Enum SmVersion 

pub enum SmVersion {
    Sm75,
    Sm80,
    Sm86,
    Sm89,
    Sm90,
    Sm90a,
    Sm100,
    Sm120,
}

NVIDIA GPU Streaming Multiprocessor version.

Each variant corresponds to a CUDA compute capability and determines the PTX ISA version, available instructions, and hardware features.

Ordering

SmVersion derives Ord so that newer architectures compare greater than older ones: Sm80 > Sm75.

Variants

Sm75

Turing (compute capability 7.5).

Sm80

Ampere (compute capability 8.0).

Sm86

Ampere GA10x (compute capability 8.6).

Sm89

Ada Lovelace (compute capability 8.9).

Sm90

Hopper (compute capability 9.0).

Sm90a

Hopper with accelerated features (compute capability 9.0a).

Sm100

Blackwell (compute capability 10.0).

Sm120

Blackwell B200 / next-gen (compute capability 12.0).

Implementations

impl SmVersion

pub const fn as_ptx_str(self) -> &'static str

Returns the PTX target string (e.g. "sm_80", "sm_90a").

pub const fn ptx_version(self) -> &'static str

Returns the PTX ISA version string appropriate for this architecture.

The PTX version determines which instructions and features are available. Later architectures require higher PTX versions.

pub const fn ptx_isa_version(self) -> (u32, u32)

Returns the PTX ISA version as a (major, minor) pair.

This is useful for programmatic version comparisons rather than string parsing.

Examples

use oxicuda_ptx::arch::SmVersion;

assert_eq!(SmVersion::Sm80.ptx_isa_version(), (7, 0));
assert_eq!(SmVersion::Sm90.ptx_isa_version(), (8, 0));
assert_eq!(SmVersion::Sm120.ptx_isa_version(), (8, 7));

pub const fn capabilities(self) -> ArchCapabilities

Returns the architecture capabilities for this SM version.

pub const fn from_compute_capability(major: i32, minor: i32) -> Option<Self>

Converts a CUDA compute capability pair to an SmVersion.

Returns None if the compute capability is not recognized.

Examples

use oxicuda_ptx::arch::SmVersion;

assert_eq!(SmVersion::from_compute_capability(8, 0), Some(SmVersion::Sm80));
assert_eq!(SmVersion::from_compute_capability(7, 5), Some(SmVersion::Sm75));
assert_eq!(SmVersion::from_compute_capability(6, 0), None);

pub const fn max_threads_per_block(self) -> u32

Returns the maximum number of threads per block for this architecture.

pub const fn max_threads_per_sm(self) -> u32

Returns the maximum number of threads per SM for this architecture.

pub const fn warp_size(self) -> u32

Returns the warp size for this architecture (always 32).

pub const fn max_shared_mem_per_block(self) -> u32

Returns the maximum shared memory per block in bytes.

Trait Implementations

impl Clone for SmVersion

fn clone(&self) -> SmVersion

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SmVersion

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

Formats the value using the given formatter.

impl Display for SmVersion

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

Formats the value using the given formatter.

impl Hash for SmVersion

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Ord for SmVersion

fn cmp(&self, other: &SmVersion) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl PartialEq for SmVersion

fn eq(&self, other: &SmVersion) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl PartialOrd for SmVersion

fn partial_cmp(&self, other: &SmVersion) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

Tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

Tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

Tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl Copy for SmVersion

impl Eq for SmVersion

impl StructuralPartialEq for SmVersion