Module nvptx

Available on target_arch="nvptx64" only.

NVPTX intrinsics (experimental)

These intrinsics form the foundation of the CUDA programming model.

The reference is the CUDA C Programming Guide. Relevant is also the LLVM NVPTX Backend documentation.

Re-exports

pub use packed::*;

Modules

packed 🔒

NVPTX Packed data types (SIMD)

Functions

__assertfail 🔒 ^⚠

block_dim_x 🔒 ^⚠

block_dim_y 🔒 ^⚠

block_dim_z 🔒 ^⚠

block_idx_x 🔒 ^⚠

block_idx_y 🔒 ^⚠

block_idx_z 🔒 ^⚠

grid_dim_x 🔒 ^⚠

grid_dim_y 🔒 ^⚠

grid_dim_z 🔒 ^⚠

syncthreads 🔒 ^⚠

thread_idx_x 🔒 ^⚠

thread_idx_y 🔒 ^⚠

thread_idx_z 🔒 ^⚠

__assert_fail^⚠Experimental

Syscall to be used whenever the assert expression produces a false value.

_block_dim_x^⚠Experimental

x-th thread-block dimension.

_block_dim_y^⚠Experimental

y-th thread-block dimension.

_block_dim_z^⚠Experimental

z-th thread-block dimension.

_block_idx_x^⚠Experimental

x-th thread-block index.

_block_idx_y^⚠Experimental

y-th thread-block index.

_block_idx_z^⚠Experimental

z-th thread-block index.

_grid_dim_x^⚠Experimental

x-th block-grid dimension.

_grid_dim_y^⚠Experimental

y-th block-grid dimension.

_grid_dim_z^⚠Experimental

z-th block-grid dimension.

_syncthreads^⚠Experimental

Synchronizes all threads in the block.

_thread_idx_x^⚠Experimental

x-th thread index.

_thread_idx_y^⚠Experimental

y-th thread index.

_thread_idx_z^⚠Experimental

z-th thread index.

free^⚠Experimental

Free previously dynamically allocated memory.

malloc^⚠Experimental

Allocate memory dynamically from a fixed-size heap in global memory.

trap^⚠Experimental

Generates the trap instruction TRAP

vprintf^⚠Experimental

Print formatted output from a kernel to a host-side output stream.