| /cmsis-dsp-3.7.0-3.6.0/Testing/ |
| D | diff.sql | 1 .headers ON
36 should be added here so that we join the ref and other cores on common benchmark definition.
57 …INNER JOIN refCore ON refCore.ID = otherCores.ID AND refCore.categoryid = otherCores.categoryid AN…
58 INNER JOIN CATEGORY ON CATEGORY.categoryid = otherCores.categoryid
59 INNER JOIN PLATFORM ON PLATFORM.platformid = otherCores.platformid
60 INNER JOIN CORE ON CORE.coreid = otherCores.coreid
61 INNER JOIN COMPILER ON COMPILER.compilerid = otherCores.compilerid
62 INNER JOIN COMPILERKIND ON COMPILERKIND.compilerkindid = COMPILER.compilerkindid
63 INNER JOIN TYPE ON TYPE.typeid = otherCores.typeid;
|
| D | createDb.sql | 6 CREATE INDEX coredef_index ON CORE(coredef);
12 CREATE INDEX platform_index ON PLATFORM(platform);
18 CREATE INDEX compilerkind_index ON COMPILERKIND(compiler);
29 CREATE INDEX compiler_index ON COMPILER(compilerkindid,version);
30 CREATE INDEX compiler_date_index ON COMPILER(testdateid);
31 CREATE INDEX compiler_all_index ON COMPILER(compilerkindid,version,testdateid);
42 CREATE INDEX type_index ON TYPE(type);
48 CREATE INDEX category_index ON CATEGORY(category);
54 CREATE INDEX testname_index ON TESTNAME(name);
60 CREATE INDEX testdate_index ON TESTDATE(date);
|
| D | README.md | 61 (If you are on Windows, use the `bin/windows64` folder)
71 **You can then run the executable on Virtual Hardware.**
73 For instance, to run the test on the virtual hardware for Corstone 300, if you have the Arm MDK ins…
109 The tests may depend on several parameters (width, height etc ...)
113 For instance, if our test is dependent on a vector size, we may want to compute a linear regression
114 to know how the performances are dependent on the vector size.
116 But, our test may also depend on another parameter B which is not interesting us in the regression.…
125 …f (to check that the execution has been successful could be running on the DUT or on a host like a…
131 #### R10 : The test may be run on the DUT or on the host
137 #### R13 : Control of the tests could run on the DUT but could also be run on a host
[all …]
|
| /cmsis-dsp-3.7.0-3.6.0/ |
| D | README.md | 55 * The static schedule can be run on the device with low overhead
96 …n `-DARM_MATH_NEON` for the C compilation. With `cmake` this option is controlled with `-DNEON=ON`.
98 * `-DLOOPUNROLL=ON` can also be used when compiling with cmake
101 Compilers are doing unrolling. So this option may not be needed but it is highly dependent on the c…
112 …not** occur when `-fno-builtin` is used and it will have a **very bad** impact on the performances.
130 …pen CMSIS-Pack](https://www.open-cmsis-pack.org/) technology and from command line on any platform.
183 CMSIS-DSP is dependent on the CMSIS Core includes. So, you should define `CMSISCORE` on the cmake c…
212 The intrinsics defined in `Core_A/Include` are not available on recent Cortex-A processors.
216 You need to build with `-D__GNUC_PYTHON__` on the compiler command line. This flag was introduced f…
232 * `-DHOST=ON`
[all …]
|
| D | LICENSE | 41 form, that is based on (or derived from) the Work and for which the
52 or by an individual or Legal Entity authorized to submit on behalf of
56 communication on electronic mailing lists, source code control systems,
57 and issue tracking systems that are managed by, or on behalf of, the
63 on behalf of whom a Contribution has been received by Licensor and
145 Contributor provides its Contributions) on an "AS IS" BASIS,
170 on Your own behalf and on Your sole responsibility, not on behalf
185 file or class name and description of purpose be included on the
198 distributed under the License is distributed on an "AS IS" BASIS,
|
| D | PythonWrapper_README.md | 5 The CMSIS-DSP is available on our [GitHub](https://github.com/ARM-software/CMSIS-DSP) or as a [CMSI…
7 …ithub.com/ARM-software/CMSIS-DSP) API to ease the migration to the final implementation on a board.
9 …Python environment and then easily converted to a C implementation running on a Cortex-M or Cortex…
24 The building of this package has been tested on Windows with the Python install from python.org and…
26 It has also been tested with `cygwin`. In that case, `python-devel` must be installed too. On Mac, …
83 Depending on the example, you may have to install more packages.
89 … can't give any support if you have problems compiling the `PythonWrapper` on your specific config…
93 …ithub.com/ARM-software/CMSIS-DSP) API to ease the migration to the final implementation on a board.
213 This example depends on a data file which can be downloaded here:
219 Lugovaya T.S. Biometric human identification based on electrocardiogram. [Master's thesis] Faculty …
[all …]
|
| /cmsis-dsp-3.7.0-3.6.0/Include/dsp/ |
| D | matrix_functions.h | 20 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
45 * The functions operate on matrix data structures. For example,
89 * By default all of the matrix functions perform size checking on the input and
171 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
184 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
197 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
210 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
223 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
237 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
249 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
[all …]
|
| D | matrix_functions_f16.h | 20 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
62 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
75 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
87 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
98 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
110 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
133 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
146 …* <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of siz…
|
| D | controller_functions.h | 20 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
74 The implementation is based on table lookup using 360 values together with linear interpolation.
120 * for Q15, Q31, and floating-point data types. The functions operate on a single sample
144 * the integral value determines the reaction based on the sum of recent errors,
145 …* and the derivative value determines the reaction based on the rate at which the error has been c…
424 …* The function operates on a single sample of data and each call to the function returns the proce…
481 There is saturation on the addition and subtraction, hence there is no risk of overflow.
524 …* The function operates on a single sample of data and each call to the function returns the proce…
578 There is saturation on the addition, hence there is no risk of overflow.
626 …* The function operates on a single sample of data and each call to the function returns the proce…
[all …]
|
| /cmsis-dsp-3.7.0-3.6.0/Documentation/Doxygen/src/ |
| D | mainpage.md | 3 …P software library, a suite of common compute processing functions for use on Cortex-M and Cortex-…
23 The library has generally separate functions for operating on 8-bit integers, 16-bit integers, 32-b…
29 …gorithm with NumPy and SciPy before writing the C version. Is is available on [PyPI.org](https://p…
35 …IS-DSP library. If you don't want to include everything, you can also rely on individual header fi…
43 The library is now tested on Fast Models building with cmake. Core M0, M4, M7, M33, M55, A32 are te…
53 �� ComputeLibrary | Small Neon kernels when building on Cortex-A
73 - Define macro ARM_MATH_MATRIX_CHECK for checking on the input and output sizes of matrices
76 - Define macro ARM_MATH_ROUNDING for rounding on support functions
82 …abled by default when Neon is available because performances are dependent on the compiler and tar…
91 …ome vector versions which may have worse performance than scalar depending on the core / compiler …
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/PatternGeneration/ |
| D | Example.py | 13 # For instance, we could test an addition on 3 samples and an addition
14 # on 9 samples to be sure that the vectorized code with tail is
32 # depending on the config object.
72 # depending on the type.
77 # Since the number of lanes depends on the type, testing vectorized code is requiring the use of
|
| /cmsis-dsp-3.7.0-3.6.0/Source/TransformFunctions/ |
| D | arm_mfcc_init_f16.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
68 and on a given number of FFT bins (the filter length).
198 and on a given number of FFT bins (the filter length).
227 and on a given number of FFT bins (the filter length).
256 and on a given number of FFT bins (the filter length).
285 and on a given number of FFT bins (the filter length).
314 and on a given number of FFT bins (the filter length).
343 and on a given number of FFT bins (the filter length).
372 and on a given number of FFT bins (the filter length).
401 and on a given number of FFT bins (the filter length).
|
| D | arm_mfcc_init_f32.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
68 and on a given number of FFT bins (the filter length).
198 and on a given number of FFT bins (the filter length).
227 and on a given number of FFT bins (the filter length).
256 and on a given number of FFT bins (the filter length).
285 and on a given number of FFT bins (the filter length).
314 and on a given number of FFT bins (the filter length).
343 and on a given number of FFT bins (the filter length).
372 and on a given number of FFT bins (the filter length).
401 and on a given number of FFT bins (the filter length).
|
| D | arm_mfcc_init_q15.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
67 and on a given number of FFT bins (the filter length).
197 and on a given number of FFT bins (the filter length).
226 and on a given number of FFT bins (the filter length).
255 and on a given number of FFT bins (the filter length).
284 and on a given number of FFT bins (the filter length).
313 and on a given number of FFT bins (the filter length).
342 and on a given number of FFT bins (the filter length).
371 and on a given number of FFT bins (the filter length).
400 and on a given number of FFT bins (the filter length).
|
| D | arm_mfcc_init_q31.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
68 and on a given number of FFT bins (the filter length).
199 and on a given number of FFT bins (the filter length).
228 and on a given number of FFT bins (the filter length).
257 and on a given number of FFT bins (the filter length).
286 and on a given number of FFT bins (the filter length).
315 and on a given number of FFT bins (the filter length).
344 and on a given number of FFT bins (the filter length).
373 and on a given number of FFT bins (the filter length).
402 and on a given number of FFT bins (the filter length).
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/cmsis_build/RTE/Device/ARMCM55/ |
| D | system_ARMCM55.c | 20 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
80 /* 0b00 | ON, PDEPU is not in low-power state */ in SystemInit()
81 /* 0b01 | ON, but the clock is off */ in SystemInit()
85 /* Clear ELPSTATE, value is 0b11 on Cold reset */ in SystemInit()
88 /* Favor best FP/MVE performance by default, avoid EPU switch-ON delays */ in SystemInit()
89 /* PDEPU ON, Clock OFF */ in SystemInit()
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/cmsis_build/RTE/Device/SSE-300-MPS3/ |
| D | fvp_sse300_mps3_s.sct | 13 ; * distributed under the License is distributed on an "AS IS" BASIS,
33 * region so that you can rely on code+veneer size combined will not exceed
35 * area used to align this section on 32 bytes boundary (for SAU conf).
41 * This dummy region ensures that the next one will be aligned on a 32 bytes
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/cmsis_build/RTE/Device/SSE-310-MPS3/ |
| D | corstone310_mps3_s.sct | 13 ; * distributed under the License is distributed on an "AS IS" BASIS,
33 * region so that you can rely on code+veneer size combined will not exceed
35 * area used to align this section on 32 bytes boundary (for SAU conf).
41 * This dummy region ensures that the next one will be aligned on a 32 bytes
|
| /cmsis-dsp-3.7.0-3.6.0/Examples/cmsis_build/RTE/Device/SSE-300-MPS3/ |
| D | fvp_sse300_mps3_s.sct | 13 ; * distributed under the License is distributed on an "AS IS" BASIS,
33 * region so that you can rely on code+veneer size combined will not exceed
35 * area used to align this section on 32 bytes boundary (for SAU conf).
41 * This dummy region ensures that the next one will be aligned on a 32 bytes
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/Source/Tests/ |
| D | ExampleCategoryF32.cpp | 7 Tests to write and test criteria depend on the algorithm.
8 When SNR is meaningful, SNR threshold depends on the type.
39 /* Check there is no buffer overflow on the output */ in test_op_f32()
70 Different allocations depending on the test. in setUp()
|
| /cmsis-dsp-3.7.0-3.6.0/.github/workflows/ |
| D | gh-pages.yml | 4 on:
5 # Runs on pushes targeting the default branch
30 runs-on: ubuntu-latest
|
| /cmsis-dsp-3.7.0-3.6.0/Documentation/Doxygen/ |
| D | dsp.dxy.in | 199 # support long names like on DOS, Mac, or CD-ROM.
325 # Doxygen selects the parser to use depending on the extension of the files it
435 # instead of on a separate page (for HTML and Man pages) or section (for LaTeX
448 # to NO, structs, classes, and unions are shown on a separate page (for HTML and
479 # during processing. When set to 0 doxygen will based this on the number of
607 # references to files without having to specify the exact matching casing. On
609 # to NO, whereas on Linux or other Unix flavors it should typically be set to
816 # The QUIET tag can be used to turn on/off the messages that are generated to
823 # The WARNINGS tag can be used to turn on/off the warning messages that are
825 # this implies that the warnings are on.
[all …]
|
| /cmsis-dsp-3.7.0-3.6.0/Testing/TestScripts/ |
| D | CodeGen.py | 42 Generation depends on the mode (fpga or semihosting)
224 # For a group, first iterate on the children then on the
226 # dependent on the children definition (member varaiables)
257 # Recurse on the children to get the listOfSuite.
357 # It is done to simplify parsing on C side
427 # Iterate on the children
601 # Compute new offset based on pattern length only
617 # Depending on the word size, this hex must be writen to
668 # Compute new offset based on pattern length only
682 # Depending on the word size, this hex must be writen to
[all …]
|
| /cmsis-dsp-3.7.0-3.6.0/Source/FilteringFunctions/ |
| D | arm_biquad_cascade_df1_init_q15.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
56 … and so on. The <code>pCoeffs</code> array contains a total of <code>6*numStages</code> values.
57 …n <code>b1</code> and <code>b2</code> facilities use of 16-bit SIMD instructions on the Cortex-M4.
65 … The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.
|
| D | arm_lms_f32.c | 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
39 …LMS filters use a gradient descent method in which the filter coefficients are updated based on th…
41 …The CMSIS DSP Library contains LMS filter functions that operate on Q15, Q31, and floating-point d…
50 …The filter coefficient update mechanism is based on the difference between the FIR filter output a…
55 The functions operate on blocks of data and each call to the function processes
61 The functions operate on a block-by-block basis.
62 Internally, the filter coefficients <code>b[n]</code> are updated on a sample-by-sample basis.
78 … signal is computed, the filter coefficients <code>b[k]</code> are updated on a sample-by-sample b…
143 …The value of <code>postShift</code> is set by the user based on the expected gain through the syst…
|
