elect.sync GPU Virtual ISA NVIDIA

elect.sync Parallel Synchronization and Communication Instructions

elect.sync d|p, membermask;

elect.sync elects one predicated active leader thread from among a set of threads specified by membermask.

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
elect.sync d|p, membermask; sm_90 elect.sync elects one predicated active leader thread from among a set of threads specified by membermask. laneid of the elected thread is returned in the 32-bit destination operand d. (see the official PTX ISA docs for the full description)

Operands

  • d|p
    Operand
  • membermask
    Operand

At a Glance

Data Types -

Related

More in Parallel Synchronization and Communication Instructions

Reference

NVIDIA PTX ISA

Description

elect.sync elects one predicated active leader thread from among a set of threads specified by membermask. laneid of the elected thread is returned in the 32-bit destination operand d. The sink symbol ‘_’ can be used for destination operand d. The predicate destination p is set to True for the leader thread, and False for all other threads. Operand membermask specifies a 32-bit integer indicating the set of threads from which a leader is to be elected. The behavior is undefined if the executing thread is not in membermask. Election of a leader thread happens deterministically, i.e. (see the official PTX ISA docs for the full description)

Examples

elect.sync    %r0|%p0, 0xffffffff;

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

Sources