Project Ne10
An open, optimized software library for the ARM architecture.
NE10_math.h
Go to the documentation of this file.
1 /*
2  * Copyright 2011-16 ARM Limited and Contributors.
3  * All rights reserved.
4  *
5  * Redistribution and use in source and binary forms, with or without
6  * modification, are permitted provided that the following conditions are met:
7  * * Redistributions of source code must retain the above copyright
8  * notice, this list of conditions and the following disclaimer.
9  * * Redistributions in binary form must reproduce the above copyright
10  * notice, this list of conditions and the following disclaimer in the
11  * documentation and/or other materials provided with the distribution.
12  * * Neither the name of ARM Limited nor the
13  * names of its contributors may be used to endorse or promote products
14  * derived from this software without specific prior written permission.
15  *
16  * THIS SOFTWARE IS PROVIDED BY ARM LIMITED AND CONTRIBUTORS "AS IS" AND
17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19  * DISCLAIMED. IN NO EVENT SHALL ARM LIMITED AND CONTRIBUTORS BE LIABLE FOR ANY
20  * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26  */
27 
28 /*
29  * NE10 Library : inc/NE10_math.h
30  */
31 
32 #include "NE10_types.h"
33 
34 #ifndef NE10_MATH_H
35 #define NE10_MATH_H
36 
37 #ifdef __cplusplus
38 extern "C" {
39 #endif
40 
63  extern ne10_result_t ne10_addc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) asm ("ne10_addc_float_neon");
66 
77  extern ne10_result_t (*ne10_addc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
79  extern ne10_result_t ne10_addc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
81  extern ne10_result_t ne10_addc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) asm ("ne10_addc_vec2f_neon");
83  extern ne10_result_t ne10_addc_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
84 
95  extern ne10_result_t (*ne10_addc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
97  extern ne10_result_t ne10_addc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
99  extern ne10_result_t ne10_addc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) asm ("ne10_addc_vec3f_neon");
101  extern ne10_result_t ne10_addc_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
102 
113  extern ne10_result_t (*ne10_addc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
115  extern ne10_result_t ne10_addc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
117  extern ne10_result_t ne10_addc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) asm ("ne10_addc_vec4f_neon");
119  extern ne10_result_t ne10_addc_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
120 
135  extern ne10_result_t ne10_add_float_neon (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) asm ("ne10_add_float_neon");
138 
149  extern ne10_result_t (*ne10_add_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
153  extern ne10_result_t ne10_add_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_add_vec2f_neon");
156 
167  extern ne10_result_t (*ne10_add_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
171  extern ne10_result_t ne10_add_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_add_vec3f_neon");
174 
185  extern ne10_result_t (*ne10_add_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
189  extern ne10_result_t ne10_add_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_add_vec4f_neon");
220 
238 
278  extern ne10_result_t (*ne10_subc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count);
285 
296  extern ne10_result_t (*ne10_subc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
298  extern ne10_result_t ne10_subc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
300  extern ne10_result_t ne10_subc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
302  extern ne10_result_t ne10_subc_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
303 
314  extern ne10_result_t (*ne10_subc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
316  extern ne10_result_t ne10_subc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
318  extern ne10_result_t ne10_subc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
320  extern ne10_result_t ne10_subc_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
321 
332  extern ne10_result_t (*ne10_subc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
334  extern ne10_result_t ne10_subc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
336  extern ne10_result_t ne10_subc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
338  extern ne10_result_t ne10_subc_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
339 
354  extern ne10_result_t ne10_sub_float_neon (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) asm ("ne10_sub_float_neon");
357 
368  extern ne10_result_t (*ne10_sub_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
372  extern ne10_result_t ne10_sub_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_sub_vec2f_neon");
375 
386  extern ne10_result_t (*ne10_sub_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
390  extern ne10_result_t ne10_sub_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_sub_vec3f_neon");
393 
404  extern ne10_result_t (*ne10_sub_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
408  extern ne10_result_t ne10_sub_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_sub_vec4f_neon");
439 
450  extern ne10_result_t (*ne10_rsbc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
452  extern ne10_result_t ne10_rsbc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
454  extern ne10_result_t ne10_rsbc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
456  extern ne10_result_t ne10_rsbc_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t *src, const ne10_vec2f_t * cst, ne10_uint32_t count);
457 
468  extern ne10_result_t (*ne10_rsbc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
470  extern ne10_result_t ne10_rsbc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
472  extern ne10_result_t ne10_rsbc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
474  extern ne10_result_t ne10_rsbc_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t *src, const ne10_vec3f_t * cst, ne10_uint32_t count);
475 
486  extern ne10_result_t (*ne10_rsbc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
488  extern ne10_result_t ne10_rsbc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
490  extern ne10_result_t ne10_rsbc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
492  extern ne10_result_t ne10_rsbc_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t *src, const ne10_vec4f_t * cst, ne10_uint32_t count);
521 
539 
578  extern ne10_result_t (*ne10_mulc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count);
585 
596  extern ne10_result_t (*ne10_mulc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
598  extern ne10_result_t ne10_mulc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
600  extern ne10_result_t ne10_mulc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
602  extern ne10_result_t ne10_mulc_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
603 
614  extern ne10_result_t (*ne10_mulc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
616  extern ne10_result_t ne10_mulc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
618  extern ne10_result_t ne10_mulc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
620  extern ne10_result_t ne10_mulc_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
621 
632  extern ne10_result_t (*ne10_mulc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
634  extern ne10_result_t ne10_mulc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
636  extern ne10_result_t ne10_mulc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
638  extern ne10_result_t ne10_mulc_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
639 
654  extern ne10_result_t ne10_mul_float_neon (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) asm ("ne10_mul_float_neon");
657 
668  extern ne10_result_t (*ne10_vmul_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
672  extern ne10_result_t ne10_vmul_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_vmul_vec2f_neon");
675 
686  extern ne10_result_t (*ne10_vmul_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
690  extern ne10_result_t ne10_vmul_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_vmul_vec3f_neon");
693 
704  extern ne10_result_t (*ne10_vmul_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
708  extern ne10_result_t ne10_vmul_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_vmul_vec4f_neon");
741 
754  extern ne10_result_t (*ne10_mlac_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
756  extern ne10_result_t ne10_mlac_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
758  extern ne10_result_t ne10_mlac_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
760  extern ne10_result_t ne10_mlac_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
761 
774  extern ne10_result_t (*ne10_mlac_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
776  extern ne10_result_t ne10_mlac_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
778  extern ne10_result_t ne10_mlac_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
780  extern ne10_result_t ne10_mlac_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
781 
794  extern ne10_result_t (*ne10_mlac_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
796  extern ne10_result_t ne10_mlac_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
798  extern ne10_result_t ne10_mlac_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
800  extern ne10_result_t ne10_mlac_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
801 
818  extern ne10_result_t ne10_mla_float_neon (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) asm ("ne10_mla_float_neon");
821 
834  extern ne10_result_t (*ne10_vmla_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
838  extern ne10_result_t ne10_vmla_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_vmla_vec2f_neon");
841 
854  extern ne10_result_t (*ne10_vmla_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
858  extern ne10_result_t ne10_vmla_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_vmla_vec3f_neon");
861 
874  extern ne10_result_t (*ne10_vmla_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
878  extern ne10_result_t ne10_vmla_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_vmla_vec4f_neon");
906  extern ne10_result_t ne10_mulmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) asm ("ne10_mulmat_4x4f_neon");
909 
924  extern ne10_result_t ne10_mulmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) asm ("ne10_mulmat_3x3f_neon");
927 
942  extern ne10_result_t ne10_mulmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) asm ("ne10_mulmat_2x2f_neon");
971  extern ne10_result_t ne10_mulcmatvec_cm4x4f_v4f_neon (ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count) asm ("ne10_mulcmatvec_cm4x4f_v4f_neon");
974 
990  extern ne10_result_t ne10_mulcmatvec_cm3x3f_v3f_neon (ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count) asm ("ne10_mulcmatvec_cm3x3f_v3f_neon");
993 
1009  extern ne10_result_t ne10_mulcmatvec_cm2x2f_v2f_neon (ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count) asm ("ne10_mulcmatvec_cm2x2f_v2f_neon");
1033  extern ne10_result_t (*ne10_divc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count);
1040 
1051  extern ne10_result_t (*ne10_divc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
1053  extern ne10_result_t ne10_divc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
1055  extern ne10_result_t ne10_divc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
1057  extern ne10_result_t ne10_divc_vec2f_asm (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count);
1058 
1069  extern ne10_result_t (*ne10_divc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
1071  extern ne10_result_t ne10_divc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
1073  extern ne10_result_t ne10_divc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
1075  extern ne10_result_t ne10_divc_vec3f_asm (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count);
1076 
1087  extern ne10_result_t (*ne10_divc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
1089  extern ne10_result_t ne10_divc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
1091  extern ne10_result_t ne10_divc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
1093  extern ne10_result_t ne10_divc_vec4f_asm (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count);
1094 
1105  extern ne10_result_t (*ne10_div_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count);
1109  extern ne10_result_t ne10_div_float_neon (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) asm ("ne10_div_float_neon");
1112 
1123  extern ne10_result_t (*ne10_vdiv_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
1127  extern ne10_result_t ne10_vdiv_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_vdiv_vec2f_neon");
1130 
1141  extern ne10_result_t (*ne10_vdiv_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
1145  extern ne10_result_t ne10_vdiv_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_vdiv_vec3f_neon");
1148 
1159  extern ne10_result_t (*ne10_vdiv_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
1163  extern ne10_result_t ne10_vdiv_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_vdiv_vec4f_neon");
1188  extern ne10_result_t (*ne10_divmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count);
1190  extern ne10_result_t ne10_divmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count);
1192  extern ne10_result_t ne10_divmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) asm ("ne10_divmat_4x4f_neon");
1194  extern ne10_result_t ne10_divmat_4x4f_asm (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count);
1195 
1206  extern ne10_result_t (*ne10_divmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count);
1208  extern ne10_result_t ne10_divmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count);
1210  extern ne10_result_t ne10_divmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) asm ("ne10_divmat_3x3f_neon");
1212  extern ne10_result_t ne10_divmat_3x3f_asm (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count);
1213 
1224  extern ne10_result_t (*ne10_divmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count);
1226  extern ne10_result_t ne10_divmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count);
1228  extern ne10_result_t ne10_divmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) asm ("ne10_divmat_2x2f_neon");
1230  extern ne10_result_t ne10_divmat_2x2f_asm (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count);
1252  extern ne10_result_t (*ne10_setc_float) (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count);
1259 
1268  extern ne10_result_t (*ne10_setc_vec2f) (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count);
1270  extern ne10_result_t ne10_setc_vec2f_c (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count);
1272  extern ne10_result_t ne10_setc_vec2f_neon (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count);
1274  extern ne10_result_t ne10_setc_vec2f_asm (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count);
1275 
1284  extern ne10_result_t (*ne10_setc_vec3f) (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count);
1286  extern ne10_result_t ne10_setc_vec3f_c (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count);
1288  extern ne10_result_t ne10_setc_vec3f_neon (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count);
1290  extern ne10_result_t ne10_setc_vec3f_asm (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count);
1291 
1300  extern ne10_result_t (*ne10_setc_vec4f) (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count);
1302  extern ne10_result_t ne10_setc_vec4f_c (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count);
1304  extern ne10_result_t ne10_setc_vec4f_neon (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count);
1306  extern ne10_result_t ne10_setc_vec4f_asm (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count);
1327  extern ne10_result_t (*ne10_len_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count);
1331  extern ne10_result_t ne10_len_vec2f_neon (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) asm ("ne10_len_vec2f_neon");
1334 
1344  extern ne10_result_t (*ne10_len_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count);
1348  extern ne10_result_t ne10_len_vec3f_neon (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) asm ("ne10_len_vec3f_neon");
1351 
1361  extern ne10_result_t (*ne10_len_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count);
1365  extern ne10_result_t ne10_len_vec4f_neon (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) asm ("ne10_len_vec4f_neon");
1393  extern ne10_result_t ne10_normalize_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) asm ("ne10_normalize_vec2f_neon");
1396 
1410  extern ne10_result_t ne10_normalize_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) asm ("ne10_normalize_vec3f_neon");
1413 
1427  extern ne10_result_t ne10_normalize_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) asm ("ne10_normalize_vec4f_neon");
1455  extern ne10_result_t ne10_abs_float_neon (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count) asm ("ne10_abs_float_neon");
1458 
1468  extern ne10_result_t (*ne10_abs_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count);
1472  extern ne10_result_t ne10_abs_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) asm ("ne10_abs_vec2f_neon");
1475 
1485  extern ne10_result_t (*ne10_abs_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count);
1489  extern ne10_result_t ne10_abs_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) asm ("ne10_abs_vec3f_neon");
1492 
1502  extern ne10_result_t (*ne10_abs_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count);
1506  extern ne10_result_t ne10_abs_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) asm ("ne10_abs_vec4f_neon");
1530  extern ne10_result_t (*ne10_dot_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count);
1534  extern ne10_result_t ne10_dot_vec2f_neon (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) asm ("ne10_dot_vec2f_neon");
1537 
1548  extern ne10_result_t (*ne10_dot_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
1552  extern ne10_result_t ne10_dot_vec3f_neon (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_dot_vec3f_neon");
1555 
1566  extern ne10_result_t (*ne10_dot_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count);
1570  extern ne10_result_t ne10_dot_vec4f_neon (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) asm ("ne10_dot_vec4f_neon");
1595  extern ne10_result_t (*ne10_cross_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count);
1599  extern ne10_result_t ne10_cross_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) asm ("ne10_cross_vec3f_neon");
1626  extern ne10_result_t ne10_detmat_4x4f_neon (ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) asm ("ne10_detmat_4x4f_neon");
1629 
1643  extern ne10_result_t ne10_detmat_3x3f_neon (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) asm ("ne10_detmat_3x3f_neon");
1646 
1660  extern ne10_result_t ne10_detmat_2x2f_neon (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) asm ("ne10_detmat_2x2f_neon");
1687  extern ne10_result_t ne10_invmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) asm ("ne10_invmat_4x4f_neon");
1690 
1704  extern ne10_result_t ne10_invmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) asm ("ne10_invmat_3x3f_neon");
1707 
1721  extern ne10_result_t ne10_invmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) asm ("ne10_invmat_2x2f_neon");
1748  extern ne10_result_t ne10_transmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) asm ("ne10_transmat_4x4f_neon");
1751 
1765  extern ne10_result_t ne10_transmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) asm ("ne10_transmat_3x3f_neon");
1768 
1782  extern ne10_result_t ne10_transmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) asm ("ne10_transmat_2x2f_neon");
1807  extern ne10_result_t ne10_identitymat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_uint32_t count) asm ("ne10_identitymat_4x4f_neon");
1810 
1822  extern ne10_result_t ne10_identitymat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_uint32_t count) asm ("ne10_identitymat_3x3f_neon");
1825 
1837  extern ne10_result_t ne10_identitymat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_uint32_t count) asm ("ne10_identitymat_2x2f_neon");
1842 #ifdef __cplusplus
1843 }
1844 #endif
1845 
1846 #endif
ne10_result_t(* ne10_detmat_4x4f)(ne10_float32_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Calculates the determinant of 4x4 matrices within an input array, storing the results in an output ar...
ne10_result_t ne10_mlac_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec2f using plain C code.
Definition: NE10_mlac.c:47
ne10_result_t(* ne10_mulc_float)(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Multiplies all scalar elements of an input array by a constant value, storing the results in an outpu...
ne10_result_t ne10_sub_float_asm(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_float using NEON assembly.
ne10_result_t ne10_len_vec3f_c(ne10_float32_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec3f using plain C code.
Definition: NE10_len.c:50
ne10_result_t(* ne10_mul_float)(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Multiplies the scalar elements of one input array by those of the same index in another, storing the results in an output array.
ne10_result_t(* ne10_vdiv_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Element-wise divides the 4D vectors of one input array by those of the same index in another...
ne10_result_t(* ne10_add_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Adds the 4D vectors of one input array with those of the same index in another, storing the results i...
ne10_result_t ne10_add_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec2f using NEON assembly.
ne10_result_t(* ne10_subc_float)(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Subtracts a constant scalar value from all elements of an input array, storing the results in an outp...
ne10_result_t ne10_vmla_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec4f using NEON assembly.
ne10_result_t(* ne10_addmat_2x2f)(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Adds the 2x2 matrices of one input array with those of the same index in another, storing the results...
ne10_result_t ne10_setc_vec3f_asm(ne10_vec3f_t *dst, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec3f using NEON assembly.
ne10_result_t ne10_addc_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count) asm("ne10_addc_vec4f_neon")
Specific implementation of ne10_addc_vec4f using NEON intrinsics.
ne10_result_t ne10_transmat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_4x4f using NEON assembly.
ne10_result_t ne10_addmat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_3x3f using NEON intrinsics.
ne10_result_t ne10_subc_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec3f using NEON intrinsics.
ne10_result_t ne10_abs_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count) asm("ne10_abs_vec4f_neon")
Specific implementation of ne10_abs_vec4f using NEON intrinsics.
ne10_result_t ne10_normalize_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count) asm("ne10_normalize_vec3f_neon")
Specific implementation of ne10_normalize_vec3f using NEON intrinsics.
ne10_result_t(* ne10_sub_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Subtracts the 4D vectors of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t(* ne10_mulcmatvec_cm4x4f_v4f)(ne10_vec4f_t *dst, const ne10_mat4x4f_t *cst, ne10_vec4f_t *src, ne10_uint32_t count)
Multiplies the 4x4 matrices of one input array by the 4D vectors of the same index in another...
ne10_result_t ne10_mlac_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec4f using NEON assembly.
ne10_result_t ne10_addc_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count) asm("ne10_addc_vec3f_neon")
Specific implementation of ne10_addc_vec3f using NEON intrinsics.
ne10_result_t ne10_mulc_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec2f using plain C code.
Definition: NE10_mulc.c:47
ne10_result_t ne10_vdiv_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec4f using NEON assembly.
ne10_result_t ne10_trans_mat2x2f_asm(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_2x2f using NEON assembly.
ne10_result_t ne10_mlac_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec4f using plain C code.
Definition: NE10_mlac.c:70
ne10_result_t(* ne10_add_float)(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Adds the scalar elements of one input array with those of the same index in another, storing the results in an output array.
ne10_result_t ne10_cross_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_cross_vec3f using plain C code.
Definition: NE10_cross.c:37
ne10_result_t ne10_transmat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_3x3f using NEON assembly.
ne10_result_t ne10_abs_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count) asm("ne10_abs_vec2f_neon")
Specific implementation of ne10_abs_vec2f using NEON intrinsics.
ne10_result_t(* ne10_add_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Adds the 3D vectors of one input array with those of the same index in another, storing the results i...
ne10_result_t(* ne10_vmla_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Element-wise multiplies all the 3D vector elements of an input array by those of the same index in an...
ne10_result_t(* ne10_mlac_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 2D vectors of an input array by a constant vector, adding this vector to another of the same index in another input array, and storing the results in an output array.
ne10_result_t(* ne10_len_vec2f)(ne10_float32_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Calculates the magnitude of 2D vectors within an input array, storing the results in an output array...
ne10_result_t ne10_divc_float_c(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_divc_float using plain C code.
Definition: NE10_divc.c:37
ne10_result_t ne10_mla_float_asm(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mla_float using NEON assembly.
ne10_result_t ne10_mulcmatvec_cm4x4f_v4f_asm(ne10_vec4f_t *dst, const ne10_mat4x4f_t *cst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm4x4f_v4f using NEON assembly.
ne10_result_t ne10_dot_vec4f_neon(ne10_float32_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_dot_vec4f_neon")
Specific implementation of ne10_dot_vec4f using NEON intrinsics.
ne10_result_t ne10_rsbc_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec2f using NEON intrinsics.
ne10_result_t ne10_mul_float_asm(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mul_float using NEON assembly.
ne10_result_t(* ne10_mulmat_2x2f)(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Multiplies the 2x2 matrices of one input array by those of the same index in another, storing the results in an output array.
ne10_result_t ne10_identitymat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_4x4f using NEON assembly.
ne10_result_t ne10_rsbc_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec2f using plain C code.
Definition: NE10_rsbc.c:47
ne10_result_t ne10_divc_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec4f using NEON intrinsics.
ne10_result_t ne10_sub_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_sub_vec2f_neon")
Specific implementation of ne10_sub_vec2f using NEON intrinsics.
ne10_result_t(* ne10_dot_vec3f)(ne10_float32_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Calculate the dot product of 3D vectors from one input array with those of the same index in another...
ne10_result_t(* ne10_dot_vec4f)(ne10_float32_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Calculates the dot product of 4D vectors from one input array with those of the same index in another...
ne10_result_t ne10_sub_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_sub_vec3f_neon")
Specific implementation of ne10_sub_vec3f using NEON intrinsics.
ne10_result_t ne10_submat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_4x4f using NEON intrinsics.
ne10_result_t ne10_rsbc_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec3f using plain C code.
Definition: NE10_rsbc.c:58
ne10_result_t ne10_setc_float_asm(ne10_float32_t *dst, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_setc_float using NEON assembly.
ne10_result_t ne10_transmat_3x3f_c(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_3x3f using plain C code.
Definition: NE10_transmat.c:58
ne10_result_t ne10_transmat_2x2f_c(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_2x2f using plain C code.
Definition: NE10_transmat.c:45
ne10_result_t(* ne10_mulc_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 4D vectors in an input array by a constant vector, storing the results in an output array.
ne10_result_t ne10_addc_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec3f using plain C code.
Definition: NE10_addc.c:58
ne10_result_t(* ne10_normalize_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Calculates the normalization of 4D vectors within an input array, storing the results in an output ar...
ne10_result_t ne10_vmla_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec4f using plain C code.
Definition: NE10_mla.c:70
A 2-tuple of ne10_float32_t values.
Definition: NE10_types.h:87
ne10_result_t ne10_dot_vec4f_c(ne10_float32_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec4f using plain C code.
Definition: NE10_dot.c:60
ne10_result_t ne10_cross_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_cross_vec3f_neon")
Specific implementation of ne10_cross_vec3f using NEON intrinsics.
ne10_result_t ne10_normalize_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count) asm("ne10_normalize_vec2f_neon")
Specific implementation of ne10_normalize_vec2f using NEON intrinsics.
ne10_result_t(* ne10_len_vec3f)(ne10_float32_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Calculates the magnitude of 3D vectors within an input array, storing the results in an output array...
ne10_result_t ne10_submat_2x2f_asm(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_2x2f using NEON assembly.
ne10_result_t ne10_detmat_3x3f_c(ne10_float32_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_3x3f using plain C code.
Definition: NE10_detmat.c:48
ne10_result_t(* ne10_mlac_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 4D vectors of an input array by a constant vector, adding this vector to another of the same index in another input array, and storing the results in an output array.
ne10_result_t ne10_abs_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec2f using NEON assembly.
ne10_result_t ne10_addmat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_4x4f using NEON intrinsics.
ne10_result_t(* ne10_invmat_4x4f)(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Calculates the inverse of 4x4 matrices within an input array, storing the results in an output array...
ne10_result_t ne10_subc_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec4f using NEON intrinsics.
ne10_result_t(* ne10_mulmat_4x4f)(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Multiplies the 4x4 matrices of one input array by those of the same index in another, storing the results in an output array.
float ne10_float32_t
Definition: NE10_types.h:80
ne10_result_t ne10_submat_4x4f_c(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_4x4f using plain C code.
Definition: NE10_submat.c:71
ne10_result_t ne10_invmat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count) asm("ne10_invmat_2x2f_neon")
Specific implementation of ne10_invmat_2x2f using NEON intrinsics.
ne10_result_t(* ne10_subc_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Subtracts a constant 4D vector from all the vectors in an input array, storing the results in an outp...
ne10_result_t ne10_identitymat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_uint32_t count) asm("ne10_identitymat_3x3f_neon")
Specific implementation of ne10_identitymat_3x3f using NEON intrinsics.
ne10_result_t ne10_vmul_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec2f using NEON assembly.
ne10_result_t(* ne10_subc_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Subtracts a constant 2D vector from all the vectors in an input array, storing the results in an outp...
ne10_result_t(* ne10_identitymat_2x2f)(ne10_mat2x2f_t *dst, ne10_uint32_t count)
Sets the elements of an array of 2x2 matrices to the identity matrix.
ne10_result_t(* ne10_submat_2x2f)(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Subtracts the 2x2 matrices of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_invmat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count) asm("ne10_invmat_4x4f_neon")
Specific implementation of ne10_invmat_4x4f using NEON intrinsics.
ne10_result_t ne10_identitymat_2x2f_c(ne10_mat2x2f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_2x2f using plain C code.
ne10_result_t ne10_mulcmatvec_cm2x2f_v2f_neon(ne10_vec2f_t *dst, const ne10_mat2x2f_t *cst, ne10_vec2f_t *src, ne10_uint32_t count) asm("ne10_mulcmatvec_cm2x2f_v2f_neon")
Specific implementation of ne10_mulcmatvec_cm2x2f_v2f using NEON intrinsics.
ne10_result_t(* ne10_addc_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Adds a constant 4D vector to all the vectors in an input array, storing the results in an output arra...
ne10_result_t ne10_add_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_add_vec2f_neon")
Specific implementation of ne10_add_vec2f using NEON intrinsics.
ne10_result_t ne10_add_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec2f using plain C code.
Definition: NE10_add.c:48
ne10_result_t ne10_add_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec3f using plain C code.
Definition: NE10_add.c:59
ne10_result_t ne10_abs_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec4f using plain C code.
Definition: NE10_abs.c:72
ne10_result_t ne10_identitymat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_uint32_t count) asm("ne10_identitymat_4x4f_neon")
Specific implementation of ne10_identitymat_4x4f using NEON intrinsics.
ne10_result_t ne10_add_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec4f using plain C code.
Definition: NE10_add.c:71
ne10_result_t ne10_vdiv_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_vdiv_vec2f_neon")
Specific implementation of ne10_vdiv_vec2f using NEON intrinsics.
ne10_result_t ne10_invmat_2x2f_asm(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_2x2f using NEON assembly.
ne10_result_t ne10_normalize_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count) asm("ne10_normalize_vec4f_neon")
Specific implementation of ne10_normalize_vec4f using NEON intrinsics.
ne10_result_t(* ne10_abs_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Calculates the element-wise absolute value of 4D vectors within an input array, storing the results i...
ne10_result_t ne10_vdiv_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec2f using plain C code.
Definition: NE10_div.c:47
ne10_result_t ne10_addc_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count) asm("ne10_addc_vec2f_neon")
Specific implementation of ne10_addc_vec2f using NEON intrinsics.
ne10_result_t ne10_addmat_2x2f_c(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_2x2f using plain C code.
Definition: NE10_addmat.c:37
ne10_result_t(* ne10_sub_float)(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Subtracts the scalar elements of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_detmat_4x4f_neon(ne10_float32_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count) asm("ne10_detmat_4x4f_neon")
Specific implementation of ne10_detmat_4x4f using NEON intrinsics.
ne10_result_t ne10_sub_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec2f using NEON assembly.
ne10_result_t ne10_add_float_asm(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_float using NEON assembly.
ne10_result_t ne10_mulc_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec3f using NEON intrinsics.
ne10_result_t(* ne10_setc_float)(ne10_float32_t *dst, const ne10_float32_t cst, ne10_uint32_t count)
Sets the scalar elements of an array to a constant value.
ne10_result_t ne10_identitymat_4x4f_c(ne10_mat4x4f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_4x4f using plain C code.
ne10_result_t ne10_mlac_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec3f using NEON intrinsics.
ne10_result_t ne10_dot_vec3f_asm(ne10_float32_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec3f using NEON assembly.
ne10_result_t ne10_mulcmatvec_cm4x4f_v4f_c(ne10_vec4f_t *dst, const ne10_mat4x4f_t *cst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm4x4f_v4f using plain C code.
ne10_result_t ne10_addc_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec2f using plain C code.
Definition: NE10_addc.c:47
ne10_result_t ne10_subc_float_asm(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_subc_float using NEON assembly.
ne10_result_t ne10_cross_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_cross_vec3f using NEON assembly.
ne10_result_t(* ne10_detmat_2x2f)(ne10_float32_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Calculates the determinant of 2x2 matrices within an input array, storing the results in an output ar...
ne10_result_t ne10_add_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec4f using NEON assembly.
ne10_result_t ne10_subc_float_c(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_subc_float using plain C code.
Definition: NE10_subc.c:37
ne10_result_t ne10_dot_vec4f_asm(ne10_float32_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec4f using NEON assembly.
ne10_result_t ne10_vmla_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec2f using NEON assembly.
ne10_result_t ne10_sub_float_neon(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count) asm("ne10_sub_float_neon")
Specific implementation of ne10_sub_float using NEON intrinsics.
ne10_result_t(* ne10_mulcmatvec_cm3x3f_v3f)(ne10_vec3f_t *dst, const ne10_mat3x3f_t *cst, ne10_vec3f_t *src, ne10_uint32_t count)
Multiplies the 3x3 matrices of one input array by the 3D vectors of the same index in another...
ne10_result_t(* ne10_abs_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Calculates the element-wise absolute value of 3D vectors within an input array, storing the results i...
ne10_result_t ne10_sub_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec4f using NEON assembly.
ne10_result_t ne10_mulc_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec3f using plain C code.
Definition: NE10_mulc.c:58
ne10_result_t(* ne10_add_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Adds the 2D vectors of one input array with those of the same index in another, storing the results i...
ne10_result_t(* ne10_detmat_3x3f)(ne10_float32_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Calculates the determinant of 3x3 matrices within an input array, storing the results in an output ar...
ne10_result_t ne10_vdiv_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec2f using NEON assembly.
ne10_result_t ne10_abs_float_asm(ne10_float32_t *dst, ne10_float32_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_float using NEON assembly.
ne10_result_t ne10_mulc_float_neon(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_float using NEON intrinsics.
uint32_t ne10_uint32_t
Definition: NE10_types.h:77
ne10_result_t ne10_sub_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec4f using plain C code.
Definition: NE10_sub.c:70
ne10_result_t ne10_mulmat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count) asm("ne10_mulmat_3x3f_neon")
Specific implementation of ne10_mulmat_3x3f using NEON intrinsics.
ne10_result_t ne10_mulc_float_c(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_float using plain C code.
Definition: NE10_mulc.c:37
ne10_result_t(* ne10_addc_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Adds a constant 3D vector to all the vectors in an input array, storing the results in an output arra...
ne10_result_t(* ne10_sub_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Subtracts the 3D vectors of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_len_vec4f_c(ne10_float32_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec4f using plain C code.
Definition: NE10_len.c:62
ne10_result_t(* ne10_vmla_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Element-wise multiplies all the 2D vector elements of an input array by those of the same index in an...
ne10_result_t ne10_vdiv_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec3f using NEON assembly.
ne10_result_t ne10_setc_vec4f_neon(ne10_vec4f_t *dst, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec4f using NEON intrinsics.
ne10_result_t ne10_identitymat_3x3f_c(ne10_mat3x3f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_3x3f using plain C code.
ne10_result_t ne10_divc_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec4f using NEON assembly.
ne10_result_t(* ne10_setc_vec2f)(ne10_vec2f_t *dst, const ne10_vec2f_t *cst, ne10_uint32_t count)
Sets the 2D vector elements of an array to a constant vector.
ne10_result_t ne10_abs_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec3f using NEON assembly.
ne10_result_t(* ne10_transmat_3x3f)(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Calculates the transpose of 3x3 matrices within an input array, storing the results in an output arra...
ne10_result_t(* ne10_mulc_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 2D vectors in an input array by a constant vector, storing the results in an output array.
ne10_result_t ne10_normalize_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec4f using plain C code.
ne10_result_t ne10_vmla_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec3f using plain C code.
Definition: NE10_mla.c:58
ne10_result_t(* ne10_mlac_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 3D vectors of an input array by a constant vector, adding this vector to another of the same index in another input array, and storing the results in an output array.
ne10_result_t(* ne10_submat_3x3f)(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Subtracts the 3x3 matrices of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_rsbc_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec3f using NEON assembly.
ne10_result_t ne10_normalize_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec3f using plain C code.
ne10_result_t ne10_mulcmatvec_cm2x2f_v2f_asm(ne10_vec2f_t *dst, const ne10_mat2x2f_t *cst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm2x2f_v2f using NEON assembly.
ne10_result_t ne10_sub_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec3f using NEON assembly.
ne10_result_t ne10_mulcmatvec_cm3x3f_v3f_neon(ne10_vec3f_t *dst, const ne10_mat3x3f_t *cst, ne10_vec3f_t *src, ne10_uint32_t count) asm("ne10_mulcmatvec_cm3x3f_v3f_neon")
Specific implementation of ne10_mulcmatvec_cm3x3f_v3f using NEON intrinsics.
ne10_result_t ne10_vmul_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec3f using NEON assembly.
ne10_result_t ne10_subc_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec3f using NEON assembly.
ne10_result_t(* ne10_divc_float)(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Divides all scalar elements of an input array by a constant value, storing the results in an output a...
ne10_result_t ne10_setc_vec2f_neon(ne10_vec2f_t *dst, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec2f using NEON intrinsics.
ne10_result_t ne10_setc_vec2f_asm(ne10_vec2f_t *dst, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec2f using NEON assembly.
ne10_result_t ne10_submat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_2x2f using NEON intrinsics.
ne10_result_t ne10_dot_vec2f_asm(ne10_float32_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec2f using NEON assembly.
ne10_result_t ne10_mulmat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_4x4f using NEON assembly.
ne10_result_t ne10_addmat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_4x4f using NEON assembly.
ne10_result_t ne10_vdiv_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_vdiv_vec4f_neon")
Specific implementation of ne10_vdiv_vec4f using NEON intrinsics.
ne10_result_t ne10_len_vec2f_c(ne10_float32_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec2f using plain C code.
Definition: NE10_len.c:39
ne10_result_t ne10_divc_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec3f using NEON intrinsics.
ne10_result_t ne10_subc_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec2f using NEON assembly.
ne10_result_t ne10_abs_float_c(ne10_float32_t *dst, ne10_float32_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_float using plain C code.
Definition: NE10_abs.c:39
ne10_result_t(* ne10_transmat_4x4f)(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Calculates the transpose of 4x4 matrices within an input array, storing the results in an output arra...
ne10_result_t ne10_rsbc_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec3f using NEON intrinsics.
ne10_result_t(* ne10_setc_vec3f)(ne10_vec3f_t *dst, const ne10_vec3f_t *cst, ne10_uint32_t count)
Sets the 3D vector elements of an array to a constant vector.
ne10_result_t ne10_addc_float_neon(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count) asm("ne10_addc_float_neon")
Specific implementation of ne10_addc_float using NEON intrinsics.
ne10_result_t ne10_vmla_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec2f using plain C code.
Definition: NE10_mla.c:47
ne10_result_t ne10_vmul_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec3f using plain C code.
Definition: NE10_mul.c:58
ne10_result_t ne10_identitymat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_uint32_t count) asm("ne10_identitymat_2x2f_neon")
Specific implementation of ne10_identitymat_2x2f using NEON intrinsics.
ne10_result_t ne10_vmla_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_vmla_vec2f_neon")
Specific implementation of ne10_vmla_vec2f using NEON intrinsics.
ne10_result_t ne10_detmat_4x4f_asm(ne10_float32_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_4x4f using NEON assembly.
ne10_result_t ne10_vdiv_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_vdiv_vec3f_neon")
Specific implementation of ne10_vdiv_vec3f using NEON intrinsics.
ne10_result_t(* ne10_mulcmatvec_cm2x2f_v2f)(ne10_vec2f_t *dst, const ne10_mat2x2f_t *cst, ne10_vec2f_t *src, ne10_uint32_t count)
Multiplies the 2x2 matrices of one input array by the 2D vectors of the same index in another...
ne10_result_t ne10_mulcmatvec_cm2x2f_v2f_c(ne10_vec2f_t *dst, const ne10_mat2x2f_t *cst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm2x2f_v2f using plain C code.
ne10_result_t(* ne10_sub_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Subtracts the 2D vectors of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_divc_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec2f using NEON assembly.
ne10_result_t(* ne10_rsbc_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Subtracts all the 4D vectors in an input array from a constant vector, storing the results in an outp...
ne10_result_t ne10_mulc_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec2f using NEON assembly.
ne10_result_t(* ne10_subc_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Subtracts a constant 3D vector from all the vectors in an input array, storing the results in an outp...
ne10_result_t ne10_div_float_c(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_div_float using plain C code.
Definition: NE10_div.c:37
ne10_result_t(* ne10_addmat_3x3f)(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Adds the 3x3 matrices of one input array with those of the same index in another, storing the results...
ne10_result_t(* ne10_rsbc_float)(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Subtracts all scalar elements of an input array from a constant value, storing the results in an outp...
ne10_result_t(* ne10_setc_vec4f)(ne10_vec4f_t *dst, const ne10_vec4f_t *cst, ne10_uint32_t count)
Sets the 4D vector elements of an array to a constant vector.
ne10_result_t ne10_mlac_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec3f using NEON assembly.
ne10_result_t ne10_mulcmatvec_cm3x3f_v3f_asm(ne10_vec3f_t *dst, const ne10_mat3x3f_t *cst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm3x3f_v3f using NEON assembly.
ne10_result_t(* ne10_normalize_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Calculates the normalization of 2D vectors within an input array, storing the results in an output ar...
ne10_result_t ne10_mul_float_neon(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count) asm("ne10_mul_float_neon")
Specific implementation of ne10_mul_float using NEON intrinsics.
ne10_result_t ne10_vmul_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec2f using plain C code.
Definition: NE10_mul.c:47
ne10_result_t ne10_detmat_2x2f_asm(ne10_float32_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_2x2f using NEON assembly.
ne10_result_t ne10_mulmat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count) asm("ne10_mulmat_2x2f_neon")
Specific implementation of ne10_mulmat_2x2f using NEON intrinsics.
ne10_result_t(* ne10_normalize_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Calculates the normalization of 3D vectors within an input array, storing the results in an output ar...
ne10_result_t ne10_addc_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec3f using NEON assembly.
ne10_result_t(* ne10_div_float)(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Divides the scalar elements of one input array by those of the same index in another, storing the results in an output array.
ne10_result_t ne10_detmat_2x2f_c(ne10_float32_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_2x2f using plain C code.
Definition: NE10_detmat.c:38
ne10_result_t ne10_rsbc_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec2f using NEON assembly.
ne10_result_t ne10_detmat_3x3f_asm(ne10_float32_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_3x3f using NEON assembly.
ne10_result_t ne10_submat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_3x3f using NEON assembly.
ne10_result_t ne10_dot_vec3f_c(ne10_float32_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec3f using plain C code.
Definition: NE10_dot.c:48
ne10_result_t ne10_mulcmatvec_cm4x4f_v4f_neon(ne10_vec4f_t *dst, const ne10_mat4x4f_t *cst, ne10_vec4f_t *src, ne10_uint32_t count) asm("ne10_mulcmatvec_cm4x4f_v4f_neon")
Specific implementation of ne10_mulcmatvec_cm4x4f_v4f using NEON intrinsics.
ne10_result_t ne10_transmat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count) asm("ne10_transmat_3x3f_neon")
Specific implementation of ne10_transmat_3x3f using NEON intrinsics.
ne10_result_t ne10_normalize_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec3f using NEON assembly.
ne10_result_t ne10_rsbc_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec4f using NEON assembly.
ne10_result_t ne10_vmul_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_vmul_vec4f_neon")
Specific implementation of ne10_vmul_vec4f using NEON intrinsics.
A 3-tuple of ne10_float32_t values.
Definition: NE10_types.h:96
ne10_result_t(* ne10_divc_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Element-wise divides all the 2D vectors in an input array by a constant vector, storing the results i...
ne10_result_t ne10_mlac_float_neon(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_float using NEON intrinsics.
ne10_result_t(* ne10_cross_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Calculate the cross product of 3D vectors from one input array with those of the same index in anothe...
ne10_result_t ne10_detmat_4x4f_c(ne10_float32_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_detmat_4x4f using plain C code.
Definition: NE10_detmat.c:58
ne10_result_t ne10_addmat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_3x3f using NEON assembly.
ne10_result_t ne10_submat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_3x3f using NEON intrinsics.
ne10_result_t ne10_addc_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec4f using plain C code.
Definition: NE10_addc.c:70
ne10_result_t(* ne10_dot_vec2f)(ne10_float32_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Calculates the dot product of 2D vectors from one input array with those of the same index in another...
ne10_result_t ne10_mlac_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec3f using plain C code.
Definition: NE10_mlac.c:58
ne10_result_t ne10_addc_float_c(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_addc_float using plain C code.
Definition: NE10_addc.c:37
ne10_result_t ne10_setc_vec3f_neon(ne10_vec3f_t *dst, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec3f using NEON intrinsics.
ne10_result_t ne10_invmat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_4x4f using NEON assembly.
ne10_result_t ne10_setc_vec3f_c(ne10_vec3f_t *dst, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec3f using plain C code.
Definition: NE10_setc.c:58
ne10_result_t ne10_divc_float_asm(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_divc_float using NEON assembly.
ne10_result_t ne10_abs_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count) asm("ne10_abs_vec3f_neon")
Specific implementation of ne10_abs_vec3f using NEON intrinsics.
ne10_result_t ne10_vmul_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec4f using NEON assembly.
ne10_result_t ne10_mulc_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec4f using plain C code.
Definition: NE10_mulc.c:70
ne10_result_t ne10_add_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_vec3f using NEON assembly.
ne10_result_t ne10_rsbc_float_neon(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_float using NEON intrinsics.
ne10_result_t ne10_len_vec2f_neon(ne10_float32_t *dst, ne10_vec2f_t *src, ne10_uint32_t count) asm("ne10_len_vec2f_neon")
Specific implementation of ne10_len_vec2f using NEON intrinsics.
ne10_result_t(* ne10_addc_float)(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Adds a constant scalar value to all elements of an input array, storing the results in an output arra...
ne10_result_t ne10_abs_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec2f using plain C code.
Definition: NE10_abs.c:49
ne10_result_t ne10_mulmat_2x2f_c(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_2x2f using plain C code.
Definition: NE10_mulmat.c:37
ne10_result_t ne10_setc_vec2f_c(ne10_vec2f_t *dst, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec2f using plain C code.
Definition: NE10_setc.c:47
ne10_result_t ne10_submat_3x3f_c(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_3x3f using plain C code.
Definition: NE10_submat.c:51
ne10_result_t(* ne10_mla_float)(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Multiplies all scalar elements of an input array by those of the same index in another, adding this product to a value of the same index in yet another input array, and storing the results in an output array.
ne10_result_t ne10_abs_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec3f using plain C code.
Definition: NE10_abs.c:60
ne10_result_t(* ne10_addmat_4x4f)(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Adds the 4x4 matrices of one input array with those of the same index in another, storing the results...
ne10_result_t ne10_add_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_add_vec3f_neon")
Specific implementation of ne10_add_vec3f using NEON intrinsics.
ne10_result_t ne10_abs_float_neon(ne10_float32_t *dst, ne10_float32_t *src, ne10_uint32_t count) asm("ne10_abs_float_neon")
Specific implementation of ne10_abs_float using NEON intrinsics.
ne10_result_t(* ne10_vmul_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Element-wise multiplies the 3D vectors of one input array by those of the same index in another...
ne10_result_t ne10_addc_float_asm(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_addc_float using NEON assembly.
ne10_result_t ne10_divc_float_neon(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_divc_float using NEON intrinsics.
ne10_result_t(* ne10_abs_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Calculates the element-wise absolute value of 2D vectors within an input array, storing the results i...
ne10_result_t(* ne10_invmat_2x2f)(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Calculates the inverse of 2x2 matrices within an input array, storing the results in an output array...
ne10_result_t ne10_vmul_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_vmul_vec3f_neon")
Specific implementation of ne10_vmul_vec3f using NEON intrinsics.
ne10_result_t ne10_submat_4x4f_asm(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_4x4f using NEON assembly.
ne10_result_t ne10_rsbc_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec4f using plain C code.
Definition: NE10_rsbc.c:70
ne10_result_t ne10_normalize_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec4f using NEON assembly.
ne10_result_t ne10_dot_vec2f_c(ne10_float32_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_dot_vec2f using plain C code.
Definition: NE10_dot.c:37
ne10_result_t ne10_subc_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec2f using plain C code.
Definition: NE10_subc.c:47
ne10_result_t(* ne10_mulc_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Element-wise multiplies all the 3D vectors in an input array by a constant vector, storing the results in an output array.
ne10_result_t ne10_mulc_float_asm(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_float using NEON assembly.
ne10_result_t(* ne10_addc_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Adds a constant 2D vector to all the vectors in an input array, storing the results in an output arra...
ne10_result_t ne10_transmat_4x4f_c(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_transmat_4x4f using plain C code.
Definition: NE10_transmat.c:78
ne10_result_t ne10_vdiv_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec3f using plain C code.
Definition: NE10_div.c:58
ne10_result_t(* ne10_identitymat_3x3f)(ne10_mat3x3f_t *dst, ne10_uint32_t count)
Sets the elements of an array of 3x3 matrices to the identity matrix.
ne10_result_t ne10_invmat_4x4f_c(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_4x4f using plain C code.
Definition: NE10_invmat.c:127
ne10_result_t ne10_mulc_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec4f using NEON assembly.
ne10_result_t ne10_vmla_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_vmla_vec4f_neon")
Specific implementation of ne10_vmla_vec4f using NEON intrinsics.
ne10_result_t ne10_vdiv_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vdiv_vec4f using plain C code.
Definition: NE10_div.c:70
ne10_result_t ne10_vmul_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_vmul_vec2f_neon")
Specific implementation of ne10_vmul_vec2f using NEON intrinsics.
ne10_result_t ne10_divc_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec3f using plain C code.
Definition: NE10_divc.c:58
ne10_result_t(* ne10_mlac_float)(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Multiplies all scalar elements of an input array by constant value, adding this product to a value of...
ne10_result_t ne10_addc_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec4f using NEON assembly.
ne10_result_t ne10_detmat_3x3f_neon(ne10_float32_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count) asm("ne10_detmat_3x3f_neon")
Specific implementation of ne10_detmat_3x3f using NEON intrinsics.
ne10_result_t(* ne10_vmul_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Element-wise multiplies the 2D vectors of one input array by those of the same index in another...
ne10_result_t ne10_mulmat_3x3f_c(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_3x3f using plain C code.
Definition: NE10_mulmat.c:69
ne10_result_t ne10_div_float_asm(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_div_float using NEON assembly.
ne10_result_t ne10_transmat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count) asm("ne10_transmat_2x2f_neon")
Specific implementation of ne10_transmat_2x2f using NEON intrinsics.
ne10_result_t ne10_dot_vec2f_neon(ne10_float32_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count) asm("ne10_dot_vec2f_neon")
Specific implementation of ne10_dot_vec2f using NEON intrinsics.
ne10_result_t ne10_vmla_vec3f_neon(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_vmla_vec3f_neon")
Specific implementation of ne10_vmla_vec3f using NEON intrinsics.
ne10_result_t ne10_mulmat_2x2f_asm(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_2x2f using NEON assembly.
ne10_result_t ne10_sub_float_c(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_float using plain C code.
Definition: NE10_sub.c:37
ne10_result_t ne10_mul_float_c(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mul_float using plain C code.
Definition: NE10_mul.c:37
ne10_result_t ne10_addmat_3x3f_c(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_3x3f using plain C code.
Definition: NE10_addmat.c:51
ne10_result_t ne10_setc_vec4f_asm(ne10_vec4f_t *dst, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec4f using NEON assembly.
ne10_result_t(* ne10_vmul_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Element-wise multiplies the 4D vectors of one input array by those of the same index in another...
ne10_result_t ne10_identity_mat2x2f_asm(ne10_mat2x2f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_2x2f using NEON assembly.
ne10_result_t ne10_vmla_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *acc, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmla_vec3f using NEON assembly.
ne10_result_t(* ne10_vmla_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Element-wise multiplies all the 4D vector elements of an input array by those of the same index in an...
ne10_result_t ne10_len_vec4f_neon(ne10_float32_t *dst, ne10_vec4f_t *src, ne10_uint32_t count) asm("ne10_len_vec4f_neon")
Specific implementation of ne10_len_vec4f using NEON intrinsics.
ne10_result_t ne10_sub_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_sub_vec4f_neon")
Specific implementation of ne10_sub_vec4f using NEON intrinsics.
ne10_result_t ne10_dot_vec3f_neon(ne10_float32_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count) asm("ne10_dot_vec3f_neon")
Specific implementation of ne10_dot_vec3f using NEON intrinsics.
ne10_result_t ne10_mulmat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count) asm("ne10_mulmat_4x4f_neon")
Specific implementation of ne10_mulmat_4x4f using NEON intrinsics.
ne10_result_t ne10_rsbc_float_asm(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_float using NEON assembly.
ne10_result_t ne10_rsbc_float_c(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_float using plain C code.
Definition: NE10_rsbc.c:37
ne10_result_t ne10_setc_vec4f_c(ne10_vec4f_t *dst, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_setc_vec4f using plain C code.
Definition: NE10_setc.c:70
ne10_result_t(* ne10_submat_4x4f)(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Subtracts the 4x4 matrices of one input array from those of the same index in another, storing the results in an output array.
ne10_result_t ne10_add_float_c(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_add_float using plain C code.
Definition: NE10_add.c:38
ne10_result_t ne10_subc_float_neon(ne10_float32_t *dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_subc_float using NEON intrinsics.
ne10_result_t ne10_mlac_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *acc, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec4f using NEON intrinsics.
ne10_result_t ne10_transmat_4x4f_neon(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src, ne10_uint32_t count) asm("ne10_transmat_4x4f_neon")
Specific implementation of ne10_transmat_4x4f using NEON intrinsics.
ne10_result_t(* ne10_len_vec4f)(ne10_float32_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Calculates the magnitude of 4D vectors within an input array, storing the results in an output array...
ne10_result_t ne10_mulc_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec3f using NEON assembly.
ne10_result_t ne10_add_float_neon(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count) asm("ne10_add_float_neon")
Specific implementation of ne10_add_float using NEON intrinsics.
ne10_result_t(* ne10_mulmat_3x3f)(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Multiplies the 3x3 matrices of one input array by those of the same index in another, storing the results in an output array.
ne10_result_t ne10_vmul_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_vmul_vec4f using plain C code.
Definition: NE10_mul.c:70
ne10_result_t ne10_mlac_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec2f using NEON assembly.
ne10_result_t ne10_sub_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec2f using plain C code.
Definition: NE10_sub.c:47
ne10_result_t ne10_len_vec3f_neon(ne10_float32_t *dst, ne10_vec3f_t *src, ne10_uint32_t count) asm("ne10_len_vec3f_neon")
Specific implementation of ne10_len_vec3f using NEON intrinsics.
ne10_result_t ne10_len_vec4f_asm(ne10_float32_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec4f using NEON assembly.
ne10_result_t ne10_invmat_3x3f_neon(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count) asm("ne10_invmat_3x3f_neon")
Specific implementation of ne10_invmat_3x3f using NEON intrinsics.
ne10_result_t ne10_divc_vec3f_asm(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec3f using NEON assembly.
ne10_result_t ne10_submat_2x2f_c(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_submat_2x2f using plain C code.
Definition: NE10_submat.c:37
ne10_result_t ne10_mlac_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *acc, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_vec2f using NEON intrinsics.
ne10_result_t ne10_detmat_2x2f_neon(ne10_float32_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count) asm("ne10_detmat_2x2f_neon")
Specific implementation of ne10_detmat_2x2f using NEON intrinsics.
ne10_result_t ne10_addmat_2x2f_asm(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_2x2f using NEON assembly.
ne10_result_t ne10_div_float_neon(ne10_float32_t *dst, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count) asm("ne10_div_float_neon")
Specific implementation of ne10_div_float using NEON intrinsics.
ne10_result_t(* ne10_transmat_2x2f)(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Calculates the transpose of 2x2 matrices within an input array, storing the results in an output arra...
ne10_result_t ne10_mlac_float_asm(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_float using NEON assembly.
ne10_result_t ne10_identitymat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_uint32_t count)
Specific implementation of ne10_identitymat_3x3f using NEON assembly.
ne10_result_t ne10_add_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src1, ne10_vec4f_t *src2, ne10_uint32_t count) asm("ne10_add_vec4f_neon")
Specific implementation of ne10_add_vec4f using NEON intrinsics.
ne10_result_t(* ne10_rsbc_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Subtracts all the 2D vectors in an input array from a constant vector, storing the results in an outp...
ne10_result_t(* ne10_divc_vec4f)(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Element-wise divides all the 4D vectors in an input array by a constant vector, storing the results i...
ne10_result_t ne10_invmat_3x3f_c(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_3x3f using plain C code.
Definition: NE10_invmat.c:65
ne10_result_t ne10_setc_float_neon(ne10_float32_t *dst, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_setc_float using NEON intrinsics.
ne10_result_t ne10_invmat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_3x3f using NEON assembly.
ne10_result_t ne10_mulmat_3x3f_asm(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src1, ne10_mat3x3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_3x3f using NEON assembly.
ne10_result_t(* ne10_vdiv_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Element-wise divides the 3D vectors of one input array by those of the same index in another...
ne10_result_t(* ne10_invmat_3x3f)(ne10_mat3x3f_t *dst, ne10_mat3x3f_t *src, ne10_uint32_t count)
Calculates the inverse of 3x3 matrices within an input array, storing the results in an output array...
ne10_result_t ne10_abs_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, ne10_uint32_t count)
Specific implementation of ne10_abs_vec4f using NEON assembly.
ne10_result_t ne10_len_vec3f_asm(ne10_float32_t *dst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec3f using NEON assembly.
ne10_result_t(* ne10_rsbc_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Subtracts all the 3D vectors in an input array from a constant vector, storing the results in an outp...
ne10_result_t ne10_subc_vec4f_asm(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec4f using NEON assembly.
ne10_result_t ne10_addmat_2x2f_neon(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src1, ne10_mat2x2f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_2x2f using NEON intrinsics.
ne10_result_t(* ne10_abs_float)(ne10_float32_t *dst, ne10_float32_t *src, ne10_uint32_t count)
Calculates the absolute value of scalars within an input array, storing the results in an output arra...
ne10_result_t ne10_normalize_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec2f using plain C code.
ne10_result_t(* ne10_vdiv_vec2f)(ne10_vec2f_t *dst, ne10_vec2f_t *src1, ne10_vec2f_t *src2, ne10_uint32_t count)
Element-wise divides the 2D vectors of one input array by those of the same index in another...
ne10_result_t ne10_mulc_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec2f using NEON intrinsics.
ne10_result_t ne10_divc_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec4f using plain C code.
Definition: NE10_divc.c:70
ne10_result_t(* ne10_divc_vec3f)(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Element-wise divides all the 3D vectors in an input array by a constant vector, storing the results i...
ne10_result_t(* ne10_identitymat_4x4f)(ne10_mat4x4f_t *dst, ne10_uint32_t count)
Sets the elements of an array of 4x4 matrices to the identity matrix.
ne10_result_t ne10_subc_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src, const ne10_vec3f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec3f using plain C code.
Definition: NE10_subc.c:58
ne10_result_t ne10_rsbc_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_rsbc_vec4f using NEON intrinsics.
ne10_result_t ne10_addmat_4x4f_c(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_addmat_4x4f using plain C code.
Definition: NE10_addmat.c:71
int ne10_result_t
Definition: NE10_types.h:82
ne10_result_t ne10_divc_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec2f using NEON intrinsics.
A 4-tuple of ne10_float32_t values.
Definition: NE10_types.h:106
ne10_result_t ne10_subc_vec4f_c(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec4f using plain C code.
Definition: NE10_subc.c:70
ne10_result_t ne10_mulc_vec4f_neon(ne10_vec4f_t *dst, ne10_vec4f_t *src, const ne10_vec4f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_mulc_vec4f using NEON intrinsics.
ne10_result_t ne10_normalize_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_normalize_vec2f using NEON assembly.
ne10_result_t ne10_mulcmatvec_cm3x3f_v3f_c(ne10_vec3f_t *dst, const ne10_mat3x3f_t *cst, ne10_vec3f_t *src, ne10_uint32_t count)
Specific implementation of ne10_mulcmatvec_cm3x3f_v3f using plain C code.
ne10_result_t ne10_mulmat_4x4f_c(ne10_mat4x4f_t *dst, ne10_mat4x4f_t *src1, ne10_mat4x4f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mulmat_4x4f using plain C code.
Definition: NE10_mulmat.c:127
ne10_result_t ne10_subc_vec2f_neon(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_subc_vec2f using NEON intrinsics.
ne10_result_t ne10_addc_vec2f_asm(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_addc_vec2f using NEON assembly.
ne10_result_t ne10_len_vec2f_asm(ne10_float32_t *dst, ne10_vec2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_len_vec2f using NEON assembly.
ne10_result_t ne10_mlac_float_c(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_mlac_float using plain C code.
Definition: NE10_mlac.c:37
ne10_result_t ne10_mla_float_c(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count)
Specific implementation of ne10_mla_float using plain C code.
Definition: NE10_mla.c:37
ne10_result_t ne10_divc_vec2f_c(ne10_vec2f_t *dst, ne10_vec2f_t *src, const ne10_vec2f_t *cst, ne10_uint32_t count)
Specific implementation of ne10_divc_vec2f using plain C code.
Definition: NE10_divc.c:47
ne10_result_t ne10_invmat_2x2f_c(ne10_mat2x2f_t *dst, ne10_mat2x2f_t *src, ne10_uint32_t count)
Specific implementation of ne10_invmat_2x2f using plain C code.
Definition: NE10_invmat.c:42
ne10_result_t ne10_mla_float_neon(ne10_float32_t *dst, ne10_float32_t *acc, ne10_float32_t *src1, ne10_float32_t *src2, ne10_uint32_t count) asm("ne10_mla_float_neon")
Specific implementation of ne10_mla_float using NEON intrinsics.
ne10_result_t ne10_sub_vec3f_c(ne10_vec3f_t *dst, ne10_vec3f_t *src1, ne10_vec3f_t *src2, ne10_uint32_t count)
Specific implementation of ne10_sub_vec3f using plain C code.
Definition: NE10_sub.c:58
ne10_result_t ne10_setc_float_c(ne10_float32_t *dst, const ne10_float32_t cst, ne10_uint32_t count)
Specific implementation of ne10_setc_float using plain C code.
Definition: NE10_setc.c:37