Does VSBC.VVM produce borrow-out?
No. VSBC writes the subtraction data result; use VMSBC to generate borrow-out mask bits.
VSBC.VVM
RISC-V VSBC.VVM Instruction Details
Instruction ManualR-typeVector integer subtract with borrow-in.
Instruction Syntax
vsbc.vvm vd, vs2, vs1, v0.t
Operand Breakdown
Destination rd: register receiving the operation result.
Source rs1: register holding the first operand.
Source rs2: register holding the second operand.
VVector IntegerCarry/Borrow
Instruction Behavior
VSBC.VVM computes vs2 - vs1 - v0.mask[i] for body elements and writes vd; v0.t is the borrow input, not an ordinary execution mask.
Quick Understanding & Search Notes
VSBC.VVM is the data-result instruction for multiword subtraction, with v0.mask[i] supplying the borrow input.
For the m-suffixed form, v0 is an arithmetic borrow input, not an ordinary execution mask.
Borrow-out is generated by VMSBC, not written as a mask by VSBC.
The SEW-width result is written to vd and can be chained with VMSBC for multiword subtraction.
Common Usage Scenarios
Multi-Precision Sub
Understand this scenario with real code like «vsbc.vvm v8, v12, v4, v0.t».
BigInt
Understand this scenario with real code like «vsbc.vvm v8, v12, v4, v0.t».
Pre-Use Checklist
Syntax Check
- Confirm the current instruction format is R-type.
- Confirm the operand order matches the example.
Semantic Check
- Ensure the destination register usage is compatible with the calling convention.
- Confirm this is not the lower-level form of a pseudo-instruction expansion.
Pitfalls / Common Confusions
vd cannot be v0
vm=0 but all body elements