AMD Radeon E9172 vs NVIDIA A2 Full Specs

Summary

512 Shaders 1.22GHz	1,280 Shaders 1.77GHz
2GB GDDR548GB/s	16GB GDDR6100.1GB/s
Peak·FP32·FP16 1.25 TFLOPS	Peak·FP32·FP16 4.53 TFLOPS
Form Factor MXM-A	Form Factor PCIe Card
TDP 35W	TDP 60W

Highlights

Peak OPS

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

Radeon E91721.25 TFLOPSFP16

x1

A2145 TOPSINT4 Tensor Sparse

x116.16

Show Top Score

Theoretical Performance

Clock Speed1219MHz UC·Base·Boost·OC	Clock Speed1770MHz UC·Base·Boost·OC
Peak OPS 1.25 TFLOPSFP16	Peak OPS 145 TOPSINT4 Tensor Sparse
-	Tensor FP16-16 18.12 TFLOPS FP16-16 Tensor Sparse 36.25 TFLOPS Tensor FP16-32 9.06 TFLOPS FP16-32 Tensor Sparse 18.12 TFLOPS
-	BF16 4.53 TFLOPS Tensor BF16 9.06 TFLOPS BF16 Tensor Sparse 18.12 TFLOPS
Tensor TF32 -	Tensor TF32 4.53 TFLOPS
FP32 1.25 TFLOPS	FP32 4.53 TFLOPS
FP64 78.02 GFLOPS	FP64 70.8 GFLOPS
Tensor INT4 -	Tensor INT4 72.5 TOPS
-	Tensor INT8 36.25 TOPS
Ray -	Ray 6.83 TOPS
Pixel Rate 19.5 GPixel/s	Pixel Rate 56.6 GPixel/s
Texture Rate 39 GTexel/s	Texture Rate 70.8 GTexel/s

Core Config

Shaders 512 Shaders	Shaders 1,280 Shaders
TMUs 32 TMUs	TMUs 40 TMUs
ROPs 16 ROPs	ROPs 32 ROPs
Tensor Cores -	Tensor Cores 40 T-Cores
RT Cores -	RT Cores 10 RT-Cores
CUs 8 CUs	SMs 10 SMs

Clocks

Base Clock 1.12GHz	Base Clock 1.44GHz
Boost Clock 1.22GHz	Boost Clock 1.77GHz

Cache

L2 Cache 512KB shared

L2 Cache 2MB shared

Memory

2GB GDDR5	16GB GDDR6
Memory Bus 64-bit	Memory Bus 128-bit
Memory Speed 6GT/s	Memory Speed 6.3GT/s
Memory Bandwidth 48GB/s	Memory Bandwidth 100.1GB/s

Power & Thermals

TDP 35W

TDP 60W

Video Output

Multi-Monitor 3	Multi-Monitor -
HDCP HDCP 2.2	HDCP -

Encoder

Encoder Model VCE 3.4

Encoder Model NVENC 7

Decoder

Decoder Model UVD 6.3

Decoder Model NVDEC 5

Card

Form Factor MXM-A	Form Factor PCIe Card
PCIe -	PCIe 1-Slots
-	Height 69 mm (2.72") Width 168 mm (6.61") Depth 20 mm (0.79")
Cooling Passive	Cooling Passive

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture GCN 4	Architecture Ampere
Family Embedded	Family Server
Branding	Branding
Codename Lexa	Codename NV177
Chip Variant Polaris 12 XL	Chip Variant GA107-140-A1
Market Segment Server	Market Segment Server
Release Date Oct 1, 2017	Release Date Nov 10, 2021

Fabrication

Foundry GlobalFoundries	Foundry Samsung
Fabrication Node 14LPP	Fabrication Node 8N
Die Size 103mm²	Die Size 200mm²
Transistor Count 2.2 Billion	Transistor Count 8.7 Billion
Transistor Density 21.36 MTr/mm²	Transistor Density 43.5 MTr/mm²

Images

No images available

No images available

Competitors

-	NVIDIAA2 vs GPU AMDRadeon PRO W7500 NVIDIAA2 vs GPU AMDRadeon RX 7400 NVIDIAA2 vs GPU AMDRadeon PRO W7400 Show 12 more