AMD EPYC 9754 128-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2406020-NE-LLL99005371 lll - Phoronix Test Suite lll AMD EPYC 9754 128-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2406020-NE-LLL99005371&grs&sor .
lll Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution a b AMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads) AMD Titanite_4G (RTI1007B BIOS) AMD Device 14a4 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG 2 x 3201GB KIOXIA KCMYXVUG3T20 ASPEED Broadcom NetXtreme BCM5720 PCIe Ubuntu 24.04 6.8.0-22-generic (x86_64) GCC 13.2.0 ext4 1920x1200 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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
lll llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - CPU svt-av1: Preset 8 - Bosphorus 1080p llamafile: Meta-Llama-3-8B-Instruct.F16 - CPU svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 5 - Bosphorus 1080p cpuminer-opt: Skeincoin whisper-cpp: ggml-medium.en - 2016 State of the Union whisper-cpp: ggml-small.en - 2016 State of the Union llamafile: mistral-7b-instruct-v0.2.Q5_K_M - CPU svt-av1: Preset 13 - Bosphorus 1080p svt-av1: Preset 3 - Bosphorus 1080p dav1d: Summer Nature 4K svt-av1: Preset 3 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 5 - Bosphorus 4K llama-cpp: Meta-Llama-3-8B-Instruct-Q8_0.gguf cpuminer-opt: Garlicoin cpuminer-opt: Deepcoin dav1d: Chimera 1080p 10-bit cpuminer-opt: Myriad-Groestl cpuminer-opt: Magi whisper-cpp: ggml-base.en - 2016 State of the Union dav1d: Chimera 1080p cpuminer-opt: Triple SHA-256, Onecoin dav1d: Summer Nature 1080p cpuminer-opt: Blake-2 S cpuminer-opt: scrypt cpuminer-opt: Quad SHA-256, Pyrite cpuminer-opt: LBC, LBRY Credits cpuminer-opt: x20r llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPU cpuminer-opt: Ringcoin llamafile: llava-v1.6-mistral-7b.Q8_0 - CPU a b 67.22 145.19 14.23 172.52 62.206 232710 700.78381 348.564 30.66 550.248 18.481 313.95 6.889 76.111 19.958 17.74 18510 45960 526.31 59580 3212.29 218.07338 560.15 413250 640.92 739430 1543.63 324310 81440 41520 6.53 12850 63.49 152.92 14.9 165.648 63.511 228790 694.43469 351.72688 30.92 545.637 18.636 315.85 6.848 76.503 20.049 17.67 18580 46070 525.12 59690 3207.7 218.38234 559.37 413700 641.59 740080 1542.43 324190 81460 41530 6.53 12850 OpenBenchmarking.org
Llamafile Test: TinyLlama-1.1B-Chat-v1.0.BF16 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: TinyLlama-1.1B-Chat-v1.0.BF16 - Acceleration: CPU a b 15 30 45 60 75 67.22 63.49
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p b a 30 60 90 120 150 152.92 145.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llamafile Test: Meta-Llama-3-8B-Instruct.F16 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: Meta-Llama-3-8B-Instruct.F16 - Acceleration: CPU b a 4 8 12 16 20 14.90 14.23
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b 40 80 120 160 200 172.52 165.65 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p b a 14 28 42 56 70 63.51 62.21 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Skeincoin a b 50K 100K 150K 200K 250K 232710 228790 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Whisper.cpp Model: ggml-medium.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-medium.en - Input: 2016 State of the Union b a 150 300 450 600 750 694.43 700.78 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Whisper.cpp Model: ggml-small.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-small.en - Input: 2016 State of the Union a b 80 160 240 320 400 348.56 351.73 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Llamafile Test: mistral-7b-instruct-v0.2.Q5_K_M - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: mistral-7b-instruct-v0.2.Q5_K_M - Acceleration: CPU b a 7 14 21 28 35 30.92 30.66
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b 120 240 360 480 600 550.25 545.64 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p b a 5 10 15 20 25 18.64 18.48 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Summer Nature 4K b a 70 140 210 280 350 315.85 313.95 1. (CC) gcc options: -pthread
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 3 - Input: Bosphorus 4K a b 2 4 6 8 10 6.889 6.848 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 8 - Input: Bosphorus 4K b a 20 40 60 80 100 76.50 76.11 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 5 - Input: Bosphorus 4K b a 5 10 15 20 25 20.05 19.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Llama.cpp Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b3067 Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf a b 4 8 12 16 20 17.74 17.67 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Garlicoin b a 4K 8K 12K 16K 20K 18580 18510 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Deepcoin b a 10K 20K 30K 40K 50K 46070 45960 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Chimera 1080p 10-bit a b 110 220 330 440 550 526.31 525.12 1. (CC) gcc options: -pthread
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Myriad-Groestl b a 13K 26K 39K 52K 65K 59690 59580 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Magi a b 700 1400 2100 2800 3500 3212.29 3207.70 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-base.en - Input: 2016 State of the Union a b 50 100 150 200 250 218.07 218.38 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Chimera 1080p a b 120 240 360 480 600 560.15 559.37 1. (CC) gcc options: -pthread
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Triple SHA-256, Onecoin b a 90K 180K 270K 360K 450K 413700 413250 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Summer Nature 1080p b a 140 280 420 560 700 641.59 640.92 1. (CC) gcc options: -pthread
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Blake-2 S b a 160K 320K 480K 640K 800K 740080 739430 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: scrypt a b 300 600 900 1200 1500 1543.63 1542.43 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Quad SHA-256, Pyrite a b 70K 140K 210K 280K 350K 324310 324190 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: LBC, LBRY Credits b a 20K 40K 60K 80K 100K 81460 81440 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: x20r OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: x20r b a 9K 18K 27K 36K 45K 41530 41520 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Llamafile Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU b a 2 4 6 8 10 6.53 6.53
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Ringcoin b a 3K 6K 9K 12K 15K 12850 12850 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Phoronix Test Suite v10.8.4