litert xnnpack

AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Pop 22.04 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 2410157-PTS-LITERTXN77
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
October 15
  3 Hours, 16 Minutes
b
October 15
  2 Hours, 29 Minutes
d
October 15
  2 Hours, 8 Minutes
Invert Behavior (Only Show Selected Data)
  2 Hours, 38 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):


litert xnnpackOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS)AMD Starship/Matisse4 x 32GB DDR4-3000MT/s CMK64GX4M2D3000C16Samsung SSD 970 EVO Plus 500GBAMD Radeon RX 5700 8GBAMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Pop 22.046.8.0-76060800daily20240311-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.44.6 Mesa 24.0.3-1pop1~1711635559~22.04~7a9f319 (LLVM 15.0.7 DRM 3.57)1.3.274GCC 11.4.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionLitert Xnnpack BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107a- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abdResult OverviewPhoronix Test Suite100%109%118%127%XNNPACKXNNPACKXNNPACKXNNPACKXNNPACKXNNPACKXNNPACKLiteRTLiteRTLiteRTLiteRTLiteRTLiteRTLiteRTLiteRTXNNPACKXNNPACKFP32MobileNetV3SmallFP32MobileNetV3LargeFP16MobileNetV3LargeFP16MobileNetV3SmallFP16MobileNetV2QS8MobileNetV2FP16MobileNetV1Mobilenet QuantQ.C.S.M.vNASNet MobileSqueezeNetI.R.VInception V4Mobilenet FloatDeepLab V3FP32MobileNetV2FP32MobileNetV1

litert xnnpackxnnpack: QS8MobileNetV2xnnpack: FP16MobileNetV3Smallxnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV1xnnpack: FP32MobileNetV3Smallxnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV1litert: Mobilenet Quantlitert: SqueezeNetlitert: Inception V4litert: DeepLab V3litert: Quantized COCO SSD MobileNet v1litert: Inception ResNet V2litert: NASNet Mobilelitert: Mobilenet Floatabd5696635790555908362153989298696442803191.886423.6456528.610506.65332.1259856.054458.34243.705691584275595983364955439174693442383089.776349.1457577.710343.95384.8058681.454646.94187.5660386057794463243825736911231688942433084.066274.4456815.610484.85207.0759960.453315.54173.74OpenBenchmarking.org

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2abd13002600390052006500SE +/- 22.24, N = 4SE +/- 27.75, N = 3SE +/- 292.13, N = 35696569160381. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallabd14002800420056007000SE +/- 506.60, N = 4SE +/- 43.47, N = 3SE +/- 252.57, N = 36357584260571. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largeabd2K4K6K8K10KSE +/- 1200.15, N = 4SE +/- 47.34, N = 3SE +/- 426.05, N = 39055755979441. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2abd14002800420056007000SE +/- 39.38, N = 4SE +/- 27.67, N = 3SE +/- 312.09, N = 35908598363241. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1abd8001600240032004000SE +/- 16.80, N = 4SE +/- 11.67, N = 3SE +/- 169.19, N = 33621364938251. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallabd16003200480064008000SE +/- 47.52, N = 4SE +/- 121.75, N = 3SE +/- 1111.98, N = 35398554373691. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largeabd2K4K6K8K10KSE +/- 69.99, N = 4SE +/- 54.24, N = 3SE +/- 1046.96, N = 392989174112311. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2abd15003000450060007500SE +/- 15.96, N = 4SE +/- 41.70, N = 3SE +/- 15.63, N = 36964693468891. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1abd9001800270036004500SE +/- 46.30, N = 4SE +/- 34.33, N = 3SE +/- 41.77, N = 34280423842431. (CXX) g++ options: -O3 -lrt -lm

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quantabd7001400210028003500SE +/- 108.69, N = 15SE +/- 81.43, N = 12SE +/- 99.43, N = 123191.883089.773084.06

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetabd14002800420056007000SE +/- 148.43, N = 15SE +/- 97.62, N = 15SE +/- 24.67, N = 36423.646349.146274.44

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4abd12K24K36K48K60KSE +/- 639.55, N = 3SE +/- 670.44, N = 15SE +/- 464.00, N = 356528.657577.756815.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3abd2K4K6K8K10KSE +/- 163.08, N = 15SE +/- 84.63, N = 3SE +/- 84.63, N = 310506.610343.910484.8

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1abd12002400360048006000SE +/- 47.15, N = 15SE +/- 72.48, N = 3SE +/- 72.45, N = 35332.125384.805207.07

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2abd13K26K39K52K65KSE +/- 665.58, N = 3SE +/- 317.66, N = 3SE +/- 319.38, N = 359856.058681.459960.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobileabd12K24K36K48K60KSE +/- 347.90, N = 3SE +/- 560.60, N = 3SE +/- 390.67, N = 354458.354646.953315.5

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floatabd9001800270036004500SE +/- 22.62, N = 3SE +/- 24.52, N = 3SE +/- 6.16, N = 34243.704187.564173.74