hw-mig
AMD EPYC 7R13 48-Core testing with a Supermicro H12SSL-I v1.02 (2.7 BIOS) and NVIDIA GeForce RTX 4090 24GB on EndeavourOS rolling via the Phoronix Test Suite.


AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB: 

	Processor: AMD EPYC 7R13 48-Core @ 3.73GHz (48 Cores / 96 Threads), Motherboard: Supermicro H12SSL-I v1.02 (2.7 BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 15363GB Micron_7450_MTFDKCC15T3TFR, Graphics: NVIDIA GeForce RTX 4090 24GB, Audio: NVIDIA AD102 HD Audio, Monitor: 38GN950, Network: 2 x Intel X710 for 10GbE SFP+

	OS: EndeavourOS rolling, Kernel: 6.7.4-zen1-1-zen (x86_64), Desktop: Xfce 4.18, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6 + CUDA 12.3, File-System: btrfs, Screen Resolution: 3840x1600

AMD EPYC 7R13 48-Core: 

	Processor: AMD EPYC 7R13 48-Core @ 3.73GHz (48 Cores / 96 Threads), Motherboard: Supermicro H12SSL-I v1.02 (2.7 BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 15363GB Micron_7450_MTFDKCC15T3TFR, Graphics: NVIDIA GeForce RTX 4090 24GB, Audio: NVIDIA AD102 HD Audio, Monitor: 38GN950, Network: 2 x Intel X710 for 10GbE SFP+

	OS: EndeavourOS rolling, Kernel: 6.7.4-zen1-1-zen (x86_64), Desktop: Xfce 4.18, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6 + CUDA 12.3, File-System: btrfs, Screen Resolution: 3840x1600


Llama.cpp b1808
Model: llama-2-7b.Q4_0.gguf
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 23.17 |=================


Llama.cpp b1808
Model: llama-2-13b.Q4_0.gguf
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 14.45 |=================


Llama.cpp b1808
Model: llama-2-70b-chat.Q5_0.gguf
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 2.86 |==================


Llamafile 0.6
Test: llava-v1.5-7b-q4 - Acceleration: CPU
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 22.30 |=================


Llamafile 0.6
Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 13.34 |=================


Llamafile 0.6
Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU
Tokens Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 4.73 |==================


Redis 7.0.4
Test: GET - Parallel Connections: 50
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 2792000.50 |============


Redis 7.0.4
Test: GET - Parallel Connections: 1000
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 2505995.40 |============


Redis 7.0.4
Test: SET - Parallel Connections: 1000
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 2055844.83 |============


Redis 7.0.4
Test: LPOP - Parallel Connections: 1000
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 1679590.47 |============


Redis 7.0.4
Test: SADD - Parallel Connections: 1000
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 2268077.83 |============


Redis 7.0.4
Test: LPUSH - Parallel Connections: 1000
Requests Per Second > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 1744859.50 |============


POV-Ray 3.7.0.7
Trace Time
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core . 10.62 |================================================


Blender 4.0
Blend File: BMW27 - Compute: NVIDIA CUDA
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 5.80 |==================


Blender 4.0
Blend File: Classroom - Compute: NVIDIA CUDA
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 10.36 |=================


Blender 4.0
Blend File: Fishy Cat - Compute: NVIDIA CUDA
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 12.00 |=================


Blender 4.0
Blend File: Barbershop - Compute: NVIDIA CUDA
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 45.57 |=================


Blender 4.0
Blend File: Pabellon Barcelona - Compute: NVIDIA CUDA
Seconds < Lower Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 21.48 |=================


Memcached 1.6.19
Set To Get Ratio: 1:1
Ops/sec > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 1375588.16 |============


Memcached 1.6.19
Set To Get Ratio: 1:5
Ops/sec > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 3850395.87 |============


Memcached 1.6.19
Set To Get Ratio: 5:1
Ops/sec > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 870630.72 |=============


Memcached 1.6.19
Set To Get Ratio: 1:10
Ops/sec > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 4989344.12 |============


Memcached 1.6.19
Set To Get Ratio: 1:100
Ops/sec > Higher Is Better
AMD EPYC 7R13 48-Core - NVIDIA GeForce RTX 4090 24GB . 5147962.66 |============