TensorFlow Lite Kernel Regression

AMD EPYC 7702 64-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED 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 2009103-FI-TENSORFLO07
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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
v5.5
September 09 2020
  10 Minutes
v5.4
September 09 2020
  34 Minutes
8c39f71ee2019e77ee14f88b1321b2348db51820
September 09 2020
  10 Minutes
3b397c7ccafe0624018cb09fc96729f8f6165573
September 09 2020
  22 Minutes
89d57dddd7d319ded00415790a0bb3c954b7e386
September 09 2020
  10 Minutes
9e7a03233e02afd3ee061e373355f34d7254f1e6
September 10 2020
  10 Minutes
df28204bb0f29cc475c0a8893c99b46a11a4903f
September 10 2020
  32 Minutes
0e3149f86b99ddabde8c5029eea0a9267e34f1a0
September 10 2020
  22 Minutes
1ae78780eda54023a0fb49ee743dbba39da148e0
September 10 2020
  10 Minutes
77a05940eee7e9891cd6add7a690a3e762ee21b0
September 10 2020
  10 Minutes
b21feab0b865c36b24d7a60b55a10c7033b03159
September 10 2020
  10 Minutes
74c578759f15cb5a0d0107759bdad671d7b52ab9
September 10 2020
  10 Minutes
2ab4092fc82d6001fdd9d51dbba27d04dec967e0
September 10 2020
  10 Minutes
a34983470301018324f0110791da452fee1318c2
September 10 2020
  11 Minutes
0b0695f2b34a4afa3f6e9aa1ff0e5336d8dad912
September 10 2020
  22 Minutes
fcf0553db6f4c79387864f6e4ab4a891601f395e
September 10 2020
  10 Minutes
Invert Hiding All Results Option
  15 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):


TensorFlow Lite Kernel RegressionOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7702 64-Core @ 2.00GHz (64 Cores / 128 Threads)ASRockRack EPYCD8 (P2.10 BIOS)AMD Starship/Matisse126GB3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash DiskASPEEDAMD Starship/Matisse2 x Intel I350Ubuntu 20.045.5.0-pts (x86_64)5.4.0-pts (x86_64)5.4.0-rc7-pts (x86_64) 202009105.4.0-rc8-pts (x86_64) 202009105.4.0-rc1-pts (x86_64) 20200910GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.8GCC 9.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelsDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionTensorFlow Lite Kernel Regression BenchmarksSystem Logs- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c- v5.5: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - v5.4: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 8c39f71ee2019e77ee14f88b1321b2348db51820: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 3b397c7ccafe0624018cb09fc96729f8f6165573: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 89d57dddd7d319ded00415790a0bb3c954b7e386: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 9e7a03233e02afd3ee061e373355f34d7254f1e6: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - df28204bb0f29cc475c0a8893c99b46a11a4903f: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 0e3149f86b99ddabde8c5029eea0a9267e34f1a0: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling - 1ae78780eda54023a0fb49ee743dbba39da148e0: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 77a05940eee7e9891cd6add7a690a3e762ee21b0: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - b21feab0b865c36b24d7a60b55a10c7033b03159: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected - 74c578759f15cb5a0d0107759bdad671d7b52ab9: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling - 2ab4092fc82d6001fdd9d51dbba27d04dec967e0: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling - a34983470301018324f0110791da452fee1318c2: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling - 0b0695f2b34a4afa3f6e9aa1ff0e5336d8dad912: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling - fcf0553db6f4c79387864f6e4ab4a891601f395e: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling

v5.5v5.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 OverviewPhoronix Test Suite100%106%112%118%TensorFlow LiteTensorFlow LiteTensorFlow LiteI.R.VInception V4Mobilenet Quant

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: Inception V4v5.5v5.48c39f71ee2019e77ee14f88b1321b2348db518203b397c7ccafe0624018cb09fc96729f8f616557389d57dddd7d319ded00415790a0bb3c954b7e3869e7a03233e02afd3ee061e373355f34d7254f1e6df28204bb0f29cc475c0a8893c99b46a11a4903f0e3149f86b99ddabde8c5029eea0a9267e34f1a01ae78780eda54023a0fb49ee743dbba39da148e077a05940eee7e9891cd6add7a690a3e762ee21b0b21feab0b865c36b24d7a60b55a10c7033b0315974c578759f15cb5a0d0107759bdad671d7b52ab92ab4092fc82d6001fdd9d51dbba27d04dec967e0a34983470301018324f0110791da452fee1318c20b0695f2b34a4afa3f6e9aa1ff0e5336d8dad912fcf0553db6f4c79387864f6e4ab4a891601f395e200K400K600K800K1000KSE +/- 5786.28, N = 3SE +/- 10230.46, N = 15SE +/- 2076.06, N = 3SE +/- 8756.66, N = 15SE +/- 3153.29, N = 3SE +/- 1129.67, N = 3SE +/- 6623.24, N = 13SE +/- 7882.56, N = 3SE +/- 3016.30, N = 3SE +/- 10918.27, N = 3SE +/- 2281.23, N = 3SE +/- 1203.18, N = 3SE +/- 1426.28, N = 3SE +/- 13759.34, N = 3SE +/- 7633.77, N = 3SE +/- 917.91, N = 399550485164710004368344131005157993248824254841356996837992760987460988541976861868227968533954546
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4v5.5v5.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: 985699 / Avg: 995504 / Max: 1005730Min: 792130 / Avg: 851646.67 / Max: 943251Min: 996959 / Avg: 1000436.33 / Max: 1004140Min: 790862 / Avg: 834412.67 / Max: 885077Min: 1001830 / Avg: 1005156.67 / Max: 1011460Min: 990999 / Avg: 993247.67 / Max: 994562Min: 794813 / Avg: 824253.85 / Max: 888744Min: 828427 / Avg: 841356 / Max: 855633Min: 990845 / Avg: 996836.67 / Max: 1000440Min: 972153 / Avg: 992759.67 / Max: 1009320Min: 982898 / Avg: 987460.33 / Max: 989770Min: 986504 / Avg: 988541.33 / Max: 990669Min: 975065 / Avg: 976860.67 / Max: 979678Min: 840928 / Avg: 868227.33 / Max: 884880Min: 953674 / Avg: 968533.33 / Max: 979000Min: 953363 / Avg: 954545.67 / Max: 956353

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantv5.5v5.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 +/- 88.14, N = 3SE +/- 436.64, N = 15SE +/- 109.54, N = 3SE +/- 601.92, N = 3SE +/- 131.82, N = 3SE +/- 282.29, N = 3SE +/- 362.35, N = 15SE +/- 389.69, N = 15SE +/- 51.34, N = 3SE +/- 139.06, N = 3SE +/- 73.64, N = 3SE +/- 64.53, N = 3SE +/- 116.94, N = 3SE +/- 550.88, N = 3SE +/- 136.90, N = 3SE +/- 40.06, N = 343291.539820.543055.139191.743430.743193.140402.140473.743319.543311.543226.643170.742829.139813.843036.643282.4
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantv5.5v5.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: 43156.8 / Avg: 43291.47 / Max: 43457.3Min: 36856.9 / Avg: 39820.55 / Max: 42325.8Min: 42888.7 / Avg: 43055.1 / Max: 43261.7Min: 38100.4 / Avg: 39191.67 / Max: 40177.5Min: 43173.4 / Avg: 43430.7 / Max: 43609.1Min: 42696.5 / Avg: 43193.07 / Max: 43674Min: 38584.4 / Avg: 40402.07 / Max: 42767Min: 38086.1 / Avg: 40473.7 / Max: 42556.6Min: 43229.2 / Avg: 43319.47 / Max: 43407Min: 43130.6 / Avg: 43311.5 / Max: 43584.9Min: 43089.3 / Avg: 43226.6 / Max: 43341.4Min: 43049.7 / Avg: 43170.67 / Max: 43270.1Min: 42674.1 / Avg: 42829.13 / Max: 43058.3Min: 38724.3 / Avg: 39813.83 / Max: 40500.3Min: 42784.9 / Avg: 43036.57 / Max: 43255.8Min: 43238.5 / Avg: 43282.4 / Max: 43362.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2v5.5v5.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 +/- 7137.69, N = 3SE +/- 4913.76, N = 3SE +/- 7425.32, N = 3SE +/- 2546.21, N = 3SE +/- 3550.66, N = 3SE +/- 1311.25, N = 3SE +/- 4037.36, N = 3SE +/- 10502.35, N = 3SE +/- 3051.65, N = 3SE +/- 1416.31, N = 3SE +/- 873.96, N = 3SE +/- 1369.49, N = 3SE +/- 2377.85, N = 3SE +/- 10351.22, N = 4SE +/- 8431.87, N = 15SE +/- 2645.52, N = 3876332717903879214713821884039889744751998720559880358877868880385878511786402755804804861859121
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2v5.5v5.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: 862313 / Avg: 876332 / Max: 885674Min: 711311 / Avg: 717902.67 / Max: 727511Min: 867475 / Avg: 879214.33 / Max: 892961Min: 709152 / Avg: 713821.33 / Max: 717916Min: 877401 / Avg: 884039 / Max: 889543Min: 887327 / Avg: 889743.67 / Max: 891834Min: 743924 / Avg: 751998.33 / Max: 756104Min: 704844 / Avg: 720558.67 / Max: 740486Min: 876154 / Avg: 880358.33 / Max: 886292Min: 875429 / Avg: 877868.33 / Max: 880335Min: 878674 / Avg: 880385 / Max: 881550Min: 876406 / Avg: 878510.67 / Max: 881081Min: 783249 / Avg: 786402.33 / Max: 791062Min: 729641 / Avg: 755803.75 / Max: 772893Min: 736157 / Avg: 804860.87 / Max: 859984Min: 853830 / Avg: 859121 / Max: 861785