AMD Radeon Pro 580 vs NVIDIA B200 SXM6

GPU · Specs Compare

Products
GPU AMD Radeon Pro 580 AMD · 2017-06
GPU NVIDIA B200 SXM6 NVIDIA · 2024-11
Graphics Card
Release Date
Jun 2017
Nov 2024
Generation
Radeon Pro Mac
Server Blackwell
Type
Mobile
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
1100 MHz
120 MHz
Boost Clock
1200 MHz
1830 MHz
Memory Clock
1695 MHz
2000 MHz
Memory
Memory Size
8GB
180GB
Memory Type
GDDR5
HBM3e
Memory Bus
256bit
8192bit
Bandwidth
217.0GB/s
8.19TB/s
Render Config
Compute Units
36
—
Shading Units
2304
18944
TMUs
144
592
ROPs
32
24
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
2 MB
126 MB
SM Count
—
148
Tensor Cores
—
592
Theoretical Performance
Pixel Rate
38.40 GPixel/s
43.92 GPixel/s
Texture Rate
172.8 GTexel/s
1083.4 GTexel/s
FP16 (half)
5.530 TFLOPS
1109.4 TFLOPS
FP32 (float)
5.530 TFLOPS
69.34 TFLOPS
FP64 (double)
345.6 GFLOPS
34.67 TFLOPS
Graphics Processor
GPU Name
Ellesmere
GB100
GPU Variant
Ellesmere XTA(216-0886220)
GB100-886N-A1
Architecture
GCN 4.0
Blackwell
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
5 nm
Transistors
5.7 billion
208 billion
Die Size
232 mm²
1628 mm²
Board Design
TDP
185W
1000W
Outputs
No outputs
No outputs
Power Connectors
None
—
Suggested PSU
—
1400 W
Graphics Features
DirectX
12 (12_0)
N/A
OpenGL
4.6
N/A
OpenCL
2.1
3.0
Vulkan
1.2
N/A
Shader Model
6.4
N/A
CUDA
—
10.0
Benchmark
3DMark Time Spy
3,791
—
3DMark Time Spy Extreme
1,684
—
▲ Specs Compare Data sourced from official specifications and benchmark tests.