diff options
| author | Julian Oes <julian@oes.ch> | 2013-05-17 11:24:02 +0200 |
|---|---|---|
| committer | Julian Oes <julian@oes.ch> | 2013-05-17 11:24:02 +0200 |
| commit | f5c157e74df12a0cb36b7d27cdad9828d96cc534 (patch) | |
| tree | 3f758990921a7b52df8afe5131a8298b1141b6f4 /src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c | |
| parent | 80e8eeab2931e79e31adb17c93f5794e666c5763 (diff) | |
| parent | fa816d0fd65da461fd5bf8803cf00caebaf23c5c (diff) | |
| download | px4-firmware-f5c157e74df12a0cb36b7d27cdad9828d96cc534.tar.gz px4-firmware-f5c157e74df12a0cb36b7d27cdad9828d96cc534.tar.bz2 px4-firmware-f5c157e74df12a0cb36b7d27cdad9828d96cc534.zip | |
Merge remote-tracking branch 'upstream/master' into new_state_machine
Conflicts:
src/drivers/px4io/px4io.cpp
src/modules/commander/commander.c
src/modules/commander/state_machine_helper.c
Diffstat (limited to 'src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c')
| -rw-r--r-- | src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c | 215 |
1 files changed, 215 insertions, 0 deletions
diff --git a/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c b/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c new file mode 100644 index 000000000..6dfd25f65 --- /dev/null +++ b/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c @@ -0,0 +1,215 @@ +/* ----------------------------------------------------------------------
+* Copyright (C) 2010 ARM Limited. All rights reserved.
+*
+* $Date: 15. February 2012
+* $Revision: V1.1.0
+*
+* Project: CMSIS DSP Library
+* Title: arm_shift_q7.c
+*
+* Description: Processing function for the Q7 Shifting
+*
+* 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
+ */
+
+/**
+ * @addtogroup shift
+ * @{
+ */
+
+
+/**
+ * @brief Shifts the elements of a Q7 vector a specified number of bits.
+ * @param[in] *pSrc points to the input vector
+ * @param[in] shiftBits number of bits to shift. A positive value shifts left; a negative value shifts right.
+ * @param[out] *pDst points to the output vector
+ * @param[in] blockSize number of samples in the vector
+ * @return none.
+ *
+ * \par Conditions for optimum performance
+ * Input and output buffers should be aligned by 32-bit
+ *
+ *
+ * <b>Scaling and Overflow Behavior:</b>
+ * \par
+ * The function uses saturating arithmetic.
+ * Results outside of the allowable Q7 range [0x8 0x7F] will be saturated.
+ */
+
+void arm_shift_q7(
+ q7_t * pSrc,
+ int8_t shiftBits,
+ q7_t * pDst,
+ uint32_t blockSize)
+{
+ uint32_t blkCnt; /* loop counter */
+ uint8_t sign; /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+ q7_t in1; /* Input value1 */
+ q7_t in2; /* Input value2 */
+ q7_t in3; /* Input value3 */
+ q7_t in4; /* Input value4 */
+
+
+ /*loop Unrolling */
+ blkCnt = blockSize >> 2u;
+
+ /* Getting the sign of shiftBits */
+ sign = (shiftBits & 0x80);
+
+ /* If the shift value is positive then do right shift else left shift */
+ if(sign == 0u)
+ {
+ /* 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 << shiftBits */
+ /* Read 4 inputs */
+ in1 = *pSrc;
+ in2 = *(pSrc + 1);
+ in3 = *(pSrc + 2);
+ in4 = *(pSrc + 3);
+
+ /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+ *__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8),
+ __SSAT((in2 << shiftBits), 8),
+ __SSAT((in3 << shiftBits), 8),
+ __SSAT((in4 << shiftBits), 8));
+ /* Update source pointer to process next sampels */
+ pSrc += 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;
+
+ while(blkCnt > 0u)
+ {
+ /* C = A << shiftBits */
+ /* Shift the input and then store the result in the destination buffer. */
+ *pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8);
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+ }
+ else
+ {
+ shiftBits = -shiftBits;
+ /* 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 >> shiftBits */
+ /* Read 4 inputs */
+ in1 = *pSrc;
+ in2 = *(pSrc + 1);
+ in3 = *(pSrc + 2);
+ in4 = *(pSrc + 3);
+
+ /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+ *__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits),
+ (in3 >> shiftBits), (in4 >> shiftBits));
+
+
+ pSrc += 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;
+
+ while(blkCnt > 0u)
+ {
+ /* C = A >> shiftBits */
+ /* Shift the input and then store the result in the destination buffer. */
+ in1 = *pSrc++;
+ *pDst++ = (in1 >> shiftBits);
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+ }
+
+#else
+
+ /* Run the below code for Cortex-M0 */
+
+ /* Getting the sign of shiftBits */
+ sign = (shiftBits & 0x80);
+
+ /* If the shift value is positive then do right shift else left shift */
+ if(sign == 0u)
+ {
+ /* Initialize blkCnt with number of samples */
+ blkCnt = blockSize;
+
+ while(blkCnt > 0u)
+ {
+ /* C = A << shiftBits */
+ /* Shift the input and then store the result in the destination buffer. */
+ *pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8);
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+ }
+ else
+ {
+ /* Initialize blkCnt with number of samples */
+ blkCnt = blockSize;
+
+ while(blkCnt > 0u)
+ {
+ /* C = A >> shiftBits */
+ /* Shift the input and then store the result in the destination buffer. */
+ *pDst++ = (*pSrc++ >> -shiftBits);
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+ }
+
+#endif /* #ifndef ARM_MATH_CM0 */
+}
+
+/**
+ * @} end of shift group
+ */
|