multimem.st.async GPU Virtual ISA NVIDIA

multimem.st.async Data Movement and Conversion Instructions

multimem.st.async.sem.scope{.ss}.type [a], b;

multimem.st.async is a non-blocking instruction which initiates an asynchronous store operation that stores the value specified by source operand b to the memory locations residing on each GPU’s memory referred to by the destination multimem address operand a.

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 9.3
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
multimem.st.async.sem.scope{.ss}.type [a], b; sm_90 multimem.st.async is a non-blocking instruction which initiates an asynchronous store operation that stores the value specified by source operand b to the memory locations residing on each GPU’s memor… (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

multimem.st.async is a non-blocking instruction which initiates an asynchronous store operation that stores the value specified by source operand b to the memory locations residing on each GPU’s memory referred to by the destination multimem address operand a. Address operand a must be a multimem address. Otherwise, the behavior is undefined.

Examples

// Release store to multimem address, GPU scope, explicit .global state space.
multimem.st.async.release.gpu.global.u32 [mm_addr], src_u32;

// Release store, system scope, generic addressing for multimem operand.
multimem.st.async.release.sys.f64 [mm_addr], src_f64;

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

Sources