For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
block_reduce
def block_reduce[ReduceFnType: def[dtype: DType, width: SIMDLength](SIMD[dtype, width], SIMD[dtype, width]) -> SIMD[dtype, width] & RegisterPassable & ImplicitlyCopyable, //, BLOCK_SIZE: Int, dtype: DType, simd_width: SIMDLength](val: SIMD[dtype, simd_width], init: Scalar[dtype], reduce_fn: ReduceFnType) -> Scalar[dtype]
Performs a block-level reduction of a single SIMD value across all threads in a GPU thread block using warp-level primitives and shared memory.
Parameters:
- ReduceFnType (
def[dtype: DType, width: SIMDLength](SIMD[dtype, width], SIMD[dtype, width]) -> SIMD[dtype, width]&RegisterPassable&ImplicitlyCopyable): The type ofreduce_fn(inferred). - BLOCK_SIZE (
Int): The number of threads per block. - dtype (
DType): The data type of the elements. - simd_width (
SIMDLength): The SIMD vector width.
Args:
- val (
SIMD[dtype, simd_width]): The per-thread SIMD value to reduce. - init (
Scalar[dtype]): The identity value for the reduction. - reduce_fn (
ReduceFnType): The binary reduction function.
Returns:
Scalar[dtype]: The reduced scalar result (valid on thread 0).
def block_reduce[ReduceFnType: def[dtype: DType, width: SIMDLength, reduction_idx: Int](SIMD[dtype, width], SIMD[dtype, width]) -> SIMD[dtype, width] & RegisterPassable & ImplicitlyCopyable, //, BLOCK_SIZE: Int, num_reductions: Int, dtype: DType, simd_width: SIMDLength](val: StaticTuple[SIMD[dtype, simd_width], num_reductions], init: StaticTuple[Scalar[dtype], num_reductions], reduce_fn: ReduceFnType) -> StaticTuple[Scalar[dtype], num_reductions]
Performs a block-level reduction of multiple fused SIMD values across all threads in a GPU thread block using warp shuffles and shared memory.
Parameters:
- ReduceFnType (
def[dtype: DType, width: SIMDLength, reduction_idx: Int](SIMD[dtype, width], SIMD[dtype, width]) -> SIMD[dtype, width]&RegisterPassable&ImplicitlyCopyable): The type ofreduce_fn(inferred). - BLOCK_SIZE (
Int): The number of threads per block. - num_reductions (
Int): The number of fused reductions to perform. - dtype (
DType): The data type of the elements. - simd_width (
SIMDLength): The SIMD vector width.
Args:
- val (
StaticTuple[SIMD[dtype, simd_width], num_reductions]): The per-thread SIMD values to reduce, one per reduction. - init (
StaticTuple[Scalar[dtype], num_reductions]): The identity values for each reduction. - reduce_fn (
ReduceFnType): The binary reduction function, parameterized by reduction index.
Returns:
StaticTuple[Scalar[dtype], num_reductions]: The reduced scalar results (valid on thread 0).