AMD Radeon E8950 vs NVIDIA A2 Full Specs

Summary

2,048 Shaders 735MHz	1,280 Shaders 1.77GHz
8GB GDDR5192GB/s	16GB GDDR6100.1GB/s
Peak·FP32·FP16 3.01 TFLOPS	Peak·FP32·FP16 4.53 TFLOPS
Form Factor MXM-B	Form Factor PCIe Card
TDP 95W	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 E89503.01 TFLOPSFP32

x1

A2145 TOPSINT4 Tensor Sparse

x48.16

Show Top Score

Theoretical Performance

Clock Speed735MHz UC·Boost·OC	Clock Speed1770MHz UC·Base·Boost·OC
Peak OPS 3.01 TFLOPSFP32	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 3.01 TFLOPS	FP32 4.53 TFLOPS
FP64 188.2 GFLOPS	FP64 70.8 GFLOPS
Tensor INT4 -	Tensor INT4 72.5 TOPS
-	Tensor INT8 36.25 TOPS
Ray -	Ray 6.83 TOPS
Pixel Rate 23.5 GPixel/s	Pixel Rate 56.6 GPixel/s
Texture Rate 94.1 GTexel/s	Texture Rate 70.8 GTexel/s

Core Config

Shaders 2,048 Shaders	Shaders 1,280 Shaders
TMUs 128 TMUs	TMUs 40 TMUs
ROPs 32 ROPs	ROPs 32 ROPs
Tensor Cores -	Tensor Cores 40 T-Cores
RT Cores -	RT Cores 10 RT-Cores
CUs 32 CUs	SMs 10 SMs

Clocks

Base Clock -	Base Clock 1.44GHz
Boost Clock 735MHz	Boost Clock 1.77GHz

Cache

L2 Cache 768KB shared

L2 Cache 2MB shared

Memory

8GB GDDR5	16GB GDDR6
Memory Bus 256-bit	Memory Bus 128-bit
Memory Speed 6GT/s	Memory Speed 6.3GT/s
Memory Bandwidth 192GB/s	Memory Bandwidth 100.1GB/s

Power & Thermals

TDP 95W

TDP 60W

Video Output

Multi-Monitor 3	Multi-Monitor -
HDCP HDCP 1.4	HDCP -

Encoder

Encoder Model VCE 3.0

Encoder Model NVENC 7

Decoder

Decoder Model UVD 5.0

Decoder Model NVDEC 5

Card

Form Factor MXM-B	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 3	Architecture Ampere
Family Embedded	Family Server
Branding	Branding
Codename Tonga	Codename NV177
Chip Variant Tonga Pro	Chip Variant GA107-140-A1
Market Segment Server	Market Segment Server
Release Date Sep 1, 2015	Release Date Nov 10, 2021

Fabrication

Foundry TSMC	Foundry Samsung
Fabrication Node 28nm	Fabrication Node 8N
Die Size 359mm²	Die Size 200mm²
Transistor Count 5 Billion	Transistor Count 8.7 Billion
Transistor Density 13.93 MTr/mm²	Transistor Density 43.5 MTr/mm²

Images

No images available

No images available

Competitors

AMDRadeon E8950 vs GPU AMDRadeon RX 7400 AMDRadeon E8950 vs GPU AMDRadeon PRO W7400 AMDRadeon E8950 vs GPU NVIDIAGeForce RTX 3050 6GB Show 9 more

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