Intel Arc Pro B50 code 43 on 32.0.101.8515 driver

hege · ‎03-26-2026

Hi,

I have an Intel Pro B50 installed and passed via SR-IOV VF to a Windows 11 VM (host machine is using a Linux KVM hypervisor with Kernel 6.18). This setup has worked well. I have updated to the latest available driver 32.0.101.8515 and now the B50 is giving me code 43 error in device manager.

I have followed the following troubleshooting steps:

1. Install the driver on bare metal windows instance so firmware upgrade can succeed. Then powered off the whole system. The bare metal instance worked after that.

2. The virtualized Windows instance still gives me error 43. I have tried reinstalling the driver with clean installation enabled (also with safe mode + DDU), the error persists.

3. I can downgrade to the previous pro drivers and that fixes the card.

Any help troubleshooting this is appreciated!

CM_Intel · ‎04-02-2026

Hello Hege,

Thank you for posting your query on the Intel® Community Forum and for taking the time to share such a detailed explanation of your setup. We truly appreciate the effort you’ve made in outlining your SR‑IOV configuration and the troubleshooting already performed across both bare‑metal and virtualized Windows environments.

We understand how frustrating it can be to encounter issues after an update—especially when your configuration was previously working as expected. Please rest assured that we’re here to help and will do our best to assist you further.

To ensure we fully understand the situation, could you please confirm whether you are referring to the Code 43 error displayed in Device Manager on your system?

Additionally, to help us review this more accurately, we kindly request that you share a screenshot of the General tab from Device Manager where the error is observed.

Thank you very much for your cooperation. Once we receive this information, we’ll review it promptly and guide you through the next steps.

Best regards,

CM

Intel Customer Support Technician

hege · ‎04-03-2026

Hi @CM_Intel ,

I am observing the yellow warning triangle on the Intel Arc Pro B50 Graphics device in the Device Manager, and the details page shows "Windows has stopped this device because it has reported problems", and the GPU disappears from Windows.

Attaching screenshots of 8314 device driver status and 8515 error. I tried to install the driver multiple ways: clean install, completely fresh windows install, powering down the entire host and reinstalling, etc. and I always get this error on the 8515 driver.

For now I'm reinstalling the older drivers and keep using that.

thanks!

CM_Intel · ‎04-06-2026

Hello Hege,

Thank you for sharing the detailed information and screenshots. We appreciate the extensive troubleshooting you’ve already performed, including clean installations and testing on a fresh Windows setup.

To help us dig deeper and provide you with a meaningful resolution, we'd like to gather some system information from your Linux environment:

1.Ensure the following BIOS settings are enabled:

• Above 4G Decoding = Enabled

• Resizable BAR = Enabled

• CSM = Disabled

2. We kindly request that you download and install the latest firmware updates rolled out by your Linux distributor, as these firmware packages may include critical updates that help address compatibility and stability issues observed with newer driver versions.

3. We kindly request you to share the system logs from both Windows and Linux environments.

Windows Logs - Please generate the SSU (System Support Utility) report using the link below:

How to get the Intel® System Support Utility Logs on Windows*

Linux Logs - Please collect the required system logs by following the guidance provided in the article below:

Help Guide for the Intel® System Support Utility

Please note: While generating both the SSU report, kindly uncheck the “Networking” option.

Once you've run the tool, please attach the generated log file. If you run into any difficulty with the SSU tool or have any questions at all, please feel free to reach out.

After we receive the requested details, we will review them promptly and determine the next course of action.

We appreciate your time and cooperation and look forward to your reply.

Best regards,

CM

Intel Customer Support Technician

CM_Intel · ‎04-13-2026

Hello Hege,

I hope you’re doing well.

I’m writing to follow up on our previous message regarding the additional system details and logs we requested from your Windows and Linux environments.

At your convenience, please let us know if you were able to review the BIOS settings and collect the requested logs. This information will help us continue our investigation and determine the next appropriate steps.

If you encountered any difficulties while gathering the details or have any questions, please feel free to reach out—we’ll be happy to assist.

Thank you for your time and cooperation. We look forward to your update.

Best regards,

CM

Intel Customer Support Technician

hege · ‎04-13-2026

Hi @CM_Intel,

thanks for the note. I am currently running TrueNAS Community 26 Beta.1. I'm attaching SSU output from the Linux box without networking, and also the raw `lspci -vvv` output and kernel logs from the `xe` driver, see below.

SSU apparently has a bug where it associates the Intel card with the `amdgpu` driver, based on the kernel and lspci output, that's incorrect information. The system is able to see/use the `xe` driver and SR-IOV passthrough works perfectly on previous Windows drivers prior to the 2026 Q1 (8515) version.

I am running the latest Linux Firmware files from https://gitlab.com/kernel-firmware/linux-firmware/-/tree/main/xe?ref_type=heads (GuC 70.60.0, HuC 8.12.10).

The system is booted with UEFI, and Resizable BAR is enabled (lspci confirms this).

[    6.707947] xe 0000:12:00.0: [drm] Running in SR-IOV PF mode
[    6.708065] xe 0000:12:00.0: [drm] Found battlemage (device ID e212) discrete display version 14.01 stepping B0
[    6.709339] xe 0000:12:00.0: [drm] VISIBLE VRAM: 0x0000007400000000, 0x0000000400000000
[    6.709368] xe 0000:12:00.0: [drm] VRAM[0]: Actual physical size 0x0000000400000000, usable size exclude stolen 0x00000003fb000000, CPU accessible size 0x00000003fb000000
[    6.709371] xe 0000:12:00.0: [drm] VRAM[0]: DPA range: [0x0000000000000000-400000000], io range: [0x0000007400000000-77fb000000]
[    6.709373] xe 0000:12:00.0: [drm] VRAM[0]: Actual physical size 0x0000000400000000, usable size exclude stolen 0x00000003fb000000, CPU accessible size 0x00000003fb000000
[    6.709375] xe 0000:12:00.0: [drm] VRAM[0]: DPA range: [0x0000000000000000-400000000], io range: [0x0000007400000000-77fb000000]
[    6.814160] xe 0000:12:00.0: [drm] Tile0: GT0: Using GuC firmware from xe/bmg_guc_70.bin version 70.60.0
[    6.826266] xe 0000:12:00.0: [drm] Finished loading DMC firmware i915/bmg_dmc.bin (v2.6)
[    7.034715] xe 0000:12:00.0: [drm] Tile0: GT0: ccs1 fused off
[    7.034718] xe 0000:12:00.0: [drm] Tile0: GT0: ccs2 fused off
[    7.034720] xe 0000:12:00.0: [drm] Tile0: GT0: ccs3 fused off
[    7.062440] xe 0000:12:00.0: [drm] Tile0: GT1: Using GuC firmware from xe/bmg_guc_70.bin version 70.60.0
[    7.065347] xe 0000:12:00.0: [drm] Tile0: GT1: Using HuC firmware from xe/bmg_huc.bin version 8.2.10
[    7.076183] xe 0000:12:00.0: [drm] Tile0: GT1: vcs1 fused off
[    7.076187] xe 0000:12:00.0: [drm] Tile0: GT1: vcs3 fused off
[    7.076189] xe 0000:12:00.0: [drm] Tile0: GT1: vcs4 fused off
[    7.076191] xe 0000:12:00.0: [drm] Tile0: GT1: vcs5 fused off
[    7.076193] xe 0000:12:00.0: [drm] Tile0: GT1: vcs6 fused off
[    7.076195] xe 0000:12:00.0: [drm] Tile0: GT1: vcs7 fused off
[    7.076197] xe 0000:12:00.0: [drm] Tile0: GT1: vecs2 fused off
[    7.076200] xe 0000:12:00.0: [drm] Tile0: GT1: vecs3 fused off
[    7.108099] xe 0000:12:00.0: [drm] Can't init xe mei late bind missing mei component
[    7.109761] xe 0000:12:00.0: [drm] Registered 4 planes with drm panic
[    7.109764] [drm] Initialized xe 1.1.0 for 0000:12:00.0 on minor 1
[    7.142371] xe 0000:12:00.0: [drm] Cannot find any crtc or sizes
[    7.143287] xe 0000:12:00.0: [drm] Using mailbox commands for power limits
[    7.143727] xe 0000:12:00.0: [drm] PL2 is supported on channel 0
[    7.207372] xe 0000:12:00.0: [drm] Cannot find any crtc or sizes
[    7.239658] xe 0000:12:00.0: [drm] Cannot find any crtc or sizes
[    8.346480] [drm] amdgpu kernel modesetting enabled.
[    8.366716] [drm] Detected VRAM RAM=512M, BAR=512M
[    8.366719] [drm] RAM width 128bits DDR4
[    8.366848] [drm] GART: num cpu pages 262144, num gpu pages 262144
[    8.366950] [drm] PCIE GART of 1024M enabled.
[    8.366953] [drm] PTB located at 0x000000F41FC00000
[    8.369676] amdgpu 0000:30:00.0: amdgpu: [drm] Loading DMUB firmware via PSP: version=0x0101002B
[    8.471729] amdgpu 0000:30:00.0: amdgpu: [drm] Display Core v3.2.351 initialized on DCN 2.1
[    8.471732] amdgpu 0000:30:00.0: amdgpu: [drm] DP-HDMI FRL PCON supported
[    8.472263] amdgpu 0000:30:00.0: amdgpu: [drm] DMUB hardware initialized: version=0x0101002B
[    8.482031] amdgpu 0000:30:00.0: [drm] Registered 4 planes with drm panic
[    8.482033] [drm] Initialized amdgpu 3.64.0 for 0000:30:00.0 on minor 2
[    8.483814] amdgpu 0000:30:00.0: [drm] Cannot find any crtc or sizes
[    8.483832] [drm] pre_validate_dsc:1667 MST_DSC dsc precompute is not needed
[   60.674300] xe 0000:12:00.0: [drm] Tile0: GT0: PF: VF1 provisioned with 4180791296 (3.89 GiB) GGTT
[   60.675215] xe 0000:12:00.0: [drm] Tile0: GT0: PF: VF1 provisioned with 16936599552 (15.8 GiB) LMEM
[   60.675335] xe 0000:12:00.0: [drm] Tile0: GT0: PF: VF1 provisioned with 65278 GuC context IDs
[   60.675411] xe 0000:12:00.0: [drm] Tile0: GT0: PF: VF1 provisioned with 256 GuC doorbell IDs
[   60.675615] xe 0000:12:00.0: [drm] Tile0: GT1: PF: VF1 provisioned with 65279 GuC context IDs
[   60.676056] xe 0000:12:00.0: [drm] Tile0: GT1: PF: VF1 provisioned with 256 GuC doorbell IDs
[   60.780810] xe 0000:12:00.1: [drm] Running in SR-IOV VF mode
[   60.782222] xe 0000:12:00.1: [drm] VF: migration disabled: experimental feature not available on production builds
[   60.798060] xe 0000:12:00.1: [drm] VISIBLE VRAM: 0x0000007800000000, 0x0000000400000000
[   60.798064] xe 0000:12:00.1: [drm] VRAM[0]: Actual physical size 0x00000003f1800000, usable size exclude stolen 0x00000003f1800000, CPU accessible size 0x00000003f1800000
[   60.798067] xe 0000:12:00.1: [drm] VRAM[0]: DPA range: [0x0000000000000000-3f1800000], io range: [0x0000007800000000-7bf1800000]
[   60.798069] xe 0000:12:00.1: [drm] VRAM[0]: Actual physical size 0x00000003f1800000, usable size exclude stolen 0x00000003f1800000, CPU accessible size 0x00000003f1800000
[   60.798071] xe 0000:12:00.1: [drm] VRAM[0]: DPA range: [0x0000000000000000-3f1800000], io range: [0x0000007800000000-7bf1800000]
[   61.055358] xe 0000:12:00.1: [drm] Tile0: GT0: ccs1 fused off
[   61.055363] xe 0000:12:00.1: [drm] Tile0: GT0: ccs2 fused off
[   61.055365] xe 0000:12:00.1: [drm] Tile0: GT0: ccs3 fused off
[   61.064644] xe 0000:12:00.1: [drm] Tile0: GT1: vcs1 fused off
[   61.064648] xe 0000:12:00.1: [drm] Tile0: GT1: vcs3 fused off
[   61.064651] xe 0000:12:00.1: [drm] Tile0: GT1: vcs4 fused off
[   61.064652] xe 0000:12:00.1: [drm] Tile0: GT1: vcs5 fused off
[   61.064654] xe 0000:12:00.1: [drm] Tile0: GT1: vcs6 fused off
[   61.064656] xe 0000:12:00.1: [drm] Tile0: GT1: vcs7 fused off
[   61.064658] xe 0000:12:00.1: [drm] Tile0: GT1: vecs2 fused off
[   61.064660] xe 0000:12:00.1: [drm] Tile0: GT1: vecs3 fused off
[   61.070781] [drm] Initialized xe 1.1.0 for 0000:12:00.1 on minor 3

12:00.0 VGA compatible controller: Intel Corporation Battlemage G21 [Intel Graphics] (prog-if 00 [VGA controller])
	Subsystem: Intel Corporation Device 1114
	Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 0, Cache Line Size: 64 bytes
	Interrupt: pin ? routed to IRQ 208
	IOMMU group: 14
	Region 0: Memory at 7c02000000 (64-bit, prefetchable) [size=16M]
	Region 2: Memory at 7400000000 (64-bit, prefetchable) [size=16G]
	Expansion ROM at fba00000 [disabled] [size=2M]
	Capabilities: [40] Vendor Specific Information: Len=0c <?>
	Capabilities: [70] Express (v2) Endpoint, IntMsgNum 0
		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s unlimited, L1 unlimited
			ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ SlotPowerLimit 0W TEE-IO-
		DevCtl:	CorrErr- NonFatalErr- FatalErr- UnsupReq-
			RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+ FLReset-
			MaxPayload 256 bytes, MaxReadReq 512 bytes
		DevSta:	CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <64ns, L1 <1us
			ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+
		LnkCtl:	ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk-
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed 2.5GT/s, Width x1
			TrErr- Train- SlotClk- DLActive- BWMgmt- ABWMgmt-
		DevCap2: Completion Timeout: Range B, TimeoutDis+ NROPrPrP- LTR+
			 10BitTagComp+ 10BitTagReq+ OBFF Not Supported, ExtFmt+ EETLPPrefix-
			 EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
			 FRS- TPHComp- ExtTPHComp-
			 AtomicOpsCap: 32bit- 64bit- 128bitCAS-
		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-
			 AtomicOpsCtl: ReqEn-
			 IDOReq- IDOCompl- LTR- EmergencyPowerReductionReq-
			 10BitTagReq- OBFF Disabled, EETLPPrefixBlk-
		LnkCap2: Supported Link Speeds: 2.5GT/s, Crosslink- Retimer- 2Retimers- DRS-
		LnkCtl2: Target Link Speed: 2.5GT/s, EnterCompliance- SpeedDis-
			 Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
			 Compliance Preset/De-emphasis: -6dB de-emphasis, 0dB preshoot
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
			 EqualizationPhase2- EqualizationPhase3- LinkEqualizationRequest-
			 Retimer- 2Retimers- CrosslinkRes: unsupported
	Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit+
		Address: 00000000fee00000  Data: 0000
		Masking: 00000000  Pending: 00000000
	Capabilities: [d0] Power Management version 3
		Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold-)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
	Capabilities: [100 v1] Alternative Routing-ID Interpretation (ARI)
		ARICap:	MFVC- ACS-, Next Function: 0
		ARICtl:	MFVC- ACS-, Function Group: 0
	Capabilities: [110 v1] Null
	Capabilities: [200 v1] Address Translation Service (ATS)
		ATSCap:	Invalidate Queue Depth: 00
		ATSCtl:	Enable+, Smallest Translation Unit: 00
	Capabilities: [420 v1] Physical Resizable BAR
		BAR 2: current size: 16GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB
	Capabilities: [220 v1] Virtual Resizable BAR
		BAR 2: current size: 16GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB
	Capabilities: [320 v1] Single Root I/O Virtualization (SR-IOV)
		IOVCap:	Migration- 10BitTagReq+ IntMsgNum 0
		IOVCtl:	Enable+ Migration- Interrupt- MSE+ ARIHierarchy+ 10BitTagReq-
		IOVSta:	Migration-
		Initial VFs: 2, Total VFs: 2, Number of VFs: 1, Function Dependency Link: 00
		VF offset: 1, stride: 1, Device ID: e212
		Supported Page Size: 00000553, System Page Size: 00000001
		Region 0: Memory at 0000007c00000000 (64-bit, prefetchable)
		Region 2: Memory at 0000007800000000 (64-bit, prefetchable)
		VF Migration: offset: 00000000, BIR: 0
	Capabilities: [400 v1] Latency Tolerance Reporting
		Max snoop latency: 0ns
		Max no snoop latency: 0ns
	Kernel driver in use: xe
	Kernel modules: xe

Thank you in advance for the help!

hege · ‎04-13-2026

Hi @CM_Intel ,

I am running Linux 6.18 with latest available firmware from https://gitlab.com/kernel-firmware/linux-firmware/-/tree/main/xe. GuC 70.60.0 and HuC 8.2.10. The system is booting with UEFI with ReBar enabled (as confirmed by lspci below).

I'm attaching SSU output from both the TrueNAS host and the Windows guest with both 8314 (working) 8515 (broken) driver installed.

Here is output from dmesg and lspci -vvv; the xe driver is loaded and fully functional in the host, with ReBAR visible + 1 virtual function also enabled and visible in lspci:

[    6.805823] xe 0000:12:00.0: [drm] Running in SR-IOV PF mode
[    6.805897] xe 0000:12:00.0: [drm] Found battlemage (device ID e212) discrete display version 14.01 stepping B0
[    6.807206] xe 0000:12:00.0: [drm] VISIBLE VRAM: 0x0000007400000000, 0x0000000400000000
[    6.807236] xe 0000:12:00.0: [drm] VRAM[0]: Actual physical size 0x0000000400000000, usable size exclude stolen 0x00000003fb000000, CPU accessible size 0x00000003fb000000
[    6.807239] xe 0000:12:00.0: [drm] VRAM[0]: DPA range: [0x0000000000000000-400000000], io range: [0x0000007400000000-77fb000000]
[    6.807241] xe 0000:12:00.0: [drm] VRAM[0]: Actual physical size 0x0000000400000000, usable size exclude stolen 0x00000003fb000000, CPU accessible size 0x00000003fb000000
[    6.807243] xe 0000:12:00.0: [drm] VRAM[0]: DPA range: [0x0000000000000000-400000000], io range: [0x0000007400000000-77fb000000]
[    6.943819] xe 0000:12:00.0: [drm] Tile0: GT0: Using GuC firmware from xe/bmg_guc_70.bin version 70.60.0
[    6.956341] xe 0000:12:00.0: [drm] Finished loading DMC firmware i915/bmg_dmc.bin (v2.6)
[    7.181383] xe 0000:12:00.0: [drm] Tile0: GT0: ccs1 fused off
[    7.181387] xe 0000:12:00.0: [drm] Tile0: GT0: ccs2 fused off
[    7.181389] xe 0000:12:00.0: [drm] Tile0: GT0: ccs3 fused off
[    7.207215] xe 0000:12:00.0: [drm] Tile0: GT1: Using GuC firmware from xe/bmg_guc_70.bin version 70.60.0
[    7.210132] xe 0000:12:00.0: [drm] Tile0: GT1: Using HuC firmware from xe/bmg_huc.bin version 8.2.10
[    7.220891] xe 0000:12:00.0: [drm] Tile0: GT1: vcs1 fused off
[    7.220894] xe 0000:12:00.0: [drm] Tile0: GT1: vcs3 fused off
[    7.220897] xe 0000:12:00.0: [drm] Tile0: GT1: vcs4 fused off
[    7.220899] xe 0000:12:00.0: [drm] Tile0: GT1: vcs5 fused off
[    7.220901] xe 0000:12:00.0: [drm] Tile0: GT1: vcs6 fused off
[    7.220903] xe 0000:12:00.0: [drm] Tile0: GT1: vcs7 fused off
[    7.220905] xe 0000:12:00.0: [drm] Tile0: GT1: vecs2 fused off
[    7.220907] xe 0000:12:00.0: [drm] Tile0: GT1: vecs3 fused off
[    7.252106] xe 0000:12:00.0: [drm] Can't init xe mei late bind missing mei component
[    7.253935] xe 0000:12:00.0: [drm] Registered 4 planes with drm panic
[    7.253939] [drm] Initialized xe 1.1.0 for 0000:12:00.0 on minor 1

12:00.0 VGA compatible controller: Intel Corporation Battlemage G21 [Intel Graphics] (prog-if 00 [VGA controller])
	Subsystem: Intel Corporation Device 1114
	Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 0, Cache Line Size: 64 bytes
	Interrupt: pin ? routed to IRQ 208
	IOMMU group: 14
	Region 0: Memory at 7c02000000 (64-bit, prefetchable) [size=16M]
	Region 2: Memory at 7400000000 (64-bit, prefetchable) [size=16G]
	Expansion ROM at fba00000 [disabled] [size=2M]
	Capabilities: [40] Vendor Specific Information: Len=0c <?>
	Capabilities: [70] Express (v2) Endpoint, IntMsgNum 0
		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s unlimited, L1 unlimited
			ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ SlotPowerLimit 0W TEE-IO-
		DevCtl:	CorrErr- NonFatalErr- FatalErr- UnsupReq-
			RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+ FLReset-
			MaxPayload 256 bytes, MaxReadReq 512 bytes
		DevSta:	CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <64ns, L1 <1us
			ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+
		LnkCtl:	ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk-
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed 2.5GT/s, Width x1
			TrErr- Train- SlotClk- DLActive- BWMgmt- ABWMgmt-
		DevCap2: Completion Timeout: Range B, TimeoutDis+ NROPrPrP- LTR+
			 10BitTagComp+ 10BitTagReq+ OBFF Not Supported, ExtFmt+ EETLPPrefix-
			 EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
			 FRS- TPHComp- ExtTPHComp-
			 AtomicOpsCap: 32bit- 64bit- 128bitCAS-
		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-
			 AtomicOpsCtl: ReqEn-
			 IDOReq- IDOCompl- LTR- EmergencyPowerReductionReq-
			 10BitTagReq- OBFF Disabled, EETLPPrefixBlk-
		LnkCap2: Supported Link Speeds: 2.5GT/s, Crosslink- Retimer- 2Retimers- DRS-
		LnkCtl2: Target Link Speed: 2.5GT/s, EnterCompliance- SpeedDis-
			 Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
			 Compliance Preset/De-emphasis: -6dB de-emphasis, 0dB preshoot
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
			 EqualizationPhase2- EqualizationPhase3- LinkEqualizationRequest-
			 Retimer- 2Retimers- CrosslinkRes: unsupported
	Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit+
		Address: 00000000fee00000  Data: 0000
		Masking: 00000000  Pending: 00000000
	Capabilities: [d0] Power Management version 3
		Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold-)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
	Capabilities: [100 v1] Alternative Routing-ID Interpretation (ARI)
		ARICap:	MFVC- ACS-, Next Function: 0
		ARICtl:	MFVC- ACS-, Function Group: 0
	Capabilities: [110 v1] Null
	Capabilities: [200 v1] Address Translation Service (ATS)
		ATSCap:	Invalidate Queue Depth: 00
		ATSCtl:	Enable+, Smallest Translation Unit: 00
	Capabilities: [420 v1] Physical Resizable BAR
		BAR 2: current size: 16GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB
	Capabilities: [220 v1] Virtual Resizable BAR
		BAR 2: current size: 16GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB
	Capabilities: [320 v1] Single Root I/O Virtualization (SR-IOV)
		IOVCap:	Migration- 10BitTagReq+ IntMsgNum 0
		IOVCtl:	Enable+ Migration- Interrupt- MSE+ ARIHierarchy+ 10BitTagReq-
		IOVSta:	Migration-
		Initial VFs: 2, Total VFs: 2, Number of VFs: 1, Function Dependency Link: 00
		VF offset: 1, stride: 1, Device ID: e212
		Supported Page Size: 00000553, System Page Size: 00000001
		Region 0: Memory at 0000007c00000000 (64-bit, prefetchable)
		Region 2: Memory at 0000007800000000 (64-bit, prefetchable)
		VF Migration: offset: 00000000, BIR: 0
	Capabilities: [400 v1] Latency Tolerance Reporting
		Max snoop latency: 0ns
		Max no snoop latency: 0ns
	Kernel driver in use: xe
	Kernel modules: xe

12:00.1 VGA compatible controller: Intel Corporation Battlemage G21 [Intel Graphics] (prog-if 00 [VGA controller])
	Subsystem: Intel Corporation Device 1114
	Control: I/O- Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 0
	Interrupt: pin ? routed to IRQ 211
	IOMMU group: 40
	Region 0: Memory at 7c00000000 (64-bit, prefetchable) [disabled] [size=16M]
	Region 2: Memory at 7800000000 (64-bit, prefetchable) [virtual] [size=16G]
	Capabilities: [70] Express (v2) Endpoint, IntMsgNum 0
		DevCap:	MaxPayload 128 bytes, PhantFunc 0, Latency L0s unlimited, L1 unlimited
			ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ SlotPowerLimit 0W TEE-IO-
		DevCtl:	CorrErr- NonFatalErr- FatalErr- UnsupReq-
			RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop- FLReset-
			MaxPayload 128 bytes, MaxReadReq 128 bytes
		DevSta:	CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <64ns, L1 <1us
			ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+
		LnkCtl:	ASPM Disabled; RCB 64 bytes, LnkDisable- CommClk-
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed unknown (downgraded), Width x0 (downgraded)
			TrErr- Train- SlotClk- DLActive- BWMgmt- ABWMgmt-
		DevCap2: Completion Timeout: Range B, TimeoutDis+ NROPrPrP- LTR+
			 10BitTagComp+ 10BitTagReq+ OBFF Not Supported, ExtFmt+ EETLPPrefix-
			 EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
			 FRS- TPHComp- ExtTPHComp-
			 AtomicOpsCap: 32bit- 64bit- 128bitCAS-
		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-
			 AtomicOpsCtl: ReqEn-
			 IDOReq- IDOCompl- LTR- EmergencyPowerReductionReq-
			 10BitTagReq- OBFF Disabled, EETLPPrefixBlk-
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
			 EqualizationPhase2- EqualizationPhase3- LinkEqualizationRequest-
			 Retimer- 2Retimers- CrosslinkRes: unsupported
	Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit+
		Address: 00000000fee00000  Data: 0000
		Masking: 00000000  Pending: 00000000
	Capabilities: [100 v1] Alternative Routing-ID Interpretation (ARI)
		ARICap:	MFVC- ACS-, Next Function: 2
		ARICtl:	MFVC- ACS-, Function Group: 0
	Capabilities: [200 v1] Address Translation Service (ATS)
		ATSCap:	Invalidate Queue Depth: 00
		ATSCtl:	Enable+, Smallest Translation Unit: 00
	Kernel driver in use: vfio-pci
	Kernel modules: xe

For now I keep using the older driver 8314 which continues to work well.

CM_Intel · ‎04-15-2026

Hello Hege,

I hope you’re having a wonderful day.

Thank you for sharing the detailed logs and providing the clarification. I’ll now investigate this further, and I’ll reach out to you as soon as I have more information or next steps to move forward.

If you have any additional observations in the meantime, please feel free to share them.

Thankyou for your patience and understanding.

Best regards,

CM

Intel Customer Support Technician

CM_Intel · ‎04-16-2026

Hello hege,

I hope you are doing well.

Kindly test the issue using graphics driver version 32.0.101.8629 and share the results with us.

You can download the driver from the link below:

https://www.intel.com/content/www/us/en/products/sku/242615/intel-arc-pro-b50-graphics/downloads.ht…

Could you please confirm whether you are experiencing the same issue while using this driver version? If possible, kindly let us know if the behavior remains unchanged or if you observe any difference after testing with this version.

Your confirmation will help us proceed further and assist you accordingly.

Thank you for your cooperation. We look forward to your response.

Best regards,

CM

Intel Customer Support Technician

hege · ‎04-16-2026

Hi @CM_Intel ,

I tried installing the 32.0.101.8629 driver linked above, and it gives the same error. After installing the driver I have hard power cycled the host, and then reinstalled the same driver again, and same problem still.

Not sure if relevant, Event Viewer has the following logs from the display driver and intel app:

{"category":"Igcl","level":"Error","message":"ctlInit, result=1073741825"}
{"category":"Igcl","level":"Error","message":"3rd Party - IGCL ctlInit - Exception"}


Device PCI\VEN_8086&DEV_E212&SUBSYS_11148086&REV_00\4&123cff10&0&000C had a problem starting.

Driver Name: display.inf
Class GUID: {4d36e968-e325-11ce-bfc1-08002be10318}
Service: BasicDisplay
Lower Filters: 
Upper Filters: 
Problem: 0xA
Problem Status: 0xC01E0438

CM_Intel · ‎04-17-2026

Hello hege,

I hope you’re doing well.

Thank you for the detailed update and for testing driver version 32.0.101.8629, including performing the hard power cycle and reinstall attempt. We appreciate the time and effort you’ve taken to try these steps.

We have noted that the issue persists after installation and have also taken into account the Event Viewer errors you shared related to the display driver and Intel application, including the device start failure and associated error codes.

At this point, we would like some additional time to review the provided details and analyze the logs to better understand the behavior you are encountering. Once the review is complete, we will get back to you with an update or the next recommended steps.

Thank you for your continued patience and cooperation. Please feel free to share any additional observations if you notice new behavior in the meantime.

Best regards,

CM

Intel Customer Support Technician

CM_Intel · ‎04-20-2026

Hello hege,

I hope you are doing well.

Thank you for your patience and for sharing the detailed logs and test results. We understand the inconvenience driver‑related issues can cause and truly appreciate the time and effort you’ve put into troubleshooting.

We recommend reviewing the following article, which explains Error Code 43 related to Intel® Graphics and outlines common scenarios in which this issue may occur:

How to Resolve Error Code 43 for Intel® Graphics

We would also like to clarify that your system is currently running a Linux‑based operating system, while the Intel graphics drivers being installed are intended for Windows. Unfortunately, Windows drivers are not compatible with Linux environments, which can explain the installation issues and errors you are experiencing.

For most Linux distributions(Linux* Operating System Vendors), Intel graphics drivers are integrated into the kernel and Mesa stack and are delivered through the distribution’s update system. Because of this, we recommend consulting your distribution’s documentation or community resources for guidance on updating graphics components specific to your environment.

For additional context, you can refer to this Intel support article:

How to Identify & Find Graphics Drivers for Linux*

If you need any further assistance in the future, please feel free to reach out. We’re always happy to help.

Best regards,

CM

Intel Customer Support Technician

hege · ‎04-20-2026

Hi,

this post makes no sense, I'm sorry to say.

I am running a Linux server which uses KVM to virtualize the Windows instance. The whole point of the SR-IOV function in the pro cards is to do just that.

Besides, every driver previously worked well, it's only the latest one that doesn't initialize.

Please do better, responses like "windows drivers aren't supported on Linux" makes me question Intel's commitment to provide technical support.

hege · ‎04-24-2026

Hi @CM_Intel

new pro driver release 32.0.101.8517 - same problem. The driver version 32.0.101.8314 and earlier still work, but anything 8515 or later will cause the virtualized Windows driver to not initialize on my system.

Please help, this makes the card useless, since I won't be able to keep the drivers updated.

CM_Intel · ‎04-27-2026

Hello hege,

Thank you for your patience and continued cooperation.

To help us better understand the observed driver behavior and further analyze the potential regression, we kindly request that you to temporarily disable ATS on the host system. This will help us determine whether ATS is contributing to the issue.

Disable ATS on the Host

- Add the following kernel parameter:

intel_iommu=on,ats=off

- Save the changes and reboot the system.

- After rebooting, please check whether the issue still occurs and share the outcome with us.

Additionally, we recommend testing with the latest available Intel graphics driver. Kindly use the link below to update the graphics drivers:

https://www.intel.com/content/www/us/en/download/741626/intel-arc-pro-graphics-windows.html

Once you have completed the above steps, please let us know the results. This information will be very helpful for our analysis and next steps.

If you have any questions or need assistance, feel free to reach out we’ll be happy to help.

Best regards,

CM

Intel Customer Support Technician

CM_Intel · ‎04-30-2026

Hello hege,

I hope you are doing well.

I’m writing to follow up on our previous communication regarding the requested configuration changes. We wanted to check if you’ve had an opportunity to review or complete the steps shared earlier, or if there’s anything we can assist with.

Your feedback and observations will help us continue our analysis and determine the next appropriate steps.

Please let us know once you’ve had a chance to proceed, or feel free to reach out if you have any questions or need further clarification. We’re happy to help.

Thank you for your time and continued cooperation. We look forward to your update.

Best regards,

CM

Intel Customer Support Technician