Intel 0000% testing with a ASUS Pro WS W790E-SAGE SE (0215 BIOS) and ASPEED on Fedora 39 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 2403182-NE-LLAMATEST04 llamatest - Phoronix Test Suite llamatest Intel 0000% testing with a ASUS Pro WS W790E-SAGE SE (0215 BIOS) and ASPEED on Fedora 39 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2403182-NE-LLAMATEST04 .
llamatest Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel OpenCL Compiler File-System Screen Resolution 4800_4ch_ll Intel 0000% @ 3.30GHz (48 Cores / 96 Threads) ASUS Pro WS W790E-SAGE SE (0215 BIOS) Intel Alder Lake-S PCH 64GB 4001GB CT4000P3SSD8 + 0GB Virtual HDisk0 ASPEED Realtek ALC1220 2 x Intel X710 for 10GBASE-T Fedora 39 6.7.7-200.fc39.x86_64 (x86_64) OpenCL 3.0 + OpenCL 1.2 Intel FPGA SDK for OpenCL 20.3 + OpenCL 3.0 LINUX + OpenCL 1.2 Intel FPGA SDK for OpenCL 20.3 GCC 13.2.1 20231205 + Clang 17.0.6 + LLVM 17.0.6 xfs 1920x1200 OpenBenchmarking.org - Transparent Huge Pages: madvise - --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xd0004b1 - SELinux + 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: Not affected + 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 RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
llamatest stream: Copy stream: Scale stream: Triad stream: Add llama-cpp-7b: llama-2-7b.Q4_0.gguf 4800_4ch_ll 89753.2 89343.0 93851.1 93610.5 19.81 OpenBenchmarking.org
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy 4800_4ch_ll 20K 40K 60K 80K 100K SE +/- 75.10, N = 5 89753.2 1. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp
Stream Type: Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale 4800_4ch_ll 20K 40K 60K 80K 100K SE +/- 86.26, N = 5 89343.0 1. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad 4800_4ch_ll 20K 40K 60K 80K 100K SE +/- 72.45, N = 5 93851.1 1. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add 4800_4ch_ll 20K 40K 60K 80K 100K SE +/- 58.69, N = 5 93610.5 1. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp
Llama.cpp Model: llama-2-7b.Q4_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b1808 Model: llama-2-7b.Q4_0.gguf 4800_4ch_ll 5 10 15 20 25 SE +/- 0.20, N = 5 19.81 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native
Phoronix Test Suite v10.8.4