Enum cubecl_cuda::compiler::WmmaInstruction
source · pub enum WmmaInstruction {
Fill {
frag: Variable,
value: Variable,
},
Load {
frag: Variable,
value: Variable,
stride: Variable,
},
Execute {
frag_a: Variable,
frag_b: Variable,
frag_c: Variable,
frag_d: Variable,
},
Store {
output: Variable,
frag: Variable,
stride: Variable,
layout: FragmentLayout,
},
}
Expand description
Warp Matrix-Multiply and Accumulate Instruction.
Variants§
Fill
Fill the fragment with the value.
Load
Load the value into the fragment given the stride.
Execute
Executes D=A*B+C;
For implementing a matmul, D=C
: C+=A*B
Store
Store the fragment in an output variable following the stride and the layout.
Trait Implementations§
source§impl Clone for WmmaInstruction
impl Clone for WmmaInstruction
source§fn clone(&self) -> WmmaInstruction
fn clone(&self) -> WmmaInstruction
Returns a copy of the value. Read more
1.0.0 · source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source
. Read moresource§impl Debug for WmmaInstruction
impl Debug for WmmaInstruction
source§impl Display for WmmaInstruction
impl Display for WmmaInstruction
impl Copy for WmmaInstruction
Auto Trait Implementations§
impl Freeze for WmmaInstruction
impl RefUnwindSafe for WmmaInstruction
impl Send for WmmaInstruction
impl Sync for WmmaInstruction
impl Unpin for WmmaInstruction
impl UnwindSafe for WmmaInstruction
Blanket Implementations§
source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
source§unsafe fn clone_to_uninit(&self, dst: *mut T)
unsafe fn clone_to_uninit(&self, dst: *mut T)
🔬This is a nightly-only experimental API. (
clone_to_uninit
)