我已经确认我本人能力无法解决这个问题，所以求助。

荣耀X16锐龙版，AMD R5 7640HS，显卡随机崩溃，具体表现为界面卡死，一段时间后图形化界面重启，有时能保留前端程序，有时不保留，但是不需要系统重启。经验证，该问题在windows和linux下都可以稳定复现。游戏测试下可以短时间复现，非游戏状态下也概率出现，给出Debian13下的关于崩溃时间点amdgpu的内核日志，我本人无法解决。

\[ 9967.231225\] amdgpu 0000:c2:00.0: amdgpu: Dumping IP State
\[ 9967.232108\] amdgpu 0000:c2:00.0: amdgpu: Dumping IP State Completed
\[ 9967.242230\] amdgpu 0000:c2:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=1109893, emitted seq=1109895
\[ 9967.242237\] amdgpu 0000:c2:00.0: amdgpu: Process information: process firefox-esr pid 7709 thread firefox-es:cs0 pid 7797
\[ 9969.246127\] amdgpu 0000:c2:00.0: amdgpu: MES failed to respond to msg=RESET
\[ 9969.246141\] \[drm:amdgpu_mes_reset_legacy_queue \[amdgpu\]\] *ERROR* failed to reset legacy queue
\[ 9969.246682\] amdgpu 0000:c2:00.0: amdgpu: GPU reset begin!
\[ 9971.322177\] amdgpu 0000:c2:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
\[ 9971.322192\] \[drm:amdgpu_mes_unmap_legacy_queue \[amdgpu\]\] *ERROR* failed to unmap legacy queue
\[ 9971.565047\] \[drm:gfx_v11_0_hw_fini \[amdgpu\]\] *ERROR* failed to halt cp gfx
\[ 9971.566631\] amdgpu 0000:c2:00.0: amdgpu: MODE2 reset
\[ 9971.601841\] amdgpu 0000:c2:00.0: amdgpu: GPU reset succeeded, trying to resume
\[ 9971.602613\] \[drm\] PCIE GART of 512M enabled (table at 0x0000008000900000).
\[ 9971.602655\] amdgpu 0000:c2:00.0: amdgpu: SMU is resuming…
\[ 9971.604018\] amdgpu 0000:c2:00.0: amdgpu: SMU is resumed successfully!
\[ 9971.612578\] \[drm\] DMUB hardware initialized: version=0x08004E00
\[ 9971.915318\] amdgpu 0000:c2:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
\[ 9971.915331\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
\[ 9971.915336\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
\[ 9971.915340\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
\[ 9971.915344\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
\[ 9971.915347\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
\[ 9971.915350\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
\[ 9971.915354\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
\[ 9971.915357\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
\[ 9971.915361\] amdgpu 0000:c2:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
\[ 9971.915365\] amdgpu 0000:c2:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
\[ 9971.915369\] amdgpu 0000:c2:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
\[ 9971.915373\] amdgpu 0000:c2:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
\[ 9971.918776\] amdgpu 0000:c2:00.0: amdgpu: GPU reset(1) succeeded!
\[ 9971.998163\] \[drm:amdgpu_cs_ioctl \[amdgpu\]\] *ERROR* Failed to initialize parser -125!
\[10074.242442\] amdgpu 0000:c2:00.0: amdgpu: Dumping IP State
\[10074.243618\] amdgpu 0000:c2:00.0: amdgpu: Dumping IP State Completed
\[10074.253643\] amdgpu 0000:c2:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=1134226, emitted seq=1134228
\[10074.253648\] amdgpu 0000:c2:00.0: amdgpu: Process information: process firefox-esr pid 7709 thread firefox-es:cs0 pid 7797
\[10076.257487\] amdgpu 0000:c2:00.0: amdgpu: MES failed to respond to msg=RESET
\[10076.257500\] \[drm:amdgpu_mes_reset_legacy_queue \[amdgpu\]\] *ERROR* failed to reset legacy queue
\[10076.257954\] amdgpu 0000:c2:00.0: amdgpu: GPU reset begin!
\[10078.327547\] amdgpu 0000:c2:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
\[10078.327569\] \[drm:amdgpu_mes_unmap_legacy_queue \[amdgpu\]\] *ERROR* failed to unmap legacy queue
\[10078.637761\] \[drm:gfx_v11_0_hw_fini \[amdgpu\]\] *ERROR* failed to halt cp gfx
\[10078.639699\] amdgpu 0000:c2:00.0: amdgpu: MODE2 reset
\[10078.673762\] amdgpu 0000:c2:00.0: amdgpu: GPU reset succeeded, trying to resume
\[10078.674719\] \[drm\] PCIE GART of 512M enabled (table at 0x0000008000900000).
\[10078.674776\] amdgpu 0000:c2:00.0: amdgpu: SMU is resuming…
\[10078.675936\] amdgpu 0000:c2:00.0: amdgpu: SMU is resumed successfully!
\[10078.683316\] \[drm\] DMUB hardware initialized: version=0x08004E00
\[10078.981878\] amdgpu 0000:c2:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
\[10078.981895\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
\[10078.981901\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
\[10078.981906\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
\[10078.981910\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
\[10078.981914\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
\[10078.981918\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
\[10078.981922\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
\[10078.981927\] amdgpu 0000:c2:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
\[10078.981931\] amdgpu 0000:c2:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
\[10078.981936\] amdgpu 0000:c2:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
\[10078.981940\] amdgpu 0000:c2:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
\[10078.981945\] amdgpu 0000:c2:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
\[10078.986323\] amdgpu 0000:c2:00.0: amdgpu: GPU reset(2) succeeded!
\[10079.052941\] \[drm:amdgpu_cs_ioctl \[amdgpu\]\] *ERROR* Failed to initialize parser -125!