tri

tri

HTML result view exported from: https://openbenchmarking.org/result/2407013-NE-TRI93793891&grr.

triProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDisplay DriverOpenCLVulkanCompilerFile-SystemScreen ResolutionSystem LayertriIntel Xeon E5-2667 v3 (4 Cores / 8 Threads)Blade Shadow ShadowM v2.0 (1.1.3 BIOS)Intel 82G33/G31/P35/P31 + ICH91 x 12GB RAM-2400MT/s Blade BY6AC7GG3YUV52-751215GB QEMU HDDRed Hat QXL paravirtual graphic card 8GBRed Hat Virtio deviceUbuntu 22.045.15.0-113-generic (x86_64)NVIDIAOpenCL 3.0 CUDA 12.4.891.3.277GCC 11.4.0ext41280x800KVMOpenBenchmarking.org- Transparent Huge Pages: madvise- CPU Microcode: 0x49- Python 3.10.12- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT Host state unknown + retbleed: Not affected + spec_rstack_overflow: 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 Retpolines; IBPB: conditional; IBRS_FW; STIBP: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Retpoline + srbds: Not affected + tsx_async_abort: Not affected

tritensorflow: GPU - 16 - VGG-16tensorflow: CPU - 16 - VGG-16tensorflow: GPU - 16 - ResNet-50pytorch: CPU - 16 - Efficientnet_v2_lai-benchmark: Device AI Scoreai-benchmark: Device Training Scoreai-benchmark: Device Inference Scorepytorch: CPU - 16 - ResNet-152tensorflow: CPU - 16 - ResNet-50tensorflow: GPU - 16 - AlexNettensorflow: GPU - 16 - GoogLeNetpytorch: CPU - 16 - ResNet-50tensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 16 - AlexNettri0.882.472.593.0811616115504.596.319.049.3111.1418.2033.29OpenBenchmarking.org

TensorFlow

Device: GPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: VGG-16tri0.1980.3960.5940.7920.99SE +/- 0.00, N = 30.88

TensorFlow

Device: CPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: VGG-16tri0.55581.11161.66742.22322.779SE +/- 0.00, N = 32.47

TensorFlow

Device: GPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: ResNet-50tri0.58281.16561.74842.33122.914SE +/- 0.01, N = 32.59

PyTorch

Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_ltri0.6931.3862.0792.7723.465SE +/- 0.00, N = 33.08MIN: 2.79 / MAX: 3.12

AI Benchmark Alpha

Device AI Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Scoretri20040060080010001161

AI Benchmark Alpha

Device Training Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Scoretri130260390520650611

AI Benchmark Alpha

Device Inference Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Scoretri120240360480600550

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-152tri1.03282.06563.09844.13125.164SE +/- 0.02, N = 34.59MIN: 4.27 / MAX: 4.66

TensorFlow

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: ResNet-50tri246810SE +/- 0.02, N = 36.31

TensorFlow

Device: GPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: AlexNettri3691215SE +/- 0.01, N = 39.04

TensorFlow

Device: GPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: GoogLeNettri3691215SE +/- 0.02, N = 39.31

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-50tri3691215SE +/- 0.15, N = 311.14MIN: 9.98 / MAX: 11.55

TensorFlow

Device: CPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: GoogLeNettri48121620SE +/- 0.04, N = 318.20

TensorFlow

Device: CPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: AlexNettri816243240SE +/- 0.02, N = 333.29

Phoronix Test Suite v10.8.4