Hard to understand info message: amdgpu 0000:05:00.0: amdgpu: SE 1, SH per SE 1, CU per SH 6, active_cu_number 6
Linux 5.17-rc5 (and before) logs the informational message below:
amdgpu 0000:05:00.0: amdgpu: SE 1, SH per SE 1, CU per SH 6, active_cu_number 6
Currently, most users will not know what these terms mean. The active_cu_number is also inconsistent with the format in the beginning. Should that be a debug message instead, or can the informational message made more understandable?
PS: More Linux log messages:
$ dmesg
[ 0.000000] Linux version 5.17.0-rc5.mx64.428 (root@theinternet.molgen.mpg.de) (gcc (GCC) 7.5.0, GNU ld (GNU Binutils) 2.37) #1 SMP PREEMPT Mon Feb 21 04:00:47 CET 2022
[ 0.000000] Command line: BOOT_IMAGE=/boot/bzImage-5.17.0-rc5.mx64.428 root=LABEL=root ro crashkernel=64G-:256M console=ttyS0,115200n8 console=tty0 init=/bin/systemd audit=0 random.trust_cpu=on systemd.unified_cgroup_hierarchy apic=verbose
[…]
[ 23.531934] [drm] amdgpu kernel modesetting enabled.
[…]
[ 23.637725] [drm] add ip block number 4 <si_dma>
[ 23.643371] [drm] add ip block number 5 <si_dpm>
[ 23.648796] [drm] add ip block number 6 <dce_v6_0>
[ 23.654516] [drm] add ip block number 7 <uvd_v3_1>
[ 23.660329] kfd kfd: amdgpu: OLAND not supported in kfd
[ 23.666580] amdgpu 0000:05:00.0: amdgpu: Fetched VBIOS from VFCT
[ 23.673669] amdgpu: ATOM BIOS: 113-C8690300-106
[ 23.679366] [drm] vm size is 64 GB, 2 levels, block size is 10-bit, fragment size is 9-bit
[ 23.814666] amdgpu 0000:05:00.0: amdgpu: VRAM: 2048M 0x000000F400000000 - 0x000000F47FFFFFFF (2048M used)
[ 23.826862] amdgpu 0000:05:00.0: amdgpu: GART: 1024M 0x000000FF00000000 - 0x000000FF3FFFFFFF
[ 23.837606] [drm] Detected VRAM RAM=2048M, BAR=256M
[ 23.843450] [drm] RAM width 64bits GDDR5
[ 23.851051] [drm] amdgpu: 2048M of VRAM memory ready
[ 23.856861] [drm] amdgpu: 3072M of GTT memory ready.
[ 23.862716] [drm] GART: num cpu pages 262144, num gpu pages 262144
[ 23.872033] amdgpu 0000:05:00.0: amdgpu: PCIE GART of 1024M enabled (table at 0x000000F40057F000).
[ 24.139617] [drm] Internal thermal controller with fan control
[ 24.147118] [drm] amdgpu: dpm initialized
[ 24.152336] [drm] AMDGPU Display Connectors
[ 24.157342] [drm] Connector 0:
[ 24.161118] [drm] DP-1
[ 24.164095] [drm] HPD1
[ 24.167227] [drm] DDC: 0x1950 0x1950 0x1951 0x1951 0x1952 0x1952 0x1953 0x1953
[ 24.176352] [drm] Encoders:
[ 24.180145] [drm] DFP1: INTERNAL_UNIPHY
[ 24.185486] [drm] Connector 1:
[ 24.189408] [drm] DVI-I-1
[ 24.193018] [drm] HPD2
[ 24.196262] [drm] DDC: 0x194c 0x194c 0x194d 0x194d 0x194e 0x194e 0x194f 0x194f
[ 24.205320] [drm] Encoders:
[ 24.205322] [drm] DFP2: INTERNAL_UNIPHY
[ 24.205324] [drm] CRT1: INTERNAL_KLDSCP_DAC1
[ 24.233439] [drm] Found UVD firmware Version: 64.0 Family ID: 13
[ 24.242530] [drm] PCIE gen 3 link speeds already enabled
[ 25.601170] [drm] UVD initialized successfully.
[ 25.606940] amdgpu 0000:05:00.0: amdgpu: SE 1, SH per SE 1, CU per SH 6, active_cu_number 6
[ 27.600470] [drm] Initialized amdgpu 3.44.0 20150101 for 0000:05:00.0 on minor 0