From: yang Date: Fri, 26 Oct 2012 03:29:42 +0000 (+0800) Subject: add prefix "ne10_" to all the functions X-Git-Tag: v1.0.0~23^2 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=7267c7a218ee8202b259e260ae7e0097d2222817;p=platform%2Fupstream%2Fne10.git add prefix "ne10_" to all the functions --- diff --git a/inc/NE10_math.h b/inc/NE10_math.h index 1d0ab76..165062f 100644 --- a/inc/NE10_math.h +++ b/inc/NE10_math.h @@ -58,7 +58,7 @@ extern "C" { @param[in] cst The constant scalar added to the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*addc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +extern 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 2D vector to all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -66,7 +66,7 @@ extern ne10_result_t (*addc_float)(ne10_float32_t * dst, ne10_float32_t * src, c @param[in] cst Pointer to the 2D vector added to the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*addc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern 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 3D vector to all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -74,7 +74,7 @@ extern ne10_result_t (*addc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const @param[in] cst Pointer to the 3D vector added to the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*addc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern 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 4D vector to all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -82,7 +82,7 @@ extern ne10_result_t (*addc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const @param[in] cst Pointer to the 4D vector added to the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*addc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_addc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -93,7 +93,7 @@ extern ne10_result_t (*addc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const @param[in] cst The constant scalar subtracted from the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*subc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +extern 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 2D vector from all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -101,7 +101,7 @@ extern ne10_result_t (*subc_float)(ne10_float32_t * dst, ne10_float32_t * src, c @param[in] cst Pointer to the 2D vector subtracted from the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*subc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern 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 3D vector from all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -109,7 +109,7 @@ extern ne10_result_t (*subc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const @param[in] cst Pointer to the 3D vector subtracted from the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*subc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern 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 4D vector from all of the vectors in an input array and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -117,7 +117,7 @@ extern ne10_result_t (*subc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const @param[in] cst Pointer to the 4D vector subtracted from the input values @param[in] count The number of items in the input array */ -extern ne10_result_t (*subc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_subc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -128,7 +128,7 @@ extern ne10_result_t (*subc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const @param[in] cst The constant scalar to subtract the input values from @param[in] count The number of items in the input array */ -extern ne10_result_t (*rsbc_float)(ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_rsbc_float)(ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); /*! Subtracts the vectors in an input array from a constant 2D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -136,7 +136,7 @@ extern ne10_result_t (*rsbc_float)(ne10_float32_t * dst, ne10_float32_t *src, co @param[in] cst Pointer to the 2D vector to subtract the input values from @param[in] count The number of items in the input array */ -extern ne10_result_t (*rsbc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_rsbc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); /*! Subtracts the vectors in an input array from a constant 3D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -144,7 +144,7 @@ extern ne10_result_t (*rsbc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const @param[in] cst Pointer to the 3D vector to subtract the input values from @param[in] count The number of items in the input array */ -extern ne10_result_t (*rsbc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_rsbc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); /*! Subtracts the vectors in an input array from a constant 4D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -152,7 +152,7 @@ extern ne10_result_t (*rsbc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const @param[in] cst Pointer to the 4D vector to subtract the input values from @param[in] count The number of items in the input array */ -extern ne10_result_t (*rsbc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_rsbc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -163,7 +163,7 @@ extern ne10_result_t (*rsbc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const @param[in] cst The constant scalar to multiply the input values with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mulc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); /*! Multiplies the components of 2D vectors in an input array by the components of a constant 2D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -171,7 +171,7 @@ extern ne10_result_t (*mulc_float)(ne10_float32_t * dst, ne10_float32_t * src, c @param[in] cst Pointer to the 2D vector to multiply the input values with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mulc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); /*! Multiplies the components of 3D vectors in an input array by the components of a constant 3D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -179,7 +179,7 @@ extern ne10_result_t (*mulc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const @param[in] cst Pointer to the 3D vector to multiply the input values with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mulc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); /*! Multiplies the components of 4D vectors in an input array by the components of a constant 4D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -187,7 +187,7 @@ extern ne10_result_t (*mulc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const @param[in] cst Pointer to the 4D vector to multiply the input values with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mulc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -198,7 +198,7 @@ extern ne10_result_t (*mulc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const @param[in] cst The constant scalar to divide the input values by @param[in] count The number of items in the input array */ -extern ne10_result_t (*divc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_divc_float)(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); /*! Divides the components of 2D vectors in an input array with the components of a constant 2D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -206,7 +206,7 @@ extern ne10_result_t (*divc_float)(ne10_float32_t * dst, ne10_float32_t * src, c @param[in] cst Pointer to the 2D vector to divide the input values by @param[in] count The number of items in the input array */ -extern ne10_result_t (*divc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_divc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); /*! Divides the components of 3D vectors in an input array with the components of a constant 3D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -214,7 +214,7 @@ extern ne10_result_t (*divc_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, const @param[in] cst Pointer to the 3D vector to divide the input values by @param[in] count The number of items in the input array */ -extern ne10_result_t (*divc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_divc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); /*! Divides the components of 4D vectors in an input array with the components of a constant 4D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @@ -222,7 +222,7 @@ extern ne10_result_t (*divc_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, const @param[in] cst Pointer to the 4D vector to divide the input values by @param[in] count The number of items in the input array */ -extern ne10_result_t (*divc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_divc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -232,28 +232,28 @@ extern ne10_result_t (*divc_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, const @param[in] cst The constant scalar to set the input values to @param[in] count The number of items in the input array */ -extern ne10_result_t (*setc_float)(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_setc_float)(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); /*! Sets the components of 2D vectors in an input array to the components of a constant 2D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @param[in] cst Pointer to the 2D vector to set the input values to @param[in] count The number of items in the input array */ -extern ne10_result_t (*setc_vec2f)(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_setc_vec2f)(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); /*! Sets the components of 3D vectors in an input array to the components of a constant 3D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @param[in] cst Pointer to the 3D vector to set the input values to @param[in] count The number of items in the input array */ -extern ne10_result_t (*setc_vec3f)(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_setc_vec3f)(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); /*! Sets the components of 3D vectors in an input array to the components of a constant 3D vector and stores the results in an output array. @param[out] dst Pointer to the destination array @param[in] cst Pointer to the 4D vector to set the input values to @param[in] count The number of items in the input array */ -extern ne10_result_t (*setc_vec4f)(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_setc_vec4f)(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); @@ -266,7 +266,7 @@ extern ne10_result_t (*setc_vec4f)(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, @param[in] cst The constant scalar to multiply the input elements with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mlac_float)(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +extern 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 each entry in the source array (src) by the 2D vector cst, then adds the result to the corresponding item of the accumulation array (acc), and stores the result in the destination array. @@ -276,7 +276,7 @@ extern ne10_result_t (*mlac_float)(ne10_float32_t * dst, ne10_float32_t * acc, n @param[in] cst Pointer to the 2D vector to multiply the input vectors with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mlac_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +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); /*! Multiplies each entry in the source array (src) by the 3D vector cst, then adds the result to the corresponding item of the accumulation array (acc), and stores the result in the destination array. @@ -286,7 +286,7 @@ extern ne10_result_t (*mlac_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_ @param[in] cst Pointer to the 3D vector to multiply the input vectors with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mlac_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +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); /*! Multiplies each entry in the source array (src) by the 4D vector cst, then adds the result to the corresponding item of the accumulation array (acc), and stores the result in the destination array. @@ -296,7 +296,7 @@ extern ne10_result_t (*mlac_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_ @param[in] cst Pointer to the 4D vector to multiply the input vectors with @param[in] count The number of items in the input array */ -extern ne10_result_t (*mlac_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +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); @@ -309,7 +309,7 @@ extern ne10_result_t (*mlac_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_ @param[in] src2 The second array to use as the input array @param[in] count The number of items in the two input arrays */ -extern ne10_result_t (*add_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_add_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); /*! Subtracts the elements of src2 from the elements of src2 and stores the results in the dst. @param[out] dst Pointer to the destination array @@ -317,7 +317,7 @@ extern ne10_result_t (*add_float)(ne10_float32_t * dst, ne10_float32_t * src1, n @param[in] src2 The second array to use as the input array @param[in] count The number of items in the two input arrays */ -extern ne10_result_t (*sub_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_sub_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); /*! Multiplies the elements of src1 by the elements of src2 and stores the results in the dst. @param[out] dst Pointer to the destination array @@ -325,7 +325,7 @@ extern ne10_result_t (*sub_float)(ne10_float32_t * dst, ne10_float32_t * src1, n @param[in] src2 The second array to use as the input array @param[in] count The number of items in the two input arrays */ -extern ne10_result_t (*mul_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_mul_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); /*! Divides the elements of src1 by the elements of src2 and stores the results in the dst. @param[out] dst Pointer to the destination array @@ -333,7 +333,7 @@ extern ne10_result_t (*mul_float)(ne10_float32_t * dst, ne10_float32_t * src1, n @param[in] src2 The second array to use as the input array @param[in] count The number of items in the two input arrays */ -extern ne10_result_t (*div_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_div_float)(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); /*! Performs a multiply and accumulate operation using the corresponding elements in acc, src1, and src2. @param[out] dst Pointer to the destination array @@ -342,14 +342,14 @@ extern ne10_result_t (*div_float)(ne10_float32_t * dst, ne10_float32_t * src1, n @param[in] src2 The second array to use as the input array @param[in] count The number of items in the two input arrays */ -extern ne10_result_t (*mla_float)(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern 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); /*! Calculates the absolute value of each element in the source array and stores the result in the corresponding entry of the destination array. @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*abs_float)(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_abs_float)(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); @@ -360,21 +360,21 @@ extern ne10_result_t (*abs_float)(ne10_float32_t * dst, ne10_float32_t * src, ne @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*len_vec2f)(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_len_vec2f)(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); /*! Returns length of 3D vectors in corresponding elements of the output array. @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*len_vec3f)(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_len_vec3f)(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); /*! Returns length of 4D vectors in corresponding elements of the output array. @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*len_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_len_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); @@ -384,21 +384,21 @@ extern ne10_result_t (*len_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src, ne10 @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*normalize_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_normalize_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); /*! Normalizes 3D vectors of the input array and stores them in the corresponding elements of the output array. @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*normalize_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_normalize_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); /*! Normalizes 4D vectors of the input array and stores them in the corresponding elements of the output array. @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*normalize_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_normalize_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); @@ -409,21 +409,21 @@ extern ne10_result_t (*normalize_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*abs_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_abs_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); /*! Generates a 3D vector from the absolute values of each of the components of an input vector @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*abs_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_abs_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); /*! Generates a 4D vector from the absolute values of each of the components of an input vector @param[out] dst Pointer to the destination array @param[in] src Pointer to the source array @param[in] count The number of items in the input array */ -extern ne10_result_t (*abs_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_abs_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); @@ -436,7 +436,7 @@ extern ne10_result_t (*abs_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_u @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmul_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vmul_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); /*! Multiplies the components of a 3D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -444,7 +444,7 @@ extern ne10_result_t (*vmul_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmul_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vmul_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); /*! Multiplies the components of a 4D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -452,7 +452,7 @@ extern ne10_result_t (*vmul_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmul_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vmul_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); @@ -463,7 +463,7 @@ extern ne10_result_t (*vmul_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10 @param[in] src2 Pointer to the denominators' source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vdiv_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vdiv_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); /*! Divides the components of a 3D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -471,7 +471,7 @@ extern ne10_result_t (*vdiv_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10 @param[in] src2 Pointer to the denominators' source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vdiv_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vdiv_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); /*! Divides the components of a 4D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -479,7 +479,7 @@ extern ne10_result_t (*vdiv_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10 @param[in] src2 Pointer to the denominators' source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vdiv_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_vdiv_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); @@ -490,7 +490,7 @@ extern ne10_result_t (*vdiv_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmla_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +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); /*! Performs a multiply and accumulate operation on the components of a 3D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -498,7 +498,7 @@ extern ne10_result_t (*vmla_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmla_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +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); /*! Performs a multiply and accumulate operation on the components of a 4D vector with the corresponding components of another @param[out] dst Pointer to the destination array @@ -506,7 +506,7 @@ extern ne10_result_t (*vmla_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*vmla_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +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); @@ -519,7 +519,7 @@ extern ne10_result_t (*vmla_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*add_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_add_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); /*! Vector addition of two 3D vectors @param[out] dst Pointer to the destination array @@ -527,7 +527,7 @@ extern ne10_result_t (*add_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*add_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_add_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); /*! Vector addition of two 4D vectors @param[out] dst Pointer to the destination array @@ -535,7 +535,7 @@ extern ne10_result_t (*add_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*add_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_add_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); @@ -546,7 +546,7 @@ extern ne10_result_t (*add_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*sub_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_sub_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); /*! Vector subtraction of two 3D vectors @param[out] dst Pointer to the destination array @@ -554,7 +554,7 @@ extern ne10_result_t (*sub_vec2f)(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*sub_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_sub_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); /*! Vector subtraction of two 4D vectors @param[out] dst Pointer to the destination array @@ -562,7 +562,7 @@ extern ne10_result_t (*sub_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*sub_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_sub_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); @@ -573,7 +573,7 @@ extern ne10_result_t (*sub_vec4f)(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_ @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*dot_vec2f)(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_dot_vec2f)(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); /*! Dot product of two 3D vectors @param[out] dst Pointer to the destination array @@ -581,7 +581,7 @@ extern ne10_result_t (*dot_vec2f)(ne10_float32_t * dst, ne10_vec2f_t * src1, ne1 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*dot_vec3f)(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_dot_vec3f)(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); /*! Dot product of two 4D vectors @param[out] dst Pointer to the destination array @@ -589,7 +589,7 @@ extern ne10_result_t (*dot_vec3f)(ne10_float32_t * dst, ne10_vec3f_t * src1, ne1 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*dot_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_dot_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); @@ -600,7 +600,7 @@ extern ne10_result_t (*dot_vec4f)(ne10_float32_t * dst, ne10_vec4f_t * src1, ne1 @param[in] src2 Pointer to the second source array @param[in] count The number of items in the input arrays */ -extern ne10_result_t (*cross_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_cross_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); @@ -608,57 +608,57 @@ extern ne10_result_t (*cross_vec3f)(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne1 // ## Matrix-Constant Arithmetic ## // ne10_mat4x4f_t -extern ne10_result_t (*addmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*submat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*mulmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*divmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*setmat_4x4f)(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_addmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_submat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_divmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_setmat_4x4f)(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t (*addmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*submat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*mulmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*divmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*setmat_3x3f)(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_addmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_submat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_divmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_setmat_3x3f)(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t (*addmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*submat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*mulmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*divmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*setmat_2x2f)(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t (*ne10_addmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_submat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_divmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_setmat_2x2f)(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); // ## Operations on Matrices ## -extern ne10_result_t (*detmat_4x4f)(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t (*detmat_3x3f)(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t (*detmat_2x2f)(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_detmat_4x4f)(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_detmat_3x3f)(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_detmat_2x2f)(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t (*invmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t (*invmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t (*invmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_invmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_invmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_invmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t (*transmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t (*identitymat_4x4f)(ne10_mat4x4f_t * dst, ne10_uint32_t count); +extern ne10_result_t (*ne10_transmat_4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_identitymat_4x4f)(ne10_mat4x4f_t * dst, ne10_uint32_t count); -extern ne10_result_t (*transmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t (*identitymat_3x3f)(ne10_mat3x3f_t * dst, ne10_uint32_t count); +extern ne10_result_t (*ne10_transmat_3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_identitymat_3x3f)(ne10_mat3x3f_t * dst, ne10_uint32_t count); -extern ne10_result_t (*transmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t (*identitymat_2x2f)(ne10_mat2x2f_t * dst, ne10_uint32_t count); +extern ne10_result_t (*ne10_transmat_2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_identitymat_2x2f)(ne10_mat2x2f_t * dst, ne10_uint32_t count); // ## Matrix-Vector Algebra ## -extern ne10_result_t (*mulcmatvec_cm4x4f_v4f)(ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t (*mulcmatvec_cm3x3f_v3f)(ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t (*mulcmatvec_cm2x2f_v2f)(ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulcmatvec_cm4x4f_v4f)(ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulcmatvec_cm3x3f_v3f)(ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t (*ne10_mulcmatvec_cm2x2f_v2f)(ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); // ## Matrix-Matrix Algebra ## -extern ne10_result_t (*multrans_mat4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*multrans_mat3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t (*multrans_mat2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_multrans_mat4x4f)(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_multrans_mat3x3f)(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t (*ne10_multrans_mat2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); /////////////////////////// @@ -668,176 +668,176 @@ extern ne10_result_t (*multrans_mat2x2f)(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * // ## Vector-Constant Arithmetic ## -extern ne10_result_t addc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addc_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_addc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t subc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) +extern ne10_result_t ne10_subc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) -extern ne10_result_t rsbc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst +extern ne10_result_t ne10_rsbc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst -extern ne10_result_t mulc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_mulc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t divc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t divc_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_divc_float_c(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t setc_float_c(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t setc_vec2f_c(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec3f_c(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec4f_c(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_float_c(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec2f_c(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec3f_c(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec4f_c(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_float_c(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern 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); +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); +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); +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); // ## Arithmetic functions over arrays of cst values ## -extern ne10_result_t add_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mul_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t div_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mla_float_c(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t abs_float_c(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_add_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mul_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_div_float_c(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern 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); +extern ne10_result_t ne10_abs_float_c(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); // ## Operations on Vectors ## -extern ne10_result_t len_vec2f_c(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec3f_c(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec4f_c(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec2f_c(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec3f_c(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec4f_c(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); // ## SIMD Component-wise Arithmetic on Two Vectors ## -extern ne10_result_t vmul_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern 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); +extern 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); +extern 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); // ## Vector-Vector Algebra ## -extern ne10_result_t add_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec2f_c(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec4f_c(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec2f_c(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec3f_c(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec4f_c(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec2f_c(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec3f_c(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec4f_c(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t cross_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_cross_vec3f_c(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); // ## Matrix-Constant Arithmetic ## // ne10_mat4x4f_t -extern ne10_result_t addmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_4x4f_c(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_4x4f_c(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_3x3f_c(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_3x3f_c(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_2x2f_c(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_2x2f_c(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); // ## Operations on Matrices ## -extern ne10_result_t detmat_4x4f_c(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_3x3f_c(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_2x2f_c(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_4x4f_c(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_3x3f_c(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_2x2f_c(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t transmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_4x4f_c(ne10_mat4x4f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_4x4f_c(ne10_mat4x4f_t * dst, ne10_uint32_t count); -extern ne10_result_t transmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_3x3f_c(ne10_mat3x3f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_3x3f_c(ne10_mat3x3f_t * dst, ne10_uint32_t count); -extern ne10_result_t transmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_2x2f_c(ne10_mat2x2f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_2x2f_c(ne10_mat2x2f_t * dst, ne10_uint32_t count); // ## Matrix-Vector Algebra ## -extern ne10_result_t mulcmatvec_cm4x4f_v4f_c(ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm3x3f_v3f_c(ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm2x2f_v2f_c(ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); +extern 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); +extern 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); +extern 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); // ## Matrix-Matrix Algebra ## -extern ne10_result_t multrans_mat4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat4x4f_c(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat3x3f_c(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); ///////////////////////////// @@ -847,181 +847,181 @@ extern ne10_result_t multrans_mat2x2f_c(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * s // ## Vector-Constant Arithmetic ## -extern ne10_result_t addc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addc_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +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); +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); +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); +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); -extern ne10_result_t subc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) +extern ne10_result_t ne10_subc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) -extern ne10_result_t rsbc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst +extern ne10_result_t ne10_rsbc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst -extern ne10_result_t mulc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_mulc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t divc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t divc_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_divc_float_neon(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t setc_float_neon(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t setc_vec2f_neon(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec3f_neon(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec4f_neon(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_float_neon(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec2f_neon(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec3f_neon(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec4f_neon(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_float_neon(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern 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); +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); +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); +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); // ## Arithmetic functions over arrays of cst values ## -extern ne10_result_t add_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mul_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t div_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mla_float_neon(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t abs_float_neon(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_add_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mul_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_div_float_neon(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +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); +extern ne10_result_t ne10_abs_float_neon(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); // ## Operations on Vectors ## -extern ne10_result_t len_vec2f_neon(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec3f_neon(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec4f_neon(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec2f_neon(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec3f_neon(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec4f_neon(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); // ## SIMD Component-wise Arithmetic on Two Vectors ## -extern ne10_result_t vmul_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +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); +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); +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); // ## Vector-Vector Algebra ## -extern ne10_result_t add_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec2f_neon(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec4f_neon(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec2f_neon(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec3f_neon(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec4f_neon(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec2f_neon(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec3f_neon(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec4f_neon(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t cross_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_cross_vec3f_neon(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); // ## Matrix-Constant Arithmetic ## // ne10_mat4x4f_t -extern ne10_result_t addmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_4x4f_neon(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_4x4f_neon(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_3x3f_neon(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_3x3f_neon(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_2x2f_neon(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_2x2f_neon(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); // ## Operations on Matrices ## -extern ne10_result_t detmat_4x4f_neon(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_3x3f_neon(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_2x2f_neon(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_4x4f_neon(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_3x3f_neon(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_2x2f_neon(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t transmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_4x4f_neon(ne10_mat4x4f_t * dst, ne10_uint32_t count); -extern ne10_result_t transmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_3x3f_neon(ne10_mat3x3f_t * dst, ne10_uint32_t count); -extern ne10_result_t transmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_2x2f_neon(ne10_mat2x2f_t * dst, ne10_uint32_t count); // ## Matrix-Vector Algebra ## -extern ne10_result_t mulcmatvec_cm4x4f_v4f_neon(ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm3x3f_v3f_neon(ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm2x2f_v2f_neon(ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); +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); +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); +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); // ## Matrix-Matrix Algebra ## -extern ne10_result_t multrans_mat4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat4x4f_neon(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat3x3f_neon(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); //////////////////////////// @@ -1030,179 +1030,179 @@ extern ne10_result_t multrans_mat2x2f_neon(ne10_mat2x2f_t * dst, ne10_mat2x2f_t // ## Vector-Constant Arithmetic ## -extern ne10_result_t addc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addc_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t addc_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_addc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t subc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) -extern ne10_result_t subc_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract cst from the element(s) +extern ne10_result_t ne10_subc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) +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); // subtract cst from the element(s) -extern ne10_result_t rsbc_float_asm(ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t *src, const ne10_vec2f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t *src, const ne10_vec3f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst -extern ne10_result_t rsbc_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t *src, const ne10_vec4f_t * cst, ne10_uint32_t count); // subtract element(s) from a cst +extern ne10_result_t ne10_rsbc_float_asm(ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst +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); // subtract element(s) from a cst -extern ne10_result_t mulc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mulc_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_mulc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t divc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t divc_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t divc_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_divc_float_asm(ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +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); +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); +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); -extern ne10_result_t setc_float_asm(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t setc_vec2f_asm(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec3f_asm(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t setc_vec4f_asm(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_float_asm(ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec2f_asm(ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec3f_asm(ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); +extern ne10_result_t ne10_setc_vec4f_asm(ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_float_asm(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -extern ne10_result_t mlac_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +extern 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); +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); +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); +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); // ## Arithmetic functions over arrays of cst values ## -extern ne10_result_t add_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mul_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t div_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t mla_float_asm(ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -extern ne10_result_t abs_float_asm(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_add_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mul_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_div_float_asm(ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +extern 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); +extern ne10_result_t ne10_abs_float_asm(ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); // ## Operations on Vectors ## -extern ne10_result_t len_vec2f_asm(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec3f_asm(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t len_vec4f_asm(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec2f_asm(ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec3f_asm(ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_len_vec4f_asm(ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t normalize_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_normalize_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t abs_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_abs_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); // ## SIMD Component-wise Arithmetic on Two Vectors ## -extern ne10_result_t vmul_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmul_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vmul_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vdiv_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_vdiv_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t vmla_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern 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); +extern 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); +extern 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); // ## Vector-Vector Algebra ## -extern ne10_result_t add_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t add_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_add_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t sub_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec2f_asm(ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_sub_vec4f_asm(ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec2f_asm(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec3f_asm(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -extern ne10_result_t dot_vec4f_asm(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec2f_asm(ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec3f_asm(ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_dot_vec4f_asm(ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -extern ne10_result_t cross_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_cross_vec3f_asm(ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); // ## Matrix-Constant Arithmetic ## // ne10_mat4x4f_t -extern ne10_result_t addmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_4x4f_asm(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_4x4f_asm(ne10_mat4x4f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_3x3f_asm(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_3x3f_asm(ne10_mat3x3f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -extern ne10_result_t addmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t submat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t mulmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t divmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -extern ne10_result_t setmat_2x2f_asm(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +extern ne10_result_t ne10_addmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_submat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_mulmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_divmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_setmat_2x2f_asm(ne10_mat2x2f_t * dst, const ne10_float32_t cst, ne10_uint32_t count); // ## Operations on Matrices ## -extern ne10_result_t detmat_4x4f_asm(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_3x3f_asm(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t detmat_2x2f_asm(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_4x4f_asm(ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_3x3f_asm(ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_detmat_2x2f_asm(ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t invmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_invmat_2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t transmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_4x4f_asm(ne10_mat4x4f_t * dst, ne10_uint32_t count); -extern ne10_result_t transmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -extern ne10_result_t identitymat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_transmat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identitymat_3x3f_asm(ne10_mat3x3f_t * dst, ne10_uint32_t count); -extern ne10_result_t trans_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -extern ne10_result_t identity_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_uint32_t count); +extern ne10_result_t ne10_trans_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +extern ne10_result_t ne10_identity_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_uint32_t count); // ## Matrix-Vector Algebra ## -extern ne10_result_t mulcmatvec_cm4x4f_v4f_asm(ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm3x3f_v3f_asm(ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); -extern ne10_result_t mulcmatvec_cm2x2f_v2f_asm(ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); +extern 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); +extern 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); +extern 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); // ## Matrix-Matrix Algebra ## -extern ne10_result_t multrans_mat4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -extern ne10_result_t multrans_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat4x4f_asm(ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat3x3f_asm(ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +extern ne10_result_t ne10_multrans_mat2x2f_asm(ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); #ifdef __cplusplus } diff --git a/modules/math/NE10_abs.asm.s b/modules/math/NE10_abs.asm.s index a6cc46d..d66b42a 100644 --- a/modules/math/NE10_abs.asm.s +++ b/modules/math/NE10_abs.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global abs_float_asm + .global ne10_abs_float_asm .thumb .thumb_func -abs_float_asm: +ne10_abs_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t abs_float(arm_float_t * dst, + @ arm_result_t ne10_abs_float(arm_float_t * dst, @ arm_float_t * src, @ unsigned int count) @ diff --git a/modules/math/NE10_abs.c b/modules/math/NE10_abs.c index 874c47a..aa364f5 100644 --- a/modules/math/NE10_abs.c +++ b/modules/math/NE10_abs.c @@ -36,7 +36,7 @@ #include -ne10_result_t abs_float_c (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count) +ne10_result_t ne10_abs_float_c (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count) { NE10_ABS_OPERATION_X_C ( @@ -44,7 +44,7 @@ ne10_result_t abs_float_c (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint ); } -ne10_result_t abs_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_abs_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) { NE10_ABS_OPERATION_X_C ( @@ -53,7 +53,7 @@ ne10_result_t abs_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t ); } -ne10_result_t abs_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_abs_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) { NE10_ABS_OPERATION_X_C ( @@ -63,7 +63,7 @@ ne10_result_t abs_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t ); } -ne10_result_t abs_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_abs_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) { NE10_ABS_OPERATION_X_C ( diff --git a/modules/math/NE10_abs.neon.s b/modules/math/NE10_abs.neon.s index f5a0c26..90d81d2 100644 --- a/modules/math/NE10_abs.neon.s +++ b/modules/math/NE10_abs.neon.s @@ -38,14 +38,14 @@ .align 4 - .global abs_float_neon + .global ne10_abs_float_neon .thumb .thumb_func -abs_float_neon: +ne10_abs_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t abs_float(arm_float_t * dst, + @ arm_result_t ne10_abs_float(arm_float_t * dst, @ arm_float_t * src, @ unsigned int count); @ @@ -105,14 +105,14 @@ abs_float_neon: .align 4 - .global abs_vec2f_neon + .global ne10_abs_vec2f_neon .thumb .thumb_func -abs_vec2f_neon: +ne10_abs_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t abs_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_abs_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, @ unsigned int count); @ @@ -171,13 +171,13 @@ abs_vec2f_neon: .align 4 - .global abs_vec3f_neon + .global ne10_abs_vec3f_neon .thumb .thumb_func -abs_vec3f_neon: +ne10_abs_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t abs_vec3f(arm_vec3t_t * dst, + @ arm_result_t ne10_abs_vec3f(arm_vec3t_t * dst, @ arm_vec3f_t * src, @ unsigned int count); @ @@ -246,13 +246,13 @@ abs_vec3f_neon: .align 4 - .global abs_vec4f_neon + .global ne10_abs_vec4f_neon .thumb .thumb_func -abs_vec4f_neon: +ne10_abs_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t abs_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_abs_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, @ unsigned int count); @ diff --git a/modules/math/NE10_add.asm.s b/modules/math/NE10_add.asm.s index cd81128..27dff8d 100644 --- a/modules/math/NE10_add.asm.s +++ b/modules/math/NE10_add.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global add_float_asm + .global ne10_add_float_asm .thumb .thumb_func -add_float_asm: +ne10_add_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t add_float(arm_vec2f_t * dst, + @ arm_result_t ne10_add_float(arm_vec2f_t * dst, @ arm_float_t * src1, const arm_float_t * src2, @ unsigned int count) @ diff --git a/modules/math/NE10_add.c b/modules/math/NE10_add.c index 9e7ae91..5728a49 100644 --- a/modules/math/NE10_add.c +++ b/modules/math/NE10_add.c @@ -34,7 +34,7 @@ #include -ne10_result_t add_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) +ne10_result_t ne10_add_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -42,7 +42,7 @@ ne10_result_t add_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_flo ); } -ne10_result_t add_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_add_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -51,7 +51,7 @@ ne10_result_t add_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t ); } -ne10_result_t add_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_add_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -61,7 +61,7 @@ ne10_result_t add_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t ); } -ne10_result_t add_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_add_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_add.neon.s b/modules/math/NE10_add.neon.s index e1c7a4d..202018a 100644 --- a/modules/math/NE10_add.neon.s +++ b/modules/math/NE10_add.neon.s @@ -38,14 +38,14 @@ .align 4 - .global add_float_neon + .global ne10_add_float_neon .thumb .thumb_func -add_float_neon: +ne10_add_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t add_float(arm_float_t * dst, + @ arm_result_t ne10_add_float(arm_float_t * dst, @ arm_float_t * src1, @ arm_float_t * src2, @ unsigned int count) @@ -113,14 +113,14 @@ add_float_neon: .align 4 - .global add_vec2f_neon + .global ne10_add_vec2f_neon .thumb .thumb_func -add_vec2f_neon: +ne10_add_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t add_float(arm_vec2f_t * dst, + @ arm_result_t ne10_add_float(arm_vec2f_t * dst, @ arm_vec2f_t * src1, @ arm_vec2f_t * src2, @ unsigned int count) @@ -186,13 +186,13 @@ add_vec2f_neon: .align 4 - .global add_vec3f_neon + .global ne10_add_vec3f_neon .thumb .thumb_func -add_vec3f_neon: +ne10_add_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t add_float(arm_vec3f_t * dst, + @ arm_result_t ne10_add_float(arm_vec3f_t * dst, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @ unsigned int count) @@ -273,13 +273,13 @@ add_vec3f_neon: .align 4 - .global add_vec4f_neon + .global ne10_add_vec4f_neon .thumb .thumb_func -add_vec4f_neon: +ne10_add_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t add_float(arm_vec4f_t * dst, + @ arm_result_t ne10_add_float(arm_vec4f_t * dst, @ arm_vec4f_t * src1, @ arm_vec4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_addc.asm.s b/modules/math/NE10_addc.asm.s index e1f18cb..d360280 100644 --- a/modules/math/NE10_addc.asm.s +++ b/modules/math/NE10_addc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global addc_float_asm + .global ne10_addc_float_asm .thumb .thumb_func -addc_float_asm: +ne10_addc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t addc_float(arm_vec2f_t * dst, + @ arm_result_t ne10_addc_float(arm_vec2f_t * dst, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -82,14 +82,14 @@ addc_float_asm: .balign 4 - .global addc_vec2f_asm + .global ne10_addc_vec2f_asm .thumb .thumb_func -addc_vec2f_asm: +ne10_addc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t addc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_addc_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -134,14 +134,14 @@ addc_vec2f_asm: .balign 4 - .global addc_vec3f_asm + .global ne10_addc_vec3f_asm .thumb .thumb_func -addc_vec3f_asm: +ne10_addc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t addc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_addc_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -189,14 +189,14 @@ addc_vec3f_asm: .balign 4 - .global addc_vec4f_asm + .global ne10_addc_vec4f_asm .thumb .thumb_func -addc_vec4f_asm: +ne10_addc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t addc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_addc_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_addc.c b/modules/math/NE10_addc.c index ec6c8ce..49d4a5f 100644 --- a/modules/math/NE10_addc.c +++ b/modules/math/NE10_addc.c @@ -34,7 +34,7 @@ #include -ne10_result_t addc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_addc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t addc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne ); } -ne10_result_t addc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t addc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_v ); } -ne10_result_t addc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t addc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_v ); } -ne10_result_t addc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( diff --git a/modules/math/NE10_addc.neon.c b/modules/math/NE10_addc.neon.c index e2a8767..bd2083c 100644 --- a/modules/math/NE10_addc.neon.c +++ b/modules/math/NE10_addc.neon.c @@ -36,7 +36,7 @@ #include "macros.h" -ne10_result_t addc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_addc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t addc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ); } -ne10_result_t addc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t addc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne1 ); } -ne10_result_t addc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC3F_NEON ( @@ -70,7 +70,7 @@ ne10_result_t addc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne1 ); } -ne10_result_t addc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_addc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_addmat.c b/modules/math/NE10_addmat.c index b552416..03f71fe 100644 --- a/modules/math/NE10_addmat.c +++ b/modules/math/NE10_addmat.c @@ -34,7 +34,7 @@ #include -ne10_result_t addmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -46,7 +46,7 @@ ne10_result_t addmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_m ); } -ne10_result_t addmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -64,7 +64,7 @@ ne10_result_t addmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_m ); } -ne10_result_t addmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_addmat.neon.c b/modules/math/NE10_addmat.neon.c index ebe9e07..0a803d7 100644 --- a/modules/math/NE10_addmat.neon.c +++ b/modules/math/NE10_addmat.neon.c @@ -27,18 +27,18 @@ #include "NE10_types.h" -ne10_result_t addmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) { - return add_vec2f_neon ( (ne10_vec2f_t*) dst, (ne10_vec2f_t*) src1, (ne10_vec2f_t*) src2, count * 2); + return ne10_add_vec2f_neon ( (ne10_vec2f_t*) dst, (ne10_vec2f_t*) src1, (ne10_vec2f_t*) src2, count * 2); } -ne10_result_t addmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) { - return add_vec3f_neon ( (ne10_vec3f_t*) dst, (ne10_vec3f_t*) src1, (ne10_vec3f_t*) src2, count * 3); + return ne10_add_vec3f_neon ( (ne10_vec3f_t*) dst, (ne10_vec3f_t*) src1, (ne10_vec3f_t*) src2, count * 3); } -ne10_result_t addmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_addmat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) { - return add_vec4f_neon ( (ne10_vec4f_t*) dst, (ne10_vec4f_t*) src1, (ne10_vec4f_t*) src2, count * 4); + return ne10_add_vec4f_neon ( (ne10_vec4f_t*) dst, (ne10_vec4f_t*) src1, (ne10_vec4f_t*) src2, count * 4); } diff --git a/modules/math/NE10_cross.c b/modules/math/NE10_cross.c index e7a17a0..68d6002 100644 --- a/modules/math/NE10_cross.c +++ b/modules/math/NE10_cross.c @@ -34,7 +34,7 @@ #include -ne10_result_t cross_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_cross_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_cross.neon.s b/modules/math/NE10_cross.neon.s index 24b2685..6ce0246 100644 --- a/modules/math/NE10_cross.neon.s +++ b/modules/math/NE10_cross.neon.s @@ -38,13 +38,13 @@ .align 4 - .global cross_vec3f_neon + .global ne10_cross_vec3f_neon .thumb .thumb_func -cross_vec3f_neon: +ne10_cross_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t cross_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_cross_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_detmat.c b/modules/math/NE10_detmat.c index 9797744..9249109 100644 --- a/modules/math/NE10_detmat.c +++ b/modules/math/NE10_detmat.c @@ -35,7 +35,7 @@ #include -ne10_result_t detmat_2x2f_c (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_detmat_2x2f_c (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( @@ -43,7 +43,7 @@ ne10_result_t detmat_2x2f_c (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_ui ); } -ne10_result_t detmat_3x3f_c (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_detmat_3x3f_c (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( @@ -52,7 +52,7 @@ ne10_result_t detmat_3x3f_c (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_ui ); } -ne10_result_t detmat_4x4f_c (ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_detmat_4x4f_c (ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( diff --git a/modules/math/NE10_detmat.neon.inc.s b/modules/math/NE10_detmat.neon.inc.s index bdaa7c9..473aa3a 100644 --- a/modules/math/NE10_detmat.neon.inc.s +++ b/modules/math/NE10_detmat.neon.inc.s @@ -54,7 +54,7 @@ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ - @ A macro used inside detmat_3x3f_neon() to load 3x3 matrices. + @ A macro used inside ne10_detmat_3x3f_neon() to load 3x3 matrices. @ Two 3x3 matrices are loaded from the source address @ into registers dst00-11. The corresponding qr00-qr05 @ registers are then rearranged so the order of the data fits the @@ -122,7 +122,7 @@ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ - @ A macro used inside detmat_4x4f_neon() to load 4x4 matrices. + @ A macro used inside ne10_detmat_4x4f_neon() to load 4x4 matrices. @ Two 4x4 matrices are loaded from the source address register \addr @ into registers dst00-15. The corresponding qr00-qr07 @ registers are then rearranged so the order of the data fits the @@ -185,7 +185,7 @@ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ - @ A macro used inside detmat_4x4f_neon() to load four 4x4 matrices + @ A macro used inside ne10_detmat_4x4f_neon() to load four 4x4 matrices @ from the memory location pointed to by the \addr register. @ The loaded matrices are stored in registers dst00-07 and @ finaklly rearranged using the corresponding registers qr00-qr03. diff --git a/modules/math/NE10_detmat.neon.s b/modules/math/NE10_detmat.neon.s index 128a6f0..3566d38 100644 --- a/modules/math/NE10_detmat.neon.s +++ b/modules/math/NE10_detmat.neon.s @@ -41,14 +41,14 @@ .align 4 - .global detmat_2x2f_neon + .global ne10_detmat_2x2f_neon .thumb .thumb_func -detmat_2x2f_neon: +ne10_detmat_2x2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t detmat_2x2f(arm_float_t * dst, + @ arm_result_t ne10_detmat_2x2f(arm_float_t * dst, @ arm_mat2x2f_t * src, @ unsigned int count) @ @@ -132,13 +132,13 @@ detmat_2x2f_neon: .align 4 - .global detmat_3x3f_neon + .global ne10_detmat_3x3f_neon .thumb .thumb_func -detmat_3x3f_neon: +ne10_detmat_3x3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t detmat_3x3f(arm_float_t * dst, + @ arm_result_t ne10_detmat_3x3f(arm_float_t * dst, @ arm_mat3x3f_t * src, @ unsigned int count) @ @@ -221,13 +221,13 @@ detmat_3x3f_neon: .align 4 - .global detmat_4x4f_neon + .global ne10_detmat_4x4f_neon .thumb .thumb_func -detmat_4x4f_neon: +ne10_detmat_4x4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t detmat_float(arm_float_t * dst, + @ arm_result_t ne10_detmat_float(arm_float_t * dst, @ arm_mat4x4f_t * src1, @ unsigned int count) @ diff --git a/modules/math/NE10_div.asm.s b/modules/math/NE10_div.asm.s index f10ebdc..5ed36e7 100644 --- a/modules/math/NE10_div.asm.s +++ b/modules/math/NE10_div.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global div_float_asm + .global ne10_div_float_asm .thumb .thumb_func -div_float_asm: +ne10_div_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t div_float(arm_vec2f_t * dst, + @ arm_result_t ne10_div_float(arm_vec2f_t * dst, @ arm_float_t * src1, const arm_float_t * src2, @ unsigned int count) @ diff --git a/modules/math/NE10_div.c b/modules/math/NE10_div.c index cc093a4..b1cc2a2 100644 --- a/modules/math/NE10_div.c +++ b/modules/math/NE10_div.c @@ -34,7 +34,7 @@ #include -ne10_result_t div_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) +ne10_result_t ne10_div_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -42,7 +42,7 @@ ne10_result_t div_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_flo ); } -ne10_result_t vdiv_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vdiv_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -51,7 +51,7 @@ ne10_result_t vdiv_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_ ); } -ne10_result_t vdiv_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vdiv_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -61,7 +61,7 @@ ne10_result_t vdiv_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_ ); } -ne10_result_t vdiv_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vdiv_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_div.neon.s b/modules/math/NE10_div.neon.s index 01b09f1..8aab9a3 100644 --- a/modules/math/NE10_div.neon.s +++ b/modules/math/NE10_div.neon.s @@ -38,14 +38,14 @@ .align 4 - .global div_float_neon + .global ne10_div_float_neon .thumb .thumb_func -div_float_neon: +ne10_div_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t div_float(arm_float_t * dst, + @ arm_result_t ne10_div_float(arm_float_t * dst, @ arm_float_t * src1, @ arm_float_t * src2, @ unsigned int count) @@ -118,14 +118,14 @@ div_float_neon: .align 4 - .global vdiv_vec2f_neon + .global ne10_vdiv_vec2f_neon .thumb .thumb_func -vdiv_vec2f_neon: +ne10_vdiv_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t div_float(arm_vec2f_t * dst, + @ arm_result_t ne10_div_float(arm_vec2f_t * dst, @ arm_vec2f_t * src1, @ arm_vec2f_t * src2, @ unsigned int count) @@ -204,13 +204,13 @@ vdiv_vec2f_neon: .align 4 - .global vdiv_vec3f_neon + .global ne10_vdiv_vec3f_neon .thumb .thumb_func -vdiv_vec3f_neon: +ne10_vdiv_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t div_float(arm_vec3f_t * dst, + @ arm_result_t ne10_div_float(arm_vec3f_t * dst, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @ unsigned int count) @@ -316,13 +316,13 @@ vdiv_vec3f_neon: .align 4 - .global vdiv_vec4f_neon + .global ne10_vdiv_vec4f_neon .thumb .thumb_func -vdiv_vec4f_neon: +ne10_vdiv_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t div_float(arm_vec4f_t * dst, + @ arm_result_t ne10_div_float(arm_vec4f_t * dst, @ arm_vec4f_t * src1, @ arm_vec4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_divc.asm.s b/modules/math/NE10_divc.asm.s index 449f7e0..0759d44 100644 --- a/modules/math/NE10_divc.asm.s +++ b/modules/math/NE10_divc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global divc_float_asm + .global ne10_divc_float_asm .thumb .thumb_func -divc_float_asm: +ne10_divc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t divc_float(arm_vec2f_t * dst, + @ arm_result_t ne10_divc_float(arm_vec2f_t * dst, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -82,14 +82,14 @@ divc_float_asm: .balign 4 - .global divc_vec2f_asm + .global ne10_divc_vec2f_asm .thumb .thumb_func -divc_vec2f_asm: +ne10_divc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t divc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_divc_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -133,14 +133,14 @@ divc_vec2f_asm: .balign 4 - .global divc_vec3f_asm + .global ne10_divc_vec3f_asm .thumb .thumb_func -divc_vec3f_asm: +ne10_divc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t divc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_divc_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -188,14 +188,14 @@ divc_vec3f_asm: .balign 4 - .global divc_vec4f_asm + .global ne10_divc_vec4f_asm .thumb .thumb_func -divc_vec4f_asm: +ne10_divc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t divc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_divc_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_divc.c b/modules/math/NE10_divc.c index 73c5040..c330757 100644 --- a/modules/math/NE10_divc.c +++ b/modules/math/NE10_divc.c @@ -34,7 +34,7 @@ #include -ne10_result_t divc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_divc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t divc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne ); } -ne10_result_t divc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t divc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_v ); } -ne10_result_t divc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t divc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_v ); } -ne10_result_t divc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( diff --git a/modules/math/NE10_divc.neon.c b/modules/math/NE10_divc.neon.c index 6c9a73f..f932434 100644 --- a/modules/math/NE10_divc.neon.c +++ b/modules/math/NE10_divc.neon.c @@ -38,7 +38,7 @@ #include #include -ne10_result_t divc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_divc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { ne10_uint32_t ii = 0; ne10_float32_t d[4]; @@ -58,7 +58,7 @@ ne10_result_t divc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ); } -ne10_result_t divc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC2F_NEON ( @@ -76,7 +76,7 @@ ne10_result_t divc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne1 ); } -ne10_result_t divc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC3F_NEON ( @@ -114,7 +114,7 @@ ne10_result_t divc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne1 ); } -ne10_result_t divc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_divc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_dot.c b/modules/math/NE10_dot.c index 46f1c5d..368aef7 100644 --- a/modules/math/NE10_dot.c +++ b/modules/math/NE10_dot.c @@ -34,7 +34,7 @@ #include -ne10_result_t dot_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_dot_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) { NE10_DOT_OPERATION_X_C ( @@ -43,7 +43,7 @@ ne10_result_t dot_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2 ); } -ne10_result_t dot_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_dot_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_DOT_OPERATION_X_C ( @@ -53,7 +53,7 @@ ne10_result_t dot_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f ); } -ne10_result_t dot_vec4f_c (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_dot_vec4f_c (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) { NE10_DOT_OPERATION_X_C ( diff --git a/modules/math/NE10_dot.neon.s b/modules/math/NE10_dot.neon.s index 7f587fe..0b8e14d 100644 --- a/modules/math/NE10_dot.neon.s +++ b/modules/math/NE10_dot.neon.s @@ -38,11 +38,11 @@ .align 4 - .global dot_vec2f_neon + .global ne10_dot_vec2f_neon .thumb .thumb_func -dot_vec2f_neon: +ne10_dot_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ @ arm_result_t dot_float(arm_float_t * dst, @@ -113,10 +113,10 @@ dot_vec2f_neon: .align 4 - .global dot_vec3f_neon + .global ne10_dot_vec3f_neon .thumb .thumb_func -dot_vec3f_neon: +ne10_dot_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ @ arm_result_t dot_float(arm_float_t * dst, @@ -199,10 +199,10 @@ dot_vec3f_neon: .align 4 - .global dot_vec4f_neon + .global ne10_dot_vec4f_neon .thumb .thumb_func -dot_vec4f_neon: +ne10_dot_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ @ arm_result_t dot_float(arm_float_t * dst, diff --git a/modules/math/NE10_identitymat.c b/modules/math/NE10_identitymat.c index d492d47..7915c12 100644 --- a/modules/math/NE10_identitymat.c +++ b/modules/math/NE10_identitymat.c @@ -32,7 +32,7 @@ #include "NE10_types.h" #include "macros.h" -ne10_result_t identitymat_2x2f_c (ne10_mat2x2f_t * dst, ne10_uint32_t count) +ne10_result_t ne10_identitymat_2x2f_c (ne10_mat2x2f_t * dst, ne10_uint32_t count) { ne10_mat2x2f_t *src = dst; // dummy placeholder @@ -45,7 +45,7 @@ ne10_result_t identitymat_2x2f_c (ne10_mat2x2f_t * dst, ne10_uint32_t count) ); } -ne10_result_t identitymat_3x3f_c (ne10_mat3x3f_t * dst, ne10_uint32_t count) +ne10_result_t ne10_identitymat_3x3f_c (ne10_mat3x3f_t * dst, ne10_uint32_t count) { ne10_mat3x3f_t *src = dst; // dummy placeholder @@ -65,7 +65,7 @@ ne10_result_t identitymat_3x3f_c (ne10_mat3x3f_t * dst, ne10_uint32_t count) ); } -ne10_result_t identitymat_4x4f_c (ne10_mat4x4f_t * dst, ne10_uint32_t count) +ne10_result_t ne10_identitymat_4x4f_c (ne10_mat4x4f_t * dst, ne10_uint32_t count) { ne10_mat4x4f_t *src = dst; // dummy placeholder diff --git a/modules/math/NE10_identitymat.neon.s b/modules/math/NE10_identitymat.neon.s index 118cd59..bca00e3 100644 --- a/modules/math/NE10_identitymat.neon.s +++ b/modules/math/NE10_identitymat.neon.s @@ -41,14 +41,14 @@ .balign 4 - .global identitymat_2x2f_neon + .global ne10_identitymat_2x2f_neon .thumb .thumb_func -identitymat_2x2f_neon: +ne10_identitymat_2x2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t identitymat_2x2f(arm_mat2x2f_t * dst, + @ arm_result_t ne10_identitymat_2x2f(arm_mat2x2f_t * dst, @ arm_mat2x2f_t * src, @ unsigned int count) @ @@ -110,13 +110,13 @@ identitymat_2x2f_neon: .align 2 - .global identitymat_3x3f_neon + .global ne10_identitymat_3x3f_neon .thumb .thumb_func -identitymat_3x3f_neon: +ne10_identitymat_3x3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t identitymat_3x3f(arm_mat3x3f_t * dst, + @ arm_result_t ne10_identitymat_3x3f(arm_mat3x3f_t * dst, @ arm_mat3x3f_t * src1, @ arm_mat3x3f_t * src2, @ unsigned int count) @@ -194,13 +194,13 @@ identitymat_3x3f_neon: .align 2 - .global identitymat_4x4f_neon + .global ne10_identitymat_4x4f_neon .thumb .thumb_func -identitymat_4x4f_neon: +ne10_identitymat_4x4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t identitymat_4x4f(arm_mat4x4f_t * dst, + @ arm_result_t ne10_identitymat_4x4f(arm_mat4x4f_t * dst, @ arm_mat4x4f_t * src1, @ arm_mat4x4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_init_math.c b/modules/math/NE10_init_math.c index f4d95e3..bf01172 100644 --- a/modules/math/NE10_init_math.c +++ b/modules/math/NE10_init_math.c @@ -33,275 +33,275 @@ ne10_result_t ne10_init_math (int is_NEON_available) { if (NE10_OK == is_NEON_available) { - addc_float = addc_float_neon; - addc_vec2f = addc_vec2f_neon; - addc_vec3f = addc_vec3f_neon; - addc_vec4f = addc_vec4f_neon; - subc_float = subc_float_neon; - subc_vec2f = subc_vec2f_neon; - subc_vec3f = subc_vec3f_neon; - subc_vec4f = subc_vec4f_neon; - rsbc_float = rsbc_float_neon; - rsbc_vec2f = rsbc_vec2f_neon; - rsbc_vec3f = rsbc_vec3f_neon; - rsbc_vec4f = rsbc_vec4f_neon; - mulc_float = mulc_float_neon; - mulc_vec2f = mulc_vec2f_neon; - mulc_vec3f = mulc_vec3f_neon; - mulc_vec4f = mulc_vec4f_neon; - divc_float = divc_float_neon; - divc_vec2f = divc_vec2f_neon; - divc_vec3f = divc_vec3f_neon; - divc_vec4f = divc_vec4f_neon; - setc_float = setc_float_neon; - setc_vec2f = setc_vec2f_neon; - setc_vec3f = setc_vec3f_neon; - setc_vec4f = setc_vec4f_neon; - mlac_float = mlac_float_neon; - mlac_vec2f = mlac_vec2f_neon; - mlac_vec3f = mlac_vec3f_neon; - mlac_vec4f = mlac_vec4f_neon; - add_float = add_float_neon; - sub_float = sub_float_neon; - mul_float = mul_float_neon; - div_float = div_float_neon; - mla_float = mla_float_neon; - abs_float = abs_float_neon; - len_vec2f = len_vec2f_neon; - len_vec3f = len_vec3f_neon; - len_vec4f = len_vec4f_neon; - normalize_vec2f = normalize_vec2f_neon; - normalize_vec3f = normalize_vec3f_neon; - normalize_vec4f = normalize_vec4f_neon; + ne10_addc_float = ne10_addc_float_neon; + ne10_addc_vec2f = ne10_addc_vec2f_neon; + ne10_addc_vec3f = ne10_addc_vec3f_neon; + ne10_addc_vec4f = ne10_addc_vec4f_neon; + ne10_subc_float = ne10_subc_float_neon; + ne10_subc_vec2f = ne10_subc_vec2f_neon; + ne10_subc_vec3f = ne10_subc_vec3f_neon; + ne10_subc_vec4f = ne10_subc_vec4f_neon; + ne10_rsbc_float = ne10_rsbc_float_neon; + ne10_rsbc_vec2f = ne10_rsbc_vec2f_neon; + ne10_rsbc_vec3f = ne10_rsbc_vec3f_neon; + ne10_rsbc_vec4f = ne10_rsbc_vec4f_neon; + ne10_mulc_float = ne10_mulc_float_neon; + ne10_mulc_vec2f = ne10_mulc_vec2f_neon; + ne10_mulc_vec3f = ne10_mulc_vec3f_neon; + ne10_mulc_vec4f = ne10_mulc_vec4f_neon; + ne10_divc_float = ne10_divc_float_neon; + ne10_divc_vec2f = ne10_divc_vec2f_neon; + ne10_divc_vec3f = ne10_divc_vec3f_neon; + ne10_divc_vec4f = ne10_divc_vec4f_neon; + ne10_setc_float = ne10_setc_float_neon; + ne10_setc_vec2f = ne10_setc_vec2f_neon; + ne10_setc_vec3f = ne10_setc_vec3f_neon; + ne10_setc_vec4f = ne10_setc_vec4f_neon; + ne10_mlac_float = ne10_mlac_float_neon; + ne10_mlac_vec2f = ne10_mlac_vec2f_neon; + ne10_mlac_vec3f = ne10_mlac_vec3f_neon; + ne10_mlac_vec4f = ne10_mlac_vec4f_neon; + ne10_add_float = ne10_add_float_neon; + ne10_sub_float = ne10_sub_float_neon; + ne10_mul_float = ne10_mul_float_neon; + ne10_div_float = ne10_div_float_neon; + ne10_mla_float = ne10_mla_float_neon; + ne10_abs_float = ne10_abs_float_neon; + ne10_len_vec2f = ne10_len_vec2f_neon; + ne10_len_vec3f = ne10_len_vec3f_neon; + ne10_len_vec4f = ne10_len_vec4f_neon; + ne10_normalize_vec2f = ne10_normalize_vec2f_neon; + ne10_normalize_vec3f = ne10_normalize_vec3f_neon; + ne10_normalize_vec4f = ne10_normalize_vec4f_neon; - abs_vec2f = abs_vec2f_neon; - abs_vec3f = abs_vec3f_neon; - abs_vec4f = abs_vec4f_neon; - vmul_vec2f = vmul_vec2f_neon; - vmul_vec3f = vmul_vec3f_neon; - vmul_vec4f = vmul_vec4f_neon; - vdiv_vec2f = vdiv_vec2f_neon; - vdiv_vec3f = vdiv_vec3f_neon; - vdiv_vec4f = vdiv_vec4f_neon; - vmla_vec2f = vmla_vec2f_neon; - vmla_vec3f = vmla_vec3f_neon; - vmla_vec4f = vmla_vec4f_neon; - add_vec2f = add_vec2f_neon; - add_vec3f = add_vec3f_neon; - add_vec4f = add_vec4f_neon; - sub_vec2f = sub_vec2f_neon; - sub_vec3f = sub_vec3f_neon; - sub_vec4f = sub_vec4f_neon; - dot_vec2f = dot_vec2f_neon; - dot_vec3f = dot_vec3f_neon; - dot_vec4f = dot_vec4f_neon; - cross_vec3f = cross_vec3f_neon; + ne10_abs_vec2f = ne10_abs_vec2f_neon; + ne10_abs_vec3f = ne10_abs_vec3f_neon; + ne10_abs_vec4f = ne10_abs_vec4f_neon; + ne10_vmul_vec2f = ne10_vmul_vec2f_neon; + ne10_vmul_vec3f = ne10_vmul_vec3f_neon; + ne10_vmul_vec4f = ne10_vmul_vec4f_neon; + ne10_vdiv_vec2f = ne10_vdiv_vec2f_neon; + ne10_vdiv_vec3f = ne10_vdiv_vec3f_neon; + ne10_vdiv_vec4f = ne10_vdiv_vec4f_neon; + ne10_vmla_vec2f = ne10_vmla_vec2f_neon; + ne10_vmla_vec3f = ne10_vmla_vec3f_neon; + ne10_vmla_vec4f = ne10_vmla_vec4f_neon; + ne10_add_vec2f = ne10_add_vec2f_neon; + ne10_add_vec3f = ne10_add_vec3f_neon; + ne10_add_vec4f = ne10_add_vec4f_neon; + ne10_sub_vec2f = ne10_sub_vec2f_neon; + ne10_sub_vec3f = ne10_sub_vec3f_neon; + ne10_sub_vec4f = ne10_sub_vec4f_neon; + ne10_dot_vec2f = ne10_dot_vec2f_neon; + ne10_dot_vec3f = ne10_dot_vec3f_neon; + ne10_dot_vec4f = ne10_dot_vec4f_neon; + ne10_cross_vec3f = ne10_cross_vec3f_neon; - addmat_2x2f = addmat_2x2f_neon; - addmat_3x3f = addmat_3x3f_neon; - addmat_4x4f = addmat_4x4f_neon; - submat_2x2f = submat_2x2f_neon; - submat_3x3f = submat_3x3f_neon; - submat_4x4f = submat_4x4f_neon; - mulmat_2x2f = mulmat_2x2f_neon; - mulmat_3x3f = mulmat_3x3f_neon; - mulmat_4x4f = mulmat_4x4f_neon; - mulcmatvec_cm2x2f_v2f = mulcmatvec_cm2x2f_v2f_neon; - mulcmatvec_cm3x3f_v3f = mulcmatvec_cm3x3f_v3f_neon; - mulcmatvec_cm4x4f_v4f = mulcmatvec_cm4x4f_v4f_neon; - detmat_2x2f = detmat_2x2f_neon; - detmat_3x3f = detmat_3x3f_neon; - detmat_4x4f = detmat_4x4f_neon; - invmat_2x2f = invmat_2x2f_neon; - invmat_3x3f = invmat_3x3f_neon; - invmat_4x4f = invmat_4x4f_neon; - transmat_4x4f = transmat_4x4f_neon; - identitymat_4x4f = identitymat_4x4f_neon; - transmat_3x3f = transmat_3x3f_neon; - identitymat_3x3f = identitymat_3x3f_neon; - transmat_2x2f = transmat_2x2f_neon; - identitymat_2x2f = identitymat_2x2f_neon; + ne10_addmat_2x2f = ne10_addmat_2x2f_neon; + ne10_addmat_3x3f = ne10_addmat_3x3f_neon; + ne10_addmat_4x4f = ne10_addmat_4x4f_neon; + ne10_submat_2x2f = ne10_submat_2x2f_neon; + ne10_submat_3x3f = ne10_submat_3x3f_neon; + ne10_submat_4x4f = ne10_submat_4x4f_neon; + ne10_mulmat_2x2f = ne10_mulmat_2x2f_neon; + ne10_mulmat_3x3f = ne10_mulmat_3x3f_neon; + ne10_mulmat_4x4f = ne10_mulmat_4x4f_neon; + ne10_mulcmatvec_cm2x2f_v2f = ne10_mulcmatvec_cm2x2f_v2f_neon; + ne10_mulcmatvec_cm3x3f_v3f = ne10_mulcmatvec_cm3x3f_v3f_neon; + ne10_mulcmatvec_cm4x4f_v4f = ne10_mulcmatvec_cm4x4f_v4f_neon; + ne10_detmat_2x2f = ne10_detmat_2x2f_neon; + ne10_detmat_3x3f = ne10_detmat_3x3f_neon; + ne10_detmat_4x4f = ne10_detmat_4x4f_neon; + ne10_invmat_2x2f = ne10_invmat_2x2f_neon; + ne10_invmat_3x3f = ne10_invmat_3x3f_neon; + ne10_invmat_4x4f = ne10_invmat_4x4f_neon; + ne10_transmat_4x4f = ne10_transmat_4x4f_neon; + ne10_identitymat_4x4f = ne10_identitymat_4x4f_neon; + ne10_transmat_3x3f = ne10_transmat_3x3f_neon; + ne10_identitymat_3x3f = ne10_identitymat_3x3f_neon; + ne10_transmat_2x2f = ne10_transmat_2x2f_neon; + ne10_identitymat_2x2f = ne10_identitymat_2x2f_neon; } else { - addc_float = addc_float_c; - addc_vec2f = addc_vec2f_c; - addc_vec3f = addc_vec3f_c; - addc_vec4f = addc_vec4f_c; - subc_float = subc_float_c; - subc_vec2f = subc_vec2f_c; - subc_vec3f = subc_vec3f_c; - subc_vec4f = subc_vec4f_c; - rsbc_float = rsbc_float_c; - rsbc_vec2f = rsbc_vec2f_c; - rsbc_vec3f = rsbc_vec3f_c; - rsbc_vec4f = rsbc_vec4f_c; - mulc_float = mulc_float_c; - mulc_vec2f = mulc_vec2f_c; - mulc_vec3f = mulc_vec3f_c; - mulc_vec4f = mulc_vec4f_c; - divc_float = divc_float_c; - divc_vec2f = divc_vec2f_c; - divc_vec3f = divc_vec3f_c; - divc_vec4f = divc_vec4f_c; - setc_float = setc_float_c; - setc_vec2f = setc_vec2f_c; - setc_vec3f = setc_vec3f_c; - setc_vec4f = setc_vec4f_c; - mlac_float = mlac_float_c; - mlac_vec2f = mlac_vec2f_c; - mlac_vec3f = mlac_vec3f_c; - mlac_vec4f = mlac_vec4f_c; - add_float = add_float_c; - sub_float = sub_float_c; - mul_float = mul_float_c; - div_float = div_float_c; - mla_float = mla_float_c; - abs_float = abs_float_c; - len_vec2f = len_vec2f_c; - len_vec3f = len_vec3f_c; - len_vec4f = len_vec4f_c; - normalize_vec2f = normalize_vec2f_c; - normalize_vec3f = normalize_vec3f_c; - normalize_vec4f = normalize_vec4f_c; + ne10_addc_float = ne10_addc_float_c; + ne10_addc_vec2f = ne10_addc_vec2f_c; + ne10_addc_vec3f = ne10_addc_vec3f_c; + ne10_addc_vec4f = ne10_addc_vec4f_c; + ne10_subc_float = ne10_subc_float_c; + ne10_subc_vec2f = ne10_subc_vec2f_c; + ne10_subc_vec3f = ne10_subc_vec3f_c; + ne10_subc_vec4f = ne10_subc_vec4f_c; + ne10_rsbc_float = ne10_rsbc_float_c; + ne10_rsbc_vec2f = ne10_rsbc_vec2f_c; + ne10_rsbc_vec3f = ne10_rsbc_vec3f_c; + ne10_rsbc_vec4f = ne10_rsbc_vec4f_c; + ne10_mulc_float = ne10_mulc_float_c; + ne10_mulc_vec2f = ne10_mulc_vec2f_c; + ne10_mulc_vec3f = ne10_mulc_vec3f_c; + ne10_mulc_vec4f = ne10_mulc_vec4f_c; + ne10_divc_float = ne10_divc_float_c; + ne10_divc_vec2f = ne10_divc_vec2f_c; + ne10_divc_vec3f = ne10_divc_vec3f_c; + ne10_divc_vec4f = ne10_divc_vec4f_c; + ne10_setc_float = ne10_setc_float_c; + ne10_setc_vec2f = ne10_setc_vec2f_c; + ne10_setc_vec3f = ne10_setc_vec3f_c; + ne10_setc_vec4f = ne10_setc_vec4f_c; + ne10_mlac_float = ne10_mlac_float_c; + ne10_mlac_vec2f = ne10_mlac_vec2f_c; + ne10_mlac_vec3f = ne10_mlac_vec3f_c; + ne10_mlac_vec4f = ne10_mlac_vec4f_c; + ne10_add_float = ne10_add_float_c; + ne10_sub_float = ne10_sub_float_c; + ne10_mul_float = ne10_mul_float_c; + ne10_div_float = ne10_div_float_c; + ne10_mla_float = ne10_mla_float_c; + ne10_abs_float = ne10_abs_float_c; + ne10_len_vec2f = ne10_len_vec2f_c; + ne10_len_vec3f = ne10_len_vec3f_c; + ne10_len_vec4f = ne10_len_vec4f_c; + ne10_normalize_vec2f = ne10_normalize_vec2f_c; + ne10_normalize_vec3f = ne10_normalize_vec3f_c; + ne10_normalize_vec4f = ne10_normalize_vec4f_c; - abs_vec2f = abs_vec2f_c; - abs_vec3f = abs_vec3f_c; - abs_vec4f = abs_vec4f_c; - vmul_vec2f = vmul_vec2f_c; - vmul_vec3f = vmul_vec3f_c; - vmul_vec4f = vmul_vec4f_c; - vdiv_vec2f = vdiv_vec2f_c; - vdiv_vec3f = vdiv_vec3f_c; - vdiv_vec4f = vdiv_vec4f_c; - vmla_vec2f = vmla_vec2f_c; - vmla_vec3f = vmla_vec3f_c; - vmla_vec4f = vmla_vec4f_c; - add_vec2f = add_vec2f_c; - add_vec3f = add_vec3f_c; - add_vec4f = add_vec4f_c; - sub_vec2f = sub_vec2f_c; - sub_vec3f = sub_vec3f_c; - sub_vec4f = sub_vec4f_c; - dot_vec2f = dot_vec2f_c; - dot_vec3f = dot_vec3f_c; - dot_vec4f = dot_vec4f_c; - cross_vec3f = cross_vec3f_c; + ne10_abs_vec2f = ne10_abs_vec2f_c; + ne10_abs_vec3f = ne10_abs_vec3f_c; + ne10_abs_vec4f = ne10_abs_vec4f_c; + ne10_vmul_vec2f = ne10_vmul_vec2f_c; + ne10_vmul_vec3f = ne10_vmul_vec3f_c; + ne10_vmul_vec4f = ne10_vmul_vec4f_c; + ne10_vdiv_vec2f = ne10_vdiv_vec2f_c; + ne10_vdiv_vec3f = ne10_vdiv_vec3f_c; + ne10_vdiv_vec4f = ne10_vdiv_vec4f_c; + ne10_vmla_vec2f = ne10_vmla_vec2f_c; + ne10_vmla_vec3f = ne10_vmla_vec3f_c; + ne10_vmla_vec4f = ne10_vmla_vec4f_c; + ne10_add_vec2f = ne10_add_vec2f_c; + ne10_add_vec3f = ne10_add_vec3f_c; + ne10_add_vec4f = ne10_add_vec4f_c; + ne10_sub_vec2f = ne10_sub_vec2f_c; + ne10_sub_vec3f = ne10_sub_vec3f_c; + ne10_sub_vec4f = ne10_sub_vec4f_c; + ne10_dot_vec2f = ne10_dot_vec2f_c; + ne10_dot_vec3f = ne10_dot_vec3f_c; + ne10_dot_vec4f = ne10_dot_vec4f_c; + ne10_cross_vec3f = ne10_cross_vec3f_c; - addmat_2x2f = addmat_2x2f_c; - addmat_3x3f = addmat_3x3f_c; - addmat_4x4f = addmat_4x4f_c; - submat_2x2f = submat_2x2f_c; - submat_3x3f = submat_3x3f_c; - submat_4x4f = submat_4x4f_c; - mulmat_2x2f = mulmat_2x2f_c; - mulmat_3x3f = mulmat_3x3f_c; - mulmat_4x4f = mulmat_4x4f_c; - mulcmatvec_cm2x2f_v2f = mulcmatvec_cm2x2f_v2f_c; - mulcmatvec_cm3x3f_v3f = mulcmatvec_cm3x3f_v3f_c; - mulcmatvec_cm4x4f_v4f = mulcmatvec_cm4x4f_v4f_c; - detmat_2x2f = detmat_2x2f_c; - detmat_3x3f = detmat_3x3f_c; - detmat_4x4f = detmat_4x4f_c; - invmat_2x2f = invmat_2x2f_c; - invmat_3x3f = invmat_3x3f_c; - invmat_4x4f = invmat_4x4f_c; - transmat_4x4f = transmat_4x4f_c; - identitymat_4x4f = identitymat_4x4f_c; - transmat_3x3f = transmat_3x3f_c; - identitymat_3x3f = identitymat_3x3f_c; - transmat_2x2f = transmat_2x2f_c; - identitymat_2x2f = identitymat_2x2f_c; + ne10_addmat_2x2f = ne10_addmat_2x2f_c; + ne10_addmat_3x3f = ne10_addmat_3x3f_c; + ne10_addmat_4x4f = ne10_addmat_4x4f_c; + ne10_submat_2x2f = ne10_submat_2x2f_c; + ne10_submat_3x3f = ne10_submat_3x3f_c; + ne10_submat_4x4f = ne10_submat_4x4f_c; + ne10_mulmat_2x2f = ne10_mulmat_2x2f_c; + ne10_mulmat_3x3f = ne10_mulmat_3x3f_c; + ne10_mulmat_4x4f = ne10_mulmat_4x4f_c; + ne10_mulcmatvec_cm2x2f_v2f = ne10_mulcmatvec_cm2x2f_v2f_c; + ne10_mulcmatvec_cm3x3f_v3f = ne10_mulcmatvec_cm3x3f_v3f_c; + ne10_mulcmatvec_cm4x4f_v4f = ne10_mulcmatvec_cm4x4f_v4f_c; + ne10_detmat_2x2f = ne10_detmat_2x2f_c; + ne10_detmat_3x3f = ne10_detmat_3x3f_c; + ne10_detmat_4x4f = ne10_detmat_4x4f_c; + ne10_invmat_2x2f = ne10_invmat_2x2f_c; + ne10_invmat_3x3f = ne10_invmat_3x3f_c; + ne10_invmat_4x4f = ne10_invmat_4x4f_c; + ne10_transmat_4x4f = ne10_transmat_4x4f_c; + ne10_identitymat_4x4f = ne10_identitymat_4x4f_c; + ne10_transmat_3x3f = ne10_transmat_3x3f_c; + ne10_identitymat_3x3f = ne10_identitymat_3x3f_c; + ne10_transmat_2x2f = ne10_transmat_2x2f_c; + ne10_identitymat_2x2f = ne10_identitymat_2x2f_c; } return NE10_OK; } // These are actual definitions of our function pointers that are declared in inc/NE10_types.h -ne10_result_t (*addc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*addc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*addc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*addc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*subc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*subc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*subc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*subc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*rsbc_float) (ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*rsbc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*rsbc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*rsbc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*mulc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*mulc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*mulc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*mulc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*divc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*divc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*divc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*divc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*setc_float) (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*setc_vec2f) (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*setc_vec3f) (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*setc_vec4f) (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*mlac_float) (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); -ne10_result_t (*mlac_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); -ne10_result_t (*mlac_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); -ne10_result_t (*mlac_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); -ne10_result_t (*add_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -ne10_result_t (*sub_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -ne10_result_t (*mul_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -ne10_result_t (*div_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -ne10_result_t (*mla_float) (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); -ne10_result_t (*abs_float) (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); -ne10_result_t (*len_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -ne10_result_t (*len_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -ne10_result_t (*len_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -ne10_result_t (*normalize_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -ne10_result_t (*normalize_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -ne10_result_t (*normalize_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_addc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_addc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_addc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_addc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_subc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_subc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_subc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_subc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_rsbc_float) (ne10_float32_t * dst, ne10_float32_t *src, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_rsbc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_rsbc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_rsbc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_mulc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_mulc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_mulc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_mulc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_divc_float) (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_divc_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_divc_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_divc_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_setc_float) (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count); +ne10_result_t (*ne10_setc_vec2f) (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_setc_vec3f) (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count); +ne10_result_t (*ne10_setc_vec4f) (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count); +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); +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); +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); +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); +ne10_result_t (*ne10_add_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_sub_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_mul_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_div_float) (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count); +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); +ne10_result_t (*ne10_abs_float) (ne10_float32_t * dst, ne10_float32_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_len_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_len_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_len_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_normalize_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_normalize_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_normalize_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -ne10_result_t (*abs_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); -ne10_result_t (*abs_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); -ne10_result_t (*abs_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); -ne10_result_t (*vmul_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*vmul_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*vmul_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*vdiv_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*vdiv_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*vdiv_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*vmla_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*vmla_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*vmla_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*add_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*add_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*add_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*sub_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*sub_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*sub_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*dot_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); -ne10_result_t (*dot_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*dot_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); -ne10_result_t (*cross_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_abs_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_abs_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_abs_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_vmul_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_vmul_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_vmul_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_vdiv_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_vdiv_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_vdiv_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +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); +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); +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); +ne10_result_t (*ne10_add_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_add_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_add_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_sub_vec2f) (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_sub_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_sub_vec4f) (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_dot_vec2f) (ne10_float32_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_dot_vec3f) (ne10_float32_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_dot_vec4f) (ne10_float32_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_cross_vec3f) (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count); -ne10_result_t (*addmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -ne10_result_t (*addmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -ne10_result_t (*addmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -ne10_result_t (*submat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -ne10_result_t (*submat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -ne10_result_t (*submat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -ne10_result_t (*mulmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); -ne10_result_t (*mulmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); -ne10_result_t (*mulmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); -ne10_result_t (*mulcmatvec_cm4x4f_v4f) (ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); -ne10_result_t (*mulcmatvec_cm3x3f_v3f) (ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); -ne10_result_t (*mulcmatvec_cm2x2f_v2f) (ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); -ne10_result_t (*detmat_4x4f) (ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -ne10_result_t (*detmat_3x3f) (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -ne10_result_t (*detmat_2x2f) (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -ne10_result_t (*invmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -ne10_result_t (*invmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -ne10_result_t (*invmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -ne10_result_t (*transmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); -ne10_result_t (*identitymat_4x4f) (ne10_mat4x4f_t * dst, ne10_uint32_t count); -ne10_result_t (*transmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); -ne10_result_t (*identitymat_3x3f) (ne10_mat3x3f_t * dst, ne10_uint32_t count); -ne10_result_t (*transmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); -ne10_result_t (*identitymat_2x2f) (ne10_mat2x2f_t * dst, ne10_uint32_t count); +ne10_result_t (*ne10_addmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_addmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_addmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_submat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_submat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_submat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_mulmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_mulmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_mulmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count); +ne10_result_t (*ne10_mulcmatvec_cm4x4f_v4f) (ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_mulcmatvec_cm3x3f_v3f) (ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_mulcmatvec_cm2x2f_v2f) (ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_detmat_4x4f) (ne10_float32_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_detmat_3x3f) (ne10_float32_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_detmat_2x2f) (ne10_float32_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_invmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_invmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_invmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_transmat_4x4f) (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_identitymat_4x4f) (ne10_mat4x4f_t * dst, ne10_uint32_t count); +ne10_result_t (*ne10_transmat_3x3f) (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_identitymat_3x3f) (ne10_mat3x3f_t * dst, ne10_uint32_t count); +ne10_result_t (*ne10_transmat_2x2f) (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count); +ne10_result_t (*ne10_identitymat_2x2f) (ne10_mat2x2f_t * dst, ne10_uint32_t count); diff --git a/modules/math/NE10_invmat.c b/modules/math/NE10_invmat.c index f78f7cc..8ebbdc6 100644 --- a/modules/math/NE10_invmat.c +++ b/modules/math/NE10_invmat.c @@ -39,7 +39,7 @@ // This macro is used to determine floating point values that are small enough to be consiedered nearly zero #define IS_FLOAT_NEAR_ZERO(x) ( ((fabs(x))<(1e-12)) ? 1 : 0 ) -ne10_result_t invmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_invmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) { ne10_float32_t det = 0.0f; @@ -60,7 +60,7 @@ ne10_result_t invmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_ui ); } -ne10_result_t invmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_invmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) { #define aa (src[ itr ].c1.r1) #define bb (src[ itr ].c1.r2) @@ -120,7 +120,7 @@ ne10_result_t invmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_ui #undef ii } -ne10_result_t invmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_invmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) { #define aa (src[ itr ].c1.r1) #define bb (src[ itr ].c1.r2) diff --git a/modules/math/NE10_invmat.neon.s b/modules/math/NE10_invmat.neon.s index 46de1f5..c07824e 100644 --- a/modules/math/NE10_invmat.neon.s +++ b/modules/math/NE10_invmat.neon.s @@ -94,14 +94,14 @@ CONST_FLOAT_1Em12: .align 4 - .global invmat_2x2f_neon + .global ne10_invmat_2x2f_neon .thumb .thumb_func -invmat_2x2f_neon: +ne10_invmat_2x2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t invmat_2x2f(arm_mat2x2f_t * dst, + @ arm_result_t ne10_invmat_2x2f(arm_mat2x2f_t * dst, @ arm_mat2x2f_t * src, @ unsigned int count) @ @@ -265,13 +265,13 @@ invmat_2x2f_neon: .align 4 - .global invmat_3x3f_neon + .global ne10_invmat_3x3f_neon .thumb .thumb_func -invmat_3x3f_neon: +ne10_invmat_3x3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t invmat_3x3f(arm_mat3x3f_t * dst, + @ arm_result_t ne10_invmat_3x3f(arm_mat3x3f_t * dst, @ arm_mat3x3f_t * src1, @ arm_mat3x3f_t * src2, @ unsigned int count) @@ -469,13 +469,13 @@ invmat_3x3f_neon: .align 4 - .global invmat_4x4f_neon + .global ne10_invmat_4x4f_neon .thumb .thumb_func -invmat_4x4f_neon: +ne10_invmat_4x4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t invmat_4x4f(arm_mat4x4f_t * dst, + @ arm_result_t ne10_invmat_4x4f(arm_mat4x4f_t * dst, @ arm_mat4x4f_t * src1, @ arm_mat4x4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_len.asm.s b/modules/math/NE10_len.asm.s index 099375e..71e1485 100644 --- a/modules/math/NE10_len.asm.s +++ b/modules/math/NE10_len.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global len_vec2f_asm + .global ne10_len_vec2f_asm .thumb .thumb_func -len_vec2f_asm: +ne10_len_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec2f(arm_float_t * dst, + @ arm_result_t ne10_len_vec2f(arm_float_t * dst, @ arm_vec2f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address @@ -73,14 +73,14 @@ len_vec2f_asm: .balign 4 - .global len_vec3f_asm + .global ne10_len_vec3f_asm .thumb .thumb_func -len_vec3f_asm: +ne10_len_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec3f(arm_float_t * dst, + @ arm_result_t ne10_len_vec3f(arm_float_t * dst, @ arm_vec3f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address @@ -113,14 +113,14 @@ len_vec3f_asm: .balign 4 - .global len_vec4f_asm + .global ne10_len_vec4f_asm .thumb .thumb_func -len_vec4f_asm: +ne10_len_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec4f(arm_float_t * dst, + @ arm_result_t ne10_len_vec4f(arm_float_t * dst, @ arm_vec4f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address diff --git a/modules/math/NE10_len.c b/modules/math/NE10_len.c index a0442eb..7729f9b 100644 --- a/modules/math/NE10_len.c +++ b/modules/math/NE10_len.c @@ -36,7 +36,7 @@ #include -ne10_result_t len_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_len_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) { NE10_LEN_OPERATION_X_C ( @@ -45,7 +45,7 @@ ne10_result_t len_vec2f_c (ne10_float32_t * dst, ne10_vec2f_t * src, ne10_uint32 ); } -ne10_result_t len_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_len_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) { NE10_LEN_OPERATION_X_C ( @@ -55,7 +55,7 @@ ne10_result_t len_vec3f_c (ne10_float32_t * dst, ne10_vec3f_t * src, ne10_uint32 ); } -ne10_result_t len_vec4f_c (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_len_vec4f_c (ne10_float32_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) { NE10_LEN_OPERATION_X_C ( diff --git a/modules/math/NE10_len.neon.s b/modules/math/NE10_len.neon.s index 65e54dc..f9994d2 100644 --- a/modules/math/NE10_len.neon.s +++ b/modules/math/NE10_len.neon.s @@ -38,14 +38,14 @@ .balign 4 - .global len_vec2f_neon + .global ne10_len_vec2f_neon .thumb .thumb_func -len_vec2f_neon: +ne10_len_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec2f(arm_float_t * dst, + @ arm_result_t ne10_len_vec2f(arm_float_t * dst, @ arm_vec2f_t * src, @ unsigned int count); @ @@ -144,13 +144,13 @@ len_vec2f_neon: .align 2 - .global len_vec3f_neon + .global ne10_len_vec3f_neon .thumb .thumb_func -len_vec3f_neon: +ne10_len_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec3f(arm_float_t * dst, + @ arm_result_t ne10_len_vec3f(arm_float_t * dst, @ arm_vec3f_t * src, @ unsigned int count); @ @@ -254,13 +254,13 @@ len_vec3f_neon: .align 2 - .global len_vec4f_neon + .global ne10_len_vec4f_neon .thumb .thumb_func -len_vec4f_neon: +ne10_len_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t len_vec4f(arm_float_t * dst, + @ arm_result_t ne10_len_vec4f(arm_float_t * dst, @ arm_vec4f_t * src, @ unsigned int count); @ diff --git a/modules/math/NE10_mla.asm.s b/modules/math/NE10_mla.asm.s index 867f1a1..7068050 100644 --- a/modules/math/NE10_mla.asm.s +++ b/modules/math/NE10_mla.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global mla_float_asm + .global ne10_mla_float_asm .thumb .thumb_func -mla_float_asm: +ne10_mla_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mla_float(arm_vec2f_t * dst, arm_float_t * acc, + @ arm_result_t ne10_mla_float(arm_vec2f_t * dst, arm_float_t * acc, @ arm_float_t * src1, const arm_float_t * src2, @ unsigned int count) @ diff --git a/modules/math/NE10_mla.c b/modules/math/NE10_mla.c index 1720325..ea12629 100644 --- a/modules/math/NE10_mla.c +++ b/modules/math/NE10_mla.c @@ -34,7 +34,7 @@ #include -ne10_result_t mla_float_c (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) +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) { NE10_X_OPERATION_FLOAT_C ( @@ -42,7 +42,7 @@ ne10_result_t mla_float_c (ne10_float32_t * dst, ne10_float32_t * acc, ne10_floa ); } -ne10_result_t vmla_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +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) { NE10_X_OPERATION_FLOAT_C ( @@ -51,7 +51,7 @@ ne10_result_t vmla_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t ); } -ne10_result_t vmla_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +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) { NE10_X_OPERATION_FLOAT_C ( @@ -61,7 +61,7 @@ ne10_result_t vmla_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t ); } -ne10_result_t vmla_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +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) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_mla.neon.s b/modules/math/NE10_mla.neon.s index 9f127c5..8fd1e08 100644 --- a/modules/math/NE10_mla.neon.s +++ b/modules/math/NE10_mla.neon.s @@ -38,14 +38,14 @@ .balign 4 - .global mla_float_neon + .global ne10_mla_float_neon .thumb .thumb_func -mla_float_neon: +ne10_mla_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mla_float(arm_float_t * dst, + @ arm_result_t ne10_mla_float(arm_float_t * dst, @ arm_float_t * acc, @ arm_float_t * src1, @ arm_float_t * src2, @@ -133,14 +133,14 @@ mla_float_neon: .balign 4 - .global vmla_vec2f_neon + .global ne10_vmla_vec2f_neon .thumb .thumb_func -vmla_vec2f_neon: +ne10_vmla_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t vmla_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_vmla_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * acc, @ arm_vec2f_t * src1, @ arm_vec2f_t * src2, @@ -230,13 +230,13 @@ vmla_vec2f_neon: .align 2 - .global vmla_vec3f_neon + .global ne10_vmla_vec3f_neon .thumb .thumb_func -vmla_vec3f_neon: +ne10_vmla_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t vmla_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_vmla_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * acc, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @@ -348,13 +348,13 @@ vmla_vec3f_neon: .align 2 - .global vmla_vec4f_neon + .global ne10_vmla_vec4f_neon .thumb .thumb_func -vmla_vec4f_neon: +ne10_vmla_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t vmla_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_vmla_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * acc, @ arm_vec4f_t * src1, @ arm_vec4f_t * src2, diff --git a/modules/math/NE10_mlac.asm.s b/modules/math/NE10_mlac.asm.s index fe1a21e..a84ea29 100644 --- a/modules/math/NE10_mlac.asm.s +++ b/modules/math/NE10_mlac.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global mlac_float_asm + .global ne10_mlac_float_asm .thumb .thumb_func -mlac_float_asm: +ne10_mlac_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mlac_float(arm_vec2f_t * dst, arm_vec2f_t * acc, + @ arm_result_t ne10_mlac_float(arm_vec2f_t * dst, arm_vec2f_t * acc, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -87,14 +87,14 @@ mlac_float_asm: .balign 4 - .global mlac_vec2f_asm + .global ne10_mlac_vec2f_asm .thumb .thumb_func -mlac_vec2f_asm: +ne10_mlac_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mlac_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_mlac_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -144,14 +144,14 @@ mlac_vec2f_asm: .balign 4 - .global mlac_vec3f_asm + .global ne10_mlac_vec3f_asm .thumb .thumb_func -mlac_vec3f_asm: +ne10_mlac_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mlac_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_mlac_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -206,14 +206,14 @@ mlac_vec3f_asm: .balign 4 - .global mlac_vec4f_asm + .global ne10_mlac_vec4f_asm .thumb .thumb_func -mlac_vec4f_asm: +ne10_mlac_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mlac_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_mlac_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_mlac.c b/modules/math/NE10_mlac.c index caa85e9..e40c9b0 100644 --- a/modules/math/NE10_mlac.c +++ b/modules/math/NE10_mlac.c @@ -34,7 +34,7 @@ #include -ne10_result_t mlac_float_c (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t mlac_float_c (ne10_float32_t * dst, ne10_float32_t * acc, ne10_flo ); } -ne10_result_t mlac_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t mlac_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t ); } -ne10_result_t mlac_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t mlac_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t ); } -ne10_result_t mlac_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_X_C ( diff --git a/modules/math/NE10_mlac.neon.c b/modules/math/NE10_mlac.neon.c index c6130d4..1d27c8d 100644 --- a/modules/math/NE10_mlac.neon.c +++ b/modules/math/NE10_mlac.neon.c @@ -36,7 +36,7 @@ #include -ne10_result_t mlac_float_neon (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t mlac_float_neon (ne10_float32_t * dst, ne10_float32_t * acc, ne10_ ); } -ne10_result_t mlac_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t mlac_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2 ); } -ne10_result_t mlac_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_VEC3F_NEON ( @@ -70,7 +70,7 @@ ne10_result_t mlac_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3 ); } -ne10_result_t mlac_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +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) { NE10_MLAC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_mul.asm.s b/modules/math/NE10_mul.asm.s index 98807ba..d0704eb 100644 --- a/modules/math/NE10_mul.asm.s +++ b/modules/math/NE10_mul.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global mul_float_asm + .global ne10_mul_float_asm .thumb .thumb_func -mul_float_asm: +ne10_mul_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mul_float(arm_vec2f_t * dst, + @ arm_result_t ne10_mul_float(arm_vec2f_t * dst, @ arm_float_t * src1, const arm_float_t * src2, @ unsigned int count) @ diff --git a/modules/math/NE10_mul.c b/modules/math/NE10_mul.c index c5c48c7..0838ea3 100644 --- a/modules/math/NE10_mul.c +++ b/modules/math/NE10_mul.c @@ -34,7 +34,7 @@ #include -ne10_result_t mul_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) +ne10_result_t ne10_mul_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -42,7 +42,7 @@ ne10_result_t mul_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_flo ); } -ne10_result_t vmul_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vmul_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -51,7 +51,7 @@ ne10_result_t vmul_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_ ); } -ne10_result_t vmul_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vmul_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -61,7 +61,7 @@ ne10_result_t vmul_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_ ); } -ne10_result_t vmul_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_vmul_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_mul.neon.s b/modules/math/NE10_mul.neon.s index 90766c7..4352b30 100644 --- a/modules/math/NE10_mul.neon.s +++ b/modules/math/NE10_mul.neon.s @@ -38,14 +38,14 @@ .align 4 - .global mul_float_neon + .global ne10_mul_float_neon .thumb .thumb_func -mul_float_neon: +ne10_mul_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mul_float(arm_float_t * dst, + @ arm_result_t ne10_mul_float(arm_float_t * dst, @ arm_float_t * src1, @ arm_float_t * src2, @ unsigned int count) @@ -124,14 +124,14 @@ mul_float_neon: .align 4 - .global vmul_vec2f_neon + .global ne10_vmul_vec2f_neon .thumb .thumb_func -vmul_vec2f_neon: +ne10_vmul_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mul_float(arm_vec2f_t * dst, + @ arm_result_t ne10_mul_float(arm_vec2f_t * dst, @ arm_vec2f_t * src1, @ arm_vec2f_t * src2, @ unsigned int count) @@ -212,13 +212,13 @@ vmul_vec2f_neon: .align 4 - .global vmul_vec3f_neon + .global ne10_vmul_vec3f_neon .thumb .thumb_func -vmul_vec3f_neon: +ne10_vmul_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mul_float(arm_vec3f_t * dst, + @ arm_result_t ne10_mul_float(arm_vec3f_t * dst, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @ unsigned int count) @@ -316,13 +316,13 @@ vmul_vec3f_neon: .align 4 - .global vmul_vec4f_neon + .global ne10_vmul_vec4f_neon .thumb .thumb_func -vmul_vec4f_neon: +ne10_vmul_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mul_float(arm_vec4f_t * dst, + @ arm_result_t ne10_mul_float(arm_vec4f_t * dst, @ arm_vec4f_t * src1, @ arm_vec4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_mulc.asm.s b/modules/math/NE10_mulc.asm.s index 582510f..105aca9 100644 --- a/modules/math/NE10_mulc.asm.s +++ b/modules/math/NE10_mulc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global mulc_float_asm + .global ne10_mulc_float_asm .thumb .thumb_func -mulc_float_asm: +ne10_mulc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulc_float(arm_vec2f_t * dst, + @ arm_result_t ne10_mulc_float(arm_vec2f_t * dst, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -82,14 +82,14 @@ mulc_float_asm: .balign 4 - .global mulc_vec2f_asm + .global ne10_mulc_vec2f_asm .thumb .thumb_func -mulc_vec2f_asm: +ne10_mulc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_mulc_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -133,14 +133,14 @@ mulc_vec2f_asm: .balign 4 - .global mulc_vec3f_asm + .global ne10_mulc_vec3f_asm .thumb .thumb_func -mulc_vec3f_asm: +ne10_mulc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_mulc_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -188,14 +188,14 @@ mulc_vec3f_asm: .balign 4 - .global mulc_vec4f_asm + .global ne10_mulc_vec4f_asm .thumb .thumb_func -mulc_vec4f_asm: +ne10_mulc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_mulc_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_mulc.c b/modules/math/NE10_mulc.c index 42eccb2..86ea7c4 100644 --- a/modules/math/NE10_mulc.c +++ b/modules/math/NE10_mulc.c @@ -34,7 +34,7 @@ #include -ne10_result_t mulc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t mulc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne ); } -ne10_result_t mulc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t mulc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_v ); } -ne10_result_t mulc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t mulc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_v ); } -ne10_result_t mulc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( diff --git a/modules/math/NE10_mulc.neon.c b/modules/math/NE10_mulc.neon.c index cd814c1..33badb3 100644 --- a/modules/math/NE10_mulc.neon.c +++ b/modules/math/NE10_mulc.neon.c @@ -36,7 +36,7 @@ #include -ne10_result_t mulc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t mulc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ); } -ne10_result_t mulc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t mulc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne1 ); } -ne10_result_t mulc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC3F_NEON ( @@ -70,7 +70,7 @@ ne10_result_t mulc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne1 ); } -ne10_result_t mulc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_mulc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_mulcmatvec.c b/modules/math/NE10_mulcmatvec.c index b855837..a73fc90 100644 --- a/modules/math/NE10_mulcmatvec.c +++ b/modules/math/NE10_mulcmatvec.c @@ -34,7 +34,7 @@ #include -ne10_result_t mulcmatvec_cm2x2f_v2f_c (ne10_vec2f_t * dst, const ne10_mat2x2f_t * cst, ne10_vec2f_t * src, ne10_uint32_t count) +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) { #define A1 cst->c1.r1 #define B1 cst->c1.r2 @@ -53,7 +53,7 @@ ne10_result_t mulcmatvec_cm2x2f_v2f_c (ne10_vec2f_t * dst, const ne10_mat2x2f_t #undef D1 } -ne10_result_t mulcmatvec_cm3x3f_v3f_c (ne10_vec3f_t * dst, const ne10_mat3x3f_t * cst, ne10_vec3f_t * src, ne10_uint32_t count) +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) { #define A1 cst->c1.r1 #define B1 cst->c1.r2 @@ -83,7 +83,7 @@ ne10_result_t mulcmatvec_cm3x3f_v3f_c (ne10_vec3f_t * dst, const ne10_mat3x3f_t #undef I1 } -extern ne10_result_t mulcmatvec_cm4x4f_v4f_c (ne10_vec4f_t * dst, const ne10_mat4x4f_t * cst, ne10_vec4f_t * src, ne10_uint32_t count) +extern 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) { #define A1 cst->c1.r1 #define B1 cst->c1.r2 diff --git a/modules/math/NE10_mulcmatvec.neon.s b/modules/math/NE10_mulcmatvec.neon.s index dc45ec9..b4bc8f0 100644 --- a/modules/math/NE10_mulcmatvec.neon.s +++ b/modules/math/NE10_mulcmatvec.neon.s @@ -43,7 +43,7 @@ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ This macro multiplies a single 2x2 matrix by eight vec2's @ The elements of the vectors are loaded into registers q8-q11 - @ by the caller (mulcmatvec_cm2x2f_v2f_neon) in the following + @ by the caller (ne10_mulcmatvec_cm2x2f_v2f_neon) in the following @ order: @ @ d16=(x1,x3) d18=(y1,y3) d20=(x2,x4) d22=(y2,y4); @@ -69,14 +69,14 @@ .balign 4 - .global mulcmatvec_cm2x2f_v2f_neon + .global ne10_mulcmatvec_cm2x2f_v2f_neon .thumb .thumb_func -mulcmatvec_cm2x2f_v2f_neon: +ne10_mulcmatvec_cm2x2f_v2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulcmatvec_cm2x2f_v2f ( arm_vec2f_t * dst, + @ arm_result_t ne10_mulcmatvec_cm2x2f_v2f ( arm_vec2f_t * dst, @ const arm_mat2x2f_t * cst, @ arm_vec2f_t * src, @ unsigned int count) @@ -220,14 +220,14 @@ mulcmatvec_cm2x2f_v2f_neon: .align 2 - .global mulcmatvec_cm3x3f_v3f_neon + .global ne10_mulcmatvec_cm3x3f_v3f_neon .thumb .thumb_func -mulcmatvec_cm3x3f_v3f_neon: +ne10_mulcmatvec_cm3x3f_v3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulcmatvec_cm3x3f_v3f ( arm_vec3f_t * dst, + @ arm_result_t ne10_mulcmatvec_cm3x3f_v3f ( arm_vec3f_t * dst, @ const arm_mat3x3f_t * cst, @ arm_vec3f_t * src, @ unsigned int count) @@ -316,7 +316,7 @@ mulcmatvec_cm3x3f_v3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ A macro to load four vec4's into registers q8-q11. @ This macro uses r2 (the thirs parameter in - @ mulcmatvec_cm4x4f_v4f_neon) as the address register. + @ ne10_mulcmatvec_cm4x4f_v4f_neon) as the address register. @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ .macro LOAD_FOUR_VEC4 vld4.32 { d16, d18, d20, d22 }, [r2]! @@ -326,7 +326,7 @@ mulcmatvec_cm3x3f_v3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ This macro multiplies the constant 4x4 matrix that is loaded - @ in mulcmatvec_cm4x4f_v4f_neon by four vec4's that are loaded in + @ in ne10_mulcmatvec_cm4x4f_v4f_neon by four vec4's that are loaded in @ the above macro LOAD_FOUR_VEC4. @ The resulting four vectors are returned in registers q12 to q15. @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @@ -360,7 +360,7 @@ mulcmatvec_cm3x3f_v3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ This macro stores the results from the above macro MUL_MAT4x4_VEC4 @ from registers q12-q15 in to the destination memory (r0) which is - @ the first parameter of mulcmatvec_cm4x4f_v4f_neon(). + @ the first parameter of ne10_mulcmatvec_cm4x4f_v4f_neon(). @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ .macro STORE_FOUR_VEC4 @@ -373,14 +373,14 @@ mulcmatvec_cm3x3f_v3f_neon: .align 2 - .global mulcmatvec_cm4x4f_v4f_neon + .global ne10_mulcmatvec_cm4x4f_v4f_neon .thumb .thumb_func -mulcmatvec_cm4x4f_v4f_neon: +ne10_mulcmatvec_cm4x4f_v4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulcmatvec_cm4x4f_v4f ( arm_vec4f_t * dst, + @ arm_result_t ne10_mulcmatvec_cm4x4f_v4f ( arm_vec4f_t * dst, @ const arm_mat4x4f_t * cst, @ arm_vec4f_t * src, @ unsigned int count) diff --git a/modules/math/NE10_mulmat.c b/modules/math/NE10_mulmat.c index dc6e88d..9c0c0af 100644 --- a/modules/math/NE10_mulmat.c +++ b/modules/math/NE10_mulmat.c @@ -34,7 +34,7 @@ #include -ne10_result_t mulmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_mulmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) { #define A1 src1[ itr ].c1.r1 #define A2 src2[ itr ].c1.r1 @@ -64,7 +64,7 @@ ne10_result_t mulmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_m #undef D2 } -ne10_result_t mulmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_mulmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) { #define A1 src1[ itr ].c1.r1 #define A2 src2[ itr ].c1.r1 @@ -120,7 +120,7 @@ ne10_result_t mulmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_m #undef I2 } -ne10_result_t mulmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_mulmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) { #define A1 src1[ itr ].c1.r1 #define A2 src2[ itr ].c1.r1 diff --git a/modules/math/NE10_mulmat.neon.s b/modules/math/NE10_mulmat.neon.s index 8d0a52f..3a9f94d 100644 --- a/modules/math/NE10_mulmat.neon.s +++ b/modules/math/NE10_mulmat.neon.s @@ -41,14 +41,14 @@ .balign 4 - .global mulmat_2x2f_neon + .global ne10_mulmat_2x2f_neon .thumb .thumb_func -mulmat_2x2f_neon: +ne10_mulmat_2x2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulmat_2x2f(arm_mat2x2f_t * dst, + @ arm_result_t ne10_mulmat_2x2f(arm_mat2x2f_t * dst, @ arm_mat2x2f_t * src1, @ arm_mat2x2f_t * src2, @ unsigned int count) @@ -282,13 +282,13 @@ mulmat_2x2f_neon: .align 2 - .global mulmat_3x3f_neon + .global ne10_mulmat_3x3f_neon .thumb .thumb_func -mulmat_3x3f_neon: +ne10_mulmat_3x3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulmat_3x3f(arm_mat3x3f_t * dst, + @ arm_result_t ne10_mulmat_3x3f(arm_mat3x3f_t * dst, @ arm_mat3x3f_t * src1, @ arm_mat3x3f_t * src2, @ unsigned int count) @@ -459,13 +459,13 @@ mulmat_3x3f_neon: .align 2 - .global mulmat_4x4f_neon + .global ne10_mulmat_4x4f_neon .thumb .thumb_func -mulmat_4x4f_neon: +ne10_mulmat_4x4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t mulmat_4x4f(arm_mat4x4f_t * dst, + @ arm_result_t ne10_mulmat_4x4f(arm_mat4x4f_t * dst, @ arm_mat4x4f_t * src1, @ arm_mat4x4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_normalize.asm.s b/modules/math/NE10_normalize.asm.s index 8d49c2d..d11444e 100644 --- a/modules/math/NE10_normalize.asm.s +++ b/modules/math/NE10_normalize.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global normalize_vec2f_asm + .global ne10_normalize_vec2f_asm .thumb .thumb_func -normalize_vec2f_asm: +ne10_normalize_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_normalize_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address @@ -75,14 +75,14 @@ normalize_vec2f_asm: .balign 4 - .global normalize_vec3f_asm + .global ne10_normalize_vec3f_asm .thumb .thumb_func -normalize_vec3f_asm: +ne10_normalize_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_normalize_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address @@ -119,14 +119,14 @@ normalize_vec3f_asm: .balign 4 - .global normalize_vec4f_asm + .global ne10_normalize_vec4f_asm .thumb .thumb_func -normalize_vec4f_asm: +ne10_normalize_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_normalize_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, unsigned int count) @ @ r0: *dst and current destination item's address diff --git a/modules/math/NE10_normalize.c b/modules/math/NE10_normalize.c index ad41f39..89e5c28 100644 --- a/modules/math/NE10_normalize.c +++ b/modules/math/NE10_normalize.c @@ -36,7 +36,7 @@ #include -ne10_result_t normalize_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_normalize_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_uint32_t count) { ne10_float32_t len; @@ -50,7 +50,7 @@ ne10_result_t normalize_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, ne10_ui ); } -ne10_result_t normalize_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_normalize_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_uint32_t count) { ne10_float32_t len; @@ -66,7 +66,7 @@ ne10_result_t normalize_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, ne10_ui ); } -ne10_result_t normalize_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_normalize_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, ne10_uint32_t count) { ne10_float32_t len; diff --git a/modules/math/NE10_normalize.neon.s b/modules/math/NE10_normalize.neon.s index 3395a2f..d8a443c 100644 --- a/modules/math/NE10_normalize.neon.s +++ b/modules/math/NE10_normalize.neon.s @@ -38,14 +38,14 @@ .balign 4 - .global normalize_vec2f_neon + .global ne10_normalize_vec2f_neon .thumb .thumb_func -normalize_vec2f_neon: +ne10_normalize_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_normalize_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, @ unsigned int count); @ @@ -150,13 +150,13 @@ normalize_vec2f_neon: .align 2 - .global normalize_vec3f_neon + .global ne10_normalize_vec3f_neon .thumb .thumb_func -normalize_vec3f_neon: +ne10_normalize_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec3f(arm_vec3t_t * dst, + @ arm_result_t ne10_normalize_vec3f(arm_vec3t_t * dst, @ arm_vec3f_t * src, @ unsigned int count); @ @@ -278,13 +278,13 @@ normalize_vec3f_neon: .align 2 - .global normalize_vec4f_neon + .global ne10_normalize_vec4f_neon .thumb .thumb_func -normalize_vec4f_neon: +ne10_normalize_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t normalize_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_normalize_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, @ unsigned int count); @ diff --git a/modules/math/NE10_rsbc.asm.s b/modules/math/NE10_rsbc.asm.s index 4eac2d1..a7677c4 100644 --- a/modules/math/NE10_rsbc.asm.s +++ b/modules/math/NE10_rsbc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global rsbc_float_asm + .global ne10_rsbc_float_asm .thumb .thumb_func -rsbc_float_asm: +ne10_rsbc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t rsbc_float(arm_vec2f_t * dst, + @ arm_result_t ne10_rsbc_float(arm_vec2f_t * dst, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -82,14 +82,14 @@ rsbc_float_asm: .balign 4 - .global rsbc_vec2f_asm + .global ne10_rsbc_vec2f_asm .thumb .thumb_func -rsbc_vec2f_asm: +ne10_rsbc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t rsbc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_rsbc_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -133,14 +133,14 @@ rsbc_vec2f_asm: .balign 4 - .global rsbc_vec3f_asm + .global ne10_rsbc_vec3f_asm .thumb .thumb_func -rsbc_vec3f_asm: +ne10_rsbc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t rsbc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_rsbc_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -189,14 +189,14 @@ rsbc_vec3f_asm: .balign 4 - .global rsbc_vec4f_asm + .global ne10_rsbc_vec4f_asm .thumb .thumb_func -rsbc_vec4f_asm: +ne10_rsbc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t rsbc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_rsbc_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_rsbc.c b/modules/math/NE10_rsbc.c index 878eac3..693794f 100644 --- a/modules/math/NE10_rsbc.c +++ b/modules/math/NE10_rsbc.c @@ -34,7 +34,7 @@ #include -ne10_result_t rsbc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t rsbc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne ); } -ne10_result_t rsbc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t rsbc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_v ); } -ne10_result_t rsbc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t rsbc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_v ); } -ne10_result_t rsbc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( diff --git a/modules/math/NE10_rsbc.neon.c b/modules/math/NE10_rsbc.neon.c index 69cb1ea..2ea49a5 100644 --- a/modules/math/NE10_rsbc.neon.c +++ b/modules/math/NE10_rsbc.neon.c @@ -36,7 +36,7 @@ #include -ne10_result_t rsbc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t rsbc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ); } -ne10_result_t rsbc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t rsbc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne1 ); } -ne10_result_t rsbc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC3F_NEON ( @@ -70,7 +70,7 @@ ne10_result_t rsbc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne1 ); } -ne10_result_t rsbc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_rsbc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_setc.asm.s b/modules/math/NE10_setc.asm.s index f5c2db3..020a21e 100644 --- a/modules/math/NE10_setc.asm.s +++ b/modules/math/NE10_setc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global setc_float_asm + .global ne10_setc_float_asm .thumb .thumb_func -setc_float_asm: +ne10_setc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t setc_float(arm_float_t * dst, + @ arm_result_t ne10_setc_float(arm_float_t * dst, @ const arm_float_t cst, @ unsigned int count) @ @@ -69,14 +69,14 @@ setc_float_asm: .balign 4 - .global setc_vec2f_asm + .global ne10_setc_vec2f_asm .thumb .thumb_func -setc_vec2f_asm: +ne10_setc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t setc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_setc_vec2f(arm_vec2f_t * dst, @ const arm_vec2f_t * cst, @ unsigned int count) @ @@ -108,14 +108,14 @@ setc_vec2f_asm: .balign 4 - .global setc_vec3f_asm + .global ne10_setc_vec3f_asm .thumb .thumb_func -setc_vec3f_asm: +ne10_setc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t setc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_setc_vec3f(arm_vec3f_t * dst, @ const arm_vec3f_t * cst, @ unsigned int count) @ @@ -149,14 +149,14 @@ setc_vec3f_asm: .balign 4 - .global setc_vec4f_asm + .global ne10_setc_vec4f_asm .thumb .thumb_func -setc_vec4f_asm: +ne10_setc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t setc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_setc_vec4f(arm_vec4f_t * dst, @ const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_setc.c b/modules/math/NE10_setc.c index f13cdf2..54721bf 100644 --- a/modules/math/NE10_setc.c +++ b/modules/math/NE10_setc.c @@ -34,7 +34,7 @@ #include -ne10_result_t setc_float_c (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_setc_float_c (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count) { NE10_SETC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t setc_float_c (ne10_float32_t * dst, const ne10_float32_t cst, ne10 ); } -ne10_result_t setc_vec2f_c (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec2f_c (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t setc_vec2f_c (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_u ); } -ne10_result_t setc_vec3f_c (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec3f_c (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t setc_vec3f_c (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_u ); } -ne10_result_t setc_vec4f_c (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec4f_c (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_X_C ( diff --git a/modules/math/NE10_setc.neon.c b/modules/math/NE10_setc.neon.c index ee368d9..0b300ed 100644 --- a/modules/math/NE10_setc.neon.c +++ b/modules/math/NE10_setc.neon.c @@ -36,7 +36,7 @@ #include -ne10_result_t setc_float_neon (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_setc_float_neon (ne10_float32_t * dst, const ne10_float32_t cst, ne10_uint32_t count) { NE10_SETC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t setc_float_neon (ne10_float32_t * dst, const ne10_float32_t cst, n ); } -ne10_result_t setc_vec2f_neon (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec2f_neon (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t setc_vec2f_neon (ne10_vec2f_t * dst, const ne10_vec2f_t * cst, ne1 ); } -ne10_result_t setc_vec3f_neon (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec3f_neon (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_VEC3F_NEON ( @@ -66,7 +66,7 @@ ne10_result_t setc_vec3f_neon (ne10_vec3f_t * dst, const ne10_vec3f_t * cst, ne1 ); } -ne10_result_t setc_vec4f_neon (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_setc_vec4f_neon (ne10_vec4f_t * dst, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_SETC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_sub.asm.s b/modules/math/NE10_sub.asm.s index 4932b1d..f18097f 100644 --- a/modules/math/NE10_sub.asm.s +++ b/modules/math/NE10_sub.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global sub_float_asm + .global ne10_sub_float_asm .thumb .thumb_func -sub_float_asm: +ne10_sub_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t sub_float(arm_vec2f_t * dst, + @ arm_result_t ne10_sub_float(arm_vec2f_t * dst, @ arm_float_t * src1, const arm_float_t * src2, @ unsigned int count) @ diff --git a/modules/math/NE10_sub.c b/modules/math/NE10_sub.c index ad212a0..4342580 100644 --- a/modules/math/NE10_sub.c +++ b/modules/math/NE10_sub.c @@ -34,7 +34,7 @@ #include -ne10_result_t sub_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) +ne10_result_t ne10_sub_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -42,7 +42,7 @@ ne10_result_t sub_float_c (ne10_float32_t * dst, ne10_float32_t * src1, ne10_flo ); } -ne10_result_t sub_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_sub_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -51,7 +51,7 @@ ne10_result_t sub_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src1, ne10_vec2f_t ); } -ne10_result_t sub_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_sub_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -61,7 +61,7 @@ ne10_result_t sub_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src1, ne10_vec3f_t ); } -ne10_result_t sub_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_sub_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_sub.neon.s b/modules/math/NE10_sub.neon.s index dc548aa..9e55b0f 100644 --- a/modules/math/NE10_sub.neon.s +++ b/modules/math/NE10_sub.neon.s @@ -38,14 +38,14 @@ .align 4 - .global sub_float_neon + .global ne10_sub_float_neon .thumb .thumb_func -sub_float_neon: +ne10_sub_float_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t sub_float(arm_float_t * dst, + @ arm_result_t ne10_sub_float(arm_float_t * dst, @ arm_float_t * src1, @ arm_float_t * src2, @ unsigned int count) @@ -126,14 +126,14 @@ sub_float_neon: .align 4 - .global sub_vec2f_neon + .global ne10_sub_vec2f_neon .thumb .thumb_func -sub_vec2f_neon: +ne10_sub_vec2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t sub_float(arm_vec2f_t * dst, + @ arm_result_t ne10_sub_float(arm_vec2f_t * dst, @ arm_vec2f_t * src1, @ arm_vec2f_t * src2, @ unsigned int count) @@ -214,13 +214,13 @@ sub_vec2f_neon: .align 4 - .global sub_vec3f_neon + .global ne10_sub_vec3f_neon .thumb .thumb_func -sub_vec3f_neon: +ne10_sub_vec3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t sub_float(arm_vec3f_t * dst, + @ arm_result_t ne10_sub_float(arm_vec3f_t * dst, @ arm_vec3f_t * src1, @ arm_vec3f_t * src2, @ unsigned int count) @@ -318,13 +318,13 @@ sub_vec3f_neon: .align 4 - .global sub_vec4f_neon + .global ne10_sub_vec4f_neon .thumb .thumb_func -sub_vec4f_neon: +ne10_sub_vec4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t sub_float(arm_vec4f_t * dst, + @ arm_result_t ne10_sub_float(arm_vec4f_t * dst, @ arm_vec4f_t * src1, @ arm_vec4f_t * src2, @ unsigned int count) diff --git a/modules/math/NE10_subc.asm.s b/modules/math/NE10_subc.asm.s index 670e9f6..2e25155 100644 --- a/modules/math/NE10_subc.asm.s +++ b/modules/math/NE10_subc.asm.s @@ -35,14 +35,14 @@ .include "NE10header.s" .balign 4 - .global subc_float_asm + .global ne10_subc_float_asm .thumb .thumb_func -subc_float_asm: +ne10_subc_float_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t subc_float(arm_vec2f_t * dst, + @ arm_result_t ne10_subc_float(arm_vec2f_t * dst, @ arm_float_t * src, const arm_float_t * cst, @ unsigned int count) @ @@ -82,14 +82,14 @@ subc_float_asm: .balign 4 - .global subc_vec2f_asm + .global ne10_subc_vec2f_asm .thumb .thumb_func -subc_vec2f_asm: +ne10_subc_vec2f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t subc_vec2f(arm_vec2f_t * dst, + @ arm_result_t ne10_subc_vec2f(arm_vec2f_t * dst, @ arm_vec2f_t * src, const arm_vec2f_t * cst, @ unsigned int count) @ @@ -133,14 +133,14 @@ subc_vec2f_asm: .balign 4 - .global subc_vec3f_asm + .global ne10_subc_vec3f_asm .thumb .thumb_func -subc_vec3f_asm: +ne10_subc_vec3f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t subc_vec3f(arm_vec3f_t * dst, + @ arm_result_t ne10_subc_vec3f(arm_vec3f_t * dst, @ arm_vec3f_t * src, const arm_vec3f_t * cst, @ unsigned int count) @ @@ -188,14 +188,14 @@ subc_vec3f_asm: .balign 4 - .global subc_vec4f_asm + .global ne10_subc_vec4f_asm .thumb .thumb_func -subc_vec4f_asm: +ne10_subc_vec4f_asm: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t subc_vec4f(arm_vec4f_t * dst, + @ arm_result_t ne10_subc_vec4f(arm_vec4f_t * dst, @ arm_vec4f_t * src, const arm_vec4f_t * cst, @ unsigned int count) @ diff --git a/modules/math/NE10_subc.c b/modules/math/NE10_subc.c index b56ef8b..8beaf0c 100644 --- a/modules/math/NE10_subc.c +++ b/modules/math/NE10_subc.c @@ -34,7 +34,7 @@ #include -ne10_result_t subc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_subc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -42,7 +42,7 @@ ne10_result_t subc_float_c (ne10_float32_t * dst, ne10_float32_t * src, const ne ); } -ne10_result_t subc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -51,7 +51,7 @@ ne10_result_t subc_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_v ); } -ne10_result_t subc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( @@ -61,7 +61,7 @@ ne10_result_t subc_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_v ); } -ne10_result_t subc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_X_C ( diff --git a/modules/math/NE10_subc.neon.c b/modules/math/NE10_subc.neon.c index 5e2383e..146c689 100644 --- a/modules/math/NE10_subc.neon.c +++ b/modules/math/NE10_subc.neon.c @@ -36,7 +36,7 @@ #include -ne10_result_t subc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) +ne10_result_t ne10_subc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ne10_float32_t cst, ne10_uint32_t count) { NE10_XC_OPERATION_FLOAT_NEON ( @@ -46,7 +46,7 @@ ne10_result_t subc_float_neon (ne10_float32_t * dst, ne10_float32_t * src, const ); } -ne10_result_t subc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne10_vec2f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC2F_NEON ( @@ -56,7 +56,7 @@ ne10_result_t subc_vec2f_neon (ne10_vec2f_t * dst, ne10_vec2f_t * src, const ne1 ); } -ne10_result_t subc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne10_vec3f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC3F_NEON ( @@ -70,7 +70,7 @@ ne10_result_t subc_vec3f_neon (ne10_vec3f_t * dst, ne10_vec3f_t * src, const ne1 ); } -ne10_result_t subc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) +ne10_result_t ne10_subc_vec4f_neon (ne10_vec4f_t * dst, ne10_vec4f_t * src, const ne10_vec4f_t * cst, ne10_uint32_t count) { NE10_XC_OPERATION_VEC4F_NEON ( diff --git a/modules/math/NE10_submat.c b/modules/math/NE10_submat.c index d5dd992..b9656aa 100644 --- a/modules/math/NE10_submat.c +++ b/modules/math/NE10_submat.c @@ -34,7 +34,7 @@ #include -ne10_result_t submat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -46,7 +46,7 @@ ne10_result_t submat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_m ); } -ne10_result_t submat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( @@ -64,7 +64,7 @@ ne10_result_t submat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_m ); } -ne10_result_t submat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) { NE10_X_OPERATION_FLOAT_C ( diff --git a/modules/math/NE10_submat.neon.c b/modules/math/NE10_submat.neon.c index b6b7da1..6390360 100644 --- a/modules/math/NE10_submat.neon.c +++ b/modules/math/NE10_submat.neon.c @@ -27,18 +27,18 @@ #include "NE10_types.h" -ne10_result_t submat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_2x2f_neon (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src1, ne10_mat2x2f_t * src2, ne10_uint32_t count) { - return sub_vec2f_neon ( (ne10_vec2f_t*) dst, (ne10_vec2f_t*) src1, (ne10_vec2f_t*) src2, count * 2); + return ne10_sub_vec2f_neon ( (ne10_vec2f_t*) dst, (ne10_vec2f_t*) src1, (ne10_vec2f_t*) src2, count * 2); } -ne10_result_t submat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_3x3f_neon (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src1, ne10_mat3x3f_t * src2, ne10_uint32_t count) { - return sub_vec3f_neon ( (ne10_vec3f_t*) dst, (ne10_vec3f_t*) src1, (ne10_vec3f_t*) src2, count * 3); + return ne10_sub_vec3f_neon ( (ne10_vec3f_t*) dst, (ne10_vec3f_t*) src1, (ne10_vec3f_t*) src2, count * 3); } -ne10_result_t submat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) +ne10_result_t ne10_submat_4x4f_neon (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src1, ne10_mat4x4f_t * src2, ne10_uint32_t count) { - return sub_vec4f_neon ( (ne10_vec4f_t*) dst, (ne10_vec4f_t*) src1, (ne10_vec4f_t*) src2, count * 4); + return ne10_sub_vec4f_neon ( (ne10_vec4f_t*) dst, (ne10_vec4f_t*) src1, (ne10_vec4f_t*) src2, count * 4); } diff --git a/modules/math/NE10_transmat.c b/modules/math/NE10_transmat.c index 7efd03c..ba959a7 100644 --- a/modules/math/NE10_transmat.c +++ b/modules/math/NE10_transmat.c @@ -42,7 +42,7 @@ inline void swap (ne10_float32_t *a, ne10_float32_t *b) *b = tmp; } -ne10_result_t transmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) +ne10_result_t ne10_transmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( @@ -53,7 +53,7 @@ ne10_result_t transmat_2x2f_c (ne10_mat2x2f_t * dst, ne10_mat2x2f_t * src, ne10_ ); } -ne10_result_t transmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) +ne10_result_t ne10_transmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( @@ -71,7 +71,7 @@ ne10_result_t transmat_3x3f_c (ne10_mat3x3f_t * dst, ne10_mat3x3f_t * src, ne10_ ); } -ne10_result_t transmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) +ne10_result_t ne10_transmat_4x4f_c (ne10_mat4x4f_t * dst, ne10_mat4x4f_t * src, ne10_uint32_t count) { NE10_DETMAT_OPERATION_X_C ( diff --git a/modules/math/NE10_transmat.neon.s b/modules/math/NE10_transmat.neon.s index 4b74810..9e72c39 100644 --- a/modules/math/NE10_transmat.neon.s +++ b/modules/math/NE10_transmat.neon.s @@ -42,14 +42,14 @@ .balign 4 - .global transmat_2x2f_neon + .global ne10_transmat_2x2f_neon .thumb .thumb_func -transmat_2x2f_neon: +ne10_transmat_2x2f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t transmat_2x2f(arm_mat2x2f_t * dst, + @ arm_result_t ne10_transmat_2x2f(arm_mat2x2f_t * dst, @ arm_mat2x2f_t * src, @ unsigned int count) @ @@ -128,13 +128,13 @@ transmat_2x2f_neon: .align 2 - .global transmat_3x3f_neon + .global ne10_transmat_3x3f_neon .thumb .thumb_func -transmat_3x3f_neon: +ne10_transmat_3x3f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t transmat_3x3f(arm_mat3x3f_t * dst, + @ arm_result_t ne10_transmat_3x3f(arm_mat3x3f_t * dst, @ arm_mat3x3f_t * src1, @ arm_mat3x3f_t * src2, @ unsigned int count) @@ -230,13 +230,13 @@ transmat_3x3f_neon: .align 2 - .global transmat_4x4f_neon + .global ne10_transmat_4x4f_neon .thumb .thumb_func -transmat_4x4f_neon: +ne10_transmat_4x4f_neon: @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ @ - @ arm_result_t transmat_4x4f(arm_mat4x4f_t * dst, + @ arm_result_t ne10_transmat_4x4f(arm_mat4x4f_t * dst, @ arm_mat4x4f_t * src1, @ arm_mat4x4f_t * src2, @ unsigned int count)