Pre-submission Checklist
GPU Hardware
Intel Arc Pro B70
DRI Devices Information
$ ls -ls /dev/dri/*
0 crw-rw----+ 1 root video 226, 0 Aug 31 19:00 /dev/dri/card0
0 crw-rw----+ 1 root render 226, 128 Aug 31 19:00 /dev/dri/renderD128
/dev/dri/by-path:
total 0
0 lrwxrwxrwx 1 root root 8 Aug 31 19:00 pci-0000:0b:00.0-card -> ../card0
0 lrwxrwxrwx 1 root root 13 Aug 31 19:00 pci-0000:0b:00.0-render -> ../renderD128
GPU Detailed Information (lspci output)
$ sudo lspci -vvv -k -s 0000:0b:00.0
0b:00.0 VGA compatible controller: Intel Corporation Battlemage G31 [Arc Pro B70] (prog-if 00 [VGA controller])
Subsystem: Intel Corporation Device 1701
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 82
Region 0: Memory at 27fb000000 (64-bit, prefetchable) [size=16M]
Region 2: Memory at 2800000000 (64-bit, prefetchable) [size=32G]
Expansion ROM at fc200000 [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 Disabled; 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: 00000000fee0b000 Data: 0022
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: 32GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB 32GB
Capabilities: [220 v1] Virtual Resizable BAR
BAR 2: current size: 8GB, supported: 256MB 512MB 1GB 2GB 4GB 8GB 16GB 32GB
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: 4, Total VFs: 4, Number of VFs: 0, Function Dependency Link: 00
VF offset: 1, stride: 1, Device ID: e223
Supported Page Size: 00000553, System Page Size: 00000001
Region 0: Memory at 00000027fc000000 (64-bit, prefetchable)
Region 2: Memory at 0000003000000000 (64-bit, prefetchable)
VF Migration: offset: 00000000, BIR: 0
Capabilities: [400 v1] Latency Tolerance Reporting
Max snoop latency: 1048576ns
Max no snoop latency: 1048576ns
Kernel driver in use: xe
Kernel modules: xe
Driver Version
26.31.39395.13
Installed GPU Driver Packages
$ dpkg -l | grep 'igc|gmm|opencl|level.zero|libze|ocloc'
ii level-zero 1.26.0 amd64 oneAPI Level Zero
ii libclc-21 1:21.1.8-7 all OpenCL C language implementation - platform support
ii libclc-21-dev 1:21.1.8-7 all OpenCL C language implementation - development files
ii libigc1:amd64 1.0.17791.18+1-3 amd64 Intel graphics compiler for OpenCL -- core libs
ii libigc2:amd64 2.28.4-4 amd64 Intel graphics compiler for OpenCL -- core libs
ii libigdfcl1:amd64 1.0.17791.18+1-3 amd64 Intel graphics compiler for OpenCL -- OpenCL library
ii libigdfcl2:amd64 2.28.4-4 amd64 Intel graphics compiler for OpenCL -- OpenCL library
ii libigdgmm12:amd64 22.10.0 amd64 Intel Graphics Memory Management Library -- shared library
ii libze-dev:amd64 1.20.6-1 amd64 oneAPI Level Zero -- development files
ii libze-intel-gpu-legacy1-1 24.35.30872.45-1 amd64 Intel oneAPI L0 support implementation for Intel legacy GPUs
ii libze-intel-gpu1 26.31.39395.13-0 amd64 Intel(R) Graphics Compute Runtime for oneAPI Level Zero.
ri libze1:amd64 1.20.6-1 amd64 oneAPI Level Zero -- share libraries
ii libzen0t64:amd64 0.4.41-2.1+b1 amd64 ZenLib C++ utility library -- runtime
ii mesa-opencl-icd:amd64 26.1.4-1 amd64 free implementation of the OpenCL API -- ICD runtime
ii ocl-icd-libopencl1:amd64 2.3.3-1 amd64 Generic OpenCL ICD Loader
ii ocl-icd-libopencl1:i386 2.3.3-1 i386 Generic OpenCL ICD Loader
ii ocl-icd-opencl-dev:amd64 2.3.3-1 amd64 OpenCL development files
ii opencl-c-headers 3.0~2024.10.24-2 all OpenCL (Open Computing Language) C header files
ii opencl-clhpp-headers 3.0~2024.10.24-2 all C++ headers for OpenCL development
ii opencl-headers 3.0~2024.10.24-2 all OpenCL (Open Computing Language) header files
Driver Installation Details
- Installed from the latest release from this github repo
- Downloaded DPKG files and installed via
apt
Linux Distribution
Other (please specify below)
Other Linux Distribution
Debian 13
Kernel Version & Boot Parameters
$ uname -r
7.1.6+deb14-amd64
$ cat /proc/cmdline
initrd=\0ef4ac2994a74d269d2edfcd92e65113\7.1.6+deb14-amd64\initrd.img-7.1.6+deb14-amd64 root=ZFS=rpool/buster/debian-1 ro quiet clearcpuid=514 amd_iommu=1 iommu=pt nouveau.config=NvGspRm=1 systemd.machine_id=0ef4ac2994a74d269d2edfcd92e65113
$ lsmod | rg 'i915|xe'
xe 4608000 10
intel_vsec 28672 2 pmt_telemetry,xe
drm_gpuvm 57344 1 xe
configfs 65536 2 xe
drm_gpusvm_helper 61440 1 xe
drm_buddy 12288 1 xe
gpu_sched 69632 1 xe
drm_ttm_helper 20480 1 xe
ttm 159744 2 drm_ttm_helper,xe
video 81920 1 xe
drm_exec 12288 2 drm_gpuvm,xe
i2c_algo_bit 16384 1 xe
drm_suballoc_helper 24576 1 xe
drm_display_helper 311296 1 xe
cec 81920 2 drm_display_helper,xe
drm_client_lib 16384 1 xe
drm_kms_helper 266240 4 drm_display_helper,drm_ttm_helper,drm_client_lib,xe
drm 929792 17 gpu_sched,drm_kms_helper,drm_exec,drm_gpuvm,drm_suballoc_helper,drm_display_helper,drm_buddy,drm_gpusvm_helper,drm_ttm_helper,drm_client_lib,xe,ttm
Actual Behavior
I've written up a gist with a minimal repro that showcases the hang between 15-45% of the time for me. Full details at https://gist.github.com/clee/6d721b381c4a744aab90739a02a4e378
Short version: Using only liblz and ngen, sometimes my code works when trying to access memory and sometimes it causes DEVICE_LOST.
Expected Behavior
The program should never crash with DEVICE_LOST.
Reproduction Rate
Rarely reproduces ~ 26% - 49%
Steps to Reproduce
Please see the full gist.
Is this a regression?
Last Known Working Driver Version
No response
First Known Failing Driver Version
No response
API Call Logs
No response
strace Logs
No response
System Logs / dmesg Output
$ sudo dmesg | grep -i -E 'xe|drm|gpu'
[ 79.482080] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482088] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482115] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482124] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482128] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482142] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482145] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482154] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482163] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482167] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482177] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482192] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482200] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482204] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482208] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482211] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482229] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482243] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482254] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482260] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482265] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482268] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482292] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482296] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482316] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482319] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482323] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482325] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482351] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482354] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482391] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482394] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482399] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482404] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482450] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482469] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482511] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482517] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482522] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482525] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482558] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482589] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482692] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482695] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482699] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482701] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482724] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482727] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482749] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482752] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482756] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482758] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482781] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482784] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482803] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482806] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482810] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482813] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482840] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482842] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482859] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482862] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482865] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482868] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482887] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482904] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482910] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482913] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482917] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482919] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482938] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482958] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.482964] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482967] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482971] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.482974] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.482997] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483013] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483019] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483021] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483025] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483028] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483049] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483067] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483073] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483076] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483080] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483083] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483114] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483117] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483126] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483129] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483132] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483135] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483181] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483201] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine memory CAT error [18]: class=ccs, logical_mask: 0x1, guc_id=11
[ 79.483229] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483232] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.483249] xe 0000:0b:00.0: [drm] Tile0: GT0:
[ 79.483252] xe 0000:0b:00.0: [drm] Tile0: GT0: Fault response: Unsuccessful -EIO
[ 79.484524] xe 0000:0b:00.0: [drm] Tile0: GT0: Engine reset: engine_class=ccs, logical_mask: 0x1, guc_id=11, state=0x
249
[ 79.484530] xe 0000:0b:00.0: [drm] Tile0: GT0: Timedout job: seqno=4294967169, lrc_seqno=4294967169, guc_id=11, flags
=0x20 in pte_flake_repro [9636]
[ 79.523205] xe 0000:0b:00.0: [drm] Xe device coredump has been created
[ 79.523207] xe 0000:0b:00.0: [drm] Check your /sys/class/drm/card0/device/devcoredump/data
[ 81.533690] xe 0000:0b:00.0: [drm] exec queue reset detected
Backtrace (if crash or hang occurred)
No response
Source Code / Reproducer
https://gist.github.com/clee/6d721b381c4a744aab90739a02a4e378
Command Line / Application Details
c++ -std=c++17 -O2 pte_flake_repro.cpp -lze_loader -o pte_flake_repro
./pte_flake_repro # (repeatedly)
oneAPI Version (if applicable)
N/A
Screenshots / Video
No response
Additional Notes
No response
Pre-submission Checklist
GPU Hardware
Intel Arc Pro B70
DRI Devices Information
GPU Detailed Information (lspci output)
Driver Version
26.31.39395.13
Installed GPU Driver Packages
Driver Installation Details
aptLinux Distribution
Other (please specify below)
Other Linux Distribution
Debian 13
Kernel Version & Boot Parameters
Actual Behavior
I've written up a gist with a minimal repro that showcases the hang between 15-45% of the time for me. Full details at https://gist.github.com/clee/6d721b381c4a744aab90739a02a4e378
Short version: Using only liblz and ngen, sometimes my code works when trying to access memory and sometimes it causes DEVICE_LOST.
Expected Behavior
The program should never crash with DEVICE_LOST.
Reproduction Rate
Rarely reproduces ~ 26% - 49%
Steps to Reproduce
Please see the full gist.
Is this a regression?
Last Known Working Driver Version
No response
First Known Failing Driver Version
No response
API Call Logs
No response
strace Logs
No response
System Logs / dmesg Output
Backtrace (if crash or hang occurred)
No response
Source Code / Reproducer
https://gist.github.com/clee/6d721b381c4a744aab90739a02a4e378
Command Line / Application Details
oneAPI Version (if applicable)
N/A
Screenshots / Video
No response
Additional Notes
No response