3400G TensorFlow Lite + NAMD
AMD Ryzen 5 3400G testing with a ASUS PRIME B450M-A (2006 BIOS) and ASUS AMD Picasso 2GB on Ubuntu 19.10 via the Phoronix Test Suite.


Try 1: 

	Processor: AMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads), Motherboard: ASUS PRIME B450M-A (2006 BIOS), Chipset: AMD Raven/Raven2, Memory: 2 x 8192 MB DDR4-3000MT/s CRUCIAL, Disk: 29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EE, Graphics: ASUS AMD Picasso 2GB (1400/1500MHz), Audio: AMD Raven/Raven2/Fenghuang, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411

	OS: Ubuntu 19.10, Kernel: 5.3.0-46-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1280x800

Try 2: 

	Processor: AMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads), Motherboard: ASUS PRIME B450M-A (2006 BIOS), Chipset: AMD Raven/Raven2, Memory: 2 x 8192 MB DDR4-3000MT/s CRUCIAL, Disk: 29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EE, Graphics: ASUS AMD Picasso 2GB (1400/1500MHz), Audio: AMD Raven/Raven2/Fenghuang, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411

	OS: Ubuntu 19.10, Kernel: 5.3.0-46-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1280x800

Try 3: 

	Processor: AMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads), Motherboard: ASUS PRIME B450M-A (2006 BIOS), Chipset: AMD Raven/Raven2, Memory: 2 x 8192 MB DDR4-3000MT/s CRUCIAL, Disk: 29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EE, Graphics: ASUS AMD Picasso 2GB (1400/1500MHz), Audio: AMD Raven/Raven2/Fenghuang, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411

	OS: Ubuntu 19.10, Kernel: 5.3.0-46-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1280x800


NAMD 2.14
ATPase Simulation - 327,506 Atoms
days/ns < Lower Is Better
Try 1 . 4.74777 |==============================================================
Try 2 . 4.74984 |==============================================================
Try 3 . 4.75337 |==============================================================


TensorFlow Lite 2020-08-23
Model: SqueezeNet
Microseconds < Lower Is Better
Try 1 . 391789 |===============================================================
Try 2 . 391858 |===============================================================
Try 3 . 391661 |===============================================================


TensorFlow Lite 2020-08-23
Model: Inception V4
Microseconds < Lower Is Better
Try 1 . 5769780 |==============================================================
Try 2 . 5787883 |==============================================================
Try 3 . 5799740 |==============================================================


TensorFlow Lite 2020-08-23
Model: NASNet Mobile
Microseconds < Lower Is Better
Try 1 . 280222 |===============================================================
Try 2 . 281361 |===============================================================
Try 3 . 281478 |===============================================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Float
Microseconds < Lower Is Better
Try 1 . 261110 |===============================================================
Try 2 . 261142 |===============================================================
Try 3 . 260997 |===============================================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Quant
Microseconds < Lower Is Better
Try 1 . 278243 |===============================================================
Try 2 . 277533 |===============================================================
Try 3 . 277236 |===============================================================


TensorFlow Lite 2020-08-23
Model: Inception ResNet V2
Microseconds < Lower Is Better
Try 1 . 5201777 |==============================================================
Try 2 . 5201413 |==============================================================
Try 3 . 5181893 |==============================================================