dnrops
/
burn
mirror of https://github.com/tracel-ai/burn.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

benchmarked, it's slower :(

This commit is contained in:
louisfd 2024-06-27 16:55:04 -04:00
parent 3b473597df
commit 71ea9fb415
3 changed files with 12 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
backend-comparison/benches/matmul.rs
View File

@ -52,10 +52,10 @@ fn bench<B: Backend>(
token: Option<&str>,
) {
const D: usize = 3;
let batch_size = 4048;
let m = 320;
let k = 4;
let n = 324;
let batch_size = 1000;
let m = 256;
let k = 512;
let n = 256;
let shape_lhs = [batch_size, m, k].into();
let shape_rhs = [batch_size, k, n].into();

2
crates/burn-jit/src/kernel/matmul/base.rs
View File

@ -108,7 +108,7 @@ pub enum MatmulStrategy {
#[cfg(feature = "autotune")]
impl Default for MatmulStrategy {
fn default() -> Self {
MatmulStrategy::Tiling2dCube(Tiling2dConfig::default())
MatmulStrategy::Autotune
}
}

11
crates/burn-jit/src/kernel/matmul/tiling2d_cube/mod.rs
View File

@ -9,7 +9,10 @@ mod tiling2d_core;
mod write_output;
pub use base::matmul_tiling_2d_cube;
pub use compute_loop::tests as compute_loop_tests;
pub use load_shared_memory::tests as load_shared_memory_tests;
pub use outer_product::tests as outer_product_tests;
pub use write_output::tests as write_output_tests;
#[cfg(feature = "export_tests")]
pub use {
compute_loop::tests as compute_loop_tests,
load_shared_memory::tests as load_shared_memory_tests,
outer_product::tests as outer_product_tests, write_output::tests as write_output_tests,
};