Intel® Gaudi® AI Accelerator
Support for the Intel® Gaudi® AI Accelerator
Ankündigungen
FPGA community forums and blogs on community.intel.com are migrating to the new Altera Community and are read-only. For urgent support needs during this transition, please visit the FPGA Design Resources page or contact an Altera Authorized Distributor.
22 Diskussionen

Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2) on gaudi1 system

Tore
Anfänger
1.539Aufrufe

Hi,

     upgraded our system and I have missing firmware.

     Kernel 5.15.0-153-generic   habanalabs driver 1.22.0-740

 

     Any idea whats going on?   Bug?

 


root@h001:~# dkms status habanalabs
habanalabs/1.22.0-740, 5.15.0-153-generic, x86_64: installed


[ 28.293367] BOOT_IMAGE=images/default-habana-image-u22.04.4LTS/vmlinuz
[ 110.523175] habanalabs_compat: loading module, version: 1.22.0-5f8fa9f
[ 110.660579] habanalabs_cn: loading driver, version: 1.22.0-5f8fa9f
[ 110.691684] habanalabs_en: loading driver, version: 1.22.0-5f8fa9f
[ 110.775942] habanalabs_ib: loading driver, version: 1.22.0-5f8fa9f
[ 111.461747] habanalabs: loading driver, version: 1.22.0-5f8fa9f
[ 111.462004] habanalabs 0000:1a:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462040] habanalabs 0000:b3:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462102] habanalabs 0000:1a:00.0: enabling device (0140 -> 0142)
[ 111.462128] habanalabs 0000:1a:00.0: PCI INT A: no GSI
[ 111.462148] habanalabs 0000:b3:00.0: enabling device (0140 -> 0142)
[ 111.462179] habanalabs 0000:b3:00.0: PCI INT A: no GSI
[ 111.462231] habanalabs 0000:33:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462320] habanalabs 0000:33:00.0: enabling device (0140 -> 0142)
[ 111.462340] habanalabs 0000:33:00.0: PCI INT A: no GSI
[ 111.462343] habanalabs 0000:b4:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462413] habanalabs 0000:34:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462428] habanalabs 0000:b4:00.0: enabling device (0140 -> 0142)
[ 111.462442] habanalabs 0000:b4:00.0: PCI INT A: no GSI
[ 111.462535] habanalabs 0000:34:00.0: enabling device (0140 -> 0142)
[ 111.462550] habanalabs 0000:34:00.0: PCI INT A: no GSI
[ 111.462556] habanalabs 0000:cc:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462640] habanalabs 0000:cc:00.0: enabling device (0140 -> 0142)
[ 111.462660] habanalabs 0000:cc:00.0: PCI INT A: no GSI
[ 111.462680] habanalabs 0000:19:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462763] habanalabs 0000:19:00.0: enabling device (0140 -> 0142)
[ 111.462780] habanalabs 0000:19:00.0: PCI INT A: no GSI
[ 111.462788] habanalabs 0000:cd:00.0: habanalabs device found [1da3:1000] (rev 1)
[ 111.462872] habanalabs 0000:cd:00.0: enabling device (0140 -> 0142)
[ 111.462887] habanalabs 0000:cd:00.0: PCI INT A: no GSI
[ 111.487530] habanalabs 0000:b4:00.0: Loading firmware to device, may take some time...
[ 111.487612] habanalabs 0000:b3:00.0: Loading firmware to device, may take some time...
[ 111.509206] habanalabs 0000:1a:00.0: Loading firmware to device, may take some time...
[ 111.509216] habanalabs 0000:34:00.0: Loading firmware to device, may take some time...
[ 111.509223] habanalabs 0000:19:00.0: Loading firmware to device, may take some time...
[ 111.509288] habanalabs 0000:33:00.0: Loading firmware to device, may take some time...
[ 111.509675] habanalabs 0000:cc:00.0: Loading firmware to device, may take some time...
[ 111.509757] habanalabs 0000:cd:00.0: Loading firmware to device, may take some time...
[ 111.559064] accel accel3: Direct firmware load for habanalabs/gaudi/gaudi-boot-fit.itb failed with error -2
[ 111.559072] habanalabs 0000:b4:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.570651] habanalabs 0000:b4:00.0: failed to load boot fit
[ 111.577289] habanalabs 0000:b4:00.0: failed to initialize CPU
[ 111.577927] habanalabs 0000:33:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.584004] habanalabs 0000:b4:00.0: failed to initialize the H/W
[ 111.595643] habanalabs 0000:33:00.0: failed to load boot fit
[ 111.602809] habanalabs 0000:b3:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.609487] habanalabs 0000:33:00.0: failed to initialize CPU
[ 111.621122] habanalabs 0000:b3:00.0: failed to load boot fit
[ 111.621129] habanalabs 0000:b3:00.0: failed to initialize CPU
[ 111.627964] habanalabs 0000:33:00.0: failed to initialize the H/W
[ 111.634676] habanalabs 0000:b3:00.0: failed to initialize the H/W
[ 111.643585] accel accel7: Direct firmware load for habanalabs/gaudi/gaudi-boot-fit.itb failed with error -2
[ 111.650551] habanalabs: Failed to initialize accel2. Device 0000:33:00.0 is NOT usable!
[ 111.656637] habanalabs 0000:cd:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.665498] habanalabs 0000:1a:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.677232] habanalabs 0000:cd:00.0: failed to load boot fit
[ 111.689074] habanalabs 0000:1a:00.0: failed to load boot fit
[ 111.689082] habanalabs 0000:1a:00.0: failed to initialize CPU
[ 111.695945] habanalabs 0000:cd:00.0: failed to initialize CPU
[ 111.702795] habanalabs 0000:1a:00.0: failed to initialize the H/W
[ 111.709720] habanalabs 0000:cd:00.0: failed to initialize the H/W
[ 111.716636] habanalabs 0000:34:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.723916] habanalabs 0000:cc:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.731184] habanalabs 0000:34:00.0: failed to load boot fit
[ 111.742925] habanalabs 0000:cc:00.0: failed to load boot fit
[ 111.754652] habanalabs 0000:34:00.0: failed to initialize CPU
[ 111.761379] habanalabs 0000:cc:00.0: failed to initialize CPU
[ 111.768093] habanalabs 0000:34:00.0: failed to initialize the H/W
[ 111.774910] habanalabs 0000:cc:00.0: failed to initialize the H/W
[ 111.781715] habanalabs 0000:19:00.0: Firmware file habanalabs/gaudi/gaudi-boot-fit.itb is not found! (error -2)
[ 111.789027] habanalabs: Failed to initialize accel1. Device 0000:b3:00.0 is NOT usable!
[ 111.796082] habanalabs 0000:19:00.0: failed to load boot fit
[ 111.807828] habanalabs: Failed to initialize accel3. Device 0000:b4:00.0 is NOT usable!
[ 111.817047] habanalabs 0000:19:00.0: failed to initialize CPU
[ 111.839997] habanalabs 0000:19:00.0: failed to initialize the H/W
[ 111.848377] habanalabs: Failed to initialize accel0. Device 0000:1a:00.0 is NOT usable!
[ 111.856361] habanalabs: Failed to initialize accel7. Device 0000:cd:00.0 is NOT usable!
[ 111.857859] habanalabs: Failed to initialize accel4. Device 0000:34:00.0 is NOT usable!
[ 111.867198] habanalabs: Failed to initialize accel5. Device 0000:cc:00.0 is NOT usable!
[ 111.876500] habanalabs: Failed to initialize accel6. Device 0000:19:00.0 is NOT usable!

0 Kudos
3 Antworten
Tore
Anfänger
1.534Aufrufe
root@h001:~# dpkg -l |grep -i habanalabs
ii  habanalabs-container-runtime              1.22.0-740                                  amd64        HABANA container runtime
ii  habanalabs-dkms                           1.22.0-740                                  all          Habanalabs driver package for processing accelerators
ii  habanalabs-firmware                       1.22.0-740                                  amd64        Firmware package for Habanalabs processing accelerators
ii  habanalabs-firmware-odm                   1.22.0-740                                  amd64        Firmware ODM package for Habana Labs processing accelerators
ii  habanalabs-firmware-tools                 1.22.0-740                                  amd64        Firmware tools package for Habana Labs processing accelerators
ii  habanalabs-graph                          1.22.0-740                                  amd64        Graph compiler package for Habanalabs processing accelerators
ii  habanalabs-hypervisor-msv                 1.22.0-740                                  all          Hypervisor memory scrubbing validator package for Habana Labs
ii  habanalabs-hypervisor-utils               1.22.0-740                                  amd64        Hypervisor utils package for Habana Labs processing accelerators
ii  habanalabs-perf-test                      1.22.0-740                                  amd64        Simple bare-metal application written in C to perform ping-pong
ii  habanalabs-qual                           1.22.0-740                                  amd64        Qual package for Habanalabs processing accelerators
ii  habanalabs-qual-workloads                 1.22.0-740                                  all          Habanalabs qual workloads data files
ii  habanalabs-rdma-core                      1.22.0-740                                  all          rdma-core package for Habanalabs processing accelerators
ii  habanalabs-thunk                          1.22.0-740                                  all          Thunk package for Habanalabs processing accelerators
Tore
Anfänger
1.532Aufrufe

 What is the last dkms supporting Gaudi1 devices?  

root@h001:~# dpkg -L habanalabs-firmware
/lib
/lib/firmware
/lib/firmware/habanalabs
/lib/firmware/habanalabs/gaudi2
/lib/firmware/habanalabs/gaudi2/gaudi2-boot-fit.itb
/lib/firmware/habanalabs/gaudi2/gaudi2-fit.itb
/lib/firmware/habanalabs/gaudi3
/lib/firmware/habanalabs/gaudi3/gaudi3-boot-fit.itb
/usr
/usr/share
/usr/share/doc
/usr/share/doc/habanalabs-firmware
/usr/share/doc/habanalabs-firmware/copyright
/usr/share/doc/habanalabs-firmware/third-party-programs.txt
/usr/share/lintian
/usr/share/lintian/overrides
/usr/share/lintian/overrides/habanalabs-firmware

 

Tore
Anfänger
1.488Aufrufe

Is Gaudi1 deprecated in 1.22.0 and later?   Last gaudi1 firmware seem to be in the 1.21.4-3 release.

 

dpkg: warning: downgrading habanalabs-firmware from 1.22.0-740 to 1.21.4-3

 

Antworten