From 76177aa280494bb36d7a0bcbda1078d4db717020 Mon Sep 17 00:00:00 2001 From: Ali Labbene Date: Mon, 9 Dec 2019 11:25:19 +0100 Subject: Official ARM version: v4.5 --- .../DSP/html/group___cmplx_by_cmplx_mult.html | 306 +++++++++++++++++++++ 1 file changed, 306 insertions(+) create mode 100644 Documentation/DSP/html/group___cmplx_by_cmplx_mult.html (limited to 'Documentation/DSP/html/group___cmplx_by_cmplx_mult.html') diff --git a/Documentation/DSP/html/group___cmplx_by_cmplx_mult.html b/Documentation/DSP/html/group___cmplx_by_cmplx_mult.html new file mode 100644 index 0000000..9627fef --- /dev/null +++ b/Documentation/DSP/html/group___cmplx_by_cmplx_mult.html @@ -0,0 +1,306 @@ + + + + + +Complex-by-Complex Multiplication +CMSIS-DSP: Complex-by-Complex Multiplication + + + + + + + + + + + + + + + +
+
+ + + + + + + +
+
CMSIS-DSP +  Version 1.4.7 +
+
CMSIS DSP Software Library
+
+
+ +
+
    + +
+
+ + + +
+
+ +
+
+
+ +
+ + + + +
+ +
+ +
+
+Functions
+
+
Complex-by-Complex Multiplication
+
Complex Math Functions
+
+ + + + + + + + + + + +

+Functions

void arm_cmplx_mult_cmplx_f32 (float32_t *pSrcA, float32_t *pSrcB, float32_t *pDst, uint32_t numSamples)
 Floating-point complex-by-complex multiplication.
 
void arm_cmplx_mult_cmplx_q15 (q15_t *pSrcA, q15_t *pSrcB, q15_t *pDst, uint32_t numSamples)
 Q15 complex-by-complex multiplication.
 
void arm_cmplx_mult_cmplx_q31 (q31_t *pSrcA, q31_t *pSrcB, q31_t *pDst, uint32_t numSamples)
 Q31 complex-by-complex multiplication.
 
+

Description

+

Multiplies a complex vector by another complex vector and generates a complex result. The data in the complex arrays is stored in an interleaved fashion (real, imag, real, imag, ...). The parameter numSamples represents the number of complex samples processed. The complex arrays have a total of 2*numSamples real values.

+

The underlying algorithm is used:

+
        
+for(n=0; n<numSamples; n++) {        
+    pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];        
+    pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];        
+}        
+

There are separate functions for floating-point, Q15, and Q31 data types.

+

Function Documentation

+ +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
void arm_cmplx_mult_cmplx_f32 (float32_t * pSrcA,
float32_t * pSrcB,
float32_t * pDst,
uint32_t numSamples 
)
+
+
Parameters
+ + + + + +
[in]*pSrcApoints to the first input vector
[in]*pSrcBpoints to the second input vector
[out]*pDstpoints to the output vector
[in]numSamplesnumber of complex samples in each vector
+
+
+
Returns
none.
+
Examples:
arm_convolution_example_f32.c.
+
+

Referenced by main().

+ +
+
+ +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
void arm_cmplx_mult_cmplx_q15 (q15_t * pSrcA,
q15_t * pSrcB,
q15_t * pDst,
uint32_t numSamples 
)
+
+
Parameters
+ + + + + +
[in]*pSrcApoints to the first input vector
[in]*pSrcBpoints to the second input vector
[out]*pDstpoints to the output vector
[in]numSamplesnumber of complex samples in each vector
+
+
+
Returns
none.
+

Scaling and Overflow Behavior:

+
The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.
+ +
+
+ +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
void arm_cmplx_mult_cmplx_q31 (q31_t * pSrcA,
q31_t * pSrcB,
q31_t * pDst,
uint32_t numSamples 
)
+
+
Parameters
+ + + + + +
[in]*pSrcApoints to the first input vector
[in]*pSrcBpoints to the second input vector
[out]*pDstpoints to the output vector
[in]numSamplesnumber of complex samples in each vector
+
+
+
Returns
none.
+

Scaling and Overflow Behavior:

+
The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format. Input down scaling is not required.
+ +

Referenced by arm_dct4_q31().

+ +
+
+
+
+ + + + -- cgit