TensorFlow Lite AMD Ryzen Threadripper
AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB on Ubuntu 20.04 via the Phoronix Test Suite.


TR 3960X: 

	Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200

	OS: Ubuntu 20.04, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Vet 2: 

	Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200

	OS: Ubuntu 20.04, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Vet 3: 

	Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200

	OS: Ubuntu 20.04, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160


TensorFlow Lite 2020-08-23
Model: SqueezeNet
Microseconds < Lower Is Better
TR 3960X . 76058.7 |===========================================================
Vet 2 .... 75628.9 |===========================================================
Vet 3 .... 75472.6 |===========================================================


TensorFlow Lite 2020-08-23
Model: Inception V4
Microseconds < Lower Is Better
TR 3960X . 1137923 |===========================================================
Vet 2 .... 1136157 |===========================================================
Vet 3 .... 1134943 |===========================================================


TensorFlow Lite 2020-08-23
Model: NASNet Mobile
Microseconds < Lower Is Better
TR 3960X . 86858.3 |===========================================================
Vet 2 .... 86852.5 |===========================================================
Vet 3 .... 86655.8 |===========================================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Float
Microseconds < Lower Is Better
TR 3960X . 51035.5 |===========================================================
Vet 2 .... 51344.7 |===========================================================
Vet 3 .... 51110.6 |===========================================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Quant
Microseconds < Lower Is Better
TR 3960X . 52131.1 |===========================================================
Vet 2 .... 52306.2 |===========================================================
Vet 3 .... 52160.5 |===========================================================


TensorFlow Lite 2020-08-23
Model: Inception ResNet V2
Microseconds < Lower Is Better
TR 3960X . 1007423 |===========================================================
Vet 2 .... 1007393 |===========================================================
Vet 3 .... 1006490 |===========================================================