ex2 GPU Virtual ISA NVIDIA

ex2 Half Precision Floating-Point Instructions

ex2.approx{.ftz}.f32 d, a;

Raise 2 to the power 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 1.0
Minimum Target sm_75

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
ex2.approx{.ftz}.f32 d, a; sm_75 Raise 2 to the power a.
ex2.approx.atype d, a; sm_75 Raise 2 to the power a. The type of operands d and a are as specified by.type. For.f16x2 or. (see the official PTX ISA docs for the full description)

Operands

  • d
    Destination register
  • a
    Source operand

At a Glance

Data Types -

Related AMDGPU Concepts

2^x (Base-2 Exponential) ↗
equivalent with restrictions
v_exp_f32 (AMDGPU)

Related

More in Half Precision Floating-Point Instructions

Reference

NVIDIA PTX ISA

Description

Raise 2 to the power a. The type of operands d and a are as specified by.type. For.f16x2 or.bf16x2 instruction type, each of the half-word operands are operated in parallel and the results are packed appropriately into a.f16x2 or.bf16x2. For.f16 instruction type, operands d and a have.f16 or.b16 type. For.f16x2 instruction type, operands d and a have.f16x2 or.b32 type. For.bf16 instruction type, operands d and a have.b16 type. For.bf16x2 instruction type, operands d and a have.b32 type.

Semantics

if (.type == .f16 || .type == .bf16) { d = 2 ^ a } else if (.type == .f16x2 || .type == .bf16x2) { fA[0] = a[0:15]; fA[1] = a[16:31]; d[0] = 2 ^ fA[0] d[1] = 2 ^ fA[1] }

Examples

ex2.approx.ftz.f32  xa, a;

ex2.approx.f16         h1, h0;
ex2.approx.f16x2       hd1, hd0;
ex2.approx.ftz.bf16    b1, b2;
ex2.approx.ftz.bf16x2  hb1, hb2;

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

Sources