No description, website, or topics provided.
C++ CMake
Permalink
Failed to load latest commit information.
benchmarks
detail
testsuite
vec
.gitignore
CMakeLists.txt
COPYING
README
simd_binary_arithmetic.hpp
simd_horizontal_functions.hpp
simd_math.hpp
simd_memory.hpp
simd_mix.hpp
simd_pan.hpp
simd_peakmeter.hpp
simd_ternary_arithmetic.hpp
simd_unary_arithmetic.hpp
simd_unit_conversion.hpp
simd_unroll_constraints.hpp
simd_utils.hpp
softclip.hpp
vec.hpp

README

nova simd

nova simd provides a framework of simdfied vector functions, designed
mainly for computer music applications.
it currently supports the following instruction sets:
- sse/sse2 family
- ppc/altivec
- avx
- arm/neon


vec class:
the simd functionality is built around a templated vec class. it usually maps
to a simd vector. the vec class can be used to compose more specific algorithms,
hiding different implementations under a common API.

template <typename FloatType>
class vec
{
public:
    typedef FloatType float_type;

    static const int size; // number of samples per vector
    static const int objects_per_cacheline; // typical number of objects per cacheline

    /* constructors */
    vec(void);
    vec(double f);
    vec(float f);
    vec(vec const & rhs);

    /* element access */
    FloatType get (int index) const;

    /* set vector */
    void set (int index, FloatType arg);
    void set_vec (FloatType value);
    FloatType set_slope(FloatType start, FloatType slope);
    FloatType set_exp(FloatType start, FloatType curve);

    /* load and store */
    void load(const WrappedType * src);
    void load_first(const WrappedType * src);
    void load_aligned(const WrappedType * data);

    void store(WrappedType * dest) const;
    void store_aligned(WrappedType * dest) const;
    void store_aligned_stream(WrappedType * dest) const;

    void clear(void);

    vec_base operator+(vec_base const & rhs) const
    vec_base operator-(vec_base const & rhs) const
    vec_base operator*(vec_base const & rhs) const
    vec_base operator/(vec_base const & rhs) const

    vec_base & operator+=(vec_base const & rhs)
    vec_base & operator-=(vec_base const & rhs)
    vec_base & operator*=(vec_base const & rhs)
    vec_base & operator/=(vec_base const & rhs)

    vec_base operator<(vec_base const & rhs) const
    vec_base operator<=(vec_base const & rhs) const
    vec_base operator==(vec_base const & rhs) const
    vec_base operator!=(vec_base const & rhs) const
    vec_base operator>(vec_base const & rhs) const
    vec_base operator>=(vec_base const & rhs) const

    friend vec madd(vec const & arg1, vec const & arg2, vec const & arg3);

    friend vec sin(vec const & arg);
    friend vec cos(vec const & arg);
    friend vec tan(vec const & arg);
    friend vec asin(vec const & arg);
    friend vec acos(vec const & arg);
    friend vec atan(vec const & arg);

    friend vec tanh(vec const & arg);

    friend vec log(vec const & arg);
    friend vec log2(vec const & arg);
    friend vec log10(vec const & arg);
    friend vec exp(vec const & arg);
    friend vec pow(vec const & lhs, vec const & rhs);

    friend vec abs(vec const & arg);
    friend vec sign(vec const & arg);
    friend vec square(vec const & arg);
    friend vec cube(vec const & arg);

    friend vec signed_sqrt(vec const & arg);
    friend vec signed_pow(vec const & lhs, vec const & rhs);

    friend vec min_(vec const & lhs, vec const & rhs);
    friend vec max_(vec const & lhs, vec const & rhs);

    friend vec round(vec const & arg);
    friend vec ceil(vec const & arg);
    friend vec floor(vec const & arg);
    friend vec frac(vec const & arg);
    friend vec trunc(vec const & arg);
};


vector functions:

this vec class has been used as building block for a number of vector functions,
which provides a traditional c++-style interface to perform a specific operation
on buffers.
(for details consult the simd_*.hpp files)

for an unary operation `foo', the following functions must be:

/* arbitrary number of iterations */
template <typename float_type>
inline void foo_vec(float_type * out, const float_type * in, unsigned int n);

/* number of iterations must be a multiple of
 * unroll_constraints<float_type>::samples_per_loop
 */
template <typename float_type>
inline void foo_vec_simd(float_type * out, const float_type * in, unsigned int n);

/* number of iterations must be a multiple of
 * unroll_constraints<float_type>::samples_per_loop
 */
template <int n,
          typename FloatType
         >
inline void foo_vec_simd(FloatType * out, const FloatType * in);


for binary and ternary operations, instances are provided for mixed
vector and scalar arguments. using the suffix _simd provides versions for compile-time
and run-time unrolled code:

template <typename float_type,
          typename Arg1,
          typename Arg2
         >
inline void foo_vec(float_type * out, Arg1 arg1, Arg2 arg2, unsigned int n);

template <typename float_type,
          typename Arg1,
          typename Arg2
         >
inline void foo_vec_simd(float_type * out, Arg1 arg1, Arg2 arg2, unsigned int n);

template <unsigned int n,
          typename float_type,
          typename Arg1,
          typename Arg2
         >
inline void foo_vec_simd(float_type * out, Arg1 arg1, Arg2 arg2);


for scalar arguments, an extension is provided to support ramping by
adding a slope to the scalar after each iteration. for binary functions,
c++ function overloading is used. compile-time unrolled versions of these
functions are also provided.


argument wrapper:
to support different kinds of arguments with a generic interface, nova-simd provides
argument wrappers. these can be generated with the following functions:

/* wrap a scalar argument */
template <typename FloatType>
/unspecified/ nova::wrap_arguments(FloatType f);

/* wrap a vector argument */
template <typename FloatType>
/unspecified/ nova::wrap_arguments(const FloatType * f);

/* wrap a ramp argument */
template <typename FloatType>
/unspecified/ nova::wrap_arguments(FloatType base, FloatType slope);


building and testing:

nova simd is a header-only library, so it cannot be compiled as
standalone libray. however some benchmark and test programs are
provided, using a cmake build system.