primal-barracuda 0.4.0

barraCuda — BARrier-free Rust Abstracted Cross-platform Unified Dimensional Algebra. Vendor-agnostic GPU compute via WGSL.
Documentation
// SPDX-License-Identifier: AGPL-3.0-or-later
// Cumprod - Cumulative product along a dimension
//
// Deep Debt Principles:
// - Pure WGSL implementation (universal compute)
// - Zero unsafe code (memory safe)
// - Hardware-agnostic (works on any GPU/CPU via WebGPU)
// - Self-contained logic (no external dependencies)

struct Params {
    size: u32,
    dim_size: u32,
    outer_size: u32,
    inner_size: u32,
}

@group(0) @binding(0) var<storage, read> input: array<f32>;
@group(0) @binding(1) var<storage, read_write> output: array<f32>;
@group(0) @binding(2) var<uniform> params: Params;

@compute @workgroup_size(256)
fn main(@builtin(global_invocation_id) global_id: vec3<u32>) {
    let idx = global_id.x;
    
    if (idx >= params.outer_size * params.inner_size) {
        return;
    }
    
    let outer = idx / params.inner_size;
    let inner = idx % params.inner_size;
    
    var product = 1.0;
    for (var i = 0u; i < params.dim_size; i++) {
        let input_idx = outer * params.dim_size * params.inner_size + i * params.inner_size + inner;
        product *= input[input_idx];
        output[input_idx] = product;
    }
}