NVIDIA Tegra X1+ vs AMD Latte Full Specs

Summary

256 Shaders 1.27GHz	320 Shaders 550MHz
Shared Memory34.1GB/s LPDDR4X·LPDDR4	2GB DDR312.8GB/s placeholder
Peak·FP32·FP16 648.7 GFLOPS	Peak·FP32·FP16 352 GFLOPS
Form Factor iGPU	Form Factor Soldered
TDP Shared	TDP 33W

Theoretical Performance

Clock Speed1267MHz UC·Boost·OC	Clock Speed550MHz UC·Boost·OC
Peak OPS 1.3 TFLOPSFP16	Peak OPS 352 GFLOPSFP32
FP32 648.7 GFLOPS	FP32 352 GFLOPS
FP64 20.27 GFLOPS	-
Pixel Rate 20.3 GPixel/s	Pixel Rate 4.4 GPixel/s
Texture Rate 20.3 GTexel/s	Texture Rate 8.8 GTexel/s

Core Config

Shaders 256 Shaders	Shaders 320 Shaders
TMUs 16 TMUs	TMUs 16 TMUs
ROPs 16 ROPs	ROPs 8 ROPs
SMs 2 SMs	CUs 4 CUs

Clocks

Boost Clock 1.27GHz

Boost Clock 550MHz

Cache

L2 Cache 256KB shared

L2 Cache -

Memory

Shared Memory LPDDR4X·LPDDR4	2GB DDR3 placeholder
Memory Bus 64-bit	Memory Bus 64-bit
Memory Speed 4.3GT/s	Memory Speed 1.6GT/s
Memory Bandwidth 34.1GB/s	Memory Bandwidth 12.8GB/s
ECC No	ECC No
EDRAM -	EDRAM 32MBSize 1024BitBus Width 70.4GB/sBandwidth

Power & Thermals

TDP Shared

TDP 33W

Video Output

Multi-Monitor -

Multi-Monitor 1

Encoder

Encoder Model NVENC 3	-
Codec AVC (H.264) HEVC (H.265)	Codec -

Decoder

Decoder Model NVDEC 2	-
Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265)	Codec -

Card

Form Factor iGPU

Form Factor Soldered

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Maxwell 2	Architecture TeraScale 2
Family Tegra	Family Console
Branding	Branding
Codename Mariko	Codename Latte
Market Segment Tablet	Market Segment Console
Release Date May 1, 2019	Release Date Nov 18, 2012

Fabrication

Foundry TSMC	Foundry Renesas
Fabrication Node 16FFC	Fabrication Node 40nm
Die Size 100mm²	Die Size 146mm²
Transistor Count 2 Billion	Transistor Count 880 Million
Transistor Density 20 MTr/mm²	Transistor Density 6.03 MTr/mm²

Images