Benchmarks by Michael Larabel for a future article.
AMD Preferred Core Patched Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu122.04)Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD Preferred Core Disabled Processor: AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads), Motherboard: ASRockRack B650D4U-2L2T/BCM (2.09 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32 GB DDR5-4800MT/s MTC20C2085S1EC48BA1, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS + 0GB Virtual HDisk0 + 0GB Virtual HDisk1 + 0GB Virtual HDisk2 + 0GB Virtual HDisk3, Graphics: ASPEED 512MB, Audio: AMD Device 1640, Monitor: VA2431, Network: 2 x Intel I210 + 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 22.04, Kernel: 6.6.0-rc4-phx-amd-pref-core (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server, Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1920x1200
AMD Preferred Core Linux - Ryzen 9 7950X3D OpenBenchmarking.org Phoronix Test Suite AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads) ASRockRack B650D4U-2L2T/BCM (2.09 BIOS) AMD Device 14d8 2 x 32 GB DDR5-4800MT/s MTC20C2085S1EC48BA1 3201GB Micron_7450_MTFDKCC3T2TFS + 0GB Virtual HDisk0 + 0GB Virtual HDisk1 + 0GB Virtual HDisk2 + 0GB Virtual HDisk3 ASPEED 512MB AMD Device 1640 VA2431 2 x Intel I210 + 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA Ubuntu 22.04 6.6.0-rc4-phx-amd-pref-core (x86_64) GNOME Shell 42.9 X Server 1.3.238 GCC 11.4.0 ext4 1920x1200 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution AMD Preferred Core Linux - Ryzen 9 7950X3D Benchmarks System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096 - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203 - OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu122.04) - Python 3.10.12 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD Preferred Core Patched vs. AMD Preferred Core Disabled Comparison Phoronix Test Suite Baseline +3.6% +3.6% +7.2% +7.2% +10.8% +10.8% 14.4% 10.2% 10% 9.2% 6.9% 5.6% 5.2% 5.2% 5.1% 4.8% 4.4% 4.2% 3.8% 3.2% 3.2% 3.1% 3.1% 3% 3% 2.7% 2.4% 2.1% 192000 - 1024 Speed 10 Realtime - Bosphorus 4K 192000 - 512 Speed 11 Realtime - Bosphorus 1080p Speed 9 Realtime - Bosphorus 1080p Speed 11 Realtime - Bosphorus 4K oltp_update_non_index - 32 Scala Dotty oltp_update_index - 16 oltp_update_non_index - 16 Speed 8 Realtime - Bosphorus 1080p oltp_read_write - 16 Speed 6 Realtime - Bosphorus 1080p 4.1% Update Rand crypto_pyaes 3.8% All 3.6% Delete - 20 - 100000 3.5% Open - 50 - 100000 3.4% A.U.C.T 3.4% Speed 6 Realtime - Bosphorus 4K Speed 6 Two-Pass - Bosphorus 1080p json_loads 3.2% Tradesoap 2 Bosphorus 1080p 3% F.H.R 32 T.F.A.T.T 2.9% Open - 20 - 1000000 2.7% resize 2.7% Server Rack - CPU-only chaos 2.6% Jython 2.6% Bosphorus 1080p - Fast 2.4% Apache Spark ALS 2.4% A.G.R.R.0.F - CPU P.B.S 2.3% 6, Lossless 2.3% H2 2.3% Bosphorus 1080p - Medium 2.3% 8 2.2% Bosphorus 1080p - Slow 2.1% JPEG - 90 2.1% Boat - CPU-only Bosphorus 1080p - Medium 2% nbody 2% pathlib 2% Stargate Digital Audio Workstation AOM AV1 Stargate Digital Audio Workstation AOM AV1 AOM AV1 AOM AV1 TiDB Community Server Renaissance TiDB Community Server TiDB Community Server AOM AV1 TiDB Community Server AOM AV1 RocksDB PyPerformance JPEG XL Decoding libjxl Apache Hadoop Apache Hadoop Renaissance AOM AV1 AOM AV1 PyPerformance DaCapo Benchmark SQLite x265 Renaissance SQLite PyBench Apache Hadoop GIMP Darktable PyPerformance DaCapo Benchmark VVenC Renaissance OpenVINO PHPBench libavif avifenc DaCapo Benchmark Kvazaar SQLite uvg266 JPEG XL libjxl Darktable uvg266 PyPerformance PyPerformance AMD Preferred Core Patched AMD Preferred Core Disabled
AMD Preferred Core Linux - Ryzen 9 7950X3D openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU memcached: 1:100 memcached: 1:10 liquid-dsp: 1 - 256 - 512 liquid-dsp: 2 - 256 - 512 liquid-dsp: 4 - 256 - 512 liquid-dsp: 8 - 256 - 512 liquid-dsp: 16 - 256 - 512 liquid-dsp: 32 - 256 - 512 openssl: RSA4096 openssl: RSA4096 openssl: SHA256 openssl: SHA512 openssl: AES-128-GCM openssl: AES-256-GCM openssl: ChaCha20 openssl: ChaCha20-Poly1305 darktable: Boat - CPU-only darktable: Masskrug - CPU-only darktable: Server Room - CPU-only darktable: Server Rack - CPU-only gimp: unsharp-mask gimp: resize gimp: rotate gimp: auto-levels john-the-ripper: MD5 john-the-ripper: Blowfish john-the-ripper: HMAC-SHA512 john-the-ripper: bcrypt john-the-ripper: WPA PSK blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Pabellon Barcelona - CPU-Only rocksdb: Seq Fill rocksdb: Rand Fill rocksdb: Rand Read rocksdb: Read While Writing rocksdb: Read Rand Write Rand rocksdb: Update Rand sqlite-speedtest: Timed Time - Size 1,000 sqlite: 2 sqlite: 4 sqlite: 8 sqlite: 16 sqlite: 32 tensorflow: CPU - 16 - ResNet-50 tensorflow: CPU - 32 - ResNet-50 jpegxl: JPEG - 90 jpegxl: JPEG - 100 jpegxl: PNG - 90 jpegxl: PNG - 100 jpegxl-decode: 1 jpegxl-decode: All build-ffmpeg: Time To Compile build-linux-kernel: defconfig svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K vvenc: Bosphorus 1080p - Fast vvenc: Bosphorus 1080p - Faster vvenc: Bosphorus 4K - Fast vvenc: Bosphorus 4K - Faster uvg266: Bosphorus 1080p - Slow uvg266: Bosphorus 1080p - Medium uvg266: Bosphorus 1080p - Very Fast uvg266: Bosphorus 1080p - Super Fast uvg266: Bosphorus 1080p - Ultra Fast uvg266: Bosphorus 4K - Slow uvg266: Bosphorus 4K - Medium uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast kvazaar: Bosphorus 1080p - Slow kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 1080p - Very Fast kvazaar: Bosphorus 1080p - Super Fast kvazaar: Bosphorus 1080p - Ultra Fast kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Medium kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 4K - Super Fast kvazaar: Bosphorus 4K - Ultra Fast redis: SET - 50 nginx: 100 nginx: 200 nginx: 500 nginx: 1000 apache: 100 apache: 200 apache: 500 apache: 1000 hadoop: Create - 20 - 100000 hadoop: Create - 20 - 1000000 hadoop: Create - 50 - 100000 hadoop: Open - 20 - 100000 hadoop: Open - 20 - 1000000 hadoop: Open - 50 - 100000 hadoop: Delete - 20 - 100000 hadoop: Delete - 20 - 1000000 hadoop: Delete - 50 - 100000 hadoop: Delete - 50 - 1000000 couchdb: 100 - 1000 - 30 couchdb: 100 - 3000 - 30 couchdb: 300 - 1000 - 30 couchdb: 300 - 3000 - 30 couchdb: 500 - 1000 - 30 apache-iotdb: 100 - 100 - 200 - 100 apache-iotdb: 100 - 100 - 200 - 100 avifenc: 0 avifenc: 2 avifenc: 6 avifenc: 6, Lossless avifenc: 10, Lossless openradioss: Bird Strike on Windshield openradioss: Rubber O-Ring Seal Installation openradioss: Cell Phone Drop Test openradioss: Bumper Beam openradioss: INIVOL and Fluid Structure Interaction Drop Container openradioss: Chrysler Neon 1M deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream aom-av1: Speed 11 Realtime - Bosphorus 1080p aom-av1: Speed 11 Realtime - Bosphorus 4K aom-av1: Speed 10 Realtime - Bosphorus 1080p aom-av1: Speed 10 Realtime - Bosphorus 4K aom-av1: Speed 9 Realtime - Bosphorus 1080p aom-av1: Speed 9 Realtime - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 1080p aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 6 Realtime - Bosphorus 1080p aom-av1: Speed 6 Realtime - Bosphorus 4K aom-av1: Speed 6 Two-Pass - Bosphorus 1080p aom-av1: Speed 6 Two-Pass - Bosphorus 4K aom-av1: Speed 4 Two-Pass - Bosphorus 1080p aom-av1: Speed 4 Two-Pass - Bosphorus 4K aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 4K ffmpeg: libx265 - Live ffmpeg: libx265 - Live ffmpeg: libx265 - Upload ffmpeg: libx265 - Upload ffmpeg: libx265 - Platform ffmpeg: libx265 - Platform ffmpeg: libx265 - Video On Demand ffmpeg: libx265 - Video On Demand pybench: Total For Average Test Times pyperformance: 2to3 pyperformance: chaos pyperformance: crypto_pyaes pyperformance: django_template pyperformance: float pyperformance: go pyperformance: json_loads pyperformance: nbody pyperformance: pathlib pyperformance: pickle_pure_python pyperformance: python_startup pyperformance: raytrace pyperformance: regex_compile phpbench: PHP Benchmark Suite renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Savina Reactors.IO renaissance: Apache Spark ALS renaissance: Rand Forest renaissance: Apache Spark Bayes renaissance: Apache Spark PageRank renaissance: In-Memory Database Shootout renaissance: Scala Dotty renaissance: Finagle HTTP Requests renaissance: Genetic Algorithm Using Jenetics + Futures renaissance: ALS Movie Lens dacapobench: H2 dacapobench: Jython dacapobench: Tradebeans dacapobench: Tradesoap tidb: oltp_read_write - 1 tidb: oltp_read_write - 16 tidb: oltp_point_select - 1 tidb: oltp_update_non_index - 1 tidb: oltp_update_non_index - 16 tidb: oltp_update_non_index - 32 tidb: oltp_update_index - 16 x265: Bosphorus 1080p x265: Bosphorus 4K gcrypt: encode-mp3: WAV To MP3 unpack-firefox: firefox-84.0.source.tar.xz stargate: 192000 - 512 stargate: 192000 - 1024 AMD Preferred Core Patched AMD Preferred Core Disabled 13.31 598.44 25.48 313.46 33562.19 0.43 47818.16 0.29 95.01 84.13 94.82 84.28 2581.07 6.12 1344.26 11.86 1605.40 4.93 1022.22 7.81 1573.81 5.06 129.97 61.44 3018.31 2.52 4397.12 3.49 746.05 21.42 588.54 27.14 436.54 18.29 522.57 15.28 3746607.05 3765364.83 16513000 32667333 65313000 130530000 252300000 371413333 14041.1 357968.1 33294033313 10581245807 246153763133 210266987817 125463772453 89227109407 2.726 3.117 2.673 0.116 17.156 16.828 12.795 14.080 4450000 42158 186094000 41984 159731 55.10 140.79 68.46 169.67 1349300 1270677 130530174 4123586 3112791 825723 47.726 2.164 2.534 3.581 5.326 10.922 39.43 40.39 9.70 0.81 10.11 0.87 55.61 247.32 22.107 43.167 164.435 169.579 79.649 5.133 22.405 41.237 7.585 14.586 55.54 61.95 160.60 174.43 194.21 13.89 15.60 42.13 45.86 53.60 81.78 84.79 175.07 231.30 278.79 20.99 21.52 45.64 59.92 77.59 3633880.25 143486.29 144792.6 146317.31 141227.15 392066.95 398392.99 330962.46 328237.07 68275 85764 68474 820810 1735185 757585 120610 137039 117693 130409 77.604 259.854 119.177 402.763 165.306 13272391 121.36 75.833 38.311 3.613 6.241 3.979 150.50 68.58 52.30 91.03 273.77 808.48 53.9978 18.5160 91.8177 87.1034 276.0535 3.6205 996.3367 8.0169 110.3739 9.0562 180.3396 44.3346 192.8564 5.1835 266.8739 29.9559 17.3763 57.5448 21.4631 372.3577 60.2586 16.5892 112.1971 71.2403 89.4066 11.1827 117.8498 67.8363 90.5116 11.0470 122.4510 65.2828 17.3724 57.5573 21.4612 372.4185 165.2136 6.0486 395.9016 20.1924 28.9689 34.5059 38.0931 209.9315 193.1113 5.1765 266.8622 29.9570 1206.2497 0.8268 3008.2187 2.6501 18.8587 53.0203 26.9245 296.4755 112.3896 8.8950 461.7168 17.3117 221.27 104.54 238.89 102.48 226.64 100.66 216.90 91.53 219.52 95.02 72.63 24.85 24.33 11.30 1.29 0.41 28.82 175.22 76.06 33.20 111.76 67.78 111.27 68.08 659 189 57.0 65.9 26.9 65.1 139 12.5 84.8 15.3 245 6.20 272 87.0 1106406 9494.1 4721.0 2133.5 437.2 903.2 2159.8 2531.2 565.8 2759.2 1247.3 9094.9 1944 2574 1850 1871 4004 42195 6940 1972 21786 31427 14845 112.24 32.26 164.883 5.352 14.853 3.064180 3.375473 13.35 596.92 25.57 312.26 33780.37 0.42 48090.16 0.29 95.03 84.11 95.24 83.93 2586.20 6.13 1345.16 11.86 1609.06 4.93 1013.34 7.87 1594.25 4.99 129.89 61.47 3040.70 2.52 4480.76 3.47 747.40 21.37 589.30 27.11 435.18 18.34 523.99 15.24 3748498.21 3776936.51 16227333 33150333 65200667 128360000 252230000 372340000 14049.1 358591.0 33399261110 10577375097 246300291620 209857528353 125775143277 89411023847 2.671 3.102 2.629 0.113 17.315 17.283 12.952 14.163 4506333 42182 184469000 42032 160031 55.05 140.74 68.58 170.05 1374435 1283572 130900421 4105943 3135076 857334 48.182 2.099 2.549 3.658 5.264 10.608 39.72 40.54 9.50 0.80 10.02 0.88 54.91 238.77 21.822 43.094 164.999 169.233 79.556 5.181 21.879 40.796 7.486 14.469 54.39 60.72 159.75 173.51 193.53 13.84 15.55 42.04 45.91 53.54 80.38 82.92 172.84 230.35 278.10 20.85 21.36 45.47 59.73 77.29 3667648.00 144206.53 143802.11 146476.98 139003.77 399046.18 401516.08 333352.80 329562.58 67323 85615 67697 822149 1689342 732532 116521 136850 116159 130289 77.143 256.290 117.705 397.446 162.667 13142738 123.49 76.581 38.679 3.659 6.383 4.042 150.00 69.10 51.70 90.75 274.18 809.03 54.3721 18.3867 91.8303 87.0660 277.8345 3.5974 988.9699 8.0773 110.4962 9.0459 180.5948 44.2785 192.9641 5.1804 267.2616 29.9177 17.4031 57.4559 21.4480 372.6340 60.3182 16.5726 111.9156 71.4102 89.3203 11.1934 117.5320 68.0284 90.4514 11.0544 122.0090 65.5256 17.3759 57.5459 21.4691 372.0523 163.7413 6.1030 394.5492 20.2615 28.9768 34.4966 38.0848 209.9980 192.8777 5.1828 267.0752 29.9339 1212.7974 0.8223 3010.9616 2.6476 18.8927 52.9252 26.9496 296.2199 112.5885 8.8793 462.4698 17.2829 241.52 110.35 236.30 112.90 242.35 102.43 226.48 92.15 210.83 98.09 74.96 24.85 24.18 11.18 1.27 0.41 28.67 176.16 76.05 33.20 111.72 67.80 111.51 67.93 678 191 58.5 68.4 27.3 65.7 137 12.9 86.5 15.6 249 6.21 277 88.2 1081018 9812.5 4788.4 2184.3 442.3 905.4 2179.9 2526.9 538.0 2678.9 1229.7 9125.2 1988 2640 1844 1814 3993 43984 6997 1992 22827 33066 15603 108.96 32.20 166.821 5.371 14.836 3.370842 3.862434 OpenBenchmarking.org
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Face Detection FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 13.31 13.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Face Detection FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 25.48 25.57 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 7K 14K 21K 28K 35K SE +/- 36.74, N = 3 SE +/- 20.93, N = 3 33562.19 33780.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 10K 20K 30K 40K 50K SE +/- 79.98, N = 3 SE +/- 64.58, N = 3 47818.16 48090.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Person Detection FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.45, N = 3 SE +/- 0.43, N = 3 95.01 95.03 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Person Detection FP32 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.38, N = 3 SE +/- 0.17, N = 3 94.82 95.24 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Weld Porosity Detection FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 600 1200 1800 2400 3000 SE +/- 1.29, N = 3 SE +/- 1.81, N = 3 2581.07 2586.20 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Weld Porosity Detection FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 300 600 900 1200 1500 SE +/- 1.24, N = 3 SE +/- 0.88, N = 3 1344.26 1345.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Vehicle Detection FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 300 600 900 1200 1500 SE +/- 1.98, N = 3 SE +/- 2.26, N = 3 1605.40 1609.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Vehicle Detection FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 200 400 600 800 1000 SE +/- 5.43, N = 3 SE +/- 2.69, N = 3 1022.22 1013.34 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Person Vehicle Bike Detection FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 300 600 900 1200 1500 SE +/- 4.57, N = 3 SE +/- 6.05, N = 3 1573.81 1594.25 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Machine Translation EN To DE FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 0.31, N = 3 129.97 129.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Face Detection Retail FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 700 1400 2100 2800 3500 SE +/- 9.55, N = 3 SE +/- 6.78, N = 3 3018.31 3040.70 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Face Detection Retail FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 1000 2000 3000 4000 5000 SE +/- 11.27, N = 3 SE +/- 4.43, N = 3 4397.12 4480.76 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Handwritten English Recognition FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 160 320 480 640 800 SE +/- 6.39, N = 3 SE +/- 4.57, N = 3 746.05 747.40 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Handwritten English Recognition FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 130 260 390 520 650 SE +/- 1.78, N = 3 SE +/- 1.19, N = 3 588.54 589.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Road Segmentation ADAS FP16 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 90 180 270 360 450 SE +/- 0.69, N = 3 SE +/- 1.87, N = 3 436.54 435.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.1 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU AMD Preferred Core Patched AMD Preferred Core Disabled 110 220 330 440 550 SE +/- 1.48, N = 3 SE +/- 1.05, N = 3 522.57 523.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
Input: drivaerFastback, Small Mesh Size
AMD Preferred Core Patched: The test quit with a non-zero exit status. E: [0] --> FOAM FATAL ERROR:
AMD Preferred Core Disabled: The test quit with a non-zero exit status. E: [0] --> FOAM FATAL ERROR:
Input: drivaerFastback, Medium Mesh Size
AMD Preferred Core Patched: The test quit with a non-zero exit status. E: [0] --> FOAM FATAL ERROR:
AMD Preferred Core Disabled: The test quit with a non-zero exit status. E: [0] --> FOAM FATAL ERROR:
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 AMD Preferred Core Patched AMD Preferred Core Disabled 3K 6K 9K 12K 15K SE +/- 12.82, N = 3 SE +/- 29.06, N = 3 14041.1 14049.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.
Threads / Copies: 1
AMD Preferred Core Patched: The test run did not produce a result.
AMD Preferred Core Disabled: The test run did not produce a result.
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
JPEG XL Decoding libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.
Connections: 20
AMD Preferred Core Patched: The test quit with a non-zero exit status.
AMD Preferred Core Disabled: The test quit with a non-zero exit status.
Apache HTTP Server This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.
Concurrent Requests: 20
AMD Preferred Core Patched: The test quit with a non-zero exit status.
AMD Preferred Core Disabled: The test quit with a non-zero exit status.
Apache IoTDB Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100 AMD Preferred Core Patched AMD Preferred Core Disabled 3M 6M 9M 12M 15M SE +/- 39383.72, N = 3 SE +/- 177739.87, N = 3 13272391 13142738
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 12 24 36 48 60 SE +/- 0.40, N = 3 SE +/- 0.04, N = 3 54.00 54.37
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 91.82 91.83
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 60 120 180 240 300 SE +/- 0.40, N = 3 SE +/- 0.89, N = 3 276.05 277.83
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 200 400 600 800 1000 SE +/- 2.15, N = 3 SE +/- 0.91, N = 3 996.34 988.97
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.31, N = 3 SE +/- 0.12, N = 3 110.37 110.50
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 40 80 120 160 200 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 180.34 180.59
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 40 80 120 160 200 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 192.86 192.96
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 60 120 180 240 300 SE +/- 0.29, N = 3 SE +/- 0.35, N = 3 266.87 267.26
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 17.38 17.40
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 21.46 21.45
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 14 28 42 56 70 SE +/- 0.20, N = 3 SE +/- 0.13, N = 3 60.26 60.32
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.39, N = 3 SE +/- 0.06, N = 3 112.20 111.92
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 89.41 89.32
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 117.85 117.53
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 90.51 90.45
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.43, N = 3 SE +/- 0.63, N = 3 122.45 122.01
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 17.37 17.38
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 21.46 21.47
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 40 80 120 160 200 SE +/- 0.66, N = 3 SE +/- 0.37, N = 3 165.21 163.74
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 90 180 270 360 450 SE +/- 0.23, N = 3 SE +/- 0.38, N = 3 395.90 394.55
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 28.97 28.98
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 38.09 38.08
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 40 80 120 160 200 SE +/- 0.22, N = 3 SE +/- 0.18, N = 3 193.11 192.88
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 1.1661 2.3322 3.4983 4.6644 5.8305 SE +/- 0.0058, N = 3 SE +/- 0.0048, N = 3 5.1765 5.1828
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 60 120 180 240 300 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 266.86 267.08
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 29.96 29.93
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 300 600 900 1200 1500 SE +/- 2.81, N = 3 SE +/- 0.74, N = 3 1206.25 1212.80
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 600 1200 1800 2400 3000 SE +/- 10.38, N = 3 SE +/- 7.50, N = 3 3008.22 3010.96
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 18.86 18.89
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 26.92 26.95
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 112.39 112.59
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream AMD Preferred Core Patched AMD Preferred Core Disabled 100 200 300 400 500 SE +/- 0.50, N = 3 SE +/- 0.86, N = 3 461.72 462.47
FFmpeg This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Live AMD Preferred Core Patched AMD Preferred Core Disabled 7 14 21 28 35 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 28.82 28.67 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Upload AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.31, N = 3 SE +/- 0.25, N = 3 76.06 76.05 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Platform AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 111.76 111.72 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Video On Demand AMD Preferred Core Patched AMD Preferred Core Disabled 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 111.27 111.51 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
DaCapo Benchmark This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.
Java Test: Eclipse
AMD Preferred Core Patched: The test quit with a non-zero exit status.
AMD Preferred Core Disabled: The test quit with a non-zero exit status.
Gcrypt Library Libgcrypt is a general purpose cryptographic library developed as part of the GnuPG project. This is a benchmark of libgcrypt's integrated benchmark and is measuring the time to run the benchmark command with a cipher/mac/hash repetition count set for 50 times as simple, high level look at the overall crypto performance of the system under test. Learn more via the OpenBenchmarking.org test page.
Stargate Digital Audio Workstation Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.
CPU Power Consumption Monitor OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring AMD Preferred Core Patched AMD Preferred Core Disabled 30 60 90 120 150 Min: 5.88 / Avg: 62.27 / Max: 138.62 Min: 6.45 / Avg: 48.65 / Max: 104.02
Meta Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts AMD Preferred Core Patched AMD Preferred Core Disabled 1500 3000 4500 6000 7500 6952.94 1025.34
AMD Preferred Core Patched Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu122.04)Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 7 October 2023 17:39 by user root.
AMD Preferred Core Disabled Processor: AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads), Motherboard: ASRockRack B650D4U-2L2T/BCM (2.09 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32 GB DDR5-4800MT/s MTC20C2085S1EC48BA1, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS + 0GB Virtual HDisk0 + 0GB Virtual HDisk1 + 0GB Virtual HDisk2 + 0GB Virtual HDisk3, Graphics: ASPEED 512MB, Audio: AMD Device 1640, Monitor: VA2431, Network: 2 x Intel I210 + 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 22.04, Kernel: 6.6.0-rc4-phx-amd-pref-core (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server, Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203Java Notes: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu122.04)Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 8 October 2023 11:28 by user root.