3900xt-november AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 aa: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better aa . 28.71 |=================================================================== a .. 28.79 |=================================================================== b .. 28.33 |================================================================== SMHasher 2022-08-22 Hash: SHA3-256 cycles/hash < Lower Is Better a .. 2598.05 |================================================================ aa . 2620.22 |================================================================= b .. 2564.21 |================================================================ SMHasher 2022-08-22 Hash: SHA3-256 MiB/sec > Higher Is Better a .. 149.08 |================================================================= aa . 148.14 |================================================================ b .. 151.76 |================================================================== nekRS 22.0 Input: TurboPipe Periodic FLOP/s > Higher Is Better a .. 31559900000 |=========================================================== aa . 32575200000 |============================================================= b .. 32544333333 |============================================================= OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better a .. 633.97 |================================================================ aa . 650.25 |================================================================== b .. 631.33 |================================================================ TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better a .. 28.64 |=================================================================== aa . 28.67 |=================================================================== b .. 28.65 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better a .. 110.36 |================================================================== aa . 110.49 |================================================================== b .. 110.02 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a .. 10.09 |=================================================================== aa . 10.06 |=================================================================== b .. 10.12 |=================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 MP/s > Higher Is Better a .. 0.68 |==================================================================== aa . 0.68 |==================================================================== b .. 0.68 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 100 MP/s > Higher Is Better a .. 0.69 |==================================================================== aa . 0.69 |==================================================================== b .. 0.69 |==================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a .. 10.29 |=================================================================== aa . 10.29 |=================================================================== b .. 10.33 |=================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Billion Interactions/s > Higher Is Better a .. 16.39 |=================================================================== aa . 16.41 |=================================================================== b .. 16.41 |=================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 GFInst/s > Higher Is Better a .. 409.86 |================================================================== aa . 410.31 |================================================================== b .. 410.14 |================================================================== OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Seconds < Lower Is Better a .. 285.69 |================================================================== aa . 286.84 |================================================================== b .. 287.33 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload FPS > Higher Is Better a .. 12.64 |=================================================================== aa . 12.64 |=================================================================== b .. 12.67 |=================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload Seconds < Lower Is Better a .. 199.73 |================================================================== aa . 199.81 |================================================================== b .. 199.35 |================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform FPS > Higher Is Better a .. 31.31 |================================================================== aa . 31.49 |=================================================================== b .. 31.55 |=================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform Seconds < Lower Is Better a .. 241.93 |================================================================== aa . 240.52 |================================================================== b .. 240.09 |================================================================= FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand FPS > Higher Is Better a .. 31.45 |=================================================================== aa . 31.62 |=================================================================== b .. 31.56 |=================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand Seconds < Lower Is Better a .. 240.84 |================================================================== aa . 239.59 |================================================================== b .. 240.03 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better a .. 109.23 |================================================================== aa . 109.38 |================================================================== b .. 109.30 |================================================================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Seconds < Lower Is Better a .. 363.22 |================================================================== aa . 361.48 |================================================================== b .. 360.00 |================================================================= OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Seconds < Lower Is Better a .. 41.82 |=================================================================== aa . 41.85 |=================================================================== b .. 42.08 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a .. 30.55 |=================================================================== aa . 30.51 |=================================================================== b .. 30.50 |=================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload FPS > Higher Is Better a .. 15.32 |=================================================================== aa . 15.33 |=================================================================== b .. 15.37 |=================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload Seconds < Lower Is Better a .. 164.80 |================================================================== aa . 164.72 |================================================================== b .. 164.26 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform FPS > Higher Is Better a .. 48.84 |=================================================================== aa . 49.01 |=================================================================== b .. 48.62 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform Seconds < Lower Is Better a .. 155.11 |================================================================== aa . 154.57 |================================================================= b .. 155.81 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand FPS > Higher Is Better a .. 48.83 |=================================================================== aa . 48.85 |=================================================================== b .. 48.77 |=================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand Seconds < Lower Is Better a .. 155.14 |================================================================== aa . 155.06 |================================================================== b .. 155.31 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a .. 10.39 |=================================================================== aa . 10.44 |=================================================================== b .. 10.44 |=================================================================== OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better a .. 131.00 |================================================================== aa . 130.82 |================================================================== b .. 130.06 |================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 MP/s > Higher Is Better a .. 8.68 |================================================================== aa . 8.98 |==================================================================== b .. 8.84 |=================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 80 MP/s > Higher Is Better a .. 9.08 |==================================================================== aa . 9.13 |==================================================================== b .. 9.12 |==================================================================== libavif avifenc 0.11 Encoder Speed: 0 Seconds < Lower Is Better a .. 130.36 |================================================================= aa . 131.57 |================================================================== b .. 130.15 |================================================================= OpenRadioss 2022.10.13 Model: Bumper Beam Seconds < Lower Is Better a .. 127.42 |================================================================== aa . 126.51 |================================================================== b .. 127.37 |================================================================== Xmrig 6.18.1 Variant: Monero - Hash Count: 1M H/s > Higher Is Better a .. 7982.6 |================================================================ aa . 7945.8 |================================================================ b .. 8175.8 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a .. 30.46 |=================================================================== aa . 30.58 |=================================================================== b .. 30.48 |=================================================================== OpenRadioss 2022.10.13 Model: Cell Phone Drop Test Seconds < Lower Is Better a .. 104.51 |================================================================== aa . 104.11 |================================================================== b .. 104.27 |================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 MP/s > Higher Is Better a .. 8.62 |=================================================================== aa . 8.76 |==================================================================== b .. 8.80 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 90 MP/s > Higher Is Better a .. 9.02 |==================================================================== aa . 9.03 |==================================================================== b .. 9.07 |==================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 7.41 |==================================================================== aa . 7.45 |==================================================================== b .. 7.41 |==================================================================== Cpuminer-Opt 3.20.3 Algorithm: Garlicoin kH/s > Higher Is Better a .. 1939.65 |============================================================ aa . 1960.71 |============================================================ b .. 2112.41 |================================================================= Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M H/s > Higher Is Better a .. 10466.6 |================================================================ aa . 10640.0 |================================================================= b .. 10577.3 |================================================================= FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live FPS > Higher Is Better a .. 75.38 |=================================================================== aa . 75.50 |=================================================================== b .. 75.10 |=================================================================== FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live Seconds < Lower Is Better a .. 66.99 |=================================================================== aa . 66.89 |=================================================================== b .. 67.26 |=================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 4075.57 |================================================================ aa . 4145.83 |================================================================= b .. 4147.65 |================================================================= AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 0.25 |==================================================================== aa . 0.25 |==================================================================== b .. 0.25 |==================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 2503.12 |================================================================= aa . 2484.90 |================================================================= b .. 2481.61 |================================================================ TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a .. 93.80 |=================================================================== aa . 93.88 |=================================================================== b .. 93.79 |=================================================================== Libplacebo 5.229.1 Test: av1_grain_lap FPS > Higher Is Better a .. 2073.69 |================================================================ aa . 2106.73 |================================================================= b .. 2093.70 |================================================================= Libplacebo 5.229.1 Test: hdr_lut FPS > Higher Is Better a .. 2797.23 |================================================================ aa . 2806.16 |================================================================ b .. 2840.16 |================================================================= Libplacebo 5.229.1 Test: hdr_peakdetect FPS > Higher Is Better a .. 2610.20 |================================================================= aa . 2598.97 |================================================================= b .. 2603.19 |================================================================= Libplacebo 5.229.1 Test: polar_nocompute FPS > Higher Is Better a .. 977.72 |================================================================== aa . 948.28 |================================================================ b .. 961.48 |================================================================= Libplacebo 5.229.1 Test: deband_heavy FPS > Higher Is Better a .. 476.59 |================================================================== aa . 479.65 |================================================================== b .. 474.53 |================================================================= Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S kH/s > Higher Is Better a .. 524680 |================================================================== aa . 528060 |================================================================== b .. 519433 |================================================================= oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 8.22740 |================================================================= aa . 5.47125 |=========================================== b .. 6.22396 |================================================= libavif avifenc 0.11 Encoder Speed: 2 Seconds < Lower Is Better a .. 63.12 |================================================================== aa . 64.02 |=================================================================== b .. 64.37 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 12.67 |=================================================================== aa . 12.68 |=================================================================== b .. 12.71 |=================================================================== spaCy 3.4.1 Model: en_core_web_trf tokens/sec > Higher Is Better aa . 833 |===================================================================== a .. 832 |===================================================================== b .. 550 |============================================== spaCy 3.4.1 Model: en_core_web_lg tokens/sec > Higher Is Better aa . 12217 |=================================================================== a .. 12196 |=================================================================== b .. 11978 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better a .. 31.89 |=================================================================== aa . 31.83 |=================================================================== b .. 31.85 |=================================================================== JPEG XL Decoding libjxl 0.7 CPU Threads: 1 MP/s > Higher Is Better a .. 48.69 |=================================================================== aa . 47.21 |================================================================= b .. 48.24 |================================================================== nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better aa . 65507.92 |=============================================================== a .. 65135.63 |=============================================================== b .. 66302.86 |================================================================ nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better aa . 76617.70 |================================================================ a .. 75259.81 |=============================================================== b .. 76562.05 |================================================================ nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better aa . 84210.42 |================================================================ a .. 83513.14 |=============================================================== b .. 82789.42 |=============================================================== nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better aa . 86726.10 |================================================================ a .. 87222.68 |================================================================ b .. 83591.65 |============================================================= miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Billion Interactions/s > Higher Is Better a .. 16.23 |=================================================================== aa . 16.27 |=================================================================== b .. 16.17 |=================================================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 GFInst/s > Higher Is Better a .. 405.82 |================================================================== aa . 406.71 |================================================================== b .. 404.25 |================================================================== AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 15.08 |=================================================================== aa . 15.01 |=================================================================== b .. 15.12 |=================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a .. 76.22 |=================================================================== aa . 76.25 |=================================================================== b .. 76.37 |=================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 1B Seconds < Lower Is Better a .. 41.52 |================================================================== aa . 41.84 |=================================================================== b .. 41.43 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live FPS > Higher Is Better a .. 204.75 |================================================================== aa . 205.03 |================================================================== b .. 204.73 |================================================================== FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live Seconds < Lower Is Better a .. 24.66 |=================================================================== aa . 24.63 |=================================================================== b .. 24.67 |=================================================================== SMHasher 2022-08-22 Hash: FarmHash128 cycles/hash < Lower Is Better a .. 64.10 |=================================================================== aa . 60.34 |=============================================================== b .. 61.81 |================================================================= SMHasher 2022-08-22 Hash: FarmHash128 MiB/sec > Higher Is Better a .. 15884.24 |============================================================= aa . 16614.28 |================================================================ b .. 16361.64 |=============================================================== oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 1.88170 |================================================================= aa . 1.27895 |============================================ b .. 1.74121 |============================================================ SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI cycles/hash < Lower Is Better a .. 57.74 |=================================================================== aa . 56.98 |================================================================== b .. 55.88 |================================================================= SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI MiB/sec > Higher Is Better a .. 37183.28 |============================================================== aa . 37904.32 |=============================================================== b .. 38610.17 |================================================================ JPEG XL Decoding libjxl 0.7 CPU Threads: All MP/s > Higher Is Better a .. 146.63 |================================================================= aa . 148.61 |================================================================== b .. 148.59 |================================================================== SMHasher 2022-08-22 Hash: Spooky32 cycles/hash < Lower Is Better a .. 49.06 |================================================================== aa . 48.98 |================================================================== b .. 49.50 |=================================================================== SMHasher 2022-08-22 Hash: Spooky32 MiB/sec > Higher Is Better a .. 14909.02 |=============================================================== aa . 15026.60 |================================================================ b .. 14856.10 |=============================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 181.46 |================================================================== a .. 180.61 |================================================================= b .. 182.26 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 33.06 |=================================================================== a .. 33.21 |=================================================================== b .. 32.91 |================================================================== TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better a .. 55.63 |=================================================================== aa . 55.47 |=================================================================== b .. 55.49 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 617.74 |================================================================== a .. 611.84 |================================================================= b .. 618.14 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 9.7085 |================================================================== a .. 9.7748 |================================================================== b .. 9.6761 |================================================================= EnCodec 0.1.1 Target Bandwidth: 24 kbps Seconds < Lower Is Better aa . 54.43 |================================================================== a .. 54.42 |================================================================== b .. 54.86 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 146.11 |================================================================== a .. 146.48 |================================================================== b .. 146.64 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 41.06 |=================================================================== a .. 40.95 |=================================================================== b .. 40.91 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 617.03 |================================================================== a .. 617.65 |================================================================== b .. 609.83 |================================================================= Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 9.7230 |================================================================= a .. 9.7133 |================================================================= b .. 9.8238 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Skeincoin kH/s > Higher Is Better a .. 106880 |================================================================= aa . 108620 |================================================================== b .. 105667 |================================================================ Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin kH/s > Higher Is Better a .. 204970 |================================================================== aa . 204950 |================================================================== b .. 205100 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Myriad-Groestl kH/s > Higher Is Better a .. 21130 |================================================================== aa . 21260 |=================================================================== b .. 21397 |=================================================================== Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite kH/s > Higher Is Better a .. 102170 |================================================================== aa . 102180 |================================================================== b .. 102017 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: x25x kH/s > Higher Is Better a .. 631.15 |================================================================== aa . 631.74 |================================================================== b .. 628.47 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Magi kH/s > Higher Is Better a .. 603.58 |================================================================== aa . 603.33 |================================================================== b .. 600.87 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits kH/s > Higher Is Better a .. 31260 |================================================================== aa . 31820 |=================================================================== b .. 31143 |================================================================== Cpuminer-Opt 3.20.3 Algorithm: Ringcoin kH/s > Higher Is Better a .. 2705.27 |================================================================ aa . 2709.03 |================================================================ b .. 2730.30 |================================================================= Cpuminer-Opt 3.20.3 Algorithm: Deepcoin kH/s > Higher Is Better a .. 11710 |=================================================================== aa . 11720 |=================================================================== b .. 11660 |=================================================================== Cpuminer-Opt 3.20.3 Algorithm: scrypt kH/s > Higher Is Better a .. 226.42 |================================================================== aa . 226.59 |================================================================== b .. 225.89 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 49.23 |=================================================================== a .. 48.49 |================================================================== b .. 49.49 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 20.31 |================================================================== a .. 20.62 |=================================================================== b .. 20.20 |================================================================== EnCodec 0.1.1 Target Bandwidth: 6 kbps Seconds < Lower Is Better aa . 48.56 |=================================================================== a .. 47.33 |================================================================= b .. 48.22 |=================================================================== EnCodec 0.1.1 Target Bandwidth: 3 kbps Seconds < Lower Is Better aa . 47.66 |================================================================== a .. 47.23 |================================================================= b .. 48.45 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 0.73 |==================================================================== aa . 0.73 |==================================================================== b .. 0.73 |==================================================================== EnCodec 0.1.1 Target Bandwidth: 1.5 kbps Seconds < Lower Is Better aa . 46.08 |================================================================== a .. 45.14 |================================================================= b .. 46.62 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 124.76 |================================================================== a .. 124.79 |================================================================== b .. 125.05 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 8.0151 |================================================================== a .. 8.0129 |================================================================== b .. 7.9966 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 125.17 |================================================================== a .. 125.35 |================================================================== b .. 125.27 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 7.9890 |================================================================== a .. 7.9776 |================================================================== b .. 7.9824 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 33.32 |=================================================================== a .. 33.39 |=================================================================== b .. 33.34 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 30.00 |=================================================================== a .. 29.95 |=================================================================== b .. 29.99 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 23.10 |=================================================================== aa . 23.20 |=================================================================== b .. 23.13 |=================================================================== SMHasher 2022-08-22 Hash: t1ha2_atonce cycles/hash < Lower Is Better a .. 32.25 |=============================================================== aa . 34.55 |=================================================================== b .. 33.68 |================================================================= SMHasher 2022-08-22 Hash: t1ha2_atonce MiB/sec > Higher Is Better a .. 16686.57 |================================================================ aa . 15706.92 |============================================================ b .. 16085.48 |============================================================== SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 cycles/hash < Lower Is Better a .. 34.81 |=================================================================== aa . 32.88 |=============================================================== b .. 33.61 |================================================================= SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 MiB/sec > Higher Is Better a .. 66796.46 |============================================================= aa . 69896.41 |================================================================ b .. 68310.66 |=============================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 74.01 |=================================================================== a .. 73.71 |=================================================================== b .. 73.77 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 81.04 |=================================================================== a .. 81.37 |=================================================================== b .. 81.31 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 113.64 |================================================================== a .. 113.46 |================================================================= b .. 114.40 |================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 52.78 |=================================================================== a .. 52.85 |=================================================================== b .. 52.42 |================================================================== FLAC Audio Encoding 1.4 WAV To FLAC Seconds < Lower Is Better a .. 17.26 |=================================================================== aa . 17.33 |=================================================================== b .. 17.21 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 53.41 |=================================================================== a .. 53.41 |=================================================================== b .. 53.44 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 112.26 |================================================================== a .. 112.28 |================================================================== b .. 112.12 |================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 16.77 |=================================================================== a .. 16.82 |=================================================================== b .. 16.83 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 59.62 |=================================================================== a .. 59.45 |=================================================================== b .. 59.41 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 23.57 |=================================================================== a .. 23.56 |=================================================================== b .. 23.60 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 42.41 |=================================================================== a .. 42.43 |=================================================================== b .. 42.36 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 12.75 |=================================================================== a .. 12.75 |=================================================================== b .. 12.76 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 78.41 |=================================================================== a .. 78.39 |=================================================================== b .. 78.31 |=================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 500M Seconds < Lower Is Better a .. 19.55 |=================================================================== aa . 19.53 |=================================================================== b .. 19.53 |=================================================================== QuadRay 2022.05.25 Scene: 5 - Resolution: 4K FPS > Higher Is Better a .. 0.66 |==================================================================== aa . 0.66 |==================================================================== b .. 0.66 |==================================================================== QuadRay 2022.05.25 Scene: 2 - Resolution: 4K FPS > Higher Is Better a .. 2.89 |==================================================================== aa . 2.90 |==================================================================== b .. 2.86 |=================================================================== QuadRay 2022.05.25 Scene: 3 - Resolution: 4K FPS > Higher Is Better a .. 2.46 |=================================================================== aa . 2.43 |================================================================== b .. 2.49 |==================================================================== QuadRay 2022.05.25 Scene: 1 - Resolution: 4K FPS > Higher Is Better a .. 10.21 |=================================================================== aa . 9.63 |=============================================================== b .. 10.14 |=================================================================== QuadRay 2022.05.25 Scene: 5 - Resolution: 1080p FPS > Higher Is Better a .. 2.64 |==================================================================== aa . 2.62 |=================================================================== b .. 2.63 |==================================================================== QuadRay 2022.05.25 Scene: 2 - Resolution: 1080p FPS > Higher Is Better a .. 11.12 |================================================================== aa . 11.22 |=================================================================== b .. 11.17 |=================================================================== QuadRay 2022.05.25 Scene: 3 - Resolution: 1080p FPS > Higher Is Better a .. 9.71 |=================================================================== aa . 9.81 |==================================================================== b .. 9.70 |=================================================================== QuadRay 2022.05.25 Scene: 1 - Resolution: 1080p FPS > Higher Is Better a .. 39.48 |=================================================================== aa . 38.50 |================================================================= b .. 39.26 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 41.57 |================================================================== aa . 42.17 |=================================================================== b .. 42.07 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 34.46 |================================================================== aa . 34.91 |=================================================================== b .. 34.60 |================================================================== Stress-NG 0.14.06 Test: Context Switching Bogo Ops/s > Higher Is Better aa . 4103283.77 |============================================================== a .. 4076744.52 |============================================================== b .. 3796353.99 |========================================================= Stress-NG 0.14.06 Test: CPU Cache Bogo Ops/s > Higher Is Better aa . 152.46 |=============================================================== a .. 158.89 |================================================================== b .. 149.79 |============================================================== Stress-NG 0.14.06 Test: MEMFD Bogo Ops/s > Higher Is Better aa . 773.07 |================================================================== a .. 747.31 |================================================================ b .. 770.89 |================================================================== Stress-NG 0.14.06 Test: Futex Bogo Ops/s > Higher Is Better aa . 2717409.38 |============================================================== a .. 2600010.05 |=========================================================== b .. 2563831.67 |========================================================== Stress-NG 0.14.06 Test: NUMA Bogo Ops/s > Higher Is Better aa . 261.26 |================================================================== a .. 260.68 |================================================================== b .. 260.02 |================================================================== Stress-NG 0.14.06 Test: System V Message Passing Bogo Ops/s > Higher Is Better aa . 7932169.44 |============================================================== a .. 7925418.15 |============================================================== b .. 7654922.05 |============================================================ Stress-NG 0.14.06 Test: Mutex Bogo Ops/s > Higher Is Better aa . 6371966.37 |============================================================== a .. 6319425.86 |============================================================= b .. 6344621.56 |============================================================== Stress-NG 0.14.06 Test: Memory Copying Bogo Ops/s > Higher Is Better aa . 3592.78 |================================================================= a .. 3599.42 |================================================================= b .. 3456.53 |============================================================== Stress-NG 0.14.06 Test: Socket Activity Bogo Ops/s > Higher Is Better aa . 8500.17 |============================================================== a .. 8595.20 |============================================================== b .. 8961.20 |================================================================= Stress-NG 0.14.06 Test: Matrix Math Bogo Ops/s > Higher Is Better aa . 61203.21 |================================================================ a .. 61078.06 |================================================================ b .. 58814.38 |============================================================== Stress-NG 0.14.06 Test: Malloc Bogo Ops/s > Higher Is Better aa . 13924963.43 |============================================================= a .. 13779284.62 |============================================================ b .. 13767394.33 |============================================================ Stress-NG 0.14.06 Test: Semaphores Bogo Ops/s > Higher Is Better aa . 2465656.19 |============================================================== a .. 2463565.68 |============================================================== b .. 2466594.73 |============================================================== Stress-NG 0.14.06 Test: Forking Bogo Ops/s > Higher Is Better aa . 40572.79 |================================================================ a .. 40818.92 |================================================================ b .. 40197.60 |=============================================================== Stress-NG 0.14.06 Test: Crypto Bogo Ops/s > Higher Is Better aa . 22525.14 |================================================================ a .. 22523.79 |================================================================ b .. 22434.69 |================================================================ Stress-NG 0.14.06 Test: MMAP Bogo Ops/s > Higher Is Better aa . 292.10 |================================================================== a .. 294.05 |================================================================== b .. 293.29 |================================================================== Stress-NG 0.14.06 Test: IO_uring Bogo Ops/s > Higher Is Better aa . 8765.88 |================================================================= a .. 5126.99 |====================================== b .. 4168.54 |=============================== Stress-NG 0.14.06 Test: Atomic Bogo Ops/s > Higher Is Better aa . 575708.53 |=============================================================== a .. 575564.96 |=============================================================== b .. 571674.68 |=============================================================== Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better aa . 192.23 |================================================================== a .. 180.77 |============================================================== b .. 184.77 |=============================================================== Stress-NG 0.14.06 Test: CPU Stress Bogo Ops/s > Higher Is Better aa . 31954.78 |============================================================== a .. 32900.39 |================================================================ b .. 30793.53 |============================================================ Stress-NG 0.14.06 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better aa . 2035501.44 |============================================================== a .. 2048965.25 |============================================================== b .. 1531955.88 |============================================== Stress-NG 0.14.06 Test: Vector Math Bogo Ops/s > Higher Is Better aa . 90998.92 |================================================================ a .. 90999.65 |================================================================ b .. 87587.66 |============================================================== Stress-NG 0.14.06 Test: SENDFILE Bogo Ops/s > Higher Is Better aa . 215163.99 |=============================================================== a .. 215308.14 |=============================================================== b .. 205666.12 |============================================================ oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 4.69026 |================================================================ aa . 4.74859 |================================================================= b .. 4.73086 |================================================================= AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 47.42 |=================================================================== aa . 47.62 |=================================================================== b .. 47.60 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 47.55 |================================================================== aa . 47.95 |=================================================================== b .. 48.23 |=================================================================== AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 45.20 |================================================================ aa . 46.98 |=================================================================== b .. 45.64 |================================================================= SMHasher 2022-08-22 Hash: fasthash32 cycles/hash < Lower Is Better a .. 36.90 |=================================================================== aa . 35.26 |================================================================ b .. 36.69 |=================================================================== SMHasher 2022-08-22 Hash: fasthash32 MiB/sec > Higher Is Better a .. 6658.92 |=============================================================== aa . 6917.32 |================================================================= b .. 6686.25 |=============================================================== libavif avifenc 0.11 Encoder Speed: 6, Lossless Seconds < Lower Is Better a .. 10.15 |=================================================================== aa . 10.09 |=================================================================== b .. 10.15 |=================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 12.06 |=================================================================== aa . 12.03 |=================================================================== b .. 12.03 |=================================================================== SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX cycles/hash < Lower Is Better a .. 40.07 |=============================================================== aa . 41.13 |================================================================= b .. 42.58 |=================================================================== SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX MiB/sec > Higher Is Better a .. 29093.03 |================================================================ aa . 28582.22 |=============================================================== b .. 27788.51 |============================================================= AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 85.22 |================================================================== aa . 85.90 |=================================================================== b .. 84.93 |================================================================== SMHasher 2022-08-22 Hash: wyhash cycles/hash < Lower Is Better a .. 25.31 |================================================================= aa . 25.29 |================================================================= b .. 25.91 |=================================================================== SMHasher 2022-08-22 Hash: wyhash MiB/sec > Higher Is Better a .. 23915.75 |================================================================ aa . 24070.66 |================================================================ b .. 23571.26 |=============================================================== oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 22.54 |=================================================================== aa . 22.55 |=================================================================== b .. 22.52 |=================================================================== libavif avifenc 0.11 Encoder Speed: 6 Seconds < Lower Is Better a .. 6.049 |=================================================================== aa . 6.076 |=================================================================== b .. 6.019 |================================================================== AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 108.47 |================================================================== aa . 108.91 |================================================================== b .. 107.41 |================================================================= AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 109.52 |================================================================= aa . 111.49 |================================================================== b .. 110.26 |================================================================= libavif avifenc 0.11 Encoder Speed: 10, Lossless Seconds < Lower Is Better a .. 5.480 |=================================================================== aa . 5.505 |=================================================================== b .. 5.497 |=================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 5.27435 |================================================================= aa . 5.25072 |================================================================= b .. 5.28794 |=================================================================