AMD Radeon RX 580X vs NVIDIA H100 CNX
GPU · Specs Compare
Graphics Card
Release Date
Apr 2018
Mar 2023
Generation
Polaris
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1257 MHz
690 MHz
Boost Clock
1340 MHz
1845 MHz
Memory Clock
2000 MHz
1593 MHz
Memory
Memory Size
8GB
80GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
256.0GB/s
2039GB/s
Render Config
Compute Units
36
—
Shading Units
2304
14592
TMUs
144
456
ROPs
32
24
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
2 MB
50 MB
SM Count
—
114
Tensor Cores
—
456
Theoretical Performance
Pixel Rate
42.88 GPixel/s
44.28 GPixel/s
Texture Rate
193.0 GTexel/s
841.3 GTexel/s
FP16 (half)
6.175 TFLOPS
215.4 TFLOPS
FP32 (float)
6.175 TFLOPS
53.84 TFLOPS
FP64 (double)
385.9 GFLOPS
26.92 TFLOPS
Graphics Processor
GPU Name
Polaris 20
GH100
GPU Variant
Polaris 20 XTX(215-0910038)
—
Architecture
GCN 4.0
Hopper
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
4 nm
Transistors
5.7 billion
80 billion
Die Size
232 mm²
814 mm²
Board Design
TDP
185W
350W
Suggested PSU
450 W
750 W
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
No outputs
Power Connectors
1x 8-pin
8-pin EPS
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
—
9.0
▲ Specs Compare
Data sourced from official specifications and benchmark tests.