tcgen05.mma.ws GPU Virtual ISA NVIDIA

tcgen05.mma.ws TensorCore 5th Generation of MMA Instructions

// 1. Floating-point type without block scaling:
tcgen05.mma.ws.cta_group::1.kind{.collector_usage} [d-tmem], a-desc, b-desc, idesc,
enable-input-d {, zero-column-mask-desc };

Instruction tcgen05.mma.ws is an asynchronous instruction which initiates an MxNxK matrix multiply and accumulate operation, D = A*B+D where the A matrix is MxK, the B matrix is KxN, and the D matrix is MxN.

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 8.6
Minimum Target sm_100a

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
// 1. Floating-point type without block scaling: tcgen05.mma.ws.cta_group::1.kind{.collector_usage} [d-tmem], a-desc, b-desc, idesc, enable-input-d {, zero-column-mask-desc }; sm_100a Instruction tcgen05.mma.ws is an asynchronous instruction which initiates an MxNxK matrix multiply and accumulate operation, D = A*B+D where the A matrix is MxK, the B matrix is KxN, and the D matrix… (see the official PTX ISA docs for the full description)

Operands

At a Glance

Data Types -

Related

More in TensorCore 5th Generation of MMA Instructions

Reference

NVIDIA PTX ISA

Description

Instruction tcgen05.mma.ws is an asynchronous instruction which initiates an MxNxK matrix multiply and accumulate operation, D = A*B+D where the A matrix is MxK, the B matrix is KxN, and the D matrix is MxN. The operation of the form D = A*B is issued when the input predicate argument enable-input-d is false. The 32-bit register operand idesc is the instruction descriptor as described in Instruction descriptor, specifies the shapes, exact types, sparsity and other details of the input matrices, output matrix and the matrix multiply and accumulate operation. The qualifier. (see the official PTX ISA docs for the full description)

Examples

tcgen05.mma.ws.cta_group::1.kind::i8.collector::b2:use [taddr2], [taddr1], bdesc, idesc, p;
tcgen05.commit.cta_group::1.mbarrier::arrive::one.b64 [mbarObj0];

loop:
mbarrier.try_wait.parity.b64 p, [mbarObj0], 0;
@!p bra loop;

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

Sources