v_readfirstlane_b32 GPU Native ISA AMD Vector
V READFIRSTLANE B32 Lane Operations
v_readfirstlane_b32 SDST, S0
Read the value of a VGPR from the first active lane into a scalar 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.
Operands
-
SDST
Destination SGPR -
S0
Source VGPR
GFX Target Compatibility
| Target | Support |
|---|---|
| gfx942 | ✅ Supported |
| gfx1100 | ✅ Supported |
Related PTX Concepts
Related
More in Lane Operations
Reference
AMDGPU / GFX ISA
Description
Read the scalar value in the lowest active lane of the input vector register and store it into a scalar register.
Semantics
SDST = S0[first active lane in EXEC]; used to move a per-lane value into scalar (wavefront-uniform) state when all active lanes are known to agree.
Example
v_readfirstlane_b32 s0, v0 // s0 = v0 from the first active laneOriginal illustrative example, written for this site (not reproduced from a specific AMD document).
Sources
- AMD Machine-Readable GPU ISA Specification ↗ - Advanced Micro Devices, Inc.