NVIDIA B200 vs AMD Radeon PRO W9070

GPU Specs Compare

Graphics Card

Release Date
Jan 2024
Unknown
Generation
Server Blackwell
Mining GPUs
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16

Clock Speeds

Base Clock
700 MHz
1120 MHz
Boost Clock
1965 MHz
1206 MHz
Memory Clock
2000 MHz
2100 MHz

Memory

Memory Size
90GB
4GB
Memory Type
HBM3e
GDDR5
Memory Bus
4096bit
256bit
Bandwidth
4.10TB/s
268.8GB/s

Render Config

SM Count
148
-
Shading Units
18944
2048
TMUs
592
128
ROPs
24
32
Tensor Cores
592
128
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
2 MB
Compute Units
-
32
RT Cores
-
64
L3 Cache
-
64 MB

Theoretical Performance

Pixel Rate
47.16 GPixel/s
38.59 GPixel/s
Texture Rate
1163.3 GTexel/s
154.4 GTexel/s
FP16 (half)
1191.2 TFLOPS
4.940 TFLOPS
FP32 (float)
74.45 TFLOPS
4.940 TFLOPS
FP64 (double)
37.22 TFLOPS
308.7 GFLOPS

Graphics Processor

GPU Name
GB100
Polaris 20
Architecture
Blackwell
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
5 nm
14 nm
Transistors
104 billion
5.7 billion
Die Size
Unknown
232 mm²
GPU Variant
-
Navi 48 XTW

Board Design

TDP
1000W
180W
Suggested PSU
1400 W
450 W
Outputs
No outputs
1x HDMI 2.0b
Power Connectors
-
2x 8-pin

Graphics Features

DirectX
N/A
12 (12_0)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.3
CUDA
10.0
-
Shader Model
N/A
6.7