Core i9 10900K TensorFlow Lite

Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2008231-SYST-COREI9100
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Go 1
August 23 2020
  24 Minutes
Go 2
August 23 2020
  24 Minutes
Go 3
August 23 2020
  24 Minutes
Invert Hiding All Results Option
  24 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Go 1

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Go 2

Go 3

Processor: Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads), Motherboard: Gigabyte Z490 AORUS MASTER (F3 BIOS), Chipset: Intel Comet Lake PCH, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Device 15f3 + Intel Wi-Fi 6 AX201

OS: Ubuntu 20.04, Kernel: 5.8.1-050801-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.2.0-devel (git-ef67218 2020-07-07 focal-oibaf-ppa) (LLVM 10.0.1), OpenCL: OpenCL 1.1 Mesa 20.2.0-devel (git-c977567db6), Vulkan: 1.2.131, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Core i9 10900K TensorFlow LiteOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Gigabyte Z490 AORUS MASTER (F3 BIOS)Intel Comet Lake PCH16GBSamsung SSD 970 EVO 250GBGigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz)Realtek ALC1220DELL P2415QIntel Device 15f3 + Intel Wi-Fi 6 AX201Ubuntu 20.045.8.1-050801-generic (x86_64)GNOME Shell 3.36.3X Server 1.20.8modesetting 1.20.84.6 Mesa 20.2.0-devel (git-ef67218 2020-07-07 focal-oibaf-ppa) (LLVM 10.0.1)OpenCL 1.1 Mesa 20.2.0-devel (git-c977567db6)1.2.131GCC 9.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionCore I9 10900K TensorFlow Lite BenchmarksSystem Logs- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8- itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Go 1Go 2Go 3Result OverviewPhoronix Test Suite100%100%101%101%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteMobilenet QuantMobilenet FloatInception V4NASNet MobileSqueezeNetI.R.V

Core i9 10900K TensorFlow Litetensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Go 1Go 2Go 3167615237927314741411429411865121418071675432375430147181114256117317214166316756023749601472131140781174102141327OpenBenchmarking.org

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetGo 2Go 3Go 140K80K120K160K200KSE +/- 34.11, N = 3SE +/- 15.56, N = 3SE +/- 25.12, N = 3167543167560167615
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetGo 2Go 3Go 130K60K90K120K150KMin: 167502 / Avg: 167543.33 / Max: 167611Min: 167536 / Avg: 167559.67 / Max: 167589Min: 167565 / Avg: 167614.67 / Max: 167646

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Go 3Go 2Go 1500K1000K1500K2000K2500KSE +/- 260.83, N = 3SE +/- 11.55, N = 3SE +/- 3903.95, N = 3237496023754302379273
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Go 3Go 2Go 1400K800K1200K1600K2000KMin: 2374450 / Avg: 2374960 / Max: 2375310Min: 2375410 / Avg: 2375430 / Max: 2375450Min: 2375250 / Avg: 2379273.33 / Max: 2387080

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileGo 2Go 3Go 130K60K90K120K150KSE +/- 89.66, N = 3SE +/- 144.80, N = 3SE +/- 66.02, N = 3147181147213147414
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileGo 2Go 3Go 130K60K90K120K150KMin: 147069 / Avg: 147180.67 / Max: 147358Min: 147021 / Avg: 147213.33 / Max: 147497Min: 147289 / Avg: 147414.33 / Max: 147513

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatGo 3Go 2Go 120K40K60K80K100KSE +/- 50.71, N = 3SE +/- 86.19, N = 3SE +/- 141.41, N = 3114078114256114294
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatGo 3Go 2Go 120K40K60K80K100KMin: 114007 / Avg: 114077.67 / Max: 114176Min: 114166 / Avg: 114255.67 / Max: 114428Min: 114138 / Avg: 114293.67 / Max: 114576

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantGo 2Go 3Go 130K60K90K120K150KSE +/- 141.34, N = 3SE +/- 210.41, N = 3SE +/- 1241.85, N = 3117317117410118651
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantGo 2Go 3Go 120K40K60K80K100KMin: 117173 / Avg: 117317.33 / Max: 117600Min: 117009 / Avg: 117410 / Max: 117721Min: 117400 / Avg: 118651.33 / Max: 121135

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Go 3Go 2Go 1500K1000K1500K2000K2500KSE +/- 61.19, N = 3SE +/- 37.12, N = 3SE +/- 140.99, N = 3214132721416632141807
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Go 3Go 2Go 1400K800K1200K1600K2000KMin: 2141230 / Avg: 2141326.67 / Max: 2141440Min: 2141590 / Avg: 2141663.33 / Max: 2141710Min: 2141610 / Avg: 2141806.67 / Max: 2142080

Go 1

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 18:43 by user system.

Go 2

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 19:47 by user system.

Go 3

Processor: Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads), Motherboard: Gigabyte Z490 AORUS MASTER (F3 BIOS), Chipset: Intel Comet Lake PCH, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Device 15f3 + Intel Wi-Fi 6 AX201

OS: Ubuntu 20.04, Kernel: 5.8.1-050801-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.2.0-devel (git-ef67218 2020-07-07 focal-oibaf-ppa) (LLVM 10.0.1), OpenCL: OpenCL 1.1 Mesa 20.2.0-devel (git-c977567db6), Vulkan: 1.2.131, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 20:31 by user system.