wgmma.commit_group GPU Virtual ISA NVIDIA

wgmma.commit_group Asynchronous Warpgroup Level Matrix Multiply-Accumulate Instructions

wgmma.commit_group.sync.aligned;

wgmma.commit_group instruction creates a new wgmma-group per warpgroup and batches all prior wgmma.mma_async instructions initiated by the executing warp but not committed to any wgmma-group into the new wgmma-group.

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_90a

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
wgmma.commit_group.sync.aligned; sm_90a wgmma.commit_group instruction creates a new wgmma-group per warpgroup and batches all prior wgmma. (see the official PTX ISA docs for the full description)

Operands

Reference

NVIDIA PTX ISA

Description

wgmma.commit_group instruction creates a new wgmma-group per warpgroup and batches all prior wgmma.mma_async instructions initiated by the executing warp but not committed to any wgmma-group into the new wgmma-group. If there are no uncommitted wgmma.mma_async instructions then wgmma.commit_group results in an empty wgmma-group. An executing thread can wait for the completion of all wgmma.mma_async operations in a wgmma-group by using wgmma.wait_group. The mandatory.sync qualifier indicates that wgmma.commit_group instruction causes the executing thread to wait until all threads in the warp execute the same wgmma.commit_group instruction before resuming execution. The mandatory. (see the official PTX ISA docs for the full description)

Examples

wgmma.commit_group.sync.aligned;

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

Sources