#version 450
// Elementwise f32 multiply: out[i] = a[i] * b[i].
layout(local_size_x = 64) in;
layout(set = 0, binding = 0) readonly buffer A { float a[]; };
layout(set = 0, binding = 1) readonly buffer B { float b[]; };
layout(set = 0, binding = 2) writeonly buffer Out { float o[]; };
layout(push_constant) uniform Pc { uint n; };
void main() {
uint i = gl_GlobalInvocationID.x;
if (i < n) {
o[i] = a[i] * b[i];
}
}