1 files changed, 153 insertions, 0 deletions
diff --git a/src/modules/mathlib/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q31.c b/src/modules/mathlib/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q31.c
new file mode 100644
index 000000000..d45ccfab2
--- /dev/null
+++ b/src/modules/mathlib/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q31.c
@@ -0,0 +1,153 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_q31.c    
+*    
+* Description:	Q31 complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Version 1.1.0 2012/02/15 
+*    Updated with more optimizations, bug fixes and minor API changes.  
+*   
+* Version 1.0.10 2011/7/15  
+*    Big Endian support added and Merged M0 and M3/M4 Source code.   
+*    
+* Version 1.0.3 2010/11/29   
+*    Re-organized the CMSIS folders and updated documentation.    
+*     
+* Version 1.0.2 2010/11/11    
+*    Documentation updated.     
+*    
+* Version 1.0.1 2010/10/05     
+*    Production release and review comments incorporated.    
+*    
+* Version 1.0.0 2010/09/20     
+*    Production release and review comments incorporated.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag_squared    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex magnitude squared    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_mag_squared_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t real, imag;                              /* Temporary variables to store real and imaginary values */
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* out = ((real * real) + (imag * imag)) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+}
+
+/**    
+ * @} end of cmplx_mag_squared group    
+ */