NVIDIA H800 SXM5 vs AMD Radeon Pro W6800X

GPU · Specs Compare

Products
GPU NVIDIA H800 SXM5 NVIDIA · 2023-03
GPU AMD Radeon Pro W6800X AMD · 2021-08
Graphics Card
Release Date
Mar 2023
Aug 2021
Generation
Server Hopper
Radeon Pro Mac
Type
AI GPU
Desktop
Bus Interface
PCIe 5.0 x16
Apple MPX
Clock Speeds
Base Clock
1095 MHz
1800 MHz
Boost Clock
1755 MHz
2087 MHz
Memory Clock
1313 MHz
2000 MHz
Memory
Memory Size
80GB
32GB
Memory Type
HBM3
GDDR6
Memory Bus
5120bit
256bit
Bandwidth
3.36TB/s
512.0GB/s
Render Config
SM Count
132
—
Shading Units
16896
3840
TMUs
528
240
ROPs
24
96
Tensor Cores
528
—
L1 Cache
256 KB (per SM)
128 KB per Array
L2 Cache
50 MB
4 MB
Compute Units
—
60
RT Cores
—
60
L3 Cache
—
128 MB
Theoretical Performance
Pixel Rate
42.12 GPixel/s
200.4 GPixel/s
Texture Rate
926.6 GTexel/s
500.9 GTexel/s
FP16 (half)
237.2 TFLOPS
32.06 TFLOPS
FP32 (float)
59.30 TFLOPS
16.03 TFLOPS
FP64 (double)
29.65 TFLOPS
1002 GFLOPS
Graphics Processor
GPU Name
GH100
Navi 21
Architecture
Hopper
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
80 billion
26.8 billion
Die Size
814 mm²
520 mm²
GPU Variant
—
Navi 21 Pro-XLA
Board Design
TDP
700W
200W
Suggested PSU
1100 W
550 W
Outputs
No outputs
1x HDMI 2.14x Thunderbolt
Power Connectors
8-pin EPS
Apple MPX
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.3
CUDA
9.0
—
Shader Model
N/A
6.7
Benchmark
Blender
—
1,424
▲ Specs Compare Data sourced from official specifications and benchmark tests.