Hey,
running view sapphire RX cards with AMDGPU-Pro 16.30.3 (linux) and on view cards i always get erros like
Nov 22 21:14:00 r7-5-3 kernel: [ 111.798083] amdgpu 0000:05:00.0: GPU fault detected: 147 0x00004402
kernel: [ 111.798108] amdgpu 0000:05:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00000000
kernel: [ 111.798129] amdgpu 0000:05:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A044002
kernel: [ 111.798151] VM fault (0x02, vmid 5) at page 0, read from 'TC5' (0x54433500) (68)
[ 429.602658] amdgpu 0000:06:00.0: IH ring buffer overflow (0x00080DE0, 0x00000EA0, 0x00000DF0)
looking for the rootcause.
Ubuntu 16.04
kernel 4.4.0-31
AMDGPU-Pro 16.30.3
first one i see. Is someone useing OpenCL 2.0 on these cards and driver ? my clinfo returns OpenCL1.2 on all Cards
Name: Ellesmere
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 2117.7 (VM)
running view sapphire RX cards with AMDGPU-Pro 16.30.3 (linux) and on view cards i always get erros like
Nov 22 21:14:00 r7-5-3 kernel: [ 111.798083] amdgpu 0000:05:00.0: GPU fault detected: 147 0x00004402
kernel: [ 111.798108] amdgpu 0000:05:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00000000
kernel: [ 111.798129] amdgpu 0000:05:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A044002
kernel: [ 111.798151] VM fault (0x02, vmid 5) at page 0, read from 'TC5' (0x54433500) (68)
[ 429.602658] amdgpu 0000:06:00.0: IH ring buffer overflow (0x00080DE0, 0x00000EA0, 0x00000DF0)
looking for the rootcause.
Ubuntu 16.04
kernel 4.4.0-31
AMDGPU-Pro 16.30.3
first one i see. Is someone useing OpenCL 2.0 on these cards and driver ? my clinfo returns OpenCL1.2 on all Cards
Name: Ellesmere
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 2117.7 (VM)