566550e15d
CMSIS-DSP: doxygen corrections
6 years ago
3359d706cf
CMSIS-DSP: Corrected build issue with Python wrapper.
...
Corrected bug in arm_mat_vec_mult_q15.
6 years ago
a20e215bfc
CMSIS-DSP: Added new matrix functions and their MVE implementation
...
arm_mat_cmplx_trans_f32.c
arm_mat_cmplx_trans_q15.c
arm_mat_cmplx_trans_q31.c
6 years ago
8268b079d5
CMSIS-DSP: Added new matrix functions and MVE version
...
arm_mat_mult_q7.c
arm_mat_trans_q7.c
arm_mat_vec_mult_f32.c
arm_mat_vec_mult_q15.c
arm_mat_vec_mult_q31.c
arm_mat_vec_mult_q7.c
6 years ago
be40746c5e
CMSIS-DSP: Improvement to test framework
...
Added support for A32.
Still some issues with cycle model.
6 years ago
6ee45c22da
CMSIS-DSP: Improvements to test framework.
6 years ago
f90143005a
Fix - arm_math.h: Use the float suffix in arm_clarke_f32
...
The float suffix replaces the need for a float cast in arm_clarke_f32.
This change is necessary to avoid large amount of warnings by arm_math.h when the -Wunsuffixed-float-constants flag is used. And using this compile flag is very reasonable on a processor with 32bit FPU.
6 years ago
a159791720
CMSIS-DSP: Improved test framework
...
Added gcc support to IPSS in test framework.
Improved f16 handling for when compiling M55 with gcc.
6 years ago
c33adc9485
CMSIS-DSP: Improvements to the float16 support for building.
6 years ago
1464ad53f7
CMSIS-DSP: Corrected a bug.
...
arm_mve.h was not included in all cases since the introduction of
the automatic MVE detection and the autovectorization test.
6 years ago
c3efab80e9
CMSIS-DSP: Improved automatic detection of MVE mode for working with autovectorization.
6 years ago
68be1c9043
CMSIS-DSP: Added automatic detection of MVE support.
6 years ago
c54fbf008b
CMSIS-DSP: Some improvement to Doxygen documentation.
6 years ago
97e7ce8e27
CMSIS-DSP: Change to f16 code to be able to build with AC5 compiler.
6 years ago
86a272902a
CMSIS-DSP: Add preliminary cfft 16 MVE code.
6 years ago
b543f5c61c
CMSIS-DSP: Added f16 support to test framework.
...
Added preliminary f16 versions of some functions
6 years ago
12af686c77
CMSIS-DSP: Correction of issue 891
...
Use of arm_cfft_init_f64 in the tests for coherency with other
cfft tests.
6 years ago
9c7329cd52
CMSIS-DSP: Updated examples.
6 years ago
e4a2262af3
CMSIS-DSP: Added tutorial link to Doxygen documentation.
...
Corrected potential build issue with packs.
6 years ago
1d51b2ba00
CMSIS-DSP: Modified spline f32 to compute coeffs at init time
...
- Moved coefficients computation to init function
- Improved documentation
6 years ago
64d43685fb
CMSIS-DSP: Added MVE support for logical operators (modified prototypes)
6 years ago
0e438b58f6
CMSIS-DSP: Fix to MVE code to allow compilation with AC6 6.14
6 years ago
fb1f6b04a7
CMSIS-DSP: Added scalar float64 entropy and kullback leibler
6 years ago
dcda169de6
CMSIS-DSP: Cleaning for RFFT
...
Updated Doxygen comments.
Moved cfft_init_f64 from PythonWrapper to normal repository.
6 years ago
f2facaa0a2
CMSIS-DSP: Correction for issue 720
6 years ago
6c98bfbc02
CMSIS-DSP: Corrected preconditions on arm_bilinear_interp functions.
...
rows and cols were switched and the bounds were not correct.
6 years ago
05fcad5977
CMSIS-DSP:Added tests for arm_bilinear_interp (f32,q31,q15 and q7).
...
Corrected bug in arm_bilinear_interp_f32. Now indexes are starting at 0
like with other bilinear versions.
6 years ago
b6d9bdd4ef
CMSIS-DSP: Added MVE code for arm_cfft_q15
6 years ago
f5c31e6af4
CMSIS-DSP: Added MVE code for cfft q31
...
Added tests patterns for RFFT Q31 and Q15.
6 years ago
3060b1da8f
CMSIS-DSP: MVE version of arm_cfft_f32.
6 years ago
169877344c
Corrected spline interpolation and merge sort
6 years ago
76153d838d
CMSIS-DSP: Corrected issues 783-786
...
Adding const to some API arguments
Updating array dimensions in some tests
6 years ago
76ab9556db
CMSIS-DSP: Added new tests
...
Added tests for arm_math.h functions read_q15x2 and similar ones ...
Improved Doxygen.
Improved functions read_q15x2 and similar ones ...
6 years ago
4e4b9ca8bb
CMSIS-DSP: Corrected build issues with AC5 and gcc. Improved Doxygen comments.
6 years ago
33a1f2fe08
CMSIS-DSP: Corrected Doxygen issues
6 years ago
bbafcb8960
Added logical operators + sorting + spline
...
- Added NEON bitwise AND, NOT, OR, XOR (q7, q15, q31)
- Added Sorting algorithms f32 (NEON bitonic sort)
- Added cubic spline interpolation function
- Added test patterns for all
6 years ago
ea8a5b2800
CMSIS-DSP: Added new tests for Biquads.
...
Added MVE code for Biquads.
6 years ago
ee57bbde54
CMSIS-DSP: Initial F64 CFFT/RFFT implementation
6 years ago
d9ca41ce8d
[MVE] clean-up of loading constant offset vectors
...
We don't need to load them with an mve intrinsic, but instead can
just pass them in where needed.
6 years ago
abdc8aa89f
CMSIS-DSP:Corrected bug in arm_div_q63_to_q31
6 years ago
767ed7b920
CMSIS-DSP: Added MVE code for FIR.
...
Improved FIR test patterns.
6 years ago
ecf9525765
CMSIS-DSP: Added test patterns for fir
...
Added MVE version of arm_fir_f32
Improved test framework to display more information about errors.
6 years ago
b1af1d4766
CMSIS-DSP: Generated test patterns for convolutions and correlations.
...
Added MVE code for convolutions and correlations.
6 years ago
98f44f4491
CMSIS-DSP: Added MVE code for Matrix functions.
...
Added test patterns for Matrix functions.
Regenerated all tests patterns to improve testing for tails.
Corrected issues in pattern generation scripts.
6 years ago
c19c41d261
CMSIS-DSP: Added a ARM_MATH_FLOAT16 compilation option.
...
It is automatically enabled when MVE support is enabled.
6 years ago
2e12da1043
CMSIS-DSP: Corrected compilation warnings
...
More compilation tests done with AC5
6 years ago
dc0be10d4e
CMSIS-DSP: Corrected compilation warnings
...
More compilation tests done with AC5
6 years ago
8526741f9e
CMSIS-DSP: Added Helium versions of Fast Math, Support, SVM, Naive Bayes, Distance and additional Statistics functions.
...
Added a new header of vectorial inline functions for Neon and Helium.
This header is used in the implementation of some functions.
Corrected used of float (float functions rather than double ones).
6 years ago
785edd1039
CMSIS-NN: Implement bit-accurate S8 Softmax (non-DSP)
6 years ago
5682780f4d
CMSIS-DSP: Moved definition of Q31,Q15 and Q7 bounds to arm_math.h
6 years ago
6945b74f8a
CMSIS-DSP: Added test patterns for Statistics functions.
...
Added MVE code for statistics functions.
Improvement to test framework.
6 years ago
dcf079cb1d
CMSIS-DSP: Added Helium support to Complex Math Functions.
...
Added new test patterns for complex math functions.
Added new tests to test framework.
Improved error handling of test framework.
6 years ago
56a540336a
CMSIS-DSP: Added Helium support for functions in BasicMaths.
...
Added test patterns for functions in BasicMaths.
Corrected github issue 622 (clarified comment for lms_norm_f32).
Added support for q63_t to the test framework.
6 years ago
2d3a2166d6
CMSIS-DSP: Added more control for MVE compilation flags.
...
Now there are ARM_MATH_MVEF and ARM_MATH_MVEI.
6 years ago
84c7261036
CMSIS-DSP: Simplification to cmake to build without test framework.
6 years ago
ee13dcb33a
CMSIS-DSP : Testing framework improvements
...
Added new tests for cfft.
Improved error handling when not enough memory allocated in testmain.cpp
Corrected arm_math.h (replaced inline by preprocessor definition).
Added example debug script to read pattern and output of tests using
scipy.
6 years ago
5019309f9c
Line ending normalization
6 years ago
4a0aa2ad26
CMSIS-DSP: Added support for Helium.
...
Only arm_dot_prod_f32 is currently providing an Helium implementation.
6 years ago
a4d73ce24e
update arm_math.h typo fix
6 years ago
cd2d0a7cbc
enable building python files for gnulinux
6 years ago
f9ca44bc50
CMSIS-DSP: Cleaning of Doxygen comments for new functions.
...
New distance patterns.
6 years ago
7a8a02f976
CMSIS-DSP: Corrected Doxygen warnings.
6 years ago
7a07cecef1
CMSIS-DSP: Added distance functions for clustering algorithms
6 years ago
aa43cfb6dd
CMSIS-DSP: Added some support functions.
...
entropy, Kullback-Leibler, LogSumExp, Dot product using LogSumExp
weighted sum, barycenter.
6 years ago
94b63664f2
CMSIS-DSP: Added Naive Gaussian Bayesian Estimator
6 years ago
302ada6633
CMSIS-DSP: Added SVM Functions and tests
...
Added more tests for BasicMathFunctions
Added script to postprocess result of benchmarks.
6 years ago
a5b854594b
CMSIS-DSP: Prevent off-by-one access past end of y-data buffer in f32 linear interpolation
7 years ago
8a4c63e4d8
CMSIS-DSP: New testing framework
...
(For our internal use. In short term, we won't give support about it).
CMSIS-DSP: Update to cmake build for the testing framework
CMSIS-NN:Implementation of arm_fully_connected_s8
Use API and quantization compatible with TF Lite.
7 years ago
bf1f324a6d
CMSIS-DSP: DSP_Lib_TestSuite can be built with cmake.
...
DSP_Lib_TestSuite can be built with cmake and run on FVP.
Some issues with CMSIS-DSP cmake where discovered and corrected.
Comments added to arm_biqaud_cascade_df2T+f32 since the Neon version
must be initialized differently (and thus the corresponding test
in DSP_Lib_TestSuite will have to be updated to pass with Neon version).
7 years ago
3bf2e2eda6
CMSIS-DSP: Enable build with MSVC compiler.
...
The goal of this commit is to allow the build of CMSIS-DSP on Windows to
enable the use of the library from Python or Matlab.
The Python wrapper has also been simplified and is now using the
CMSIS-DSP directly without requiring specific include files or source files.
7 years ago
080b994dd7
CMSIS-DSP: Customization of FFT tables.
...
Compilation symbols have been introduced to allow to include only the
FFT tables which are useful in a given application.
The README.md in DSP is giving more details.
7 years ago
de626e2391
CMSIS DSP : Added a cmake build system
...
It is not replacing the current MDK and ArmDS projects.
It is a complementary way to build CMSIS-DSP.
Current version is supporting ARM AC6 compiler from ArmDS.
The result of the build can be run on a FVP for instance.
It could be extended to use different toolchain and build for different
targets.
The README.md in DSP folder is giving all the details.
7 years ago
5792f80cf1
New NEON float32 algorithms for Cortex A5 (TransformFunctions excluded) with armDS project
7 years ago
a8cf6e9bb1
Updated file versions, dates and copyright headers.
...
Change-Id: I2fe43d2ad56cff4347424929fd1f82eccd1cc770
7 years ago
84aa3d6da5
Added SIMD macros to arm_math.h again. CMSIS NN uses this macros.
7 years ago
5648cfd4af
DSP_Lib changes:
...
- new version V1.5.5
- reworked DSP library source files
added macro ARM_MATH_LOOPUNROLL
removed macro UNALIGNED_SUPPORT_DISABLE
relpaced arm_bitreversal2.S with C version
added const-correctness
replaced SIMD pointer construct with memcpy solution
- reworked DSP library documentation
- moved DSP libraries to folder ./DSP/Lib
- ARM DSP Libraries are built with ARMCLANG
- Added DSP Libraries Source variant
7 years ago
f20c424e92
Revert "Const-qualify all read-only pointers in CMSIS-DSP ( #349 )"
7 years ago
23765aeff4
Fix const warnings
7 years ago
b54e1f9bf1
Converting C sources to use `const` where appropriate using regular expressions. Fix typos
7 years ago
35e58d27d8
`const`-qualify all float32_t pSrc pointers in arm_math.h
7 years ago
ec2013d0c7
`const`-qualify all twiddle, bitrev and cosfactor table pointers in arm_math.h
7 years ago
e70bcb70d5
`const`-qualify all pSrc pointers in arm_math.h
7 years ago
ddee94e8db
DSP_Lib:
...
- updated arm_math.h
- reduced ARM_MATH_CMx macros
7 years ago
0f5b33ee1b
Split rfft_fast_init_f32 into separate initializer functions.
...
The rationale here is that if the caller knows the size FFT they require
at compile time, only the look-up tables required for that size are
placed in the data segment (ROM). This saves between ~40k to ~80k of
ROM when only using a single FFT size.
7 years ago
06eff37277
removes unnecessary and non-portable type casts
7 years ago
61fc77406b
Updating company brand
...
- Converted ARM to Arm in all documentative text in source, header, and doxygen.
- Converted ARM to Arm in descriptive texts in pack description file.
All identifier strings, like vendor, are kept unchanged due to compatibility reasons.
- Updated copyright year and file date.
8 years ago
3b50ea13ea
Release preparation: Aligned version information and updated change histories.
8 years ago
8913e1bed5
Fixed typo
8 years ago
bd2ae0a021
DSP: Clean up arm_math.h
...
- Removed CM0 implementation for __SSAT after moving this to Core(M).
8 years ago
2208df0e14
Global MISRA-C Rule 10.6 fix up: Unsigned constant values with U suffix, uppercase instead of lowercase. (Issue #227 )
8 years ago
b665acba90
DSP: Fix issue #188 gnu compiler specific diagnostics in arm_math.h
9 years ago
de2ce55a61
Updated CMSIS_DSP. Added ARMv8M support, changed copyrigth note.
9 years ago
adbc210886
updated DSP Lib to V1.5.0.
9 years ago
76d02e9f1a
Deleted obsolete macro TABLE_SIZE from arm_math.h.
9 years ago
bc3b6d0e2f
DSP ARMv8M preparation.
9 years ago
1c78832899
Updated DSP_Lib changelog and libraries.
9 years ago
5d3e72e111
Merge pull request #81 from dpalframan/develop
...
performance optimizations for arm_mat_mult_fast_q15 and arm_mat_mult_fast_q31
9 years ago
d33d90dd52
Minor typo fix
...
Changed CortexM0+ to Cortex-M0+
9 years ago
365d910888
performance optimizations for arm_mat_mult_fast_q15 and arm_mat_mult_fast_q31
9 years ago
7a4fea9150
Renamed folder DSP_Lib to DSP to be consistent with documentation.
10 years ago
Christophe Favergeon
Martin
ClaudioMartino
FabKlein
Sjoerd Meijer
Giorgio Arena
Chris Knorowski
Ryan Mullen
Jonatan Antoni
GuentherMartin
Torfinn Berset
Dave Flogeras
johan-uden
Christopher Seidl
David Palframan