Skip to main content

gpu_include_parse

vyre_libs::parsing::c::preprocess::gpu_include_parse

Function gpu_include_parse 

Source 
pub fn gpu_include_parse(num_tokens: u32, source_len: u32) -> Program
Expand description

Build the 17b.7 #include row parser Program.

Hybrid runtime/static-bound: kernel BODY uses Expr::buf_len() for every per-thread bound (so program AST is constant across files), num_tokens is kept ONLY for output buffer sizing (CUDA backend requires static byte length for readback), source_len is unused.