From 4447282260be0780eb6e36f5e953bf56888a5688 Mon Sep 17 00:00:00 2001
From: px4dev <px4@purgatory.org>
Date: Sun, 6 Jan 2013 12:52:05 -0800
Subject: Integrate the interesting parts of the CMSIS 3.01 (r3p1) DSP library

---
 .../Source/BasicMathFunctions/arm_offset_f32.c     | 158 +++++++++++++++++++++
 1 file changed, 158 insertions(+)
 create mode 100644 apps/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c

(limited to 'apps/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c')

diff --git a/apps/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c b/apps/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c
new file mode 100644
index 000000000..4bdf06ee8
--- /dev/null
+++ b/apps/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c
@@ -0,0 +1,158 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010 ARM Limited. All rights reserved.    
+*    
+* $Date:        15. February 2012  
+* $Revision: 	V1.1.0  
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_f32.c    
+*    
+* Description:	Floating-point vector offset.    
+*    
+* 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.    
+*    
+* Version 0.0.7  2010/06/10     
+*    Misra-C changes done    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup offset Vector Offset        
+ *        
+ * Adds a constant offset to each element of a vector.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] + offset,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup offset        
+ * @{        
+ */
+
+/**        
+ * @brief  Adds a constant offset to a floating-point vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  offset is the offset to be added        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+
+void arm_offset_f32(
+  float32_t * pSrc,
+  float32_t offset,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;
+
+  /*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 + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    /* read samples from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+
+    /* add offset to input */
+    in1 = in1 + offset;
+
+    /* read samples from source */
+    in3 = *(pSrc + 2);
+
+    /* add offset to input */
+    in2 = in2 + offset;
+
+    /* read samples from source */
+    in4 = *(pSrc + 3);
+
+    /* add offset to input */
+    in3 = in3 + offset;
+
+    /* store result to destination */
+    *pDst = in1;
+
+    /* add offset to input */
+    in4 = in4 + offset;
+
+    /* store result to destination */
+    *(pDst + 1) = in2;
+
+    /* store result to destination */
+    *(pDst + 2) = in3;
+
+    /* store result to destination */
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* 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 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0 */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (*pSrc++) + offset;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of offset group        
+ */
-- 
cgit v1.2.3