v_cos_f32 GPU Native ISA AMD Vector

Vector Arithmetic

v_cos_f32

Calculate the trigonometric cosine of a single-precision float value using IEEE rules and store the result into a vector register.

Encoding

Binary Layout (AMD CDNA 5)
0111111
31:25
VDST
24:17
unassigned
16
0110110
15:9
SRC0
8:0
 

The ENC_VOP1 layout from AMD's machine-readable ISA specification (AMD CDNA 5). Opcode 54 in OP rebuilds 0x7E006C00, an identifier AMD lists for this encoding. Bits marked unassigned have no field in the specification. Not the same in every generation: AMD CDNA 4 (opcode 42, field layout), AMD CDNA 3 (opcode 42, field layout), AMD CDNA 2 (opcode 42, field layout), AMD CDNA 1 (opcode 42, field layout), AMD RDNA 3.5 (field layout), AMD RDNA 3 (field layout), AMD RDNA 2 (field layout), AMD RDNA 1 (field layout). The same in AMD RDNA 4.

Format VOP1
Width 32 bits
Opcode 54
Identifier 0x7E006C00

Operands

  • VDST
    Written. Operand must be a vector GPR. Uses an 8-bit operand field. Data format: 32-bit single-precision floating point value. (OPR_VGPR, FMT_NUM_F32)
  • SRC0
    Read. All operands. Covers all operands that are allowed as scalar or vector sources. Data format: 32-bit single-precision floating point value. (OPR_SRC, FMT_NUM_F32)

In AMD's order, as its machine-readable ISA specification lists them for the ENC_VOP1 encoding (AMD CDNA 5).

GFX Target Compatibility

TargetSupport
gfx1100✅ Supported

Denormals are supported. Full range input is supported.

Related PTX Concepts

Cosine ↗
equivalent with restrictions
cos (PTX)

Related

More in Vector Arithmetic

Reference

AMDGPU / GFX ISA

Description

Calculate the trigonometric cosine of a single-precision float value using IEEE rules and store the result into a vector register. The operand is calculated by scaling the vector input by 2 PI.

Semantics

D0.f32 = cos(S0.f32 * 32'F(PI * 2.0))

Example

V_COS_F32(0xff800000) => 0xffc00000     // cos(-INF) = NAN
V_COS_F32(0xff7fffff) => 0x3f800000     // -MaxFloat, finite
V_COS_F32(0x80000000) => 0x3f800000     // cos(-0.0) = 1
V_COS_F32(0x3e800000) => 0x00000000     // cos(0.25) = 0

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

Sources