pub struct ChipKnobs {
pub name: &'static str,
pub max_dst_tiles: usize,
pub grid_x: usize,
pub grid_y: usize,
pub l1_kib: usize,
}Expand description
Per-chip capability knobs — the hardware limits that make the fastest tiling chip-specific. A bigger DST register file lets a core hold a larger reuse sub-block; a bigger worker grid lets the work spread across more cores; more L1 lets wider inner blocks stay resident. The autotuner searches within these, so the SAME matmul compiles to a DIFFERENT (faster) kernel on a different part.
Fields§
§name: &'static strHuman-readable part name (for the emitted kernel header + provenance).
max_dst_tiles: usizeDST register-file capacity in 32×32 output tiles per acquire (the reuse sub-block ceiling).
grid_x: usizeWorker-grid width (max cores across the N dimension).
grid_y: usizeWorker-grid height (max cores across the M dimension).
l1_kib: usizePer-core L1 SRAM (KiB) — budgets the resident A/B blocks (bounds in0_block_w).
Implementations§
Source§impl ChipKnobs
impl ChipKnobs
Sourcepub fn blackhole() -> Self
pub fn blackhole() -> Self
Blackhole: 16-tile DST (double the reuse), a larger 13×10 worker grid, ~1.46 MB L1.
Sourcepub fn tile_limits(&self, knobs: &ComputeKnobs) -> TileLimits
pub fn tile_limits(&self, knobs: &ComputeKnobs) -> TileLimits
This part’s limits in the units the lattice search filters by, under the requested compute knobs (fp32 dest-accumulate halves the addressable DST tiles).
Trait Implementations§
impl Copy for ChipKnobs
impl Eq for ChipKnobs
impl StructuralPartialEq for ChipKnobs
Auto Trait Implementations§
impl Freeze for ChipKnobs
impl RefUnwindSafe for ChipKnobs
impl Send for ChipKnobs
impl Sync for ChipKnobs
impl Unpin for ChipKnobs
impl UnsafeUnpin for ChipKnobs
impl UnwindSafe for ChipKnobs
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
§impl<T> Downcast for Twhere
T: Any,
impl<T> Downcast for Twhere
T: Any,
§fn into_any(self: Box<T>) -> Box<dyn Any>
fn into_any(self: Box<T>) -> Box<dyn Any>
Box<dyn Trait> (where Trait: Downcast) to Box<dyn Any>. Box<dyn Any> can
then be further downcast into Box<ConcreteType> where ConcreteType implements Trait.§fn into_any_rc(self: Rc<T>) -> Rc<dyn Any>
fn into_any_rc(self: Rc<T>) -> Rc<dyn Any>
Rc<Trait> (where Trait: Downcast) to Rc<Any>. Rc<Any> can then be
further downcast into Rc<ConcreteType> where ConcreteType implements Trait.§fn as_any(&self) -> &(dyn Any + 'static)
fn as_any(&self) -> &(dyn Any + 'static)
&Trait (where Trait: Downcast) to &Any. This is needed since Rust cannot
generate &Any’s vtable from &Trait’s.§fn as_any_mut(&mut self) -> &mut (dyn Any + 'static)
fn as_any_mut(&mut self) -> &mut (dyn Any + 'static)
&mut Trait (where Trait: Downcast) to &Any. This is needed since Rust cannot
generate &mut Any’s vtable from &mut Trait’s.§impl<T> DowncastSync for T
impl<T> DowncastSync for T
§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
key and return true if they are equal.