ds_min_rtn_f32 GPU Native ISA AMD Vector
DS MIN RTN F32 LDS / Data Share
ds_min_rtn_f32
Select the minimum of two single-precision float inputs, given two values stored in the data register and a location in a data share.
Encoding
Verified bit-level encoding data is not yet available for this instruction.
The instruction-format classification below (DS)
is well-documented and stable; exact per-target opcode/field bit positions have not
yet been imported from a verified source.
Operands
Operand details have not yet been curated for this instruction.
GFX Target Compatibility
| Target | Support |
|---|---|
| gfx1100 | ✅ Supported |
Floating-point compare handles NAN/INF/denorm.
Related
More in LDS / Data Share
Reference
AMDGPU / GFX ISA
Description
Select the minimum of two single-precision float inputs, given two values stored in the data register and a location in a data share. Update the data share with the selected value. Store the original value from data share into a vector register.
Semantics
addr = CalcDsAddr(ADDR.b32, OFFSET0.b32, OFFSET1.b32);
tmp = MEM[addr].f32;
src = DATA.f32;
MEM[addr].f32 = src < tmp ? src : tmp;
RETURN_DATA.f32 = tmp
Example
ds_min_rtn_f32 v5, v1, v2A real instruction accepted by the LLVM assembler, taken verbatim from LLVM's own AMDGPU MC test suite (gfx11). Not from an AMD document, and not authored here.
Sources
- User Guide for AMDGPU Backend ↗ - LLVM Project
-
"AMD Instinct MI300" Instruction Set Architecture: Reference Guide ↗
- Advanced Micro Devices, Inc.
Reference Guide, page 430. - LLVM MC assembler tests for AMDGPU (gfx11) ↗ - LLVM Project