AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (0805 BIOS) and AMD Radeon RX 6800/6800 XT / 6900 on Ubuntu 22.10 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 2301241-NE-DEEPSPARS52
deepsparse 7950x
AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (0805 BIOS) and AMD Radeon RX 6800/6800 XT / 6900 on Ubuntu 22.10 via the Phoronix Test Suite.
a:
Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0805 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 257GB Flash Drive, Graphics: AMD Radeon RX 6800/6800 XT / 6900, Audio: AMD Navi 21/23, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.10, Kernel: 5.19.0-29-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server + Wayland, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160
bb:
Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0805 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 257GB Flash Drive, Graphics: AMD Radeon RX 6800/6800 XT / 6900 (2575/1000MHz), Audio: AMD Navi 21/23, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.10, Kernel: 5.19.0-29-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160
c:
Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0805 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 257GB Flash Drive, Graphics: AMD Radeon RX 6800/6800 XT / 6900 (2575/1000MHz), Audio: AMD Navi 21/23, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.10, Kernel: 5.19.0-29-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160
d:
Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0805 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 257GB Flash Drive, Graphics: AMD Radeon RX 6800/6800 XT / 6900 (2575/1000MHz), Audio: AMD Navi 21/23, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.10, Kernel: 5.19.0-29-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160
Neural Magic DeepSparse 1.3.2
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 12.70 |===================================================================
bb . 12.64 |===================================================================
c .. 12.59 |==================================================================
d .. 12.64 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 11.76 |===================================================================
bb . 11.72 |===================================================================
c .. 11.69 |===================================================================
d .. 11.72 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 447.31 |==================================================================
bb . 445.89 |==================================================================
c .. 446.65 |==================================================================
d .. 446.73 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 163.77 |==================================================================
bb . 163.25 |==================================================================
c .. 162.78 |=================================================================
d .. 164.27 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 101.26 |==================================================================
bb . 101.57 |==================================================================
c .. 100.75 |=================================================================
d .. 100.93 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 64.84 |===================================================================
bb . 64.16 |==================================================================
c .. 64.39 |===================================================================
d .. 64.44 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 116.66 |=================================================================
bb . 117.61 |==================================================================
c .. 115.99 |=================================================================
d .. 116.06 |=================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 88.72 |===================================================================
bb . 88.80 |===================================================================
c .. 89.05 |===================================================================
d .. 88.95 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 298.27 |==================================================================
bb . 298.34 |==================================================================
c .. 298.62 |==================================================================
d .. 297.80 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 204.37 |==================================================================
bb . 204.04 |==================================================================
c .. 204.66 |==================================================================
d .. 204.44 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 184.90 |==================================================================
bb . 184.42 |==================================================================
c .. 182.96 |=================================================================
d .. 182.03 |=================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 116.74 |==================================================================
bb . 117.54 |==================================================================
c .. 116.61 |=================================================================
d .. 117.53 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 39.76 |===================================================================
bb . 39.64 |===================================================================
c .. 39.87 |===================================================================
d .. 39.85 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 33.91 |===================================================================
bb . 33.89 |===================================================================
c .. 33.90 |===================================================================
d .. 33.87 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 96.06 |===================================================================
bb . 95.57 |===================================================================
c .. 96.28 |===================================================================
d .. 95.61 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 61.73 |===================================================================
bb . 61.14 |==================================================================
c .. 61.90 |===================================================================
d .. 61.93 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a .. 12.59 |===================================================================
bb . 12.63 |===================================================================
c .. 12.63 |===================================================================
d .. 12.59 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
items/sec > Higher Is Better
a .. 11.72 |===================================================================
bb . 11.71 |===================================================================
c .. 11.74 |===================================================================
d .. 11.73 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 627.44 |=================================================================
bb . 630.52 |==================================================================
c .. 632.93 |==================================================================
d .. 630.36 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 85.03 |===================================================================
bb . 85.33 |===================================================================
c .. 85.51 |===================================================================
d .. 85.32 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 17.87 |===================================================================
bb . 17.93 |===================================================================
c .. 17.90 |===================================================================
d .. 17.89 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 6.1019 |==================================================================
bb . 6.1208 |==================================================================
c .. 6.1393 |==================================================================
d .. 6.0829 |=================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 78.98 |===================================================================
bb . 78.74 |==================================================================
c .. 79.38 |===================================================================
d .. 79.24 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 15.42 |==================================================================
bb . 15.58 |===================================================================
c .. 15.52 |===================================================================
d .. 15.51 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 68.51 |===================================================================
bb . 67.95 |==================================================================
c .. 68.93 |===================================================================
d .. 68.88 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 11.25 |===================================================================
bb . 11.25 |===================================================================
c .. 11.21 |===================================================================
d .. 11.23 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 26.81 |===================================================================
bb . 26.80 |===================================================================
c .. 26.78 |===================================================================
d .. 26.85 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 4.8880 |==================================================================
bb . 4.8960 |==================================================================
c .. 4.8812 |==================================================================
d .. 4.8865 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 43.25 |==================================================================
bb . 43.37 |==================================================================
c .. 43.71 |===================================================================
d .. 43.94 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 8.5625 |==================================================================
bb . 8.5043 |=================================================================
c .. 8.5719 |==================================================================
d .. 8.5044 |=================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 201.01 |==================================================================
bb . 201.36 |==================================================================
c .. 200.48 |==================================================================
d .. 200.53 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 29.48 |===================================================================
bb . 29.49 |===================================================================
c .. 29.49 |===================================================================
d .. 29.51 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 83.27 |===================================================================
bb . 83.70 |===================================================================
c .. 83.08 |===================================================================
d .. 83.66 |===================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 16.20 |==================================================================
bb . 16.35 |===================================================================
c .. 16.15 |==================================================================
d .. 16.14 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a .. 633.18 |==================================================================
bb . 630.80 |==================================================================
c .. 631.30 |==================================================================
d .. 632.16 |==================================================================
Neural Magic DeepSparse 1.3.2
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream
ms/batch < Lower Is Better
a .. 85.35 |===================================================================
bb . 85.38 |===================================================================
c .. 85.18 |===================================================================
d .. 85.22 |===================================================================