/* ---------------------------------------------------------------------- * Project: CMSIS DSP Library * Title: arm_offset_q7.c * Description: Q7 vector offset * * $Date: 23 April 2021 * $Revision: V1.9.0 * * Target Processor: Cortex-M and Cortex-A cores * -------------------------------------------------------------------- */ /* * Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved. * * SPDX-License-Identifier: Apache-2.0 * * Licensed under the Apache License, Version 2.0 (the License); you may * not use this file except in compliance with the License. * You may obtain a copy of the License at * * www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an AS IS BASIS, WITHOUT * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ #include "dsp/basic_math_functions.h" /** @ingroup groupMath */ /** @addtogroup BasicOffset @{ */ /** @brief Adds a constant offset to a Q7 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 each vector @return none @par Scaling and Overflow Behavior The function uses saturating arithmetic. Results outside of the allowable Q7 range [0x80 0x7F] are saturated. */ #if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE) #include "arm_helium_utils.h" void arm_offset_q7( const q7_t * pSrc, q7_t offset, q7_t * pDst, uint32_t blockSize) { uint32_t blkCnt; /* loop counters */ q7x16_t vecSrc; /* Compute 16 outputs at a time */ blkCnt = blockSize >> 4; while (blkCnt > 0U) { /* * C = A + offset * Add offset and then store the result in the destination buffer. */ vecSrc = vld1q(pSrc); vst1q(pDst, vqaddq(vecSrc, offset)); /* * Decrement the blockSize loop counter */ blkCnt--; /* * advance vector source and destination pointers */ pSrc += 16; pDst += 16; } /* * tail */ blkCnt = blockSize & 0xF; if (blkCnt > 0U) { mve_pred16_t p0 = vctp8q(blkCnt); vecSrc = vld1q(pSrc); vstrbq_p(pDst, vqaddq(vecSrc, offset), p0); } } #else void arm_offset_q7( const q7_t * pSrc, q7_t offset, q7_t * pDst, uint32_t blockSize) { uint32_t blkCnt; /* Loop counter */ #if defined (ARM_MATH_LOOPUNROLL) #if defined (ARM_MATH_DSP) q31_t offset_packed; /* Offset packed to 32 bit */ /* Offset is packed to 32 bit in order to use SIMD32 for addition */ offset_packed = __PACKq7(offset, offset, offset, offset); #endif /* Loop unrolling: Compute 4 outputs at a time */ blkCnt = blockSize >> 2U; while (blkCnt > 0U) { /* C = A + offset */ #if defined (ARM_MATH_DSP) /* Add offset and store result in destination buffer (4 samples at a time). */ write_q7x4_ia (&pDst, __QADD8(read_q7x4_ia (&pSrc), offset_packed)); #else *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8); *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8); *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8); *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8); #endif /* Decrement loop counter */ blkCnt--; } /* Loop unrolling: Compute remaining outputs */ blkCnt = blockSize % 0x4U; #else /* Initialize blkCnt with number of samples */ blkCnt = blockSize; #endif /* #if defined (ARM_MATH_LOOPUNROLL) */ while (blkCnt > 0U) { /* C = A + offset */ /* Add offset and store result in destination buffer. */ *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8); /* Decrement loop counter */ blkCnt--; } } #endif /* defined(ARM_MATH_MVEI) */ /** @} end of BasicOffset group */