Crate gpu 

Re-exports

pub use prelude::*;

Modules

arch

cg

chunk

chunk_scope

iter

prelude

sync

Synchronization and atomic operations for GPU programming.

vector

Macros

asm

debug_once

println

println_once

reshape_map

Maps a multi-dimensional local index and thread layout into a reshaped global index. The idea is that the user need to specify the dimensions of logical index (local + thread ids), and the target tensor dimensions, then we map the logical index into the corresponding target multi-dimension tensor. We have:

shuffle

define a macro to use shuffle with a specific mode xor, up, down.

Functions

add_mlir_string_attr

Add a string attribute to the MLIR module.