f_32f_s32f_interleave_16sc_a16_H
+#ifndef INCLUDED_volk_32f_x2_s32f_interleave_16ic_a16_H
+#define INCLUDED_volk_32f_x2_s32f_interleave_16ic_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param scalar The scaling value being multiplied against each data point
     \param num_points The number of complex data values to be interleaved
   */
-static inline void volk_32f_32f_s32f_interleave_16sc_a16_sse2(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
+static inline void volk_32f_x2_s32f_interleave_16ic_a16_sse2(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const float* iBufferPtr = iBuffer;
     const float* qBufferPtr = qBuffer;
@@ -72,7 +72,7 @@ static inline void volk_32f_32f_s32f_interleave_16sc_a16_sse2(lv_16sc_t* complex
     \param scalar The scaling value being multiplied against each data point
     \param num_points The number of complex data values to be interleaved
   */
-static inline void volk_32f_32f_s32f_interleave_16sc_a16_sse(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
+static inline void volk_32f_x2_s32f_interleave_16ic_a16_sse(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const float* iBufferPtr = iBuffer;
     const float* qBufferPtr = qBuffer;
@@ -136,7 +136,7 @@ static inline void volk_32f_32f_s32f_interleave_16sc_a16_sse(lv_16sc_t* complexV
     \param scalar The scaling value being multiplied against each data point
     \param num_points The number of complex data values to be interleaved
   */
-static inline void volk_32f_32f_s32f_interleave_16sc_a16_generic(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
+static inline void volk_32f_x2_s32f_interleave_16ic_a16_generic(lv_16sc_t* complexVector, const float* iBuffer, const float* qBuffer, const float scalar, unsigned int num_points){
   int16_t* complexVectorPtr = (int16_t*)complexVector;
   const float* iBufferPtr = iBuffer;
   const float* qBufferPtr = qBuffer;
@@ -152,4 +152,4 @@ static inline void volk_32f_32f_s32f_interleave_16sc_a16_generic(lv_16sc_t* comp
 
 
 
-#endif /* INCLUDED_volk_32f_32f_s32f_interleave_16sc_a16_H */
+#endif /* INCLUDED_volk_32f_x2_s32f_interleave_16ic_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_subtract_32f_a16.h b/volk/include/volk/volk_32f_x2_subtract_32f_a16.h
index 9fea6aa27..7404bfe79 100644
--- a/volk/include/volk/volk_32f_32f_subtract_32f_a16.h
+++ b/volk/include/volk/volk_32f_x2_subtract_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_subtract_32f_a16_H
-#define INCLUDED_volk_32f_32f_subtract_32f_a16_H
+#ifndef INCLUDED_volk_32f_x2_subtract_32f_a16_H
+#define INCLUDED_volk_32f_x2_subtract_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The vector to be subtracted
   \param num_points The number of values in aVector and bVector to be subtracted together and stored into cVector
 */
-static inline void volk_32f_32f_subtract_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_subtract_32f_a16_sse(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32f_32f_subtract_32f_a16_sse(float* cVector, const float
   \param bVector The vector to be subtracted
   \param num_points The number of values in aVector and bVector to be subtracted together and stored into cVector
 */
-static inline void volk_32f_32f_subtract_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+static inline void volk_32f_x2_subtract_32f_a16_generic(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
     float* cPtr = cVector;
     const float* aPtr = aVector;
     const float* bPtr=  bVector;
@@ -71,11 +71,11 @@ static inline void volk_32f_32f_subtract_32f_a16_generic(float* cVector, const f
   \param bVector The vector to be subtracted
   \param num_points The number of values in aVector and bVector to be subtracted together and stored into cVector
 */
-extern void volk_32f_32f_subtract_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
-static inline void volk_32f_32f_subtract_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
-    volk_32f_32f_subtract_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32f_x2_subtract_32f_a16_orc_impl(float* cVector, const float* aVector, const float* bVector, unsigned int num_points);
+static inline void volk_32f_x2_subtract_32f_a16_orc(float* cVector, const float* aVector, const float* bVector, unsigned int num_points){
+    volk_32f_x2_subtract_32f_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32f_32f_subtract_32f_a16_H */
+#endif /* INCLUDED_volk_32f_x2_subtract_32f_a16_H */
diff --git a/volk/include/volk/volk_32f_32f_32f_sum_of_poly_32f_a16.h b/volk/include/volk/volk_32f_x3_sum_of_poly_32f_a16.h
index a0f97f94e..af9e39537 100644
--- a/volk/include/volk/volk_32f_32f_32f_sum_of_poly_32f_a16.h
+++ b/volk/include/volk/volk_32f_x3_sum_of_poly_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32f_32f_32f_sum_of_poly_32f_a16_H
-#define INCLUDED_volk_32f_32f_32f_sum_of_poly_32f_a16_H
+#ifndef INCLUDED_volk_32f_x3_sum_of_poly_32f_a16_H
+#define INCLUDED_volk_32f_x3_sum_of_poly_32f_a16_H
 
 #include<inttypes.h>
 #include<stdio.h>
@@ -13,7 +13,7 @@
 #include<xmmintrin.h>
 #include<pmmintrin.h>
 
-static inline void volk_32f_32f_32f_sum_of_poly_32f_a16_sse3(float* target, float* src0, float* center_point_array, float* cutoff, unsigned int num_bytes) {
+static inline void volk_32f_x3_sum_of_poly_32f_a16_sse3(float* target, float* src0, float* center_point_array, float* cutoff, unsigned int num_bytes) {
   
   
   float result = 0.0;
@@ -100,7 +100,7 @@ static inline void volk_32f_32f_32f_sum_of_poly_32f_a16_sse3(float* target, floa
 
 #if LV_HAVE_GENERIC
 
-static inline void volk_32f_32f_32f_sum_of_poly_32f_a16_generic(float* target, float* src0, float* center_point_array, float* cutoff, unsigned int num_bytes) {
+static inline void volk_32f_x3_sum_of_poly_32f_a16_generic(float* target, float* src0, float* center_point_array, float* cutoff, unsigned int num_bytes) {
 
 
     
@@ -148,4 +148,4 @@ static inline void volk_32f_32f_32f_sum_of_poly_32f_a16_generic(float* target, f
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_32f_32f_32f_sum_of_poly_32f_a16_H*/
+#endif /*INCLUDED_volk_32f_x3_sum_of_poly_32f_a16_H*/
diff --git a/volk/include/volk/volk_32fc_deinterleave_32f_32f_a16.h b/volk/include/volk/volk_32fc_deinterleave_32f_x2_a16.h
index 3ee579c2e..84d2576ed 100644
--- a/volk/include/volk/volk_32fc_deinterleave_32f_32f_a16.h
+++ b/volk/include/volk/volk_32fc_deinterleave_32f_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_deinterleave_32f_32f_a16_H
-#define INCLUDED_volk_32fc_deinterleave_32f_32f_a16_H
+#ifndef INCLUDED_volk_32fc_deinterleave_32f_x2_a16_H
+#define INCLUDED_volk_32fc_deinterleave_32f_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_32f_32f_a16_sse(float* iBuffer, float* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
+static inline void volk_32fc_deinterleave_32f_x2_a16_sse(float* iBuffer, float* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
   const float* complexVectorPtr = (float*)complexVector;
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
@@ -57,7 +57,7 @@ static inline void volk_32fc_deinterleave_32f_32f_a16_sse(float* iBuffer, float*
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_32f_32f_a16_generic(float* iBuffer, float* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
+static inline void volk_32fc_deinterleave_32f_x2_a16_generic(float* iBuffer, float* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
   const float* complexVectorPtr = (float*)complexVector;
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
@@ -72,4 +72,4 @@ static inline void volk_32fc_deinterleave_32f_32f_a16_generic(float* iBuffer, fl
 
 
 
-#endif /* INCLUDED_volk_32fc_deinterleave_32f_32f_a16_H */
+#endif /* INCLUDED_volk_32fc_deinterleave_32f_x2_a16_H */
diff --git a/volk/include/volk/volk_32fc_deinterleave_64f_64f_a16.h b/volk/include/volk/volk_32fc_deinterleave_64f_x2_a16.h
index 404defc36..34262a7af 100644
--- a/volk/include/volk/volk_32fc_deinterleave_64f_64f_a16.h
+++ b/volk/include/volk/volk_32fc_deinterleave_64f_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_deinterleave_64f_64f_a16_H
-#define INCLUDED_volk_32fc_deinterleave_64f_64f_a16_H
+#ifndef INCLUDED_volk_32fc_deinterleave_64f_x2_a16_H
+#define INCLUDED_volk_32fc_deinterleave_64f_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_64f_64f_a16_sse2(double* iBuffer, double* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
+static inline void volk_32fc_deinterleave_64f_x2_a16_sse2(double* iBuffer, double* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
 
     const float* complexVectorPtr = (float*)complexVector;
@@ -59,7 +59,7 @@ static inline void volk_32fc_deinterleave_64f_64f_a16_sse2(double* iBuffer, doub
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_64f_64f_a16_generic(double* iBuffer, double* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
+static inline void volk_32fc_deinterleave_64f_x2_a16_generic(double* iBuffer, double* qBuffer, const lv_32fc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const float* complexVectorPtr = (float*)complexVector;
   double* iBufferPtr = iBuffer;
@@ -75,4 +75,4 @@ static inline void volk_32fc_deinterleave_64f_64f_a16_generic(double* iBuffer, d
 
 
 
-#endif /* INCLUDED_volk_32fc_deinterleave_64f_64f_a16_H */
+#endif /* INCLUDED_volk_32fc_deinterleave_64f_x2_a16_H */
diff --git a/volk/include/volk/volk_32fc_deinterleave_real_16s_a16.h b/volk/include/volk/volk_32fc_deinterleave_real_16i_a16.h
index 53235e5f7..6042e6d62 100644
--- a/volk/include/volk/volk_32fc_deinterleave_real_16s_a16.h
+++ b/volk/include/volk/volk_32fc_deinterleave_real_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_deinterleave_real_16s_a16_H
-#define INCLUDED_volk_32fc_deinterleave_real_16s_a16_H
+#ifndef INCLUDED_volk_32fc_deinterleave_real_16i_a16_H
+#define INCLUDED_volk_32fc_deinterleave_real_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_real_16s_a16_sse(int16_t* iBuffer, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_32fc_deinterleave_real_16i_a16_sse(int16_t* iBuffer, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -62,7 +62,7 @@ static inline void volk_32fc_deinterleave_real_16s_a16_sse(int16_t* iBuffer, con
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_32fc_deinterleave_real_16s_a16_generic(int16_t* iBuffer, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_32fc_deinterleave_real_16i_a16_generic(int16_t* iBuffer, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
   const float* complexVectorPtr = (float*)complexVector;
   int16_t* iBufferPtr = iBuffer;
   unsigned int number = 0;
@@ -77,4 +77,4 @@ static inline void volk_32fc_deinterleave_real_16s_a16_generic(int16_t* iBuffer,
 
 
 
-#endif /* INCLUDED_volk_32fc_deinterleave_real_16s_a16_H */
+#endif /* INCLUDED_volk_32fc_deinterleave_real_16i_a16_H */
diff --git a/volk/include/volk/volk_32fc_s32f_magnitude_16s_a16.h b/volk/include/volk/volk_32fc_s32f_magnitude_16i_a16.h
index dc3c6741a..530359600 100644
--- a/volk/include/volk/volk_32fc_s32f_magnitude_16s_a16.h
+++ b/volk/include/volk/volk_32fc_s32f_magnitude_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_s32f_magnitude_16s_a16_H
-#define INCLUDED_volk_32fc_s32f_magnitude_16s_a16_H
+#ifndef INCLUDED_volk_32fc_s32f_magnitude_16i_a16_H
+#define INCLUDED_volk_32fc_s32f_magnitude_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_32fc_s32f_magnitude_16s_a16_sse3(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_32fc_s32f_magnitude_16i_a16_sse3(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -69,7 +69,7 @@ static inline void volk_32fc_s32f_magnitude_16s_a16_sse3(int16_t* magnitudeVecto
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_32fc_s32f_magnitude_16s_a16_sse(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_32fc_s32f_magnitude_16i_a16_sse(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -128,7 +128,7 @@ static inline void volk_32fc_s32f_magnitude_16s_a16_sse(int16_t* magnitudeVector
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-static inline void volk_32fc_s32f_magnitude_16s_a16_generic(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_32fc_s32f_magnitude_16i_a16_generic(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
   const float* complexVectorPtr = (float*)complexVector;
   int16_t* magnitudeVectorPtr = magnitudeVector;
   unsigned int number = 0;
@@ -148,11 +148,11 @@ static inline void volk_32fc_s32f_magnitude_16s_a16_generic(int16_t* magnitudeVe
   \param magnitudeVector The vector containing the real output values
   \param num_points The number of complex values in complexVector to be calculated and stored into cVector
 */
-extern void volk_32fc_s32f_magnitude_16s_a16_orc_impl(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points);
-static inline void volk_32fc_s32f_magnitude_16s_a16_orc(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
-    volk_32fc_s32f_magnitude_16s_a16_orc_impl(magnitudeVector, complexVector, scalar, num_points);
+extern void volk_32fc_s32f_magnitude_16i_a16_orc_impl(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points);
+static inline void volk_32fc_s32f_magnitude_16i_a16_orc(int16_t* magnitudeVector, const lv_32fc_t* complexVector, const float scalar, unsigned int num_points){
+    volk_32fc_s32f_magnitude_16i_a16_orc_impl(magnitudeVector, complexVector, scalar, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32fc_s32f_magnitude_16s_a16_H */
+#endif /* INCLUDED_volk_32fc_s32f_magnitude_16i_a16_H */
diff --git a/volk/include/volk/volk_32fc_s32f_s32f_power_spectral_density_32f_a16.h b/volk/include/volk/volk_32fc_s32f_x2_power_spectral_density_32f_a16.h
index 29ccdaef7..0120b5307 100644
--- a/volk/include/volk/volk_32fc_s32f_s32f_power_spectral_density_32f_a16.h
+++ b/volk/include/volk/volk_32fc_s32f_x2_power_spectral_density_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_s32f_s32f_power_spectral_density_32f_a16_H
-#define INCLUDED_volk_32fc_s32f_s32f_power_spectral_density_32f_a16_H
+#ifndef INCLUDED_volk_32fc_s32f_x2_power_spectral_density_32f_a16_H
+#define INCLUDED_volk_32fc_s32f_x2_power_spectral_density_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -20,7 +20,7 @@
   \param rbw The resolution bandwith of the fft spectrum
   \param num_points The number of fft data points
 */
-static inline void volk_32fc_s32f_s32f_power_spectral_density_32f_a16_sse3(float* logPowerOutput, const lv_32fc_t* complexFFTInput, const float normalizationFactor, const float rbw, unsigned int num_points){
+static inline void volk_32fc_s32f_x2_power_spectral_density_32f_a16_sse3(float* logPowerOutput, const lv_32fc_t* complexFFTInput, const float normalizationFactor, const float rbw, unsigned int num_points){
   const float* inputPtr = (const float*)complexFFTInput;
   float* destPtr = logPowerOutput;
   uint64_t number = 0;
@@ -103,7 +103,7 @@ static inline void volk_32fc_s32f_s32f_power_spectral_density_32f_a16_sse3(float
   \param rbw The resolution bandwith of the fft spectrum
   \param num_points The number of fft data points
 */
-static inline void volk_32fc_s32f_s32f_power_spectral_density_32f_a16_generic(float* logPowerOutput, const lv_32fc_t* complexFFTInput, const float normalizationFactor, const float rbw, unsigned int num_points){
+static inline void volk_32fc_s32f_x2_power_spectral_density_32f_a16_generic(float* logPowerOutput, const lv_32fc_t* complexFFTInput, const float normalizationFactor, const float rbw, unsigned int num_points){
   // Calculate the Power of the complex point
   const float* inputPtr = (float*)complexFFTInput;
   float* realFFTDataPointsPtr = logPowerOutput;
@@ -131,4 +131,4 @@ static inline void volk_32fc_s32f_s32f_power_spectral_density_32f_a16_generic(fl
 
 
 
-#endif /* INCLUDED_volk_32fc_s32f_s32f_power_spectral_density_32f_a16_H */
+#endif /* INCLUDED_volk_32fc_s32f_x2_power_spectral_density_32f_a16_H */
diff --git a/volk/include/volk/volk_32fc_32fc_conjugate_dot_prod_32fc_a16.h b/volk/include/volk/volk_32fc_x2_conjugate_dot_prod_32fc_a16.h
index cd9cc8160..a01971df3 100644
--- a/volk/include/volk/volk_32fc_32fc_conjugate_dot_prod_32fc_a16.h
+++ b/volk/include/volk/volk_32fc_x2_conjugate_dot_prod_32fc_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_32fc_conjugate_dot_prod_32fc_a16_H
-#define INCLUDED_volk_32fc_32fc_conjugate_dot_prod_32fc_a16_H
+#ifndef INCLUDED_volk_32fc_x2_conjugate_dot_prod_32fc_a16_H
+#define INCLUDED_volk_32fc_x2_conjugate_dot_prod_32fc_a16_H
 
 #include<volk/volk_complex.h>
 #include<stdio.h>
@@ -8,7 +8,7 @@
 #if LV_HAVE_GENERIC
 
 
-static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_generic(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_conjugate_dot_prod_32fc_a16_generic(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
   float * res = (float*) result;
   float * in = (float*) input;
@@ -62,7 +62,7 @@ static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_generic(lv_32fc_t*
 #if LV_HAVE_SSE && LV_HAVE_64
 
 
-static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_sse(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_conjugate_dot_prod_32fc_a16_sse(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
   static const uint32_t conjugator[4] __attribute__((aligned(16)))= {0x00000000, 0x80000000, 0x00000000, 0x80000000};
   
@@ -203,7 +203,7 @@ static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_sse(lv_32fc_t* res
 #endif
 
 #if LV_HAVE_SSE && LV_HAVE_32
-static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_sse_32(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_conjugate_dot_prod_32fc_a16_sse_32(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
   static const uint32_t conjugator[4] __attribute__((aligned(16)))= {0x00000000, 0x80000000, 0x00000000, 0x80000000};
 
@@ -341,4 +341,4 @@ static inline void volk_32fc_32fc_conjugate_dot_prod_32fc_a16_sse_32(lv_32fc_t*
 
 
 
-#endif /*INCLUDED_volk_32fc_32fc_conjugate_dot_prod_32fc_a16_H*/
+#endif /*INCLUDED_volk_32fc_x2_conjugate_dot_prod_32fc_a16_H*/
diff --git a/volk/include/volk/volk_32fc_32fc_dot_prod_32fc_a16.h b/volk/include/volk/volk_32fc_x2_dot_prod_32fc_a16.h
index 2ccfcf2f2..9a7b65ab4 100644
--- a/volk/include/volk/volk_32fc_32fc_dot_prod_32fc_a16.h
+++ b/volk/include/volk/volk_32fc_x2_dot_prod_32fc_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_32fc_dot_prod_32fc_a16_H
-#define INCLUDED_volk_32fc_32fc_dot_prod_32fc_a16_H
+#ifndef INCLUDED_volk_32fc_x2_dot_prod_32fc_a16_H
+#define INCLUDED_volk_32fc_x2_dot_prod_32fc_a16_H
 
 #include <volk/volk_complex.h>
 #include <stdio.h>
@@ -9,7 +9,7 @@
 #if LV_HAVE_GENERIC 
 
 
-static inline void volk_32fc_32fc_dot_prod_32fc_a16_generic(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_dot_prod_32fc_a16_generic(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
   float * res = (float*) result;
   float * in = (float*) input;
@@ -59,7 +59,7 @@ static inline void volk_32fc_32fc_dot_prod_32fc_a16_generic(lv_32fc_t* result, c
 #if LV_HAVE_SSE && LV_HAVE_64
 
 
-static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse_64(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_dot_prod_32fc_a16_sse_64(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
 
   asm 
@@ -194,7 +194,7 @@ static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse_64(lv_32fc_t* result, co
 
 #if LV_HAVE_SSE && LV_HAVE_32
 
-static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse_32(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_dot_prod_32fc_a16_sse_32(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
   asm volatile 
     (
@@ -320,7 +320,7 @@ static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse_32(lv_32fc_t* result, co
 
 #include <pmmintrin.h>
 
-static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+static inline void volk_32fc_x2_dot_prod_32fc_a16_sse3(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
   
 
   lv_32fc_t dotProduct;
@@ -377,8 +377,8 @@ static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse3(lv_32fc_t* result, cons
 
 #include <smmintrin.h>
 
-static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
-  volk_32fc_32fc_dot_prod_32fc_a16_sse3(result, input, taps, num_bytes);
+static inline void volk_32fc_x2_dot_prod_32fc_a16_sse4_1(lv_32fc_t* result, const lv_32fc_t* input, const lv_32fc_t* taps, unsigned int num_bytes) {
+  volk_32fc_x2_dot_prod_32fc_a16_sse3(result, input, taps, num_bytes);
   // SSE3 version runs twice as fast as the SSE4.1 version, so turning off SSE4 version for now
    /* 
     __m128 xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, real0, real1, im0, im1;
@@ -465,4 +465,4 @@ static inline void volk_32fc_32fc_dot_prod_32fc_a16_sse4_1(lv_32fc_t* result, co
 
 #endif /*LV_HAVE_SSE4_1*/
 
-#endif /*INCLUDED_volk_32fc_32fc_dot_prod_32fc_a16_H*/
+#endif /*INCLUDED_volk_32fc_x2_dot_prod_32fc_a16_H*/
diff --git a/volk/include/volk/volk_32fc_32fc_multiply_32fc_a16.h b/volk/include/volk/volk_32fc_x2_multiply_32fc_a16.h
index 59259882c..224ab19c8 100644
--- a/volk/include/volk/volk_32fc_32fc_multiply_32fc_a16.h
+++ b/volk/include/volk/volk_32fc_x2_multiply_32fc_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_32fc_multiply_32fc_a16_H
-#define INCLUDED_volk_32fc_32fc_multiply_32fc_a16_H
+#ifndef INCLUDED_volk_32fc_x2_multiply_32fc_a16_H
+#define INCLUDED_volk_32fc_x2_multiply_32fc_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -15,7 +15,7 @@
     \param bVector One of the vectors to be multiplied
     \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
   */
-static inline void volk_32fc_32fc_multiply_32fc_a16_sse3(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
+static inline void volk_32fc_x2_multiply_32fc_a16_sse3(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
   unsigned int number = 0;
     const unsigned int halfPoints = num_points / 2;
 
@@ -61,7 +61,7 @@ static inline void volk_32fc_32fc_multiply_32fc_a16_sse3(lv_32fc_t* cVector, con
     \param bVector One of the vectors to be multiplied
     \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
   */
-static inline void volk_32fc_32fc_multiply_32fc_a16_generic(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
+static inline void volk_32fc_x2_multiply_32fc_a16_generic(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
     lv_32fc_t* cPtr = cVector;
     const lv_32fc_t* aPtr = aVector;
     const lv_32fc_t* bPtr=  bVector;
@@ -81,10 +81,10 @@ static inline void volk_32fc_32fc_multiply_32fc_a16_generic(lv_32fc_t* cVector,
     \param bVector One of the vectors to be multiplied
     \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
   */
-extern void volk_32fc_32fc_multiply_32fc_a16_orc_impl(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, float mask, unsigned int num_points);
-static inline void volk_32fc_32fc_multiply_32fc_a16_orc(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
+extern void volk_32fc_x2_multiply_32fc_a16_orc_impl(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, float mask, unsigned int num_points);
+static inline void volk_32fc_x2_multiply_32fc_a16_orc(lv_32fc_t* cVector, const lv_32fc_t* aVector, const lv_32fc_t* bVector, unsigned int num_points){
     static const float mask = -0.0;
-    volk_32fc_32fc_multiply_32fc_a16_orc_impl(cVector, aVector, bVector, mask, num_points);
+    volk_32fc_x2_multiply_32fc_a16_orc_impl(cVector, aVector, bVector, mask, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
@@ -92,4 +92,4 @@ static inline void volk_32fc_32fc_multiply_32fc_a16_orc(lv_32fc_t* cVector, cons
 
 
 
-#endif /* INCLUDED_volk_32fc_32fc_multiply_32fc_a16_H */
+#endif /* INCLUDED_volk_32fc_x2_multiply_32fc_a16_H */
diff --git a/volk/include/volk/volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16.h b/volk/include/volk/volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16.h
index 14f511697..6a863b16d 100644
--- a/volk/include/volk/volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16.h
+++ b/volk/include/volk/volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_H
-#define INCLUDED_volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_H
+#ifndef INCLUDED_volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16_H
+#define INCLUDED_volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16_H
 
 #include<inttypes.h>
 #include<stdio.h>
@@ -10,7 +10,7 @@
 #include<xmmintrin.h>
 #include<pmmintrin.h>
 
-static inline void volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_sse3(float* target, lv_32fc_t* src0, lv_32fc_t* points, float scalar, unsigned int num_bytes) {
+static inline void volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16_sse3(float* target, lv_32fc_t* src0, lv_32fc_t* points, float scalar, unsigned int num_bytes) {
   
 
   __m128 xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8;
@@ -106,7 +106,7 @@ static inline void volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_sse3(floa
 #endif /*LV_HAVE_SSE3*/
 
 #if LV_HAVE_GENERIC
-static inline void volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_generic(float* target, lv_32fc_t* src0, lv_32fc_t* points, float scalar, unsigned int num_bytes) {
+static inline void volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16_generic(float* target, lv_32fc_t* src0, lv_32fc_t* points, float scalar, unsigned int num_bytes) {
   lv_32fc_t diff;
   float sq_dist;
   int i = 0; 
@@ -123,4 +123,4 @@ static inline void volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_generic(f
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_32fc_32fc_s32f_square_dist_scalar_mult_32f_a16_H*/
+#endif /*INCLUDED_volk_32fc_x2_s32f_square_dist_scalar_mult_32f_a16_H*/
diff --git a/volk/include/volk/volk_32fc_32fc_square_dist_32f_a16.h b/volk/include/volk/volk_32fc_x2_square_dist_32f_a16.h
index b6c72adbf..406097fc8 100644
--- a/volk/include/volk/volk_32fc_32fc_square_dist_32f_a16.h
+++ b/volk/include/volk/volk_32fc_x2_square_dist_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32fc_32fc_square_dist_32f_a16_H
-#define INCLUDED_volk_32fc_32fc_square_dist_32f_a16_H
+#ifndef INCLUDED_volk_32fc_x2_square_dist_32f_a16_H
+#define INCLUDED_volk_32fc_x2_square_dist_32f_a16_H
 
 #include<inttypes.h>
 #include<stdio.h>
@@ -9,7 +9,7 @@
 #include<xmmintrin.h>
 #include<pmmintrin.h>
 
-static inline void volk_32fc_32fc_square_dist_32f_a16_sse3(float* target, lv_32fc_t* src0, lv_32fc_t* points, unsigned int num_bytes) {
+static inline void volk_32fc_x2_square_dist_32f_a16_sse3(float* target, lv_32fc_t* src0, lv_32fc_t* points, unsigned int num_bytes) {
   
 
   __m128 xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7;
@@ -92,7 +92,7 @@ static inline void volk_32fc_32fc_square_dist_32f_a16_sse3(float* target, lv_32f
 #endif /*LV_HAVE_SSE3*/
 
 #if LV_HAVE_GENERIC
-static inline void volk_32fc_32fc_square_dist_32f_a16_generic(float* target, lv_32fc_t* src0, lv_32fc_t* points, unsigned int num_bytes) {
+static inline void volk_32fc_x2_square_dist_32f_a16_generic(float* target, lv_32fc_t* src0, lv_32fc_t* points, unsigned int num_bytes) {
   lv_32fc_t diff;
   float sq_dist;
   int i = 0; 
@@ -109,4 +109,4 @@ static inline void volk_32fc_32fc_square_dist_32f_a16_generic(float* target, lv_
 #endif /*LV_HAVE_GENERIC*/
 
 
-#endif /*INCLUDED_volk_32fc_32fc_square_dist_32f_a16_H*/
+#endif /*INCLUDED_volk_32fc_x2_square_dist_32f_a16_H*/
diff --git a/volk/include/volk/volk_32s_s32f_convert_32f_a16.h b/volk/include/volk/volk_32i_s32f_convert_32f_a16.h
index c16ecc9dd..0fcadd9cb 100644
--- a/volk/include/volk/volk_32s_s32f_convert_32f_a16.h
+++ b/volk/include/volk/volk_32i_s32f_convert_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32s_s32f_convert_32f_a16_H
-#define INCLUDED_volk_32s_s32f_convert_32f_a16_H
+#ifndef INCLUDED_volk_32i_s32f_convert_32f_a16_H
+#define INCLUDED_volk_32i_s32f_convert_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32s_s32f_convert_32f_a16_sse2(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32i_s32f_convert_32f_a16_sse2(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
     
@@ -55,7 +55,7 @@ static inline void volk_32s_s32f_convert_32f_a16_sse2(float* outputVector, const
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_32s_s32f_convert_32f_a16_generic(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32i_s32f_convert_32f_a16_generic(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int32_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -70,4 +70,4 @@ static inline void volk_32s_s32f_convert_32f_a16_generic(float* outputVector, co
 
 
 
-#endif /* INCLUDED_volk_32s_s32f_convert_32f_a16_H */
+#endif /* INCLUDED_volk_32i_s32f_convert_32f_a16_H */
diff --git a/volk/include/volk/volk_32s_s32f_convert_32f_ua16.h b/volk/include/volk/volk_32i_s32f_convert_32f_u.h
index 4eb5a5b85..1dd6422f8 100644
--- a/volk/include/volk/volk_32s_s32f_convert_32f_ua16.h
+++ b/volk/include/volk/volk_32i_s32f_convert_32f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32s_s32f_convert_32f_ua16_H
-#define INCLUDED_volk_32s_s32f_convert_32f_ua16_H
+#ifndef INCLUDED_volk_32i_s32f_convert_32f_u_H
+#define INCLUDED_volk_32i_s32f_convert_32f_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -15,7 +15,7 @@
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_32s_s32f_convert_32f_ua16_sse2(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32i_s32f_convert_32f_u_sse2(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
     
@@ -57,7 +57,7 @@ static inline void volk_32s_s32f_convert_32f_ua16_sse2(float* outputVector, cons
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_32s_s32f_convert_32f_ua16_generic(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_32i_s32f_convert_32f_u_generic(float* outputVector, const int32_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int32_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -72,4 +72,4 @@ static inline void volk_32s_s32f_convert_32f_ua16_generic(float* outputVector, c
 
 
 
-#endif /* INCLUDED_volk_32s_s32f_convert_32f_ua16_H */
+#endif /* INCLUDED_volk_32i_s32f_convert_32f_u_H */
diff --git a/volk/include/volk/volk_32s_32s_and_32s_a16.h b/volk/include/volk/volk_32i_x2_and_32i_a16.h
index 0e8380757..3baa1d856 100644
--- a/volk/include/volk/volk_32s_32s_and_32s_a16.h
+++ b/volk/include/volk/volk_32i_x2_and_32i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32s_32s_and_32s_a16_H
-#define INCLUDED_volk_32s_32s_and_32s_a16_H
+#ifndef INCLUDED_volk_32i_x2_and_32i_a16_H
+#define INCLUDED_volk_32i_x2_and_32i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector One of the vectors
   \param num_points The number of values in aVector and bVector to be anded together and stored into cVector
 */
-static inline void volk_32s_32s_and_32s_a16_sse(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+static inline void volk_32i_x2_and_32i_a16_sse(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32s_32s_and_32s_a16_sse(int32_t* cVector, const int32_t*
   \param bVector One of the vectors
   \param num_points The number of values in aVector and bVector to be anded together and stored into cVector
 */
-static inline void volk_32s_32s_and_32s_a16_generic(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+static inline void volk_32i_x2_and_32i_a16_generic(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
     int32_t* cPtr = cVector;
     const int32_t* aPtr = aVector;
     const int32_t* bPtr=  bVector;
@@ -71,11 +71,11 @@ static inline void volk_32s_32s_and_32s_a16_generic(int32_t* cVector, const int3
   \param bVector One of the vectors
   \param num_points The number of values in aVector and bVector to be anded together and stored into cVector
 */
-extern void volk_32s_32s_and_32s_a16_orc_impl(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points);
-static inline void volk_32s_32s_and_32s_a16_orc(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
-    volk_32s_32s_and_32s_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32i_x2_and_32i_a16_orc_impl(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points);
+static inline void volk_32i_x2_and_32i_a16_orc(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+    volk_32i_x2_and_32i_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32s_32s_and_32s_a16_H */
+#endif /* INCLUDED_volk_32i_x2_and_32i_a16_H */
diff --git a/volk/include/volk/volk_32s_32s_or_32s_a16.h b/volk/include/volk/volk_32i_x2_or_32i_a16.h
index 2dcf2e551..0be22f00a 100644
--- a/volk/include/volk/volk_32s_32s_or_32s_a16.h
+++ b/volk/include/volk/volk_32i_x2_or_32i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_32s_32s_or_32s_a16_H
-#define INCLUDED_volk_32s_32s_or_32s_a16_H
+#ifndef INCLUDED_volk_32i_x2_or_32i_a16_H
+#define INCLUDED_volk_32i_x2_or_32i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector One of the vectors to be ored
   \param num_points The number of values in aVector and bVector to be ored together and stored into cVector
 */
-static inline void volk_32s_32s_or_32s_a16_sse(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+static inline void volk_32i_x2_or_32i_a16_sse(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int quarterPoints = num_points / 4;
 
@@ -51,7 +51,7 @@ static inline void volk_32s_32s_or_32s_a16_sse(int32_t* cVector, const int32_t*
   \param bVector One of the vectors to be ored
   \param num_points The number of values in aVector and bVector to be ored together and stored into cVector
 */
-static inline void volk_32s_32s_or_32s_a16_generic(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+static inline void volk_32i_x2_or_32i_a16_generic(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
     int32_t* cPtr = cVector;
     const int32_t* aPtr = aVector;
     const int32_t* bPtr=  bVector;
@@ -71,11 +71,11 @@ static inline void volk_32s_32s_or_32s_a16_generic(int32_t* cVector, const int32
   \param bVector One of the vectors to be ored
   \param num_points The number of values in aVector and bVector to be ored together and stored into cVector
 */
-extern void volk_32s_32s_or_32s_a16_orc_impl(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points);
-static inline void volk_32s_32s_or_32s_a16_orc(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
-    volk_32s_32s_or_32s_a16_orc_impl(cVector, aVector, bVector, num_points);
+extern void volk_32i_x2_or_32i_a16_orc_impl(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points);
+static inline void volk_32i_x2_or_32i_a16_orc(int32_t* cVector, const int32_t* aVector, const int32_t* bVector, unsigned int num_points){
+    volk_32i_x2_or_32i_a16_orc_impl(cVector, aVector, bVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
 
-#endif /* INCLUDED_volk_32s_32s_or_32s_a16_H */
+#endif /* INCLUDED_volk_32i_x2_or_32i_a16_H */
diff --git a/volk/include/volk/volk_64f_convert_32f_ua16.h b/volk/include/volk/volk_64f_convert_32f_u.h
index 7774db1b7..6338c1433 100644
--- a/volk/include/volk/volk_64f_convert_32f_ua16.h
+++ b/volk/include/volk/volk_64f_convert_32f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_64f_convert_32f_ua16_H
-#define INCLUDED_volk_64f_convert_32f_ua16_H
+#ifndef INCLUDED_volk_64f_convert_32f_u_H
+#define INCLUDED_volk_64f_convert_32f_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
     \param fVector The double vector values to be converted
     \param num_points The number of points in the two vectors to be converted
   */
-static inline void volk_64f_convert_32f_ua16_sse2(float* outputVector, const double* inputVector, unsigned int num_points){
+static inline void volk_64f_convert_32f_u_sse2(float* outputVector, const double* inputVector, unsigned int num_points){
   unsigned int number = 0;
 
   const unsigned int quarterPoints = num_points / 4;
@@ -50,7 +50,7 @@ static inline void volk_64f_convert_32f_ua16_sse2(float* outputVector, const dou
   \param fVector The double vector values to be converted
   \param num_points The number of points in the two vectors to be converted
 */
-static inline void volk_64f_convert_32f_ua16_generic(float* outputVector, const double* inputVector, unsigned int num_points){
+static inline void volk_64f_convert_32f_u_generic(float* outputVector, const double* inputVector, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const double* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -64,4 +64,4 @@ static inline void volk_64f_convert_32f_ua16_generic(float* outputVector, const
 
 
 
-#endif /* INCLUDED_volk_64f_convert_32f_ua16_H */
+#endif /* INCLUDED_volk_64f_convert_32f_u_H */
diff --git a/volk/include/volk/volk_64f_64f_max_64f_a16.h b/volk/include/volk/volk_64f_x2_max_64f_a16.h
index 7e091851f..4b0c1f5f1 100644
--- a/volk/include/volk/volk_64f_64f_max_64f_a16.h
+++ b/volk/include/volk/volk_64f_x2_max_64f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_64f_64f_max_64f_a16_H
-#define INCLUDED_volk_64f_64f_max_64f_a16_H
+#ifndef INCLUDED_volk_64f_x2_max_64f_a16_H
+#define INCLUDED_volk_64f_x2_max_64f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_64f_64f_max_64f_a16_sse2(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
+static inline void volk_64f_x2_max_64f_a16_sse2(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int halfPoints = num_points / 2;
 
@@ -53,7 +53,7 @@ static inline void volk_64f_64f_max_64f_a16_sse2(double* cVector, const double*
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_64f_64f_max_64f_a16_generic(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
+static inline void volk_64f_x2_max_64f_a16_generic(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
     double* cPtr = cVector;
     const double* aPtr = aVector;
     const double* bPtr=  bVector;
@@ -68,4 +68,4 @@ static inline void volk_64f_64f_max_64f_a16_generic(double* cVector, const doubl
 #endif /* LV_HAVE_GENERIC */
 
 
-#endif /* INCLUDED_volk_64f_64f_max_64f_a16_H */
+#endif /* INCLUDED_volk_64f_x2_max_64f_a16_H */
diff --git a/volk/include/volk/volk_64f_64f_min_64f_a16.h b/volk/include/volk/volk_64f_x2_min_64f_a16.h
index f2bcbe83b..aa961e384 100644
--- a/volk/include/volk/volk_64f_64f_min_64f_a16.h
+++ b/volk/include/volk/volk_64f_x2_min_64f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_64f_64f_min_64f_a16_H
-#define INCLUDED_volk_64f_64f_min_64f_a16_H
+#ifndef INCLUDED_volk_64f_x2_min_64f_a16_H
+#define INCLUDED_volk_64f_x2_min_64f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_64f_64f_min_64f_a16_sse2(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
+static inline void volk_64f_x2_min_64f_a16_sse2(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int halfPoints = num_points / 2;
 
@@ -53,7 +53,7 @@ static inline void volk_64f_64f_min_64f_a16_sse2(double* cVector, const double*
   \param bVector The vector to be checked
   \param num_points The number of values in aVector and bVector to be checked and stored into cVector
 */
-static inline void volk_64f_64f_min_64f_a16_generic(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
+static inline void volk_64f_x2_min_64f_a16_generic(double* cVector, const double* aVector, const double* bVector, unsigned int num_points){
     double* cPtr = cVector;
     const double* aPtr = aVector;
     const double* bPtr=  bVector;
@@ -68,4 +68,4 @@ static inline void volk_64f_64f_min_64f_a16_generic(double* cVector, const doubl
 #endif /* LV_HAVE_GENERIC */
 
 
-#endif /* INCLUDED_volk_64f_64f_min_64f_a16_H */
+#endif /* INCLUDED_volk_64f_x2_min_64f_a16_H */
diff --git a/volk/include/volk/volk_8s_convert_16s_a16.h b/volk/include/volk/volk_8i_convert_16i_a16.h
index 38efdb6a3..3d7045753 100644
--- a/volk/include/volk/volk_8s_convert_16s_a16.h
+++ b/volk/include/volk/volk_8i_convert_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8s_convert_16s_a16_H
-#define INCLUDED_volk_8s_convert_16s_a16_H
+#ifndef INCLUDED_volk_8i_convert_16i_a16_H
+#define INCLUDED_volk_8i_convert_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
     \param outputVector The 16 bit output data buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_8s_convert_16s_a16_sse4_1(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
+static inline void volk_8i_convert_16i_a16_sse4_1(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
 
@@ -54,7 +54,7 @@ static inline void volk_8s_convert_16s_a16_sse4_1(int16_t* outputVector, const i
     \param outputVector The 16 bit output data buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_8s_convert_16s_a16_generic(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
+static inline void volk_8i_convert_16i_a16_generic(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
   int16_t* outputVectorPtr = outputVector;
   const int8_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -72,9 +72,9 @@ static inline void volk_8s_convert_16s_a16_generic(int16_t* outputVector, const
     \param outputVector The 16 bit output data buffer
     \param num_points The number of data values to be converted
   */
-extern void volk_8s_convert_16s_a16_orc_impl(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points);
-static inline void volk_8s_convert_16s_a16_orc(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
-    volk_8s_convert_16s_a16_orc_impl(outputVector, inputVector, num_points);
+extern void volk_8i_convert_16i_a16_orc_impl(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points);
+static inline void volk_8i_convert_16i_a16_orc(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
+    volk_8i_convert_16i_a16_orc_impl(outputVector, inputVector, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
diff --git a/volk/include/volk/volk_8s_convert_16s_ua16.h b/volk/include/volk/volk_8i_convert_16i_u.h
index a726bfb5e..bcff13406 100644
--- a/volk/include/volk/volk_8s_convert_16s_ua16.h
+++ b/volk/include/volk/volk_8i_convert_16i_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8s_convert_16s_ua16_H
-#define INCLUDED_volk_8s_convert_16s_ua16_H
+#ifndef INCLUDED_volk_8i_convert_16i_u_H
+#define INCLUDED_volk_8i_convert_16i_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param num_points The number of data values to be converted
     \note Input and output buffers do NOT need to be properly aligned
   */
-static inline void volk_8s_convert_16s_ua16_sse4_1(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
+static inline void volk_8i_convert_16i_u_sse4_1(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
 
@@ -56,7 +56,7 @@ static inline void volk_8s_convert_16s_ua16_sse4_1(int16_t* outputVector, const
     \param num_points The number of data values to be converted
     \note Input and output buffers do NOT need to be properly aligned
   */
-static inline void volk_8s_convert_16s_ua16_generic(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
+static inline void volk_8i_convert_16i_u_generic(int16_t* outputVector, const int8_t* inputVector, unsigned int num_points){
   int16_t* outputVectorPtr = outputVector;
   const int8_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
diff --git a/volk/include/volk/volk_8s_s32f_convert_32f_a16.h b/volk/include/volk/volk_8i_s32f_convert_32f_a16.h
index 45185ac2e..d5c8eeb51 100644
--- a/volk/include/volk/volk_8s_s32f_convert_32f_a16.h
+++ b/volk/include/volk/volk_8i_s32f_convert_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8s_s32f_convert_32f_a16_H
-#define INCLUDED_volk_8s_s32f_convert_32f_a16_H
+#ifndef INCLUDED_volk_8i_s32f_convert_32f_a16_H
+#define INCLUDED_volk_8i_s32f_convert_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_8s_s32f_convert_32f_a16_sse4_1(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_8i_s32f_convert_32f_a16_sse4_1(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
     
@@ -74,7 +74,7 @@ static inline void volk_8s_s32f_convert_32f_a16_sse4_1(float* outputVector, cons
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-static inline void volk_8s_s32f_convert_32f_a16_generic(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_8i_s32f_convert_32f_a16_generic(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int8_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
@@ -94,9 +94,9 @@ static inline void volk_8s_s32f_convert_32f_a16_generic(float* outputVector, con
     \param scalar The value divided against each point in the output buffer
     \param num_points The number of data values to be converted
   */
-extern void volk_8s_s32f_convert_32f_a16_orc_impl(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points);
-static inline void volk_8s_s32f_convert_32f_a16_orc(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
-    volk_8s_s32f_convert_32f_a16_orc_impl(outputVector, inputVector, scalar, num_points);
+extern void volk_8i_s32f_convert_32f_a16_orc_impl(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points);
+static inline void volk_8i_s32f_convert_32f_a16_orc(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
+    volk_8i_s32f_convert_32f_a16_orc_impl(outputVector, inputVector, scalar, num_points);
 }
 #endif /* LV_HAVE_ORC */
 
diff --git a/volk/include/volk/volk_8s_s32f_convert_32f_ua16.h b/volk/include/volk/volk_8i_s32f_convert_32f_u.h
index 310824580..1e30957e8 100644
--- a/volk/include/volk/volk_8s_s32f_convert_32f_ua16.h
+++ b/volk/include/volk/volk_8i_s32f_convert_32f_u.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8s_s32f_convert_32f_ua16_H
-#define INCLUDED_volk_8s_s32f_convert_32f_ua16_H
+#ifndef INCLUDED_volk_8i_s32f_convert_32f_u_H
+#define INCLUDED_volk_8i_s32f_convert_32f_u_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -15,7 +15,7 @@
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_8s_s32f_convert_32f_ua16_sse4_1(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_8i_s32f_convert_32f_u_sse4_1(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
     unsigned int number = 0;
     const unsigned int sixteenthPoints = num_points / 16;
     
@@ -76,7 +76,7 @@ static inline void volk_8s_s32f_convert_32f_ua16_sse4_1(float* outputVector, con
     \param num_points The number of data values to be converted
     \note Output buffer does NOT need to be properly aligned
   */
-static inline void volk_8s_s32f_convert_32f_ua16_generic(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
+static inline void volk_8i_s32f_convert_32f_u_generic(float* outputVector, const int8_t* inputVector, const float scalar, unsigned int num_points){
   float* outputVectorPtr = outputVector;
   const int8_t* inputVectorPtr = inputVector;
   unsigned int number = 0;
diff --git a/volk/include/volk/volk_8sc_deinterleave_16s_16s_a16.h b/volk/include/volk/volk_8ic_deinterleave_16i_x2_a16.h
index 6a35e969d..91c9b2c58 100644
--- a/volk/include/volk/volk_8sc_deinterleave_16s_16s_a16.h
+++ b/volk/include/volk/volk_8ic_deinterleave_16i_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_deinterleave_16s_16s_a16_H
-#define INCLUDED_volk_8sc_deinterleave_16s_16s_a16_H
+#ifndef INCLUDED_volk_8ic_deinterleave_16i_x2_a16_H
+#define INCLUDED_volk_8ic_deinterleave_16i_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_16s_16s_a16_sse4_1(int16_t* iBuffer, int16_t* qBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_16i_x2_a16_sse4_1(int16_t* iBuffer, int16_t* qBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -59,7 +59,7 @@ static inline void volk_8sc_deinterleave_16s_16s_a16_sse4_1(int16_t* iBuffer, in
   \param qBuffer The Q buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_16s_16s_a16_generic(int16_t* iBuffer, int16_t* qBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_16i_x2_a16_generic(int16_t* iBuffer, int16_t* qBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   const int8_t* complexVectorPtr = (const int8_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
   int16_t* qBufferPtr = qBuffer;
@@ -74,4 +74,4 @@ static inline void volk_8sc_deinterleave_16s_16s_a16_generic(int16_t* iBuffer, i
 
 
 
-#endif /* INCLUDED_volk_8sc_deinterleave_16s_16s_a16_H */
+#endif /* INCLUDED_volk_8ic_deinterleave_16i_x2_a16_H */
diff --git a/volk/include/volk/volk_8sc_deinterleave_real_16s_a16.h b/volk/include/volk/volk_8ic_deinterleave_real_16i_a16.h
index 67ffebd99..bf3dc20dd 100644
--- a/volk/include/volk/volk_8sc_deinterleave_real_16s_a16.h
+++ b/volk/include/volk/volk_8ic_deinterleave_real_16i_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_deinterleave_real_16s_a16_H
-#define INCLUDED_volk_8sc_deinterleave_real_16s_a16_H
+#ifndef INCLUDED_volk_8ic_deinterleave_real_16i_a16_H
+#define INCLUDED_volk_8ic_deinterleave_real_16i_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -12,7 +12,7 @@
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_real_16s_a16_sse4_1(int16_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_real_16i_a16_sse4_1(int16_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -49,7 +49,7 @@ static inline void volk_8sc_deinterleave_real_16s_a16_sse4_1(int16_t* iBuffer, c
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_real_16s_a16_generic(int16_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_real_16i_a16_generic(int16_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (const int8_t*)complexVector;
   int16_t* iBufferPtr = iBuffer;
@@ -63,4 +63,4 @@ static inline void volk_8sc_deinterleave_real_16s_a16_generic(int16_t* iBuffer,
 
 
 
-#endif /* INCLUDED_volk_8sc_deinterleave_real_16s_a16_H */
+#endif /* INCLUDED_volk_8ic_deinterleave_real_16i_a16_H */
diff --git a/volk/include/volk/volk_8sc_deinterleave_real_8s_a16.h b/volk/include/volk/volk_8ic_deinterleave_real_8i_a16.h
index ecffc092e..13de79423 100644
--- a/volk/include/volk/volk_8sc_deinterleave_real_8s_a16.h
+++ b/volk/include/volk/volk_8ic_deinterleave_real_8i_a16.h
@@ -12,7 +12,7 @@
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_real_8s_a16_ssse3(int8_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_real_8i_a16_ssse3(int8_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int8_t* iBufferPtr = iBuffer;
@@ -50,7 +50,7 @@ static inline void volk_8sc_deinterleave_real_8s_a16_ssse3(int8_t* iBuffer, cons
   \param iBuffer The I buffer output data
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_deinterleave_real_8s_a16_generic(int8_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
+static inline void volk_8ic_deinterleave_real_8i_a16_generic(int8_t* iBuffer, const lv_8sc_t* complexVector, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (int8_t*)complexVector;
   int8_t* iBufferPtr = iBuffer;
diff --git a/volk/include/volk/volk_8sc_s32f_deinterleave_32f_32f_a16.h b/volk/include/volk/volk_8ic_s32f_deinterleave_32f_x2_a16.h
index cedbf202c..22c3ebb23 100644
--- a/volk/include/volk/volk_8sc_s32f_deinterleave_32f_32f_a16.h
+++ b/volk/include/volk/volk_8ic_s32f_deinterleave_32f_x2_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_s32f_deinterleave_32f_32f_a16_H
-#define INCLUDED_volk_8sc_s32f_deinterleave_32f_32f_a16_H
+#ifndef INCLUDED_volk_8ic_s32f_deinterleave_32f_x2_a16_H
+#define INCLUDED_volk_8ic_s32f_deinterleave_32f_x2_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_sse4_1(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_32f_x2_a16_sse4_1(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
 
@@ -84,7 +84,7 @@ static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_sse4_1(float* iBuffer,
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_sse(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_32f_x2_a16_sse(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
 
@@ -145,7 +145,7 @@ static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_sse(float* iBuffer, fl
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_generic(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_32f_x2_a16_generic(float* iBuffer, float* qBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   const int8_t* complexVectorPtr = (const int8_t*)complexVector;
   float* iBufferPtr = iBuffer;
   float* qBufferPtr = qBuffer;
@@ -161,4 +161,4 @@ static inline void volk_8sc_s32f_deinterleave_32f_32f_a16_generic(float* iBuffer
 
 
 
-#endif /* INCLUDED_volk_8sc_s32f_deinterleave_32f_32f_a16_H */
+#endif /* INCLUDED_volk_8ic_s32f_deinterleave_32f_x2_a16_H */
diff --git a/volk/include/volk/volk_8sc_s32f_deinterleave_real_32f_a16.h b/volk/include/volk/volk_8ic_s32f_deinterleave_real_32f_a16.h
index 902795131..5f1430394 100644
--- a/volk/include/volk/volk_8sc_s32f_deinterleave_real_32f_a16.h
+++ b/volk/include/volk/volk_8ic_s32f_deinterleave_real_32f_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_s32f_deinterleave_real_32f_a16_H
-#define INCLUDED_volk_8sc_s32f_deinterleave_real_32f_a16_H
+#ifndef INCLUDED_volk_8ic_s32f_deinterleave_real_32f_a16_H
+#define INCLUDED_volk_8ic_s32f_deinterleave_real_32f_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -13,7 +13,7 @@
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
 
   unsigned int number = 0;
@@ -70,7 +70,7 @@ static inline void volk_8sc_s32f_deinterleave_real_32f_a16_sse4_1(float* iBuffer
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_real_32f_a16_sse(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_real_32f_a16_sse(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   float* iBufferPtr = iBuffer;
 
   unsigned int number = 0;
@@ -115,7 +115,7 @@ static inline void volk_8sc_s32f_deinterleave_real_32f_a16_sse(float* iBuffer, c
   \param scalar The scaling value being multiplied against each data point
   \param num_points The number of complex data values to be deinterleaved
 */
-static inline void volk_8sc_s32f_deinterleave_real_32f_a16_generic(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_s32f_deinterleave_real_32f_a16_generic(float* iBuffer, const lv_8sc_t* complexVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const int8_t* complexVectorPtr = (const int8_t*)complexVector;
   float* iBufferPtr = iBuffer;
@@ -130,4 +130,4 @@ static inline void volk_8sc_s32f_deinterleave_real_32f_a16_generic(float* iBuffe
 
 
 
-#endif /* INCLUDED_volk_8sc_s32f_deinterleave_real_32f_a16_H */
+#endif /* INCLUDED_volk_8ic_s32f_deinterleave_real_32f_a16_H */
diff --git a/volk/include/volk/volk_8sc_8sc_multiply_conjugate_16sc_a16.h b/volk/include/volk/volk_8ic_x2_multiply_conjugate_16ic_a16.h
index eae1185ec..d9cacbf46 100644
--- a/volk/include/volk/volk_8sc_8sc_multiply_conjugate_16sc_a16.h
+++ b/volk/include/volk/volk_8ic_x2_multiply_conjugate_16ic_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_8sc_multiply_conjugate_16sc_a16_H
-#define INCLUDED_volk_8sc_8sc_multiply_conjugate_16sc_a16_H
+#ifndef INCLUDED_volk_8ic_x2_multiply_conjugate_16ic_a16_H
+#define INCLUDED_volk_8ic_x2_multiply_conjugate_16ic_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param bVector The complex vector which will be converted to complex conjugate and multiplied
   \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_8sc_8sc_multiply_conjugate_16sc_a16_sse4_1(lv_16sc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, unsigned int num_points){
+static inline void volk_8ic_x2_multiply_conjugate_16ic_a16_sse4_1(lv_16sc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -76,7 +76,7 @@ static inline void volk_8sc_8sc_multiply_conjugate_16sc_a16_sse4_1(lv_16sc_t* cV
   \param bVector The complex vector which will be converted to complex conjugate and multiplied
   \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_8sc_8sc_multiply_conjugate_16sc_a16_generic(lv_16sc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, unsigned int num_points){
+static inline void volk_8ic_x2_multiply_conjugate_16ic_a16_generic(lv_16sc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, unsigned int num_points){
   unsigned int number = 0;
   int16_t* c16Ptr = (int16_t*)cVector;
   int8_t* a8Ptr = (int8_t*)aVector;
@@ -99,4 +99,4 @@ static inline void volk_8sc_8sc_multiply_conjugate_16sc_a16_generic(lv_16sc_t* c
 
 
 
-#endif /* INCLUDED_volk_8sc_8sc_multiply_conjugate_16sc_a16_H */
+#endif /* INCLUDED_volk_8ic_x2_multiply_conjugate_16ic_a16_H */
diff --git a/volk/include/volk/volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16.h b/volk/include/volk/volk_8ic_x2_s32f_multiply_conjugate_32fc_a16.h
index 621276b08..6ec923a4f 100644
--- a/volk/include/volk/volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16.h
+++ b/volk/include/volk/volk_8ic_x2_s32f_multiply_conjugate_32fc_a16.h
@@ -1,5 +1,5 @@
-#ifndef INCLUDED_volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_H
-#define INCLUDED_volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_H
+#ifndef INCLUDED_volk_8ic_x2_s32f_multiply_conjugate_32fc_a16_H
+#define INCLUDED_volk_8ic_x2_s32f_multiply_conjugate_32fc_a16_H
 
 #include <inttypes.h>
 #include <stdio.h>
@@ -14,7 +14,7 @@
   \param bVector The complex vector which will be converted to complex conjugate and multiplied
   \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_sse4_1(lv_32fc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_x2_s32f_multiply_conjugate_32fc_a16_sse4_1(lv_32fc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   const unsigned int quarterPoints = num_points / 4;
 
@@ -95,7 +95,7 @@ static inline void volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_sse4_1(lv_32fc_
   \param bVector The complex vector which will be converted to complex conjugate and multiplied
   \param num_points The number of complex values in aVector and bVector to be multiplied together and stored into cVector
 */
-static inline void volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_generic(lv_32fc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, const float scalar, unsigned int num_points){
+static inline void volk_8ic_x2_s32f_multiply_conjugate_32fc_a16_generic(lv_32fc_t* cVector, const lv_8sc_t* aVector, const lv_8sc_t* bVector, const float scalar, unsigned int num_points){
   unsigned int number = 0;
   float* cPtr = (float*)cVector;
   const float invScalar = 1.0 / scalar;
@@ -119,4 +119,4 @@ static inline void volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_generic(lv_32fc
 
 
 
-#endif /* INCLUDED_volk_8sc_8sc_s32f_multiply_conjugate_32fc_a16_H */
+#endif /* INCLUDED_volk_8ic_x2_s32f_multiply_conjugate_32fc_a16_H */
diff --git a/volk/include/volk/volk_register.py b/volk/include/volk/volk_register.py
index fc1ec10ef..bc8f959af 100755
--- a/volk/include/volk/volk_register.py
+++ b/volk/include/volk/volk_register.py
@@ -55,7 +55,7 @@ functions = [];
 
 
 for line in mfile:
-    subline = re.search(".*(a16).*", line);
+    subline = re.search(".*_(a16|u)\.h.*", line);
     if subline:
         subsubline = re.search("(?<=volk_).*", subline.group(0));
         if subsubline:
@@ -70,7 +70,7 @@ datatypes = set(datatypes);
 for line in mfile:
     for dt in datatypes:
         if dt in line:
-            subline = re.search("(volk_" + dt +"_.*(a16).*\.h)", line);
+            subline = re.search("(volk_" + dt +"_.*(a16|u).*\.h)", line);
             if subline:
                 
                 subsubline = re.search(".+(?=\.h)", subline.group(0));
diff --git a/volk/lib/qa_utils.cc b/volk/lib/qa_utils.cc
index e73b70985..4c151bd6f 100644
--- a/volk/lib/qa_utils.cc
+++ b/volk/lib/qa_utils.cc
@@ -19,7 +19,8 @@ float uniform() {
   return 2.0 * ((float) rand() / RAND_MAX - 0.5);	// uniformly (-1, 1)
 }
 
-void random_floats (float *buf, unsigned n)
+template <class t>
+void random_floats (t *buf, unsigned n)
 {
   for (unsigned i = 0; i < n; i++)
     buf[i] = uniform ();
@@ -28,8 +29,8 @@ void random_floats (float *buf, unsigned n)
 void load_random_data(void *data, volk_type_t type, unsigned int n) {
     if(type.is_complex) n *= 2;
     if(type.is_float) {
-        assert(type.size == 4); //TODO: double support
-        random_floats((float *)data, n);
+        if(type.size == 8) random_floats<double>((double *)data, n);
+        else random_floats<float>((float *)data, n);
     } else {
         float int_max = pow(2, type.size*8);
         if(type.is_signed) int_max /= 2.0;
@@ -54,7 +55,7 @@ void load_random_data(void *data, volk_type_t type, unsigned int n) {
                 else ((uint8_t *)data)[i] = (uint8_t) scaled_rand;
             break;
             default:
-                throw; //no shenanigans here
+                throw "load_random_data: no support for data size > 8 or < 1"; //no shenanigans here
             }
         }
     }
@@ -94,6 +95,9 @@ static std::vector<std::string> get_arch_list(const int archs[]) {
         case (1<<LV_SSE2):
             archlist.push_back("sse2");
             break;
+        case (1<<LV_SSE3):
+            archlist.push_back("sse3");
+            break;
         case (1<<LV_SSSE3):
             archlist.push_back("ssse3");
             break;
@@ -128,7 +132,7 @@ volk_type_t volk_type_from_string(std::string name) {
     type.size = 0;
     type.str = name;
     
-    assert(name.size() > 1);
+    if(name.size() < 2) throw std::string("name too short to be a datatype");
     
     //is it a scalar?
     if(name[0] == 's') { 
@@ -138,7 +142,7 @@ volk_type_t volk_type_from_string(std::string name) {
     
     //get the data size
     int last_size_pos = name.find_last_of("0123456789");
-    if(last_size_pos < 0) throw 0;
+    if(last_size_pos < 0) throw std::string("no size spec in type ").append(name);
     //will throw if malformed
     int size = boost::lexical_cast<int>(name.substr(0, last_size_pos+1));
 
@@ -182,12 +186,14 @@ static void get_signatures_from_name(std::vector<volk_type_t> &inputsig,
     //ok. we're assuming a string in the form
     //(sig)_(multiplier-opt)_..._(name)_(sig)_(multiplier-opt)_..._(alignment)
 
-    enum { SIDE_INPUT, SIDE_OUTPUT } side = SIDE_INPUT;
+    enum { SIDE_INPUT, SIDE_NAME, SIDE_OUTPUT } side = SIDE_INPUT;
     std::string fn_name;
     volk_type_t type;
     BOOST_FOREACH(std::string token, toked) {
         try {
             type = volk_type_from_string(token);
+            if(side == SIDE_NAME) side = SIDE_OUTPUT; //if this is the first one after the name...
+            
             if(side == SIDE_INPUT) inputsig.push_back(type);
             else outputsig.push_back(type);
         } catch (...){
@@ -201,9 +207,11 @@ static void get_signatures_from_name(std::vector<volk_type_t> &inputsig,
                 }
             }
             else if(side == SIDE_INPUT) { //it's the function name, at least it better be
-                side = SIDE_OUTPUT;
-                fn_name = token;
-            } else {
+                side = SIDE_NAME;
+                fn_name.append("_");
+                fn_name.append(token);
+            } 
+            else if(side == SIDE_OUTPUT) {
                 if(token != toked.back()) throw; //the last token in the name is the alignment
             }
         }
@@ -236,20 +244,40 @@ inline void run_cast_test2_s32f(volk_fn_2arg_s32f func, void *outbuff, std::vect
     while(iter--) func(outbuff, inbuffs[0], scalar, vlen, arch.c_str());
 }
 
+inline void run_cast_test3_s32f(volk_fn_3arg_s32f func, void *outbuff, std::vector<void *> &inbuffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch) {
+    while(iter--) func(outbuff, inbuffs[0], inbuffs[1], scalar, vlen, arch.c_str());
+}
+
 template <class t>
 bool fcompare(t *in1, t *in2, unsigned int vlen, float tol) {
+    bool fail = false;
+    int print_max_errs = 10;
     for(int i=0; i<vlen; i++) {
-        if(fabs(((t *)(in1))[i] - ((t *)(in2))[i]) > tol) return 1;
+        if(fabs(((t *)(in1))[i] - ((t *)(in2))[i])/(((t *)in1)[i]) > tol) {
+            fail=true;
+            if(print_max_errs-- > 0) {
+                std::cout << "offset " << i << " in1: " << t(((t *)(in1))[i]) << " in2: " << t(((t *)(in2))[i]) << std::endl;
+            }
+        }
     }
-    return 0;
+    
+    return fail;
 }
 
 template <class t>
-bool icompare(t *in1, t *in2, unsigned int vlen) {
+bool icompare(t *in1, t *in2, unsigned int vlen, float tol) {
+    bool fail = false;
+    int print_max_errs = 10;
     for(int i=0; i<vlen; i++) {
-        if(((t *)(in1))[i] != ((t *)(in2))[i]) return 1;
+        if(((t *)(in1))[i] != ((t *)(in2))[i]) {
+            fail=true;
+            if(print_max_errs-- > 0) {
+                std::cout << "offset " << i << " in1: " << int(((t *)(in1))[i]) << " in2: " << int(((t *)(in2))[i]) << std::endl;
+            }
+        }
     }
-    return 0;
+    
+    return fail;
 }
 
 bool run_volk_tests(const int archs[], void (*manual_func)(), std::string name, float tol, int vlen, int iter) {
@@ -300,7 +328,7 @@ bool run_volk_tests(const int archs[], void (*manual_func)(), std::string name,
             load_random_data(inbuffs[i], inputsig[i], vlen);        
         }
     }
-    
+
     //now run the test
     clock_t start, end;
     for(int i = 0; i < arch_list.size(); i++) {
@@ -311,18 +339,22 @@ bool run_volk_tests(const int archs[], void (*manual_func)(), std::string name,
                 if(inputsc.size() == 0) {
                     run_cast_test1((volk_fn_1arg)(manual_func), outbuffs[i], vlen, iter, arch_list[i]); 
                 } else if(inputsc.size() == 1 && inputsc[0].is_float) {
-                    run_cast_test1_s32f((volk_fn_1arg_s32f)(manual_func), outbuffs[i], 1000.0, vlen, iter, arch_list[i]);
+                    run_cast_test1_s32f((volk_fn_1arg_s32f)(manual_func), outbuffs[i], 255.0, vlen, iter, arch_list[i]);
                 } else throw "unsupported 1 arg function >1 scalars";
                 break;
             case 2:
                 if(inputsc.size() == 0) {
                     run_cast_test2((volk_fn_2arg)(manual_func), outbuffs[i], inbuffs, vlen, iter, arch_list[i]);
                 } else if(inputsc.size() == 1 && inputsc[0].is_float) {
-                    run_cast_test2_s32f((volk_fn_2arg_s32f)(manual_func), outbuffs[i], inbuffs, 1000.0, vlen, iter, arch_list[i]);
+                    run_cast_test2_s32f((volk_fn_2arg_s32f)(manual_func), outbuffs[i], inbuffs, 255.0, vlen, iter, arch_list[i]);
                 } else throw "unsupported 2 arg function >1 scalars";
                 break;
             case 3:
-                run_cast_test3((volk_fn_3arg)(manual_func), outbuffs[i], inbuffs, vlen, iter, arch_list[i]);
+                if(inputsc.size() == 0) {
+                    run_cast_test3((volk_fn_3arg)(manual_func), outbuffs[i], inbuffs, vlen, iter, arch_list[i]);
+                } else if(inputsc.size() == 1 && inputsc[0].is_float) {
+                    run_cast_test3_s32f((volk_fn_3arg_s32f)(manual_func), outbuffs[i], inbuffs, 255.0, vlen, iter, arch_list[i]);
+                } else throw "unsupported 3 arg function >1 scalars";
                 break;
             case 4:
                 run_cast_test4((volk_fn_4arg)(manual_func), outbuffs[i], inbuffs, vlen, iter, arch_list[i]);
@@ -337,29 +369,24 @@ bool run_volk_tests(const int archs[], void (*manual_func)(), std::string name,
     }
     //and now compare each output to the generic output
     //first we have to know which output is the generic one, they aren't in order...
-    int generic_offset;
+    int generic_offset=0;
     for(int i=0; i<arch_list.size(); i++) 
         if(arch_list[i] == "generic") generic_offset=i;
-        
+
     //now compare
     if(outputsig.size() == 0) outputsig = inputsig; //a hack, i know
 
     bool fail = false;
     for(int i=0; i<arch_list.size(); i++) {
         if(i != generic_offset) {
-            if(outputsig[0].str == "32fc") {
-                fail = fcompare((float *) outbuffs[generic_offset], (float *) outbuffs[i], vlen*2, tol);
-            } else if(outputsig[0].str == "32f") {
-                fail = fcompare((float *) outbuffs[generic_offset], (float *) outbuffs[i], vlen, tol);
-            } else if(outputsig[0].str == "32u" || outputsig[0].str == "32s" || outputsig[0].str == "16sc") {
-                fail = icompare((uint32_t *) outbuffs[generic_offset], (uint32_t *) outbuffs[i], vlen);
-            } else if(outputsig[0].size == 2) {
-                fail = icompare((uint16_t *) outbuffs[generic_offset], (uint16_t *) outbuffs[i], vlen);
-            } else if(outputsig[0].size == 1) {
-                fail = icompare((uint8_t *) outbuffs[generic_offset], (uint8_t *) outbuffs[i], vlen);
-            } else { 
-                std::cout << "Error: invalid type " << outputsig[0].str << std::endl;
-                fail = true;
+            if(outputsig[0].is_float) {
+                if(outputsig[0].size == 8) {
+                    fail = fcompare((double *) outbuffs[generic_offset], (double *) outbuffs[i], vlen*(outputsig[0].is_complex ? 2 : 1), tol);
+                } else {
+                    fail = fcompare((float *) outbuffs[generic_offset], (float *) outbuffs[i], vlen*(outputsig[0].is_complex ? 2 : 1), tol);
+                }
+            } else {
+                fail = memcmp(outbuffs[generic_offset], outbuffs[i], outputsig[0].size * vlen * (outputsig[0].is_complex ? 2:1));
             }
             if(fail) {
                 std::cout << name << ": fail on arch " << arch_list[i] << std::endl;
@@ -367,12 +394,6 @@ bool run_volk_tests(const int archs[], void (*manual_func)(), std::string name,
         }
     }
 
-//    BOOST_FOREACH(void *buf, inbuffs) {
-//        free(buf);
-//    }
-//    BOOST_FOREACH(void *buf, outbuffs) {
-//        free(buf);
-//    }
     return fail;
 }
 
diff --git a/volk/lib/qa_utils.h b/volk/lib/qa_utils.h
index 79c5d7778..79fc8f006 100644
--- a/volk/lib/qa_utils.h
+++ b/volk/lib/qa_utils.h
@@ -28,5 +28,6 @@ typedef void (*volk_fn_3arg)(void *, void *, void *, unsigned int, const char*);
 typedef void (*volk_fn_4arg)(void *, void *, void *, void *, unsigned int, const char*);
 typedef void (*volk_fn_1arg_s32f)(void *, float, unsigned int, const char*); //one input vector, one scalar float input
 typedef void (*volk_fn_2arg_s32f)(void *, void *, float, unsigned int, const char*);
+typedef void (*volk_fn_3arg_s32f)(void *, void *, void *, float, unsigned int, const char*);
 
 #endif //VOLK_QA_UTILS_H
diff --git a/volk/orc/Makefile.am b/volk/orc/Makefile.am
index 43f38543c..6b5e4f8b6 100644
--- a/volk/orc/Makefile.am
+++ b/volk/orc/Makefile.am
@@ -25,27 +25,28 @@ lib_LTLIBRARIES = libvolk_orc.la
 libvolk_orc_la_LDFLAGS = $(ORC_LDFLAGS)
 
 libvolk_orc_la_SOURCES = \
-volk_8s_convert_16s_a16_orc_impl.orc \
-volk_8s_s32f_convert_32f_a16_orc_impl.orc \
+volk_8i_convert_16i_a16_orc_impl.orc \
+volk_8i_s32f_convert_32f_a16_orc_impl.orc \
 volk_16u_byteswap_a16_orc_impl.orc \
-volk_32s_32s_and_32s_a16_orc_impl.orc \
-volk_32s_32s_or_32s_a16_orc_impl.orc \
-volk_32f_32f_add_32f_a16_orc_impl.orc \
-volk_32f_32f_subtract_32f_a16_orc_impl.orc \
-volk_32f_32f_divide_32f_a16_orc_impl.orc \
-volk_32f_32f_multiply_32f_a16_orc_impl.orc \
-volk_32fc_32fc_multiply_32fc_a16_orc_impl.orc \
+volk_32i_x2_and_32i_a16_orc_impl.orc \
+volk_32i_x2_or_32i_a16_orc_impl.orc \
+volk_32f_x2_add_32f_a16_orc_impl.orc \
+volk_32f_x2_subtract_32f_a16_orc_impl.orc \
+volk_32f_x2_divide_32f_a16_orc_impl.orc \
+volk_32f_x2_multiply_32f_a16_orc_impl.orc \
+volk_32fc_x2_multiply_32fc_a16_orc_impl.orc \
 volk_32fc_32f_multiply_32fc_a16_orc_impl.orc \
 volk_32f_sqrt_32f_a16_orc_impl.orc \
-volk_32f_32f_max_32f_a16_orc_impl.orc \
-volk_32f_32f_min_32f_a16_orc_impl.orc \
+volk_32f_x2_max_32f_a16_orc_impl.orc \
+volk_32f_x2_min_32f_a16_orc_impl.orc \
 volk_32f_s32f_normalize_a16_orc_impl.orc \
 volk_32fc_magnitude_32f_a16_orc_impl.orc \
-volk_32fc_s32f_magnitude_16s_a16_orc_impl.orc \
-volk_16sc_magnitude_16s_a16_orc_impl.orc \
-volk_16sc_deinterleave_16s_16s_a16_orc_impl.orc \
-volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl.orc \
-volk_16sc_deinterleave_real_8s_a16_orc_impl.orc
+volk_32fc_s32f_magnitude_16i_a16_orc_impl.orc \
+volk_16ic_magnitude_16i_a16_orc_impl.orc \
+volk_16ic_deinterleave_16i_x2_a16_orc_impl.orc \
+volk_16i_s32f_deinterleave_32f_x2_a16_orc_impl.orc \
+volk_16ic_deinterleave_real_8i_a16_orc_impl.orc
+
 
 
 
diff --git a/volk/orc/volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl.orc b/volk/orc/volk_16i_s32f_deinterleave_32f_x2_a16_orc_impl.orc
index 47c3d28a9..0189fbf5d 100644
--- a/volk/orc/volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_16i_s32f_deinterleave_32f_x2_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_16sc_s32f_deinterleave_32f_32f_a16_orc_impl
+.function volk_16ic_s32f_deinterleave_32f_x2_a16_orc_impl
 .dest 4 idst
 .dest 4 qdst
 .source 4 src
diff --git a/volk/orc/volk_16sc_deinterleave_16s_16s_a16_orc_impl.orc b/volk/orc/volk_16ic_deinterleave_16i_x2_a16_orc_impl.orc
index d396a0052..56018edda 100644
--- a/volk/orc/volk_16sc_deinterleave_16s_16s_a16_orc_impl.orc
+++ b/volk/orc/volk_16ic_deinterleave_16i_x2_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_16sc_deinterleave_16s_16s_a16_orc_impl
+.function volk_16ic_deinterleave_16i_x2_a16_orc_impl
 .dest 2 idst
 .dest 2 qdst
 .source 4 src
diff --git a/volk/orc/volk_16sc_deinterleave_real_8s_a16_orc_impl.orc b/volk/orc/volk_16ic_deinterleave_real_8i_a16_orc_impl.orc
index 5954c406f..dba9a4c8e 100644
--- a/volk/orc/volk_16sc_deinterleave_real_8s_a16_orc_impl.orc
+++ b/volk/orc/volk_16ic_deinterleave_real_8i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_16sc_deinterleave_real_8s_a16_orc_impl
+.function volk_16ic_deinterleave_real_8i_a16_orc_impl
 .dest 1 dst
 .source 4 src
 .temp 2 iw
diff --git a/volk/orc/volk_16sc_magnitude_16s_a16_orc_impl.orc b/volk/orc/volk_16ic_magnitude_16i_a16_orc_impl.orc
index 2a49d4ecb..37225e9b8 100644
--- a/volk/orc/volk_16sc_magnitude_16s_a16_orc_impl.orc
+++ b/volk/orc/volk_16ic_magnitude_16i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_16sc_magnitude_16s_a16_orc_impl
+.function volk_16ic_magnitude_16i_a16_orc_impl
 .source 4 src
 .dest 2 dst
 .floatparam 4 scalar
diff --git a/volk/orc/volk_16sc_magnitude_32f_aligned16_orc_impl.orc b/volk/orc/volk_16sc_magnitude_32f_aligned16_orc_impl.orc
index 6d2ed8197..1e2380837 100644
--- a/volk/orc/volk_16sc_magnitude_32f_aligned16_orc_impl.orc
+++ b/volk/orc/volk_16sc_magnitude_32f_aligned16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_16sc_magnitude_32f_aligned16_orc_impl
+.function volk_16ic_magnitude_32f_a16_orc_impl
 .source 4 src
 .dest 4 dst
 .floatparam 4 scalar
diff --git a/volk/orc/volk_32f_32f_add_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_add_32f_a16_orc_impl.orc
index e6a30cf01..8d095a052 100644
--- a/volk/orc/volk_32f_32f_add_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_add_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_add_32f_a16_orc_impl
+.function volk_32f_x2_add_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32f_32f_divide_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_divide_32f_a16_orc_impl.orc
index 0bdcd0010..0097646cb 100644
--- a/volk/orc/volk_32f_32f_divide_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_divide_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_divide_32f_a16_orc_impl
+.function volk_32f_x2_divide_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32f_32f_max_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_max_32f_a16_orc_impl.orc
index 9584e6634..b7f008737 100644
--- a/volk/orc/volk_32f_32f_max_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_max_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_max_32f_a16_orc_impl
+.function volk_32f_x2_max_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32f_32f_min_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_min_32f_a16_orc_impl.orc
index 47b9c05db..78328b576 100644
--- a/volk/orc/volk_32f_32f_min_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_min_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_min_32f_a16_orc_impl
+.function volk_32f_x2_min_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32f_32f_multiply_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_multiply_32f_a16_orc_impl.orc
index e5a049c16..e8fadff19 100644
--- a/volk/orc/volk_32f_32f_multiply_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_multiply_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_multiply_32f_a16_orc_impl
+.function volk_32f_x2_multiply_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32f_32f_subtract_32f_a16_orc_impl.orc b/volk/orc/volk_32f_x2_subtract_32f_a16_orc_impl.orc
index 2ab42d5f6..13fbe8c83 100644
--- a/volk/orc/volk_32f_32f_subtract_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_32f_x2_subtract_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32f_32f_subtract_32f_a16_orc_impl
+.function volk_32f_x2_subtract_32f_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32fc_s32f_magnitude_16s_a16_orc_impl.orc b/volk/orc/volk_32fc_s32f_magnitude_16i_a16_orc_impl.orc
index cccda8a0f..9e2599084 100644
--- a/volk/orc/volk_32fc_s32f_magnitude_16s_a16_orc_impl.orc
+++ b/volk/orc/volk_32fc_s32f_magnitude_16i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32fc_s32f_magnitude_16s_a16_orc_impl
+.function volk_32fc_s32f_magnitude_16i_a16_orc_impl
 .source 8 src
 .dest 2 dst
 .floatparam 4 scalar
diff --git a/volk/orc/volk_32fc_32fc_multiply_32fc_a16_orc_impl.orc b/volk/orc/volk_32fc_x2_multiply_32fc_a16_orc_impl.orc
index ed928b90f..d23892880 100644
--- a/volk/orc/volk_32fc_32fc_multiply_32fc_a16_orc_impl.orc
+++ b/volk/orc/volk_32fc_x2_multiply_32fc_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32fc_32fc_multiply_32fc_a16_orc_impl
+.function volk_32fc_x2_multiply_32fc_a16_orc_impl
 .source 8 src1
 .source 8 src2
 .dest 8 dst
diff --git a/volk/orc/volk_32s_32s_and_32s_a16_orc_impl.orc b/volk/orc/volk_32i_x2_and_32i_a16_orc_impl.orc
index bff3af875..7b331f8ed 100644
--- a/volk/orc/volk_32s_32s_and_32s_a16_orc_impl.orc
+++ b/volk/orc/volk_32i_x2_and_32i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32s_32s_and_32s_a16_orc_impl
+.function volk_32i_x2_and_32i_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_32s_32s_or_32s_a16_orc_impl.orc b/volk/orc/volk_32i_x2_or_32i_a16_orc_impl.orc
index b6961f79e..4984a9ced 100644
--- a/volk/orc/volk_32s_32s_or_32s_a16_orc_impl.orc
+++ b/volk/orc/volk_32i_x2_or_32i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_32s_32s_or_32s_a16_orc_impl
+.function volk_32i_x2_or_32i_a16_orc_impl
 .dest 4 dst
 .source 4 src1
 .source 4 src2
diff --git a/volk/orc/volk_8s_convert_16s_a16_orc_impl.orc b/volk/orc/volk_8i_convert_16i_a16_orc_impl.orc
index a55c7f723..f44845c88 100644
--- a/volk/orc/volk_8s_convert_16s_a16_orc_impl.orc
+++ b/volk/orc/volk_8i_convert_16i_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_8s_convert_16s_a16_orc_impl
+.function volk_8i_convert_16i_a16_orc_impl
 .source 1 src
 .dest 2 dst
 convsbw dst, src
diff --git a/volk/orc/volk_8s_s32f_convert_32f_a16_orc_impl.orc b/volk/orc/volk_8i_s32f_convert_32f_a16_orc_impl.orc
index 3274ab9d6..4e33f7b3b 100644
--- a/volk/orc/volk_8s_s32f_convert_32f_a16_orc_impl.orc
+++ b/volk/orc/volk_8i_s32f_convert_32f_a16_orc_impl.orc
@@ -1,4 +1,4 @@
-.function volk_8s_s32f_convert_32f_a16_orc_impl
+.function volk_8i_s32f_convert_32f_a16_orc_impl
 .source 2 src
 .dest 4 dst
 .floatparam 4 scalar