mirror of https://github.com/tracel-ai/burn.git
benchmark
This commit is contained in:
parent
43877da1f2
commit
e87c553c9a
|
@ -53,9 +53,9 @@ fn bench<B: Backend>(
|
|||
) {
|
||||
const D: usize = 3;
|
||||
let batch_size = 32;
|
||||
let m = 256;
|
||||
let k = 1024;
|
||||
let n = 256;
|
||||
let m = 1024;
|
||||
let k = 256;
|
||||
let n = 1024;
|
||||
let shape_lhs = [batch_size, m, k].into();
|
||||
let shape_rhs = [batch_size, k, n].into();
|
||||
|
||||
|
|
|
@ -31,10 +31,7 @@ pub enum MatmulStrategy {
|
|||
#[cfg(feature = "autotune")]
|
||||
impl Default for MatmulStrategy {
|
||||
fn default() -> Self {
|
||||
MatmulStrategy::Simple {
|
||||
grid_x: 16,
|
||||
grid_y: 16,
|
||||
}
|
||||
MatmulStrategy::Autotune
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
@ -193,6 +193,8 @@ pub fn matmul_tiling_2d_cube<R: JitRuntime, E: FloatElement, const D: usize>(
|
|||
} => (tensor, transposed),
|
||||
MemoryLayout::HighlyPermuted => (into_contiguous(tensor), false),
|
||||
};
|
||||
|
||||
// let check_layout = |tensor: JitTensor<R, E, D>| (into_contiguous(tensor), false);
|
||||
let (lhs, lhs_transposed) = check_layout(lhs);
|
||||
let (rhs, rhs_transposed) = check_layout(rhs);
|
||||
|
||||
|
|
Loading…
Reference in New Issue