Special-Function Approximation Arithmetic

Fast, reduced-precision hardware approximation of a transcendental function (reciprocal, reciprocal sqrt, sin, log2, exp2, ...).

Vendor-Neutral Definition

d ≈ f(a) for f in {1/x, 1/sqrt(x), sin, cos, log2, exp2, ...}; precision (ULP error bound) is hardware- and instruction-specific and is generally lower than a fully-rounded IEEE result.
⚠️ Cross-vendor mappings describe semantic relationships and are not guaranteed one-to-one compiler translations.
equivalent with restrictions Both provide fast, reduced-precision hardware approximations of transcendental functions.
Property NVIDIA PTX AMDGPU
Instruction rsqrt, sin, lg2, sqrt, rcp v_rsq_f32, v_sin_f32, v_sqrt_f32, v_rcp_f32
ISA Layer Virtual Native
Data Types f32 f32
Version / Target Introduced PTX ISA 1.0, PTX ISA 1.0, PTX ISA 1.0, PTX ISA 1.0, PTX ISA 1.0 gfx942/gfx1100, gfx942/gfx1100, gfx1100, gfx1100

Important Differences

  • Approximation error bounds (max ULP) are hardware-generation-specific on both vendors and are not guaranteed to match; do not assume bit-identical results across vendors even when both are described as 'approx'.

Source Evidence

Verification method: documentation