AMD EPYC 7773X Compilers AMD EPYC 7773X GCC / Clang / AOCC compiler benchmarking by Michael Larabel for a future article. GCC 11.2: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (TYM1008C BIOS), Chipset: AMD Starship/Matisse, Memory: 16 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2E2, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc8-generic (x86_64), Desktop: GNOME Shell 42.0, Display Server: X Server, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 Clang 14.0: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (TYM1008C BIOS), Chipset: AMD Starship/Matisse, Memory: 16 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2E2, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc8-generic (x86_64), Desktop: GNOME Shell 42.0, Display Server: X Server, Vulkan: 1.2.204, Compiler: Clang 14.0.0-1ubuntu1, File-System: ext4, Screen Resolution: 1920x1080 AMD AOCC 3.2: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (TYM1008C BIOS), Chipset: AMD Starship/Matisse, Memory: 16 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2E2, Disk: 800GB INTEL SSDPF21Q800GB, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc8-generic (x86_64), Desktop: GNOME Shell 42.0, Display Server: X Server, Vulkan: 1.2.204, Compiler: Clang 13.0.0, File-System: ext4, Screen Resolution: 1920x1080 QuantLib 1.21 MFLOPS > Higher Is Better GCC 11.2 ..... 2125.3 |===================================================== Clang 14.0 ... 2240.3 |======================================================== AMD AOCC 3.2 . 2251.4 |======================================================== Etcpak 0.7 Configuration: DXT1 Mpx/s > Higher Is Better GCC 11.2 ..... 844.05 |======================= Clang 14.0 ... 1926.47 |===================================================== AMD AOCC 3.2 . 2012.57 |======================================================= Etcpak 0.7 Configuration: ETC2 Mpx/s > Higher Is Better GCC 11.2 ..... 134.04 |============================================= Clang 14.0 ... 166.39 |======================================================== AMD AOCC 3.2 . 158.35 |===================================================== LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better GCC 11.2 ..... 4159 |===================================================== Clang 14.0 ... 4224 |====================================================== AMD AOCC 3.2 . 4551 |========================================================== LeelaChessZero 0.28 Backend: Eigen Nodes Per Second > Higher Is Better GCC 11.2 ..... 4187 |============================================ Clang 14.0 ... 5107 |===================================================== AMD AOCC 3.2 . 5570 |========================================================== LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: 20k Atoms ns/day > Higher Is Better GCC 11.2 ..... 35.97 |======================================================== Clang 14.0 ... 36.01 |========================================================= AMD AOCC 3.2 . 36.32 |========================================================= LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein ns/day > Higher Is Better GCC 11.2 ..... 28.47 |===================================================== Clang 14.0 ... 29.95 |======================================================== AMD AOCC 3.2 . 30.35 |========================================================= WebP Image Encode 1.1 Encode Settings: Default Encode Time - Seconds < Lower Is Better GCC 11.2 ..... 1.695 |========================================================= Clang 14.0 ... 1.701 |========================================================= AMD AOCC 3.2 . 1.660 |======================================================== WebP Image Encode 1.1 Encode Settings: Quality 100 Encode Time - Seconds < Lower Is Better GCC 11.2 ..... 2.906 |========================================================= Clang 14.0 ... 2.871 |======================================================== AMD AOCC 3.2 . 2.759 |====================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Encode Time - Seconds < Lower Is Better GCC 11.2 ..... 24.56 |========================================================= Clang 14.0 ... 23.87 |======================================================= AMD AOCC 3.2 . 22.76 |===================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Encode Time - Seconds < Lower Is Better GCC 11.2 ..... 8.798 |========================================================= Clang 14.0 ... 8.585 |======================================================== AMD AOCC 3.2 . 8.026 |==================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression Encode Time - Seconds < Lower Is Better GCC 11.2 ..... 50.64 |========================================================= Clang 14.0 ... 45.09 |=================================================== AMD AOCC 3.2 . 45.90 |==================================================== Xmrig 6.12.1 Variant: Monero - Hash Count: 1M H/s > Higher Is Better GCC 11.2 ..... 41100.5 |======================================================= Clang 14.0 ... 40338.2 |====================================================== AMD AOCC 3.2 . 38790.7 |==================================================== Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M H/s > Higher Is Better GCC 11.2 ..... 42309.7 |======================================================= Clang 14.0 ... 40922.7 |===================================================== AMD AOCC 3.2 . 36998.0 |================================================ Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed MB/s > Higher Is Better GCC 11.2 ..... 98.8 |========================================================== Clang 14.0 ... 99.0 |========================================================== AMD AOCC 3.2 . 98.7 |========================================================== Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better GCC 11.2 ..... 2269.9 |======================================================= Clang 14.0 ... 2086.0 |=================================================== AMD AOCC 3.2 . 2311.1 |======================================================== JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 8 MP/s > Higher Is Better GCC 11.2 ..... 0.72 |===================================================== Clang 14.0 ... 0.67 |================================================= AMD AOCC 3.2 . 0.79 |========================================================== JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 7 MP/s > Higher Is Better GCC 11.2 ..... 71.13 |================================================= Clang 14.0 ... 78.02 |====================================================== AMD AOCC 3.2 . 82.75 |========================================================= JPEG XL Decoding libjxl 0.6.1 CPU Threads: 1 MP/s > Higher Is Better GCC 11.2 ..... 46.70 |=============================================== Clang 14.0 ... 53.78 |====================================================== AMD AOCC 3.2 . 57.14 |========================================================= JPEG XL Decoding libjxl 0.6.1 CPU Threads: All MP/s > Higher Is Better GCC 11.2 ..... 564.28 |==================================================== Clang 14.0 ... 605.18 |======================================================== AMD AOCC 3.2 . 599.49 |======================================================= TSCP 1.81 AI Chess Performance Nodes Per Second > Higher Is Better GCC 11.2 ..... 1094141 |================================================= Clang 14.0 ... 1231667 |======================================================= AMD AOCC 3.2 . 1172438 |==================================================== GraphicsMagick 1.3.33 Operation: Rotate Iterations Per Minute > Higher Is Better GCC 11.2 ..... 537 |=================================================== Clang 14.0 ... 450 |=========================================== AMD AOCC 3.2 . 616 |=========================================================== GraphicsMagick 1.3.33 Operation: Resizing Iterations Per Minute > Higher Is Better GCC 11.2 ..... 164 |==================================== Clang 14.0 ... 93 |==================== AMD AOCC 3.2 . 268 |=========================================================== Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better GCC 11.2 ..... 31.52 |====================================================== Clang 14.0 ... 33.21 |========================================================= AMD AOCC 3.2 . 32.92 |========================================================= Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better GCC 11.2 ..... 43.64 |======================================================= Clang 14.0 ... 45.28 |========================================================= AMD AOCC 3.2 . 45.36 |========================================================= SVT-AV1 0.9 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better GCC 11.2 ..... 4.082 |==================================================== Clang 14.0 ... 4.005 |=================================================== AMD AOCC 3.2 . 4.483 |========================================================= SVT-AV1 0.9 Encoder Mode: Preset 10 - Input: Bosphorus 4K Frames Per Second > Higher Is Better GCC 11.2 ..... 107.65 |====================================================== Clang 14.0 ... 104.56 |===================================================== AMD AOCC 3.2 . 110.84 |======================================================== SVT-AV1 0.9 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better GCC 11.2 ..... 140.46 |======================================================== Clang 14.0 ... 129.33 |==================================================== AMD AOCC 3.2 . 132.78 |===================================================== SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better GCC 11.2 ..... 288.97 |===================================================== Clang 14.0 ... 303.09 |======================================================= AMD AOCC 3.2 . 308.11 |======================================================== SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better GCC 11.2 ..... 376.34 |============================================= Clang 14.0 ... 437.24 |==================================================== AMD AOCC 3.2 . 472.24 |======================================================== SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better GCC 11.2 ..... 330.00 |================================================== Clang 14.0 ... 362.42 |======================================================= AMD AOCC 3.2 . 367.81 |======================================================== x265 3.4 Video Input: Bosphorus 4K Frames Per Second > Higher Is Better GCC 11.2 ..... 19.37 |============================================ Clang 14.0 ... 21.31 |================================================= AMD AOCC 3.2 . 25.03 |========================================================= Coremark 1.0 CoreMark Size 666 - Iterations Per Second Iterations/Sec > Higher Is Better GCC 11.2 ..... 4447513.21 |==================================================== Clang 14.0 ... 3705497.02 |=========================================== AMD AOCC 3.2 . 4242648.80 |================================================== libavif avifenc 0.10 Encoder Speed: 0 Seconds < Lower Is Better GCC 11.2 ..... 88.76 |========================================================= Clang 14.0 ... 87.25 |======================================================== AMD AOCC 3.2 . 84.82 |====================================================== libavif avifenc 0.10 Encoder Speed: 2 Seconds < Lower Is Better GCC 11.2 ..... 48.78 |========================================================= Clang 14.0 ... 47.51 |======================================================== AMD AOCC 3.2 . 46.27 |====================================================== libavif avifenc 0.10 Encoder Speed: 6 Seconds < Lower Is Better GCC 11.2 ..... 5.020 |========================================================= Clang 14.0 ... 4.911 |======================================================== AMD AOCC 3.2 . 4.635 |===================================================== libavif avifenc 0.10 Encoder Speed: 6, Lossless Seconds < Lower Is Better GCC 11.2 ..... 8.318 |========================================================= Clang 14.0 ... 7.976 |======================================================= AMD AOCC 3.2 . 7.822 |====================================================== Primesieve 7.7 1e12 Prime Number Generation Seconds < Lower Is Better GCC 11.2 ..... 2.613 |========================================================= Clang 14.0 ... 2.611 |========================================================= AMD AOCC 3.2 . 2.564 |======================================================== AOBench Size: 2048 x 2048 - Total Time Seconds < Lower Is Better GCC 11.2 ..... 49.74 |======================================================== Clang 14.0 ... 50.30 |========================================================= AMD AOCC 3.2 . 47.94 |====================================================== FLAC Audio Encoding 1.3.3 WAV To FLAC Seconds < Lower Is Better GCC 11.2 ..... 21.52 |======================================================== Clang 14.0 ... 21.83 |========================================================= AMD AOCC 3.2 . 21.80 |========================================================= LAME MP3 Encoding 3.100 WAV To MP3 Seconds < Lower Is Better GCC 11.2 ..... 8.988 |=================================================== Clang 14.0 ... 9.986 |========================================================= AMD AOCC 3.2 . 9.782 |======================================================== OpenJPEG 2.4 Encode: NASA Curiosity Panorama M34 ms < Lower Is Better GCC 11.2 ..... 362483 |======================================================== Clang 14.0 ... 349040 |====================================================== AMD AOCC 3.2 . 352848 |======================================================= OpenSSL 3.0 Algorithm: SHA256 byte/s > Higher Is Better GCC 11.2 ..... 156404481030 |============================================ Clang 14.0 ... 170350109150 |================================================ AMD AOCC 3.2 . 176385148413 |================================================== OpenSSL 3.0 Algorithm: RSA4096 sign/s > Higher Is Better GCC 11.2 ..... 26996.8 |======================================================= Clang 14.0 ... 26924.9 |======================================================= AMD AOCC 3.2 . 26972.4 |======================================================= OpenSSL 3.0 Algorithm: RSA4096 verify/s > Higher Is Better GCC 11.2 ..... 1770209.9 |===================================================== Clang 14.0 ... 1774479.0 |===================================================== AMD AOCC 3.2 . 1768233.2 |===================================================== Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better GCC 11.2 ..... 5825600000 |=================================================== Clang 14.0 ... 5867933333 |=================================================== AMD AOCC 3.2 . 5949000000 |==================================================== Liquid-DSP 2021.01.31 Threads: 256 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better GCC 11.2 ..... 6127133333 |============================================= Clang 14.0 ... 6229033333 |============================================== AMD AOCC 3.2 . 7010600000 |==================================================== libjpeg-turbo tjbench 2.1.0 Test: Decompression Throughput Megapixels/sec > Higher Is Better GCC 11.2 ..... 163.49 |======================================================== Clang 14.0 ... 150.72 |==================================================== AMD AOCC 3.2 . 160.29 |======================================================= ASTC Encoder 3.2 Preset: Thorough Seconds < Lower Is Better GCC 11.2 ..... 6.4222 |======================================================== Clang 14.0 ... 5.9580 |==================================================== AMD AOCC 3.2 . 5.7378 |================================================== ASTC Encoder 3.2 Preset: Exhaustive Seconds < Lower Is Better GCC 11.2 ..... 5.8792 |======================================================== Clang 14.0 ... 5.7737 |======================================================= AMD AOCC 3.2 . 5.5686 |===================================================== KTX-Software toktx 4.0 Settings: UASTC 3 Seconds < Lower Is Better GCC 11.2 ..... 4.604 |======================================================= Clang 14.0 ... 4.738 |========================================================= AMD AOCC 3.2 . 4.684 |======================================================== KTX-Software toktx 4.0 Settings: Zstd Compression 9 Seconds < Lower Is Better GCC 11.2 ..... 3.839 |======================================================== Clang 14.0 ... 3.886 |========================================================= AMD AOCC 3.2 . 3.832 |======================================================== KTX-Software toktx 4.0 Settings: Zstd Compression 19 Seconds < Lower Is Better GCC 11.2 ..... 21.44 |===================================================== Clang 14.0 ... 22.99 |========================================================= AMD AOCC 3.2 . 21.81 |====================================================== KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 Seconds < Lower Is Better GCC 11.2 ..... 9.015 |======================================================= Clang 14.0 ... 9.389 |========================================================= AMD AOCC 3.2 . 9.071 |======================================================= KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 Seconds < Lower Is Better GCC 11.2 ..... 35.58 |========================================================= Clang 14.0 ... 35.53 |========================================================= AMD AOCC 3.2 . 35.39 |========================================================= Google Draco 1.5.0 Model: Lion ms < Lower Is Better GCC 11.2 ..... 5952 |======================================================== Clang 14.0 ... 6176 |========================================================== AMD AOCC 3.2 . 5859 |=======================================================