This is a collection of Intel®’ IA32® Software Developer's Manuals (URL of the day) and AMD' AMD64 Architecture Programmer's Manual together with the related specifications, application notes, white papers, and change logs. The collection aims to keep all available revisions. It was originally created by Michal Necasek, see OS/2 Museum.

If you have a public document, related to the IA32® specifications and missing from the collection, please mail it to me. The content of this URL and all sub-ULRs is available for convenient bulk download by rsync x86docs password "" (empty).

PMDEVAFF

PMDEVAFF, Performance Monitors Device Affinity register

The PMDEVAFF characteristics are:

Purpose

Copy of the PE MPIDR_EL1 register that allows a debugger to determine which PE in a multiprocessor system the Performance Monitor component relates to.

Configuration

This register is present only when FEAT_PMUv3_EXT64 is implemented.

If FEAT_DoPD is implemented, this register is in the Core power domain. If FEAT_DoPD is not implemented, this register is in the Debug power domain.

Attributes

PMDEVAFF is a 64-bit register.

This register is part of the PMU block.

Field descriptions

6362616059585756555453525150494847464544434241403938373635343332
313029282726252423222120191817161514131211109876543210
RES0Aff3
RAO/WIURES0MTAff2Aff1Aff0

Bits [63:40]

Reserved, RES0.

Aff3, bits [39:32]

Affinity level 3. See the description of Aff0 for more information.

This field has an IMPLEMENTATION DEFINED value.

Access to this field is RO.

Bit [31]

Reserved, RAO/WI.

U, bit [30]

Indicates a Uniprocessor system, as distinct from PE 0 in a multiprocessor system.

The value of this field is an IMPLEMENTATION DEFINED choice of:

UMeaning
0b0

Processor is part of a multiprocessor system.

0b1

Processor is part of a uniprocessor system.

Access to this field is RO.

Bits [29:25]

Reserved, RES0.

MT, bit [24]

Indicates whether the lowest level of affinity consists of logical PEs that are implemented using an interdependent approach, such as multithreading. See the description of Aff0 for more information about affinity levels.

The value of this field is an IMPLEMENTATION DEFINED choice of:

MTMeaning
0b0

Performance of PEs with different affinity level 0 values, and the same values for affinity level 1 and higher, is largely independent.

0b1

Performance of PEs with different affinity level 0 values, and the same values for affinity level 1 and higher, is very interdependent.

Note

This field does not indicate that multithreading is implemented and does not indicate that PEs with different affinity level 0 values, and the same values for affinity level 1 and higher are implemented.

Access to this field is RO.

Aff2, bits [23:16]

Affinity level 2. See the description of Aff0 for more information.

This field has an IMPLEMENTATION DEFINED value.

Access to this field is RO.

Aff1, bits [15:8]

Affinity level 1. See the description of Aff0 for more information.

This field has an IMPLEMENTATION DEFINED value.

Access to this field is RO.

Aff0, bits [7:0]

Affinity level 0. The value of the MPIDR.{Aff2, Aff1, Aff0} or MPIDR_EL1.{Aff3, Aff2, Aff1, Aff0} set of fields of each PE must be unique within the system as a whole.

This field has an IMPLEMENTATION DEFINED value.

Access to this field is RO.

Accessing PMDEVAFF

If FEAT_PMUv3_EXT32 is implemented, then the same content is present in the same locations, and can be accessed using PMDEVAFF0[31:0] and PMDEVAFF1[31:0].

Accesses to this register use the following encodings:

Accessible at offset 0xFA8 from PMU


2026-03-12 12:23:09, 2025-09_rel_asl1

Copyright © 2010-2025 Arm Limited or its affiliates. All rights reserved. This document is Non-Confidential.