CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cmsis_dsp/StatisticsFunctions/arm_mean_q7.c	Wed Nov 28 12:30:09 2012 +0000
@@ -0,0 +1,125 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision:     V1.1.0  
+*    
+* Project:         CMSIS DSP Library    
+* Title:        arm_mean_q7.c    
+*    
+* Description:    Mean value of a Q7 vector.   
+*    
+* 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 groupStats    
+ */
+
+/**    
+ * @addtogroup mean    
+ * @{    
+ */
+
+/**    
+ * @brief Mean value of a Q7 vector.    
+ * @param[in]       *pSrc points to the input vector    
+ * @param[in]       blockSize length of the input vector    
+ * @param[out]      *pResult mean value returned here    
+ * @return none.    
+ *    
+ * @details    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function is implemented using a 32-bit internal accumulator.     
+ * The input is represented in 1.7 format and is accumulated in a 32-bit    
+ * accumulator in 25.7 format.    
+ * There is no risk of internal overflow with this approach, and the     
+ * full precision of intermediate result is preserved.     
+ * Finally, the accumulator is truncated to yield a result of 1.7 format.    
+ *    
+ */
+
+
+void arm_mean_q7(
+  q7_t * pSrc,
+  uint32_t blockSize,
+  q7_t * pResult)
+{
+  q31_t sum = 0;                                 /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 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 = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
+    in = *__SIMD32(pSrc)++;
+
+    sum += ((in << 24) >> 24);
+    sum += ((in << 16) >> 24);
+    sum += ((in << 8) >> 24);
+    sum += (in >> 24);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Loop over blockSize number of values */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
+    sum += *pSrc++;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize  */
+  /* Store the result to the destination */
+  *pResult = (q7_t) (sum / (int32_t) blockSize);
+}
+
+/**    
+ * @} end of mean group    
+ */