fggd Tests for a future article. AMD Ryzen 7 7840U testing with a PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS) and AMD Phoenix1 512MB on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 7840U @ 5.29GHz (8 Cores / 16 Threads), Motherboard: PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 4GB DRAM-6400MT/s K3LKBKB0BM-MGCP, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: AMD Phoenix1 512MB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.1~git2401230600.42fc83~oibaf~m (git-42fc83a 2024-01-23 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3200x2000 b: Processor: AMD Ryzen 7 7840U @ 5.29GHz (8 Cores / 16 Threads), Motherboard: PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 4GB DRAM-6400MT/s K3LKBKB0BM-MGCP, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: AMD Phoenix1 512MB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7922 802.11ax PCI OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.1~git2401230600.42fc83~oibaf~m (git-42fc83a 2024-01-23 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3200x2000 SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.857 |====================================================== b . 3.619 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 22.23 |===================================================== b . 28.70 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 63.13 |============================================================= b . 70.63 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 63.70 |================================================================ b . 67.84 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 10.80 |========================================================== b . 12.77 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 77.98 |=========================================================== b . 90.24 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 327.71 |============================================================= b . 358.95 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 410.69 |=============================================================== b . 436.41 |=================================================================== Timed Linux Kernel Compilation 6.8 Build: defconfig Seconds < Lower Is Better a . 176.42 |=================================================================== b . 162.74 |============================================================== Timed Linux Kernel Compilation 6.8 Build: allmodconfig Seconds < Lower Is Better a . 2616.59 |================================================================== b . 2587.39 |================================================================= Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Seconds < Lower Is Better a . 10.98 |=================================================================== b . 11.08 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 5.2615 |================================================================== b . 5.3183 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 568.02 |=================================================================== b . 563.38 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 5.5471 |================================================================== b . 5.6015 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 180.26 |=================================================================== b . 178.51 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 220.66 |================================================================= b . 227.17 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 13.57 |==================================================================== b . 13.18 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 157.69 |================================================================= b . 161.81 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 6.3251 |=================================================================== b . 6.1647 |================================================================= Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 71.36 |================================================================== b . 74.04 |==================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 42.00 |==================================================================== b . 40.47 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 57.39 |================================================================== b . 58.75 |==================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 17.41 |==================================================================== b . 17.01 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 599.85 |================================================================= b . 616.44 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 4.9744 |=================================================================== b . 4.8394 |================================================================= Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 373.53 |================================================================== b . 377.91 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 2.6549 |=================================================================== b . 2.6245 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2.7165 |=================================================================== b . 2.7230 |=================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 1094.29 |================================================================== b . 1087.73 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 5.2143 |=================================================================== b . 5.2192 |=================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 191.75 |=================================================================== b . 191.57 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 64.81 |=================================================================== b . 66.04 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 46.25 |==================================================================== b . 45.38 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 54.10 |==================================================================== b . 54.20 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 18.47 |==================================================================== b . 18.43 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 32.20 |==================================================================== b . 32.11 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 93.13 |==================================================================== b . 93.38 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 29.05 |==================================================================== b . 28.58 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 34.40 |=================================================================== b . 34.97 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 47.26 |==================================================================== b . 46.28 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 63.44 |=================================================================== b . 64.76 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 42.99 |==================================================================== b . 42.72 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 23.25 |==================================================================== b . 23.39 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 9.5583 |=================================================================== b . 9.5532 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 313.73 |=================================================================== b . 313.96 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 9.6551 |=================================================================== b . 9.5857 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 103.54 |=================================================================== b . 104.29 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 94.17 |=================================================================== b . 95.43 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 31.82 |==================================================================== b . 31.40 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 73.34 |==================================================================== b . 71.01 |================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 13.61 |================================================================== b . 14.06 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 5.2084 |=================================================================== b . 5.0336 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 573.12 |================================================================= b . 593.88 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 5.1893 |=================================================================== b . 5.1251 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 192.69 |================================================================== b . 195.10 |===================================================================