v_rcp_f32 GPU Native ISA AMD Vector

V RCP F32 Vector Arithmetic

v_rcp_f32

Calculate the reciprocal of the single-precision float input using IEEE rules and store the result into a vector register.

Encoding

Verified bit-level encoding data is not yet available for this instruction. The instruction-format classification below (VOP1) is well-documented and stable; exact per-target opcode/field bit positions have not yet been imported from a verified source.
Format VOP1
Execution Unit

Operands

Operand details have not yet been curated for this instruction.

GFX Target Compatibility

TargetSupport
gfx1100✅ Supported

1ULP accuracy. Accuracy converges to < 0.5ULP when using the Newton-Raphson method and 2 FMA operations. Denormals are flushed.

Related PTX Concepts

Special-Function Approximation ↗
equivalent with restrictions
rsqrt (PTX)
sin (PTX)
lg2 (PTX)
sqrt (PTX)
rcp (PTX)

Related

More in Vector Arithmetic

Reference

AMDGPU / GFX ISA

Semantics

D0.f32 = 1.0F / S0.f32

Example

V_RCP_F32(0xff800000) => 0x80000000     // rcp(-INF) = -0
V_RCP_F32(0xc0000000) => 0xbf000000     // rcp(-2.0) = -0.5
V_RCP_F32(0x80000000) => 0xff800000     // rcp(-0.0) = -INF
V_RCP_F32(0x00000000) => 0x7f800000     // rcp(+0.0) = +INF

Reproduced from AMD's official "AMD Instinct MI300" ISA Reference Guide for technical accuracy.

Sources