Maratyszcza / NNPACK

Acceleration package for neural networks on multi-core CPUs
BSD 2-Clause "Simplified" License
1.67k stars 317 forks source link

NNPack is not supported here! #150

Closed obendidi closed 5 years ago

obendidi commented 6 years ago

Hello,

I'm trying to run a caffe2 model in lambda , but I get the following error :

Error in cpuinfo: failed to parse the list of possible procesors in /sys/devices/system/cpu/possible Error in cpuinfo: failed to parse the list of present procesors in /sys/devices/system/cpu/present RuntimeError: [enforce fail at conv_op.cc:24] nnpack_status == nnp_status_success. NNPack is not supported here!Error from operator: input: "data" input: "conv1_w" input: "res_conv1_bn_b" output: "conv1" name: "" type: "Conv" arg { name: "kernel" i: 7 } arg { name: "exhaustive_search" i: 0 } arg { name: "pad" i: 3 } arg { name: "order" s: "NCHW" } arg { name: "stride" i: 2 } device_option {} engine: "NNPACK"

I'm building caffe2 using the following cmake config :

cmake -DUSE_GFLAGS=OFF \ -DUSE_GLOG=OFF \ -DBUILD_SHARED_LIBS=OFF \ -DCMAKE_INSTALL_PREFIX="/cf2/" \ -DCMAKE_PREFIX_PATH="/cf2/" \ -DUSE_GLOO=OFF \ -DUSE_CUDA=OFF \ -DUSE_MPI=OFF \ -DUSE_METAL=OFF \ -DUSE_NCCL=OFF \ -DUSE_MOBILE_OPENGL=OFF \ -DBUILD_CUSTOM_PROTOBUF=OFF \ -DUSE_LEVELDB=OFF \ -DUSE_LMDB=OFF \ -DUSE_NUMA=OFF \ -DUSE_OPENCV=OFF \ -DUSE_NCCL=OFF \ ..

thanks !

Maratyszcza commented 6 years ago

The error originated not in NNPACK, but in cpuinfo library. Apparently, the files /sys/devices/system/cpu/present and /sys/devices/system/cpu/possible are not available on this system, which is unusual. Could you post a dump of /sys/devices/system/cpu/ tree on this system?

obendidi commented 6 years ago

No such file or directory: '/sys/devices/system/cpu/', I'm running this on amazon lambda function , so I guess it's normal to not have access to the cpuinfo

Maratyszcza commented 6 years ago

Is sysfs mounted on this system?

VisionZQ commented 5 years ago

I also meet the same issue. Can you give me some suggestion?

/sys/devices/system/cpu/
|-- cpu0
|   |-- cache
|   |   |-- index0
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index1
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index2
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index3
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- power
|   |   |   |-- async
|   |   |   |-- autosuspend_delay_ms
|   |   |   |-- control
|   |   |   |-- runtime_active_kids
|   |   |   |-- runtime_active_time
|   |   |   |-- runtime_enabled
|   |   |   |-- runtime_status
|   |   |   |-- runtime_suspended_time
|   |   |   `-- runtime_usage
|   |   `-- uevent
|   |-- cpufreq -> ../cpufreq/policy0
|   |-- cpuidle
|   |   |-- state0
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state1
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state2
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state3
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   `-- state4
|   |       |-- desc
|   |       |-- disable
|   |       |-- latency
|   |       |-- name
|   |       |-- power
|   |       |-- residency
|   |       |-- time
|   |       `-- usage
|   |-- crash_notes
|   |-- crash_notes_size
|   |-- driver -> ../../../../bus/cpu/drivers/processor
|   |-- firmware_node -> ../../../LNXSYSTM:00/LNXCPU:00
|   |-- microcode
|   |   |-- processor_flags
|   |   `-- version
|   |-- node0 -> ../../node/node0
|   |-- power
|   |   |-- async
|   |   |-- autosuspend_delay_ms
|   |   |-- control
|   |   |-- runtime_active_kids
|   |   |-- runtime_active_time
|   |   |-- runtime_enabled
|   |   |-- runtime_status
|   |   |-- runtime_suspended_time
|   |   `-- runtime_usage
|   |-- subsystem -> ../../../../bus/cpu
|   |-- thermal_throttle
|   |   |-- core_throttle_count
|   |   `-- package_throttle_count
|   |-- topology
|   |   |-- core_id
|   |   |-- core_siblings
|   |   |-- core_siblings_list
|   |   |-- physical_package_id
|   |   |-- thread_siblings
|   |   `-- thread_siblings_list
|   `-- uevent
|-- cpu1
|   |-- cache
|   |   |-- index0
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index1
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index2
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index3
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- power
|   |   |   |-- async
|   |   |   |-- autosuspend_delay_ms
|   |   |   |-- control
|   |   |   |-- runtime_active_kids
|   |   |   |-- runtime_active_time
|   |   |   |-- runtime_enabled
|   |   |   |-- runtime_status
|   |   |   |-- runtime_suspended_time
|   |   |   `-- runtime_usage
|   |   `-- uevent
|   |-- cpufreq -> ../cpufreq/policy1
|   |-- cpuidle
|   |   |-- state0
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state1
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state2
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state3
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   `-- state4
|   |       |-- desc
|   |       |-- disable
|   |       |-- latency
|   |       |-- name
|   |       |-- power
|   |       |-- residency
|   |       |-- time
|   |       `-- usage
|   |-- crash_notes
|   |-- crash_notes_size
|   |-- driver -> ../../../../bus/cpu/drivers/processor
|   |-- firmware_node -> ../../../LNXSYSTM:00/LNXCPU:01
|   |-- microcode
|   |   |-- processor_flags
|   |   `-- version
|   |-- node0 -> ../../node/node0
|   |-- online
|   |-- power
|   |   |-- async
|   |   |-- autosuspend_delay_ms
|   |   |-- control
|   |   |-- runtime_active_kids
|   |   |-- runtime_active_time
|   |   |-- runtime_enabled
|   |   |-- runtime_status
|   |   |-- runtime_suspended_time
|   |   `-- runtime_usage
|   |-- subsystem -> ../../../../bus/cpu
|   |-- thermal_throttle
|   |   |-- core_throttle_count
|   |   `-- package_throttle_count
|   |-- topology
|   |   |-- core_id
|   |   |-- core_siblings
|   |   |-- core_siblings_list
|   |   |-- physical_package_id
|   |   |-- thread_siblings
|   |   `-- thread_siblings_list
|   `-- uevent
|-- cpu2
|   |-- cache
|   |   |-- index0
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index1
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index2
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index3
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- power
|   |   |   |-- async
|   |   |   |-- autosuspend_delay_ms
|   |   |   |-- control
|   |   |   |-- runtime_active_kids
|   |   |   |-- runtime_active_time
|   |   |   |-- runtime_enabled
|   |   |   |-- runtime_status
|   |   |   |-- runtime_suspended_time
|   |   |   `-- runtime_usage
|   |   `-- uevent
|   |-- cpufreq -> ../cpufreq/policy2
|   |-- cpuidle
|   |   |-- state0
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state1
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state2
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state3
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   `-- state4
|   |       |-- desc
|   |       |-- disable
|   |       |-- latency
|   |       |-- name
|   |       |-- power
|   |       |-- residency
|   |       |-- time
|   |       `-- usage
|   |-- crash_notes
|   |-- crash_notes_size
|   |-- driver -> ../../../../bus/cpu/drivers/processor
|   |-- firmware_node -> ../../../LNXSYSTM:00/LNXCPU:02
|   |-- microcode
|   |   |-- processor_flags
|   |   `-- version
|   |-- node0 -> ../../node/node0
|   |-- online
|   |-- power
|   |   |-- async
|   |   |-- autosuspend_delay_ms
|   |   |-- control
|   |   |-- runtime_active_kids
|   |   |-- runtime_active_time
|   |   |-- runtime_enabled
|   |   |-- runtime_status
|   |   |-- runtime_suspended_time
|   |   `-- runtime_usage
|   |-- subsystem -> ../../../../bus/cpu
|   |-- thermal_throttle
|   |   |-- core_throttle_count
|   |   `-- package_throttle_count
|   |-- topology
|   |   |-- core_id
|   |   |-- core_siblings
|   |   |-- core_siblings_list
|   |   |-- physical_package_id
|   |   |-- thread_siblings
|   |   `-- thread_siblings_list
|   `-- uevent
|-- cpu3
|   |-- cache
|   |   |-- index0
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index1
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index2
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- index3
|   |   |   |-- coherency_line_size
|   |   |   |-- level
|   |   |   |-- number_of_sets
|   |   |   |-- physical_line_partition
|   |   |   |-- power
|   |   |   |   |-- async
|   |   |   |   |-- autosuspend_delay_ms
|   |   |   |   |-- control
|   |   |   |   |-- runtime_active_kids
|   |   |   |   |-- runtime_active_time
|   |   |   |   |-- runtime_enabled
|   |   |   |   |-- runtime_status
|   |   |   |   |-- runtime_suspended_time
|   |   |   |   `-- runtime_usage
|   |   |   |-- shared_cpu_list
|   |   |   |-- shared_cpu_map
|   |   |   |-- size
|   |   |   |-- type
|   |   |   |-- uevent
|   |   |   `-- ways_of_associativity
|   |   |-- power
|   |   |   |-- async
|   |   |   |-- autosuspend_delay_ms
|   |   |   |-- control
|   |   |   |-- runtime_active_kids
|   |   |   |-- runtime_active_time
|   |   |   |-- runtime_enabled
|   |   |   |-- runtime_status
|   |   |   |-- runtime_suspended_time
|   |   |   `-- runtime_usage
|   |   `-- uevent
|   |-- cpufreq -> ../cpufreq/policy3
|   |-- cpuidle
|   |   |-- state0
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state1
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state2
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   |-- state3
|   |   |   |-- desc
|   |   |   |-- disable
|   |   |   |-- latency
|   |   |   |-- name
|   |   |   |-- power
|   |   |   |-- residency
|   |   |   |-- time
|   |   |   `-- usage
|   |   `-- state4
|   |       |-- desc
|   |       |-- disable
|   |       |-- latency
|   |       |-- name
|   |       |-- power
|   |       |-- residency
|   |       |-- time
|   |       `-- usage
|   |-- crash_notes
|   |-- crash_notes_size
|   |-- driver -> ../../../../bus/cpu/drivers/processor
|   |-- firmware_node -> ../../../LNXSYSTM:00/LNXCPU:03
|   |-- microcode
|   |   |-- processor_flags
|   |   `-- version
|   |-- node0 -> ../../node/node0
|   |-- online
|   |-- power
|   |   |-- async
|   |   |-- autosuspend_delay_ms
|   |   |-- control
|   |   |-- runtime_active_kids
|   |   |-- runtime_active_time
|   |   |-- runtime_enabled
|   |   |-- runtime_status
|   |   |-- runtime_suspended_time
|   |   `-- runtime_usage
|   |-- subsystem -> ../../../../bus/cpu
|   |-- thermal_throttle
|   |   |-- core_throttle_count
|   |   `-- package_throttle_count
|   |-- topology
|   |   |-- core_id
|   |   |-- core_siblings
|   |   |-- core_siblings_list
|   |   |-- physical_package_id
|   |   |-- thread_siblings
|   |   `-- thread_siblings_list
|   `-- uevent
|-- cpufreq
|   |-- policy0
|   |   |-- affected_cpus
|   |   |-- cpuinfo_cur_freq
|   |   |-- cpuinfo_max_freq
|   |   |-- cpuinfo_min_freq
|   |   |-- cpuinfo_transition_latency
|   |   |-- related_cpus
|   |   |-- scaling_available_governors
|   |   |-- scaling_cur_freq
|   |   |-- scaling_driver
|   |   |-- scaling_governor
|   |   |-- scaling_max_freq
|   |   |-- scaling_min_freq
|   |   `-- scaling_setspeed
|   |-- policy1
|   |   |-- affected_cpus
|   |   |-- cpuinfo_cur_freq
|   |   |-- cpuinfo_max_freq
|   |   |-- cpuinfo_min_freq
|   |   |-- cpuinfo_transition_latency
|   |   |-- related_cpus
|   |   |-- scaling_available_governors
|   |   |-- scaling_cur_freq
|   |   |-- scaling_driver
|   |   |-- scaling_governor
|   |   |-- scaling_max_freq
|   |   |-- scaling_min_freq
|   |   `-- scaling_setspeed
|   |-- policy2
|   |   |-- affected_cpus
|   |   |-- cpuinfo_cur_freq
|   |   |-- cpuinfo_max_freq
|   |   |-- cpuinfo_min_freq
|   |   |-- cpuinfo_transition_latency
|   |   |-- related_cpus
|   |   |-- scaling_available_governors
|   |   |-- scaling_cur_freq
|   |   |-- scaling_driver
|   |   |-- scaling_governor
|   |   |-- scaling_max_freq
|   |   |-- scaling_min_freq
|   |   `-- scaling_setspeed
|   `-- policy3
|       |-- affected_cpus
|       |-- cpuinfo_cur_freq
|       |-- cpuinfo_max_freq
|       |-- cpuinfo_min_freq
|       |-- cpuinfo_transition_latency
|       |-- related_cpus
|       |-- scaling_available_governors
|       |-- scaling_cur_freq
|       |-- scaling_driver
|       |-- scaling_governor
|       |-- scaling_max_freq
|       |-- scaling_min_freq
|       `-- scaling_setspeed
|-- cpuidle
|   |-- current_driver
|   `-- current_governor_ro
|-- intel_pstate
|   |-- max_perf_pct
|   |-- min_perf_pct
|   |-- no_turbo
|   |-- num_pstates
|   `-- turbo_pct
|-- isolated
|-- kernel_max
|-- microcode
|   `-- reload
|-- modalias
|-- offline
|-- online
|-- possible
|-- power
|   |-- async
|   |-- autosuspend_delay_ms
|   |-- control
|   |-- runtime_active_kids
|   |-- runtime_active_time
|   |-- runtime_enabled
|   |-- runtime_status
|   |-- runtime_suspended_time
|   `-- runtime_usage
|-- present
|-- smt
|   |-- active
|   `-- control
|-- uevent
`-- vulnerabilities
    |-- l1tf
    |-- meltdown
    |-- spec_store_bypass
    |-- spectre_v1
    `-- spectre_v2

115 directories, 679 files
Maratyszcza commented 5 years ago

I see that both /sys/devices/system/cpu/present and /sys/devices/system/cpu/possible files exist. @VisionZQ: could you dump the contents of these files?

VisionZQ commented 5 years ago

Hi, I have check the Platforms and requirements table again. 3-level cache hierarchy exist in my PC. Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 4 On-line CPU(s) list: 0-3 Thread(s) per core: 1 Core(s) per socket: 4 Socket(s): 1 NUMA node(s): 1 Vendor ID: GenuineIntel CPU family: 6 Model: 58 Model name: Intel(R) Core(TM) i5-3470 CPU @ 3.20GHz Stepping: 9 CPU MHz: 3399.875 CPU max MHz: 3600.0000 CPU min MHz: 1600.0000 BogoMIPS: 6385.67 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 6144K NUMA node0 CPU(s): 0-3

But, AVX2 is not support to CPU!!!!! so, this is is right reason caused the issue? ` NUMA node0 CPU(s): 0-3 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm epb ssbd ibrs ibpb stibp kaiser tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts flush_l1d

`

Maratyszcza commented 5 years ago

yes, NNPACK on x86-64 requires AVX2