Intel Core i5-12600K testing with a ASUS PRIME Z690-P WIFI D4 (0605 BIOS) and ASUS Intel ADL-S GT1 15GB on Ubuntu 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 2210141-PTS-FGDS239097
fgds
Intel Core i5-12600K testing with a ASUS PRIME Z690-P WIFI D4 (0605 BIOS) and ASUS Intel ADL-S GT1 15GB on Ubuntu 22.04 via the Phoronix Test Suite.
A:
Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0
OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
B:
Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0
OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
C:
Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0
OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
SMHasher 2022-08-22
Hash: wyhash
MiB/sec > Higher Is Better
A . 29154.23 |=================================================================
B . 29184.54 |=================================================================
C . 29220.87 |=================================================================
SMHasher 2022-08-22
Hash: wyhash
cycles/hash < Lower Is Better
A . 18.55 |====================================================================
B . 18.55 |====================================================================
C . 18.55 |====================================================================
SMHasher 2022-08-22
Hash: SHA3-256
MiB/sec > Higher Is Better
A . 244.07 |===================================================================
B . 245.01 |===================================================================
C . 245.08 |===================================================================
SMHasher 2022-08-22
Hash: SHA3-256
cycles/hash < Lower Is Better
A . 1599.28 |==================================================================
B . 1595.18 |==================================================================
C . 1596.08 |==================================================================
SMHasher 2022-08-22
Hash: Spooky32
MiB/sec > Higher Is Better
A . 17969.01 |=================================================================
B . 17981.71 |=================================================================
C . 17979.56 |=================================================================
SMHasher 2022-08-22
Hash: Spooky32
cycles/hash < Lower Is Better
A . 33.85 |====================================================================
B . 33.78 |====================================================================
C . 33.82 |====================================================================
SMHasher 2022-08-22
Hash: fasthash32
MiB/sec > Higher Is Better
A . 7604.24 |==================================================================
B . 7603.85 |==================================================================
C . 7604.38 |==================================================================
SMHasher 2022-08-22
Hash: fasthash32
cycles/hash < Lower Is Better
A . 28.19 |====================================================================
B . 28.19 |====================================================================
C . 28.19 |====================================================================
SMHasher 2022-08-22
Hash: FarmHash128
MiB/sec > Higher Is Better
A . 19170.14 |=================================================================
B . 19201.69 |=================================================================
C . 19197.59 |=================================================================
SMHasher 2022-08-22
Hash: FarmHash128
cycles/hash < Lower Is Better
A . 53.74 |====================================================================
B . 53.74 |====================================================================
C . 53.74 |====================================================================
SMHasher 2022-08-22
Hash: t1ha2_atonce
MiB/sec > Higher Is Better
A . 21936.55 |=================================================================
B . 21929.77 |=================================================================
C . 21936.73 |=================================================================
SMHasher 2022-08-22
Hash: t1ha2_atonce
cycles/hash < Lower Is Better
A . 25.30 |====================================================================
B . 25.30 |====================================================================
C . 25.30 |====================================================================
SMHasher 2022-08-22
Hash: FarmHash32 x86_64 AVX
MiB/sec > Higher Is Better
A . 26888.83 |=================================================================
B . 26897.98 |=================================================================
C . 26713.68 |=================================================================
SMHasher 2022-08-22
Hash: FarmHash32 x86_64 AVX
cycles/hash < Lower Is Better
A . 32.83 |====================================================================
B . 32.61 |====================================================================
C . 32.82 |====================================================================
SMHasher 2022-08-22
Hash: t1ha0_aes_avx2 x86_64
MiB/sec > Higher Is Better
A . 72005.91 |=================================================================
B . 72004.31 |=================================================================
C . 71999.16 |=================================================================
SMHasher 2022-08-22
Hash: t1ha0_aes_avx2 x86_64
cycles/hash < Lower Is Better
A . 25.07 |====================================================================
B . 25.07 |====================================================================
C . 25.07 |====================================================================
SMHasher 2022-08-22
Hash: MeowHash x86_64 AES-NI
MiB/sec > Higher Is Better
A . 49353.69 |=================================================================
B . 48796.81 |================================================================
C . 49349.97 |=================================================================
SMHasher 2022-08-22
Hash: MeowHash x86_64 AES-NI
cycles/hash < Lower Is Better
A . 54.28 |====================================================================
B . 54.33 |====================================================================
C . 54.32 |====================================================================
OpenRadioss 2022.10.13
Model: Bumper Beam
Seconds < Lower Is Better
A . 247.09 |===================================================================
B . 229.96 |==============================================================
C . 228.07 |==============================================================
OpenRadioss 2022.10.13
Model: Cell Phone Drop Test
Seconds < Lower Is Better
A . 176.92 |===================================================================
B . 167.33 |===============================================================
C . 164.08 |==============================================================
OpenRadioss 2022.10.13
Model: Bird Strike on Windshield
Seconds < Lower Is Better
A . 385.82 |===================================================================
B . 372.34 |=================================================================
C . 375.12 |=================================================================
OpenRadioss 2022.10.13
Model: Rubber O-Ring Seal Installation
Seconds < Lower Is Better
A . 288.06 |===================================================================
B . 285.73 |==================================================================
C . 284.58 |==================================================================
OpenRadioss 2022.10.13
Model: INIVOL and Fluid Structure Interaction Drop Container
Seconds < Lower Is Better
A . 801.99 |===================================================================
B . 783.86 |=================================================================
C . 785.09 |==================================================================
QuadRay 2022.05.25
Scene: 1 - Resolution: 4K
FPS > Higher Is Better
A . 4.97 |=====================================================================
B . 4.98 |=====================================================================
C . 4.97 |=====================================================================
QuadRay 2022.05.25
Scene: 2 - Resolution: 4K
FPS > Higher Is Better
A . 1.42 |=====================================================================
B . 1.42 |=====================================================================
C . 1.42 |=====================================================================
QuadRay 2022.05.25
Scene: 3 - Resolution: 4K
FPS > Higher Is Better
A . 1.18 |=====================================================================
B . 1.18 |=====================================================================
C . 1.18 |=====================================================================
QuadRay 2022.05.25
Scene: 5 - Resolution: 4K
FPS > Higher Is Better
A . 0.32 |=====================================================================
B . 0.32 |=====================================================================
C . 0.32 |=====================================================================
QuadRay 2022.05.25
Scene: 1 - Resolution: 1080p
FPS > Higher Is Better
A . 19.50 |====================================================================
B . 19.57 |====================================================================
C . 19.49 |====================================================================
QuadRay 2022.05.25
Scene: 2 - Resolution: 1080p
FPS > Higher Is Better
A . 5.60 |=====================================================================
B . 5.61 |=====================================================================
C . 5.61 |=====================================================================
QuadRay 2022.05.25
Scene: 3 - Resolution: 1080p
FPS > Higher Is Better
A . 4.59 |=====================================================================
B . 4.60 |=====================================================================
C . 4.60 |=====================================================================
QuadRay 2022.05.25
Scene: 5 - Resolution: 1080p
FPS > Higher Is Better
A . 1.25 |=================================================================
B . 1.30 |====================================================================
C . 1.32 |=====================================================================
AOM AV1 3.5
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 0.24 |=====================================================================
B . 0.24 |=====================================================================
C . 0.24 |=====================================================================
AOM AV1 3.5
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 7.14 |====================================================================
B . 7.17 |=====================================================================
C . 7.21 |=====================================================================
AOM AV1 3.5
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 32.46 |===================================================================
B . 33.16 |====================================================================
C . 32.90 |===================================================================
AOM AV1 3.5
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 12.81 |===================================================================
B . 12.87 |====================================================================
C . 12.94 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 47.81 |==================================================================
B . 49.44 |====================================================================
C . 49.03 |===================================================================
AOM AV1 3.5
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 66.80 |===================================================================
B . 67.47 |===================================================================
C . 68.15 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
A . 67.80 |===================================================================
B . 68.67 |====================================================================
C . 68.96 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 0.71 |====================================================================
B . 0.72 |=====================================================================
C . 0.72 |=====================================================================
AOM AV1 3.5
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 16.65 |=================================================================
B . 17.49 |====================================================================
C . 17.49 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 58.85 |===============================================================
B . 57.88 |==============================================================
C . 63.46 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 40.35 |==================================================================
B . 41.89 |====================================================================
C . 41.88 |====================================================================
AOM AV1 3.5
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 120.56 |===============================================================
B . 127.40 |===================================================================
C . 125.13 |==================================================================
AOM AV1 3.5
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 143.74 |================================================================
B . 149.25 |===================================================================
C . 149.74 |===================================================================
AOM AV1 3.5
Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
A . 152.85 |=========================================================
B . 178.37 |===================================================================
C . 153.46 |==========================================================
Y-Cruncher 0.7.10.9513
Pi Digits To Calculate: 1B
Seconds < Lower Is Better
A . 43.40 |===================================================================
B . 43.47 |===================================================================
C . 44.05 |====================================================================
Y-Cruncher 0.7.10.9513
Pi Digits To Calculate: 500M
Seconds < Lower Is Better
A . 20.71 |====================================================================
B . 20.58 |====================================================================
C . 20.34 |===================================================================
oneDNN 2.7
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 4.02417 |==================================================================
B . 3.91825 |================================================================
C . 3.98114 |=================================================================
oneDNN 2.7
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 10.60 |===================================================================
B . 10.70 |====================================================================
C . 10.70 |====================================================================
oneDNN 2.7
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 1.46342 |==================================================================
B . 1.46173 |==================================================================
C . 1.46136 |==================================================================
oneDNN 2.7
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 2.16332 |===============================================================
B . 2.28320 |==================================================================
C . 2.27602 |==================================================================
oneDNN 2.7
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 14.33 |====================================================================
B . 14.43 |====================================================================
C . 14.39 |====================================================================
oneDNN 2.7
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 9.81485 |================================================================
B . 9.81997 |================================================================
C . 10.02650 |=================================================================
oneDNN 2.7
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 8.14523 |==================================================================
B . 8.06747 |=================================================================
C . 8.11715 |==================================================================
oneDNN 2.7
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 12.32 |===================================================================
B . 12.45 |====================================================================
C . 12.19 |===================================================================
oneDNN 2.7
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 2.09297 |=================================================================
B . 2.11167 |==================================================================
C . 2.09377 |=================================================================
oneDNN 2.7
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 3.21457 |==================================================================
B . 2.97401 |=============================================================
C . 3.14484 |=================================================================
oneDNN 2.7
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 4508.32 |==================================================================
B . 4410.31 |=================================================================
C . 4439.89 |=================================================================
oneDNN 2.7
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 2177.70 |==================================================================
B . 2160.58 |=================================================================
C . 2179.57 |==================================================================
oneDNN 2.7
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 4474.24 |==================================================================
B . 4409.87 |=================================================================
C . 4439.06 |=================================================================
oneDNN 2.7
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 2168.08 |==================================================================
B . 2159.81 |=================================================================
C . 2183.19 |==================================================================
oneDNN 2.7
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
ms < Lower Is Better
A . 2.81573 |==================================================================
B . 2.74589 |================================================================
C . 2.54921 |============================================================
oneDNN 2.7
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
A . 4439.64 |==================================================================
B . 4407.58 |==================================================================
C . 4429.54 |==================================================================
oneDNN 2.7
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
A . 2161.75 |=================================================================
B . 2160.41 |=================================================================
C . 2182.09 |==================================================================
oneDNN 2.7
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
A . 1.15139 |==========================================================
B . 1.01232 |===================================================
C . 1.30001 |==================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 16 - Model: AlexNet
images/sec > Higher Is Better
A . 80.04 |====================================================================
B . 80.10 |====================================================================
C . 80.04 |====================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 32 - Model: AlexNet
images/sec > Higher Is Better
A . 102.28 |==================================================================
B . 102.95 |===================================================================
C . 103.34 |===================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 16 - Model: GoogLeNet
images/sec > Higher Is Better
A . 52.52 |====================================================================
B . 52.25 |====================================================================
C . 52.37 |====================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 16 - Model: ResNet-50
images/sec > Higher Is Better
A . 17.83 |====================================================================
B . 17.88 |====================================================================
C . 17.93 |====================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 32 - Model: GoogLeNet
images/sec > Higher Is Better
A . 54.43 |====================================================================
B . 54.06 |====================================================================
C . 54.29 |====================================================================
TensorFlow 2.10
Device: CPU - Batch Size: 32 - Model: ResNet-50
images/sec > Higher Is Better
A . 18.44 |====================================================================
B . 18.39 |====================================================================
C . 18.47 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 6.8952 |==================================================================
B . 6.9928 |===================================================================
C . 6.8642 |==================================================================
Neural Magic DeepSparse 1.1
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 718.18 |===================================================================
B . 713.09 |==================================================================
C . 720.94 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 6.5652 |==================================================================
B . 6.5403 |==================================================================
C . 6.6166 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 152.31 |===================================================================
B . 152.90 |===================================================================
C . 151.13 |==================================================================
Neural Magic DeepSparse 1.1
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 27.45 |====================================================================
B . 27.59 |====================================================================
C . 27.16 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 181.39 |==================================================================
B . 180.40 |==================================================================
C . 183.74 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 22.93 |====================================================================
B . 22.91 |====================================================================
C . 22.87 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 43.61 |====================================================================
B . 43.63 |====================================================================
C . 43.72 |====================================================================
Neural Magic DeepSparse 1.1
Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 44.11 |====================================================================
B . 44.23 |====================================================================
C . 43.78 |===================================================================
Neural Magic DeepSparse 1.1
Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 112.51 |===================================================================
B . 112.26 |==================================================================
C . 113.28 |===================================================================
Neural Magic DeepSparse 1.1
Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 38.35 |====================================================================
B . 38.27 |====================================================================
C . 37.96 |===================================================================
Neural Magic DeepSparse 1.1
Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 26.07 |===================================================================
B . 26.12 |===================================================================
C . 26.34 |====================================================================
Neural Magic DeepSparse 1.1
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 87.76 |====================================================================
B . 88.32 |====================================================================
C . 88.07 |====================================================================
Neural Magic DeepSparse 1.1
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 56.78 |====================================================================
B . 56.42 |====================================================================
C . 56.74 |====================================================================
Neural Magic DeepSparse 1.1
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 70.86 |====================================================================
B . 70.74 |====================================================================
C . 70.66 |====================================================================
Neural Magic DeepSparse 1.1
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 14.11 |====================================================================
B . 14.13 |====================================================================
C . 14.15 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 56.69 |====================================================================
B . 56.79 |====================================================================
C . 55.69 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 87.71 |===================================================================
B . 87.68 |===================================================================
C . 89.28 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 48.79 |====================================================================
B . 48.60 |====================================================================
C . 48.05 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 20.49 |===================================================================
B . 20.57 |===================================================================
C . 20.81 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 28.61 |====================================================================
B . 28.39 |===================================================================
C . 28.76 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 174.68 |===================================================================
B . 175.71 |===================================================================
C . 172.62 |==================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 24.37 |===================================================================
B . 24.16 |==================================================================
C . 24.90 |====================================================================
Neural Magic DeepSparse 1.1
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 41.03 |===================================================================
B . 41.39 |====================================================================
C . 40.16 |==================================================================
Neural Magic DeepSparse 1.1
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
A . 6.8935 |===================================================================
B . 6.8793 |===================================================================
C . 6.8706 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
A . 719.46 |===================================================================
B . 720.35 |===================================================================
C . 720.18 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
A . 6.4771 |==================================================================
B . 6.4710 |==================================================================
C . 6.5651 |===================================================================
Neural Magic DeepSparse 1.1
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
A . 154.39 |===================================================================
B . 154.53 |===================================================================
C . 152.32 |==================================================================
spaCy 3.4.1
Model: en_core_web_lg
tokens/sec > Higher Is Better
A . 17226 |====================================================================
B . 17254 |====================================================================
C . 17118 |===================================================================
spaCy 3.4.1
Model: en_core_web_trf
tokens/sec > Higher Is Better
A . 1089 |=====================================================================
B . 1070 |====================================================================
C . 1074 |====================================================================