Struct DeviceParams 

pub struct DeviceParams {
    pub cc: &'static str,
    pub sm_count: u32,
    pub max_threads_per_sm: u32,
    pub max_warps_per_sm: u32,
    pub max_blocks_per_sm: u32,
    pub smem_per_block_default: u64,
    pub smem_per_sm: u64,
}

Per-SM limits by compute capability.

Every field but sm_count is a compute-capability fact, taken from the CUDA C++ Programming Guide’s “Technical Specifications per Compute Capability” table. sm_count is a product fact — two parts at the same capability differ — so each entry names the part its count came from.

An unknown cc is an error, never a guess: a fabricated capacity would produce an occupancy number, and an occupancy number is exactly the sort of thing a reader believes.

Fields

cc: &'static str

The capability this row describes, as "<major>.<minor>" — the string --cc is matched against.

sm_count: u32

Streaming multiprocessors on the named part. Not a capability fact.

Ranking within one kernel’s space is barely sensitive to it: it enters only through waves = grid / (blocks_per_sm * sm_count), a constant divisor that scales every candidate’s cost alike, and it changes an ordering only where the .max(1.0) clamp on waves bites. It matters for reading waves as a number, not for choosing between candidates.

max_threads_per_sm: u32

Resident threads per SM. With max_warps_per_sm this is the same fact twice — a warp is 32 threads — and a test holds them equal.

max_warps_per_sm: u32

Resident warps per SM; the occupancy denominator.

max_blocks_per_sm: u32

Resident thread blocks per SM. Binds before the thread limit for small blocks, which is why a 32-thread block rarely fills an SM.

smem_per_block_default: u64

Statically allocatable shared memory per block, without the dynamic opt-in. 48 KiB on every architecture here — deliberately flat.

smem_per_sm: u64

Shared memory per SM. Note this is the per-SM capacity, one KiB above the per-block opt-in maximum on Ampere and later, where the driver reserves 1 KiB.

Trait Implementations

impl Clone for DeviceParams

fn clone(&self) -> DeviceParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for DeviceParams

impl Debug for DeviceParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.