trueno 0.17.1

//! Reduction operations for Vector<f32>
//!
//! This module provides reduction operations that aggregate vector elements:
//! - Basic: `sum`, `dot`, `max`, `min`
//! - Index-finding: `argmax`, `argmin`
//! - Statistical: `mean`, `variance`, `stddev`, `covariance`, `correlation`
//! - Numerically stable: `sum_kahan`, `sum_of_squares`

mod stats;
#[cfg(test)]
mod tests;

#[cfg(target_arch = "x86_64")]
use crate::backends::avx2::Avx2Backend;
#[cfg(target_arch = "x86_64")]
use crate::backends::avx512::Avx512Backend;
#[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
use crate::backends::neon::NeonBackend;
use crate::backends::scalar::ScalarBackend;
#[cfg(target_arch = "x86_64")]
use crate::backends::sse2::Sse2Backend;
#[cfg(target_arch = "wasm32")]
use crate::backends::wasm::WasmBackend;
use crate::backends::VectorBackend;
use crate::vector::Vector;
use crate::{dispatch_reduction, Backend, Result, TruenoError};

impl Vector<f32> {
    /// Dot product
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let a = Vector::from_slice(&[1.0, 2.0, 3.0]);
    /// let b = Vector::from_slice(&[4.0, 5.0, 6.0]);
    /// let result = a.dot(&b)?;
    ///
    /// assert_eq!(result, 32.0); // 1*4 + 2*5 + 3*6 = 4 + 10 + 18 = 32
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    pub fn dot(&self, other: &Self) -> Result<f32> {
        if self.len() != other.len() {
            return Err(TruenoError::SizeMismatch { expected: self.len(), actual: other.len() });
        }

        // SAFETY: Unsafe block delegates to backend implementation which maintains safety invariants
        let result = unsafe {
            match self.backend {
                Backend::Scalar => ScalarBackend::dot(&self.data, &other.data),
                #[cfg(target_arch = "x86_64")]
                Backend::SSE2 | Backend::AVX => Sse2Backend::dot(&self.data, &other.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX2 => Avx2Backend::dot(&self.data, &other.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX512 => Avx512Backend::dot(&self.data, &other.data),
                #[cfg(not(target_arch = "x86_64"))]
                Backend::SSE2 | Backend::AVX | Backend::AVX2 | Backend::AVX512 => {
                    ScalarBackend::dot(&self.data, &other.data)
                }
                #[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
                Backend::NEON => NeonBackend::dot(&self.data, &other.data),
                #[cfg(not(any(target_arch = "aarch64", target_arch = "arm")))]
                Backend::NEON => ScalarBackend::dot(&self.data, &other.data),
                #[cfg(target_arch = "wasm32")]
                Backend::WasmSIMD => WasmBackend::dot(&self.data, &other.data),
                #[cfg(not(target_arch = "wasm32"))]
                Backend::WasmSIMD => ScalarBackend::dot(&self.data, &other.data),
                Backend::GPU | Backend::Auto => ScalarBackend::dot(&self.data, &other.data),
            }
        };

        Ok(result)
    }

    /// Sum all elements
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let v = Vector::from_slice(&[1.0, 2.0, 3.0, 4.0]);
    /// assert_eq!(v.sum()?, 10.0);
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    pub fn sum(&self) -> Result<f32> {
        Ok(dispatch_reduction!(self.backend, sum, &self.data))
    }

    /// Find maximum element
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let v = Vector::from_slice(&[1.0, 5.0, 3.0, 2.0]);
    /// assert_eq!(v.max()?, 5.0);
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    ///
    /// # Errors
    ///
    /// Returns [`TruenoError::InvalidInput`] if vector is empty.
    pub fn max(&self) -> Result<f32> {
        if self.data.is_empty() {
            return Err(TruenoError::InvalidInput("Empty vector".to_string()));
        }

        // SAFETY: Unsafe block delegates to backend implementation which maintains safety invariants
        let result = unsafe {
            match self.backend {
                Backend::Scalar => ScalarBackend::max(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::SSE2 | Backend::AVX => Sse2Backend::max(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX2 | Backend::AVX512 => Avx2Backend::max(&self.data),
                #[cfg(not(target_arch = "x86_64"))]
                Backend::SSE2 | Backend::AVX | Backend::AVX2 | Backend::AVX512 => {
                    ScalarBackend::max(&self.data)
                }
                #[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
                Backend::NEON => NeonBackend::max(&self.data),
                #[cfg(not(any(target_arch = "aarch64", target_arch = "arm")))]
                Backend::NEON => ScalarBackend::max(&self.data),
                #[cfg(target_arch = "wasm32")]
                Backend::WasmSIMD => WasmBackend::max(&self.data),
                #[cfg(not(target_arch = "wasm32"))]
                Backend::WasmSIMD => ScalarBackend::max(&self.data),
                Backend::GPU | Backend::Auto => ScalarBackend::max(&self.data),
            }
        };

        Ok(result)
    }

    /// Find minimum value in the vector
    ///
    /// Returns the smallest element in the vector using SIMD optimization.
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let v = Vector::from_slice(&[1.0, 5.0, 3.0, 2.0]);
    /// assert_eq!(v.min()?, 1.0);
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    ///
    /// # Errors
    ///
    /// Returns [`TruenoError::InvalidInput`] if vector is empty.
    pub fn min(&self) -> Result<f32> {
        if self.data.is_empty() {
            return Err(TruenoError::InvalidInput("Empty vector".to_string()));
        }

        // SAFETY: Unsafe block delegates to backend implementation which maintains safety invariants
        let result = unsafe {
            match self.backend {
                Backend::Scalar => ScalarBackend::min(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::SSE2 | Backend::AVX => Sse2Backend::min(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX2 | Backend::AVX512 => Avx2Backend::min(&self.data),
                #[cfg(not(target_arch = "x86_64"))]
                Backend::SSE2 | Backend::AVX | Backend::AVX2 | Backend::AVX512 => {
                    ScalarBackend::min(&self.data)
                }
                #[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
                Backend::NEON => NeonBackend::min(&self.data),
                #[cfg(not(any(target_arch = "aarch64", target_arch = "arm")))]
                Backend::NEON => ScalarBackend::min(&self.data),
                #[cfg(target_arch = "wasm32")]
                Backend::WasmSIMD => WasmBackend::min(&self.data),
                #[cfg(not(target_arch = "wasm32"))]
                Backend::WasmSIMD => ScalarBackend::min(&self.data),
                Backend::GPU | Backend::Auto => ScalarBackend::min(&self.data),
            }
        };

        Ok(result)
    }

    /// Find index of maximum value in the vector
    ///
    /// Returns the index of the first occurrence of the maximum value using SIMD optimization.
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let v = Vector::from_slice(&[1.0, 5.0, 3.0, 2.0]);
    /// assert_eq!(v.argmax()?, 1); // max value 5.0 is at index 1
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    ///
    /// # Errors
    ///
    /// Returns [`TruenoError::InvalidInput`] if vector is empty.
    pub fn argmax(&self) -> Result<usize> {
        if self.data.is_empty() {
            return Err(TruenoError::InvalidInput("Empty vector".to_string()));
        }

        // SAFETY: Unsafe block delegates to backend implementation which maintains safety invariants
        let result = unsafe {
            match self.backend {
                Backend::Scalar => ScalarBackend::argmax(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::SSE2 | Backend::AVX => Sse2Backend::argmax(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX2 | Backend::AVX512 => Avx2Backend::argmax(&self.data),
                #[cfg(not(target_arch = "x86_64"))]
                Backend::SSE2 | Backend::AVX | Backend::AVX2 | Backend::AVX512 => {
                    ScalarBackend::argmax(&self.data)
                }
                #[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
                Backend::NEON => NeonBackend::argmax(&self.data),
                #[cfg(not(any(target_arch = "aarch64", target_arch = "arm")))]
                Backend::NEON => ScalarBackend::argmax(&self.data),
                #[cfg(target_arch = "wasm32")]
                Backend::WasmSIMD => WasmBackend::argmax(&self.data),
                #[cfg(not(target_arch = "wasm32"))]
                Backend::WasmSIMD => ScalarBackend::argmax(&self.data),
                Backend::GPU | Backend::Auto => ScalarBackend::argmax(&self.data),
            }
        };

        Ok(result)
    }

    /// Find index of minimum value in the vector
    ///
    /// Returns the index of the first occurrence of the minimum value using SIMD optimization.
    ///
    /// # Examples
    ///
    /// ```
    /// use trueno::Vector;
    ///
    /// let v = Vector::from_slice(&[1.0, 5.0, 3.0, 2.0]);
    /// assert_eq!(v.argmin()?, 0); // min value 1.0 is at index 0
    /// # Ok::<(), trueno::TruenoError>(())
    /// ```
    ///
    /// # Errors
    ///
    /// Returns [`TruenoError::InvalidInput`] if vector is empty.
    pub fn argmin(&self) -> Result<usize> {
        if self.data.is_empty() {
            return Err(TruenoError::InvalidInput("Empty vector".to_string()));
        }

        // SAFETY: Unsafe block delegates to backend implementation which maintains safety invariants
        let result = unsafe {
            match self.backend {
                Backend::Scalar => ScalarBackend::argmin(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::SSE2 | Backend::AVX => Sse2Backend::argmin(&self.data),
                #[cfg(target_arch = "x86_64")]
                Backend::AVX2 | Backend::AVX512 => Avx2Backend::argmin(&self.data),
                #[cfg(not(target_arch = "x86_64"))]
                Backend::SSE2 | Backend::AVX | Backend::AVX2 | Backend::AVX512 => {
                    ScalarBackend::argmin(&self.data)
                }
                #[cfg(any(target_arch = "aarch64", target_arch = "arm"))]
                Backend::NEON => NeonBackend::argmin(&self.data),
                #[cfg(not(any(target_arch = "aarch64", target_arch = "arm")))]
                Backend::NEON => ScalarBackend::argmin(&self.data),
                #[cfg(target_arch = "wasm32")]
                Backend::WasmSIMD => WasmBackend::argmin(&self.data),
                #[cfg(not(target_arch = "wasm32"))]
                Backend::WasmSIMD => ScalarBackend::argmin(&self.data),
                Backend::GPU | Backend::Auto => ScalarBackend::argmin(&self.data),
            }
        };

        Ok(result)
    }
}