Module kernels 

Built-in SoftGPU Functional IR kernels (Rust builders + JSON twins).

Functions

kernarg_one_ptr

kernarg_two_ptrs

Pack two u64 pointers into a 16-byte kernarg.

tiny_add

b[i] = a[i] + 1 for i = global_id_x. Pointers in kernarg at 0 and 8.

tiny_copy

b[i] = a[i] copy.

tiny_index

out[i] = global_id_x (index write).