cp.reduce.async.bulk.tensor GPU Virtual ISA NVIDIA

cp.reduce.async.bulk.tensor Data Movement and Conversion Instructions

// shared::cta -> global:
cp.reduce.async.bulk.tensor.dim.dst.src.redOp{.load_mode}.completion_mechanism{.level::cache_hint}
[tensorMap, tensorCoords], [srcMem] {,cache_policy}

cp.reduce.async.bulk.tensor is a non-blocking instruction which initiates an asynchronous reduction operation of tensor data in the.dst state space with tensor data in the.src state space.

Encoding

PTX is a virtual instruction set. It has no single, stable native binary encoding - the compiler lowers this instruction to different native machine code depending on the selected NVIDIA target architecture (compute capability). This page intentionally shows no bit-diagram; see the target/version requirements below for what governs how this instruction compiles.
PTX ISA Version Introduced PTX ISA 8.0
Minimum Target sm_90

Syntax Forms

One mnemonic covers many type / state-space / scope / modifier combinations - each row below is an independently valid form.

Syntax Data Types State Space(s) Modifiers Min. Target Description
// shared::cta -> global: cp.reduce.async.bulk.tensor.dim.dst.src.redOp{.load_mode}.completion_mechanism{.level::cache_hint} [tensorMap, tensorCoords], [srcMem] {,cache_policy} sm_90 cp.reduce.async.bulk.tensor is a non-blocking instruction which initiates an asynchronous reduction operation of tensor data in the.dst state space with tensor data in the.src state space. (see the official PTX ISA docs for the full description)

Operands

At a Glance

Data Types -

Related

More in Data Movement and Conversion Instructions

Reference

NVIDIA PTX ISA

Description

cp.reduce.async.bulk.tensor is a non-blocking instruction which initiates an asynchronous reduction operation of tensor data in the.dst state space with tensor data in the.src state space. The operand srcMem specifies the location of the tensor data in the.src state space using which the reduction operation has to be performed. The operand tensorMap is the generic address of the opaque tensor-map object which resides in.param space or.const space or.global space. The operand tensorMap specifies the properties of the tensor copy operation, as described in Tensor-map. The tensorMap is accessed in tensormap proxy. (see the official PTX ISA docs for the full description)

Examples

cp.reduce.async.bulk.tensor.1d.global.shared::cta.add.tile.bulk_group
                                             [tensorMap0, {tc0}], [sMem0];

cp.reduce.async.bulk.tensor.2d.global.shared::cta.and.bulk_group.L2::cache_hint
                                             [tensorMap1, {tc0, tc1}], [sMem1] , policy;
// (truncated - see the official PTX ISA docs for the full example)

Reproduced from NVIDIA's official PTX ISA documentation for technical accuracy.

Sources