1.. _Arm Emulation: 2 3A-profile CPU architecture support 4================================== 5 6QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7 and 7Armv8 versions of the A-profile architecture. It also has support for 8the following architecture extensions: 9 10- FEAT_AA32BF16 (AArch32 BFloat16 instructions) 11- FEAT_AA32HPD (AArch32 hierarchical permission disables) 12- FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) 13- FEAT_AES (AESD and AESE instructions) 14- FEAT_BBM at level 2 (Translation table break-before-make levels) 15- FEAT_BF16 (AArch64 BFloat16 instructions) 16- FEAT_BTI (Branch Target Identification) 17- FEAT_CRC32 (CRC32 instructions) 18- FEAT_CSV2 (Cache speculation variant 2) 19- FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) 20- FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) 21- FEAT_CSV2_2 (Cache speculation variant 2, version 2) 22- FEAT_CSV3 (Cache speculation variant 3) 23- FEAT_DGH (Data gathering hint) 24- FEAT_DIT (Data Independent Timing instructions) 25- FEAT_DPB (DC CVAP instruction) 26- FEAT_Debugv8p2 (Debug changes for v8.2) 27- FEAT_Debugv8p4 (Debug changes for v8.4) 28- FEAT_DotProd (Advanced SIMD dot product instructions) 29- FEAT_DoubleFault (Double Fault Extension) 30- FEAT_E0PD (Preventing EL0 access to halves of address maps) 31- FEAT_EPAC (Enhanced pointer authentication) 32- FEAT_ETS (Enhanced Translation Synchronization) 33- FEAT_EVT (Enhanced Virtualization Traps) 34- FEAT_FCMA (Floating-point complex number instructions) 35- FEAT_FGT (Fine-Grained Traps) 36- FEAT_FHM (Floating-point half-precision multiplication instructions) 37- FEAT_FP16 (Half-precision floating-point data processing) 38- FEAT_FPAC (Faulting on AUT* instructions) 39- FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions) 40- FEAT_FRINTTS (Floating-point to integer instructions) 41- FEAT_FlagM (Flag manipulation instructions v2) 42- FEAT_FlagM2 (Enhancements to flag manipulation instructions) 43- FEAT_GTG (Guest translation granule size) 44- FEAT_HAFDBS (Hardware management of the access flag and dirty bit state) 45- FEAT_HBC (Hinted conditional branches) 46- FEAT_HCX (Support for the HCRX_EL2 register) 47- FEAT_HPDS (Hierarchical permission disables) 48- FEAT_HPDS2 (Translation table page-based hardware attributes) 49- FEAT_HPMN0 (Setting of MDCR_EL2.HPMN to zero) 50- FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) 51- FEAT_IDST (ID space trap handling) 52- FEAT_IESB (Implicit error synchronization event) 53- FEAT_JSCVT (JavaScript conversion instructions) 54- FEAT_LOR (Limited ordering regions) 55- FEAT_LPA (Large Physical Address space) 56- FEAT_LPA2 (Large Physical and virtual Address space v2) 57- FEAT_LRCPC (Load-acquire RCpc instructions) 58- FEAT_LRCPC2 (Load-acquire RCpc instructions v2) 59- FEAT_LSE (Large System Extensions) 60- FEAT_LSE2 (Large System Extensions v2) 61- FEAT_LVA (Large Virtual Address space) 62- FEAT_MOPS (Standardization of memory operations) 63- FEAT_MTE (Memory Tagging Extension) 64- FEAT_MTE2 (Memory Tagging Extension) 65- FEAT_MTE3 (MTE Asymmetric Fault Handling) 66- FEAT_NV (Nested Virtualization) 67- FEAT_NV2 (Enhanced nested virtualization support) 68- FEAT_PACIMP (Pointer authentication - IMPLEMENTATION DEFINED algorithm) 69- FEAT_PACQARMA3 (Pointer authentication - QARMA3 algorithm) 70- FEAT_PACQARMA5 (Pointer authentication - QARMA5 algorithm) 71- FEAT_PAN (Privileged access never) 72- FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN) 73- FEAT_PAN3 (Support for SCTLR_ELx.EPAN) 74- FEAT_PAuth (Pointer authentication) 75- FEAT_PAuth2 (Enhancements to pointer authentication) 76- FEAT_PMULL (PMULL, PMULL2 instructions) 77- FEAT_PMUv3p1 (PMU Extensions v3.1) 78- FEAT_PMUv3p4 (PMU Extensions v3.4) 79- FEAT_PMUv3p5 (PMU Extensions v3.5) 80- FEAT_RAS (Reliability, availability, and serviceability) 81- FEAT_RASv1p1 (RAS Extension v1.1) 82- FEAT_RDM (Advanced SIMD rounding double multiply accumulate instructions) 83- FEAT_RME (Realm Management Extension) (NB: support status in QEMU is experimental) 84- FEAT_RNG (Random number generator) 85- FEAT_S2FWB (Stage 2 forced Write-Back) 86- FEAT_SB (Speculation Barrier) 87- FEAT_SEL2 (Secure EL2) 88- FEAT_SHA1 (SHA1 instructions) 89- FEAT_SHA256 (SHA256 instructions) 90- FEAT_SHA3 (Advanced SIMD SHA3 instructions) 91- FEAT_SHA512 (Advanced SIMD SHA512 instructions) 92- FEAT_SM3 (Advanced SIMD SM3 instructions) 93- FEAT_SM4 (Advanced SIMD SM4 instructions) 94- FEAT_SME (Scalable Matrix Extension) 95- FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) 96- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) 97- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) 98- FEAT_SPECRES (Speculation restriction instructions) 99- FEAT_SSBS (Speculative Store Bypass Safe) 100- FEAT_TIDCP1 (EL0 use of IMPLEMENTATION DEFINED functionality) 101- FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) 102- FEAT_TLBIRANGE (TLB invalidate range instructions) 103- FEAT_TTCNP (Translation table Common not private translations) 104- FEAT_TTL (Translation Table Level) 105- FEAT_TTST (Small translation tables) 106- FEAT_UAO (Unprivileged Access Override control) 107- FEAT_VHE (Virtualization Host Extensions) 108- FEAT_VMID16 (16-bit VMID) 109- FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) 110- SVE (The Scalable Vector Extension) 111- SVE2 (The Scalable Vector Extension v2) 112 113For information on the specifics of these extensions, please refer 114to the `Armv8-A Arm Architecture Reference Manual 115<https://developer.arm.com/documentation/ddi0487/latest>`_. 116 117When a specific named CPU is being emulated, only those features which 118are present in hardware for that CPU are emulated. (If a feature is 119not in the list above then it is not supported, even if the real 120hardware should have it.) The ``max`` CPU enables all features. 121 122R-profile CPU architecture support 123================================== 124 125QEMU's TCG emulation support for R-profile CPUs is currently limited. 126We emulate only the Cortex-R5 and Cortex-R5F CPUs. 127 128M-profile CPU architecture support 129================================== 130 131QEMU's TCG emulation includes support for Armv6-M, Armv7-M, Armv8-M, and 132Armv8.1-M versions of the M-profile architucture. It also has support 133for the following architecture extensions: 134 135- FP (Floating-point Extension) 136- FPCXT (FPCXT access instructions) 137- HP (Half-precision floating-point instructions) 138- LOB (Low Overhead loops and Branch future) 139- M (Main Extension) 140- MPU (Memory Protection Unit Extension) 141- PXN (Privileged Execute Never) 142- RAS (Reliability, Serviceability and Availability): "minimum RAS Extension" only 143- S (Security Extension) 144- ST (System Timer Extension) 145 146For information on the specifics of these extensions, please refer 147to the `Armv8-M Arm Architecture Reference Manual 148<https://developer.arm.com/documentation/ddi0553/latest>`_. 149 150When a specific named CPU is being emulated, only those features which 151are present in hardware for that CPU are emulated. (If a feature is 152not in the list above then it is not supported, even if the real 153hardware should have it.) There is no equivalent of the ``max`` CPU for 154M-profile. 155