AMD Radeon Instinct MI60 vs NVIDIA CMP 40HX

GPU Specs Compare

G

NVIDIA CMP 40HX

NVIDIA 2021-02

Graphics Card

Release Date
Nov 2018
Feb 2021
Generation
Radeon Instinct
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4

Clock Speeds

Base Clock
1200 MHz
1470 MHz
Boost Clock
1800 MHz
1650 MHz
Memory Clock
1000 MHz
1750 MHz

Memory

Memory Size
32GB
8GB
Memory Type
HBM2
GDDR6
Memory Bus
4096bit
256bit
Bandwidth
1024GB/s
448.0GB/s

Render Config

Compute Units
64
-
Shading Units
4096
2304
TMUs
256
144
ROPs
64
64
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
4 MB
4 MB
SM Count
-
36
Tensor Cores
-
288
RT Cores
-
36

Theoretical Performance

Pixel Rate
115.2 GPixel/s
105.6 GPixel/s
Texture Rate
460.8 GTexel/s
237.6 GTexel/s
FP16 (half)
29.49 TFLOPS
15.21 TFLOPS
FP32 (float)
14.75 TFLOPS
7.603 TFLOPS
FP64 (double)
7.373 TFLOPS
237.6 GFLOPS

Graphics Processor

GPU Name
Vega 20
TU106
GPU Variant
Vega 20 GL
TU106-100-A1
Architecture
GCN 5.1
Turing
Foundry
TSMC
TSMC
Process Size
7 nm
12 nm
Transistors
13.23 billion
10.8 billion
Die Size
331 mm²
445 mm²

Board Design

TDP
300W
185W
Suggested PSU
700 W
450 W
Outputs
1x mini-DisplayPort 1.4a
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
1x 8-pin

Graphics Features

DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.2
1.3
Shader Model
6.4
6.8
CUDA
-
7.5

📊 Benchmark

Blender
-
1,174