AMD Oberon vs NVIDIA Tegra Switch 2 Full Specs

Summary

2,304 Shaders 2.23GHz	1,536 Shaders 1.01GHz
Shared Memory	Shared Memory136.5GB/sLPDDR5X
Peak·FP32·FP16 10.29 TFLOPS	Peak·FP32·FP16 3.09 TFLOPS
Form Factor iGPU	Form Factor iGPU
TDP 180W	TDP Shared

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Oberon20.58 TFLOPSFP16

x1

Tegra Switch 298.99 TOPSINT4 Tensor Sparse

x4.81

Show Top Score

Theoretical Performance

Clock Speed2233MHz UC·Boost·OC	Clock Speed1007MHz UC·Base·Boost·OC
Peak OPS 20.58 TFLOPSFP16	Peak OPS 98.99 TOPSINT4 Tensor Sparse
-	Tensor FP16-16 12.37 TFLOPS FP16-16 Tensor Sparse 24.75 TFLOPS Tensor FP16-32 6.19 TFLOPS FP16-32 Tensor Sparse 12.37 TFLOPS
-	Tensor BF16 6.19 TFLOPS BF16 Tensor Sparse 12.37 TFLOPS
Tensor TF32 -	Tensor TF32 3.09 TFLOPS
FP32 10.29 TFLOPS	FP32 3.09 TFLOPS
FP64 643.1 GFLOPS	-
Tensor INT4 -	Tensor INT4 49.5 TOPS
-	Tensor INT8 24.75 TOPS
Ray -	Ray 6.04 TOPS
Pixel Rate 142.9 GPixel/s	Pixel Rate 24.2 GPixel/s
Texture Rate 321.6 GTexel/s	Texture Rate 48.3 GTexel/s

Core Config

Shaders 2,304 Shaders	Shaders 1,536 Shaders
TMUs 144 TMUs	TMUs 48 TMUs
ROPs 64 ROPs	ROPs 24 ROPs
Tensor Cores -	Tensor Cores 48 T-Cores
RT Cores 36 RT-Cores	RT Cores 12 RT-Cores
CUs 36 CUs	SMs 12 SMs

Clocks

Base Clock -	Base Clock 561MHz
Boost Clock 2.23GHz	Boost Clock 1.01GHz

Cache

L2 Cache 4.1MB shared

L2 Cache 1MB shared

Memory

Shared Memory	Shared MemoryLPDDR5X
Memory Bus 256-bit	Memory Bus 128-bit
Memory Speed 14GT/s	Memory Speed 8.5GT/s
Memory Bandwidth 448GB/s	Memory Bandwidth 136.5GB/s
ECC No	ECC No

Power & Thermals

TDP 180W

TDP Shared

Video Output

Multi-Monitor 1

Multi-Monitor -

Encoder

-	Encoder Model NVENC 8

Decoder

-	Decoder Model NVDEC 5

Card

Form Factor iGPU

Form Factor iGPU

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 2	Architecture Ampere
Family Console	Family Tegra
Branding	Branding
Market Segment Console	Market Segment Console
Release Date Nov 12, 2020	Release Date Jan 16, 2025

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N7	Fabrication Node N7
Die Size 308mm²	Die Size -
Transistor Count 10.6 Billion	Transistor Count -
Transistor Density 34 MTr/mm²	Transistor Density -

Images

No images available

No images available

Used In

CPUs Oberon Oberon Plus

CPUs Tegra Switch 2

Competitors

AMDOberon vs GPU AMDViola AMDOberon vs GPU Apple20-Core M5 Pro AMDOberon vs GPU Apple16-Core M5 Pro Show 7 more

NVIDIATegra Switch 2 vs GPU QualcommAdreno 830 NVIDIATegra Switch 2 vs GPU QualcommAdreno 840 NVIDIATegra Switch 2 vs GPU Apple8-Core M4-FL Show 12 more