From 96d6da4e252b06dcfdc041e7df23e86161c33007 Mon Sep 17 00:00:00 2001 From: rihab kouki Date: Tue, 28 Jul 2020 11:24:49 +0100 Subject: Official ARM version: v5.6.0 --- docs/DSP/html/group__PartialConv.html | 353 ++++++++++++++++++---------------- 1 file changed, 185 insertions(+), 168 deletions(-) (limited to 'docs/DSP/html/group__PartialConv.html') diff --git a/docs/DSP/html/group__PartialConv.html b/docs/DSP/html/group__PartialConv.html index acc6526..e94f691 100644 --- a/docs/DSP/html/group__PartialConv.html +++ b/docs/DSP/html/group__PartialConv.html @@ -32,7 +32,7 @@ Logo
CMSIS-DSP -  Version 1.5.2 +  Version 1.7.0
CMSIS DSP Software Library
@@ -116,51 +116,49 @@ $(document).ready(function(){initNavTree('group__PartialConv.html','');}); - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + +

Functions

arm_status arm_conv_partial_f32 (float32_t *pSrcA, uint32_t srcALen, float32_t *pSrcB, uint32_t srcBLen, float32_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of floating-point sequences. More...
 
arm_status arm_conv_partial_fast_opt_q15 (q15_t *pSrcA, uint32_t srcALen, q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4. More...
 
arm_status arm_conv_partial_fast_q15 (q15_t *pSrcA, uint32_t srcALen, q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4. More...
 
arm_status arm_conv_partial_fast_q31 (q31_t *pSrcA, uint32_t srcALen, q31_t *pSrcB, uint32_t srcBLen, q31_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4. More...
 
arm_status arm_conv_partial_opt_q15 (q15_t *pSrcA, uint32_t srcALen, q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q15 sequences. More...
 
arm_status arm_conv_partial_opt_q7 (q7_t *pSrcA, uint32_t srcALen, q7_t *pSrcB, uint32_t srcBLen, q7_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q7 sequences. More...
 
arm_status arm_conv_partial_q15 (q15_t *pSrcA, uint32_t srcALen, q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q15 sequences. More...
 
arm_status arm_conv_partial_q31 (q31_t *pSrcA, uint32_t srcALen, q31_t *pSrcB, uint32_t srcBLen, q31_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q31 sequences. More...
 
arm_status arm_conv_partial_q7 (q7_t *pSrcA, uint32_t srcALen, q7_t *pSrcB, uint32_t srcBLen, q7_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q7 sequences. More...
 
arm_status arm_conv_partial_f32 (const float32_t *pSrcA, uint32_t srcALen, const float32_t *pSrcB, uint32_t srcBLen, float32_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of floating-point sequences. More...
 
arm_status arm_conv_partial_fast_opt_q15 (const q15_t *pSrcA, uint32_t srcALen, const q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q15 sequences (fast version). More...
 
arm_status arm_conv_partial_fast_q15 (const q15_t *pSrcA, uint32_t srcALen, const q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q15 sequences (fast version). More...
 
arm_status arm_conv_partial_fast_q31 (const q31_t *pSrcA, uint32_t srcALen, const q31_t *pSrcB, uint32_t srcBLen, q31_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q31 sequences (fast version). More...
 
arm_status arm_conv_partial_opt_q15 (const q15_t *pSrcA, uint32_t srcALen, const q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q15 sequences. More...
 
arm_status arm_conv_partial_opt_q7 (const q7_t *pSrcA, uint32_t srcALen, const q7_t *pSrcB, uint32_t srcBLen, q7_t *pDst, uint32_t firstIndex, uint32_t numPoints, q15_t *pScratch1, q15_t *pScratch2)
 Partial convolution of Q7 sequences. More...
 
arm_status arm_conv_partial_q15 (const q15_t *pSrcA, uint32_t srcALen, const q15_t *pSrcB, uint32_t srcBLen, q15_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q15 sequences. More...
 
arm_status arm_conv_partial_q31 (const q31_t *pSrcA, uint32_t srcALen, const q31_t *pSrcB, uint32_t srcBLen, q31_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q31 sequences. More...
 
arm_status arm_conv_partial_q7 (const q7_t *pSrcA, uint32_t srcALen, const q7_t *pSrcB, uint32_t srcBLen, q7_t *pDst, uint32_t firstIndex, uint32_t numPoints)
 Partial convolution of Q7 sequences. More...
 

Description

Partial Convolution is equivalent to Convolution except that a subset of the output samples is generated. Each function has two additional arguments. firstIndex specifies the starting index of the subset of output samples. numPoints is the number of output samples to compute. The function computes the output in the range [firstIndex, ..., firstIndex+numPoints-1]. The output array pDst contains numPoints values.

The allowable range of output indices is [0 srcALen+srcBLen-2]. If the requested subset does not fall in this range then the functions return ARM_MATH_ARGUMENT_ERROR. Otherwise the functions return ARM_MATH_SUCCESS.

-
Note
Refer arm_conv_f32() for details on fixed point behavior.
-

Fast Versions

-
Fast versions are supported for Q31 and Q15 of partial convolution. Cycles for Fast versions are less compared to Q31 and Q15 of partial conv and the design requires the input signals should be scaled down to avoid intermediate overflows.
-

Opt Versions

-
Opt versions are supported for Q15 and Q7. Design uses internal scratch buffer for getting good optimisation. These versions are optimised in cycles and consumes more memory(Scratch memory) compared to Q15 and Q7 versions of partial convolution
+
Note
Refer to arm_conv_f32() for details on fixed point behavior.
+
Fast Versions
Fast versions are supported for Q31 and Q15 of partial convolution. Cycles for Fast versions are less compared to Q31 and Q15 of partial conv and the design requires the input signals should be scaled down to avoid intermediate overflows.
+
Opt Versions
Opt versions are supported for Q15 and Q7. Design uses internal scratch buffer for getting good optimisation. These versions are optimised in cycles and consumes more memory (Scratch memory) compared to Q15 and Q7 versions of partial convolution

Function Documentation

- +
- + @@ -172,7 +170,7 @@ Functions - + @@ -208,30 +206,32 @@ Functions
Parameters
arm_status arm_conv_partial_f32 (float32_t * const float32_t *  pSrcA,
float32_t * const float32_t *  pSrcB,
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
- -

References ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
- +
- + @@ -243,7 +243,7 @@ Functions - + @@ -289,36 +289,38 @@ Functions
arm_status arm_conv_partial_fast_opt_q15 (q15_t * const q15_t *  pSrcA,
q15_t * const q15_t *  pSrcB,
+

Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.

Parameters
- - - - - - - - - + + + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]*pScratch1points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
[in]*pScratch2points to scratch buffer of size min(srcALen, srcBLen).
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
[in]pScratch1points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2
[in]pScratch2points to scratch buffer of size min(srcALen, srcBLen)
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-

See arm_conv_partial_q15() for a slower implementation of this function which uses a 64-bit accumulator to avoid wrap around distortion.

-
Restrictions
If the silicon does not support unaligned memory access enable the macro UNALIGNED_SUPPORT_DISABLE In this case input, output, scratch1 and scratch2 buffers should be aligned by 32-bit
- -

References __PKHBT, __SIMD32, __SMLAD(), __SMLADX(), _SIMD32_OFFSET, arm_copy_q15(), arm_fill_q15(), ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_q15() for a slower implementation of this function which uses a 64-bit accumulator to avoid wrap around distortion.
- +
- + @@ -330,7 +332,7 @@ Functions - + @@ -364,33 +366,36 @@ Functions
arm_status arm_conv_partial_fast_q15 (q15_t * const q15_t *  pSrcA,
q15_t * const q15_t *  pSrcB,
+

Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.

Parameters
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-

See arm_conv_partial_q15() for a slower implementation of this function which uses a 64-bit accumulator to avoid wrap around distortion.

- -

References __PKHBT, __SIMD32, __SMLAD(), __SMLADX(), _SIMD32_OFFSET, ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_q15() for a slower implementation of this function which uses a 64-bit accumulator to avoid wrap around distortion.
- +
- + @@ -402,7 +407,7 @@ Functions - + @@ -436,33 +441,36 @@ Functions
arm_status arm_conv_partial_fast_q31 (q31_t * const q31_t *  pSrcA,
q31_t * const q31_t *  pSrcB,
+

Partial convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4.

Parameters
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-
See arm_conv_partial_q31() for a slower implementation of this function which uses a 64-bit accumulator to provide higher precision.
- -

References ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_q31() for a slower implementation of this function which uses a 64-bit accumulator to provide higher precision.
- +
- + @@ -474,7 +482,7 @@ Functions - + @@ -522,34 +530,35 @@ Functions
Parameters
arm_status arm_conv_partial_opt_q15 (q15_t * const q15_t *  pSrcA,
q15_t * const q15_t *  pSrcB,
- - - - - - - - - + + + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]*pScratch1points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
[in]*pScratch2points to scratch buffer of size min(srcALen, srcBLen).
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
[in]pScratch1points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
[in]pScratch2points to scratch buffer of size min(srcALen, srcBLen).
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-
Restrictions
If the silicon does not support unaligned memory access enable the macro UNALIGNED_SUPPORT_DISABLE In this case input, output, state buffers should be aligned by 32-bit
-

Refer to arm_conv_partial_fast_q15() for a faster but less precise version of this function for Cortex-M3 and Cortex-M4.

- -

References __PKHBT, __SIMD32, __SMLALD(), __SMLALDX(), _SIMD32_OFFSET, arm_copy_q15(), arm_fill_q15(), ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_fast_q15() for a faster but less precise version of this function.
- +
- + @@ -561,7 +570,7 @@ Functions - + @@ -609,33 +618,34 @@ Functions
Parameters
arm_status arm_conv_partial_opt_q7 (q7_t * const q7_t *  pSrcA,
q7_t * const q7_t *  pSrcB,
- - - - - - - - - + + + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]*pScratch1points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
[in]*pScratch2points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
[in]pScratch1points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
[in]pScratch2points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-
Restrictions
If the silicon does not support unaligned memory access enable the macro UNALIGNED_SUPPORT_DISABLE In this case input, output, scratch1 and scratch2 buffers should be aligned by 32-bit
- -

References __PACKq7, __PKHBT, __SIMD32, __SMLAD(), __SMLADX(), _SIMD32_OFFSET, arm_fill_q15(), ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
- +
- + @@ -647,7 +657,7 @@ Functions - + @@ -683,32 +693,35 @@ Functions
Parameters
arm_status arm_conv_partial_q15 (q15_t * const q15_t *  pSrcA,
q15_t * const q15_t *  pSrcB,
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-

Refer to arm_conv_partial_fast_q15() for a faster but less precise version of this function for Cortex-M3 and Cortex-M4.

-
Refer the function arm_conv_partial_opt_q15() for a faster implementation of this function using scratch buffers.
- -

References __PKHBT, __SIMD32, __SMLALD(), __SMLALDX(), _SIMD32_OFFSET, ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_fast_q15() for a faster but less precise version of this function.
+
+Refer to arm_conv_partial_opt_q15() for a faster implementation of this function using scratch buffers.
- +
- + @@ -720,7 +733,7 @@ Functions - + @@ -756,31 +769,33 @@ Functions
Parameters
arm_status arm_conv_partial_q31 (q31_t * const q31_t *  pSrcA,
q31_t * const q31_t *  pSrcB,
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-

See arm_conv_partial_fast_q31() for a faster but less precise implementation of this function for Cortex-M3 and Cortex-M4.

- -

References ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_fast_q31() for a faster but less precise implementation of this function.
- +
- + @@ -792,7 +807,7 @@ Functions - + @@ -828,20 +843,22 @@ Functions
Parameters
arm_status arm_conv_partial_q7 (q7_t * const q7_t *  pSrcA,
q7_t * const q7_t *  pSrcB,
- - - - - - - + + + + + + +
[in]*pSrcApoints to the first input sequence.
[in]srcALenlength of the first input sequence.
[in]*pSrcBpoints to the second input sequence.
[in]srcBLenlength of the second input sequence.
[out]*pDstpoints to the location where the output result is written.
[in]firstIndexis the first output sample to start with.
[in]numPointsis the number of output points to be computed.
[in]pSrcApoints to the first input sequence
[in]srcALenlength of the first input sequence
[in]pSrcBpoints to the second input sequence
[in]srcBLenlength of the second input sequence
[out]pDstpoints to the location where the output result is written
[in]firstIndexis the first output sample to start with
[in]numPointsis the number of output points to be computed
-
Returns
Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
-
Refer the function arm_conv_partial_opt_q7() for a faster implementation of this function.
- -

References __SMLAD(), ARM_MATH_ARGUMENT_ERROR, ARM_MATH_SUCCESS, srcALen, srcBLen, and status.

+
Returns
execution status +
+
Remarks
Refer to arm_conv_partial_opt_q7() for a faster implementation of this function.
@@ -850,7 +867,7 @@ Functions