Extensions
Forms
1 (1 Legacy)
Data
Intel XED v2026.08.23

XABORT ends an RTM transaction on purpose. Like any abort, it throws away the transaction’s stores, puts the registers back as they were at XBEGIN, and resumes at the fallback address of the outermost XBEGIN, with the status in EAX. For XABORT, bit 0 of EAX is set and bits 31:24 hold its 8-bit immediate, a code of the program’s choosing; bit 1, “a retry may succeed”, is always clear, and bit 5 is set when the abort came from a nested transaction. Outside a transaction XABORT does nothing at all. It is three bytes, C6 F8 ib.

Telling the fallback why

The usual reason is a lock taken by another thread. Code that elides a lock starts a transaction, reads the lock, and calls _xabort when it is held, since running on would race with the holder; XEND’s page explains why reading it also aborts the transaction when the lock is taken later. The fallback then reads the code:

if ((s & _XABORT_EXPLICIT) && _XABORT_CODE(s) == 0xff)

With -mrtm, GCC 14 at -O2 compiles _xabort(0xff) to xabort 255 and that test to test al, 1, then shr eax, 24 and cmp eax, 255. Clang 23 folds the two checks into one: not eax and test eax, -16777215, that is FF000001H, zero only when bit 0 and all eight code bits are set. The code is an immediate, so _xabort takes a constant, and one XABORT site can report only one code.

Intel’s manual lists XABORT among the instructions that abort a transaction on every implementation, together with CPUID and PAUSE; XTEST tells code whether it runs inside one.

Where it runs

XABORT needs RTM, CPUID.(EAX=7,ECX=0):EBX[11]; without it, it raises #UD even outside a transaction. XBEGIN’s page says where Intel’s microcode disables RTM. AMD’s manual defines no XABORT, and on this site’s Zen 5, both recorded cases, with codes 0 and 255, raised #UD.

Forms

Every encoding of XABORT that Intel XED knows, one row per XED instruction form (iform). How to read the notation.
InstructionEncodingRequires
XABORT imm8 XABORT_IMMbC6 F8 ibRTM

Latency and throughput

What the scheduling models of LLVM 23.1.2 give for each form, not measurements: latency / reciprocal throughput in cycles, the ports under them. A row is a model, or models that agree; a dash, a form that its processors lack. Memory forms: latency from the address, ports without the load and store units. Which processors each model covers.
Modelimm8
Haswell, Broadwell, Skylake, Skylake-SP, Ice Lake, Sapphire Rapids100 / 0.25p0156

Operation

What the forms do, in pseudocode that our tests run against results recorded on real processors. How to read.

if not cpuid_leaf(7, 0)[1] >> 11 & 1:
    fault(UD)                    # CPUID: no RTM
if rtm_active:
    s = imm << 24 | 1            # bit 0: XABORT; bits 31:24: imm8
    if rtm_nest > 1:
        s = s | 0x20             # bit 5: inside a nested one
    tx_abort(s)
# outside a transaction a NOP

Run on AMD Zen 5 (EPYC 9645): 2 cases. Its cases ran where CPUID reported no RTM, and every one raised an exception.

Operands

What each form reads and writes, as Intel XED records it: the operands of its syntax, in order, and the implicit ones that the syntax does not name. How to read.
OperandKindAction
XABORT imm8
imm8explicitread
EAXimplicitread, conditional write

Flags

None: XED records no flag that the forms test or change.

Intrinsics

The C intrinsics of Clang 23.1.2 that compile to XABORT, each with the form it compiles to and the Clang options it needs. The forms come from compiling every intrinsic and decoding the result with Intel XED; all intrinsics A–Z explains the method.

IntrinsicCompiles to
_xabort void _xabort(const int imm)

XABORT imm8 Legacy -mrtm

CPUID and processors

Each form belongs to an XED ISA set. A form can be used when the processor reports every CPUID bit of one of its ISA set's alternatives.

CPUID requirements and processors of the XED ISA sets above. Alternatives are separated by “or”; processors follow XED’s chip model, whose AMD processors end with Zen 2, and the CPU data of this site for Zen 3 to Zen 6.

More RTM instructions

Sources

  1. Intel XED v2026.08.23 (commit 0bcb6237345c): forms, encodings, operands, flags, exception classes, attributes, ISA sets, CPUID bits and chip model.
  2. Clang's x86 intrinsic headers, LLVM 23.1.2 (commit 85ac56026243): the intrinsics, their signatures and doc comments, and the Clang of that release, which compiled each of them.
  3. LLVM 23.1.2's x86 scheduling models (commit 85ac56026243): the latency, reciprocal throughput and ports of each form, as llvm-mca reports them.
  4. Intel 64 and IA-32 Architectures Software Developer's Manual, Volume 2 (325383-093, September 2026): Volume 2D, page 6-21 (XABORT)
  5. Intel 64 and IA-32 Architectures Software Developer's Manual, Volume 1 (253665-093, September 2026)
  6. AMD64 Architecture Programmer's Manual, Volume 3: General-Purpose and System Instructions (24594, rev. 3.38, July 2026)

The tables are derived from Intel XED, Copyright Intel Corporation, licensed under the Apache License 2.0; x86-64.net converted and reformatted them. The intrinsics and their signatures come from Clang and the timings from LLVM's scheduling models, both part of the LLVM Project, licensed under the Apache License 2.0 with LLVM Exceptions. The text is our own.