NVIDIA CMP 30HX vs AMD FireStream 9350

GPU Specs Compare

G

NVIDIA CMP 30HX

NVIDIA 2021-02
G

AMD FireStream 9350

AMD 2010-06

Graphics Card

Release Date
Feb 2021
Jun 2010
Generation
Mining GPUs
FireStream
Type
Desktop
Desktop
Bus Interface
PCIe 1.0 x4
PCIe 2.0 x16

Clock Speeds

Base Clock
1530 MHz
-
Boost Clock
1785 MHz
-
Memory Clock
1750 MHz
1000 MHz

Memory

Memory Size
6GB
2GB
Memory Type
GDDR6
GDDR5
Memory Bus
192bit
256bit
Bandwidth
336.0GB/s
128.0GB/s

Render Config

SM Count
22
-
Shading Units
1408
1440
TMUs
88
72
ROPs
48
32
L1 Cache
64 KB (per SM)
8 KB (per CU)
L2 Cache
1536 KB
512 KB
Compute Units
-
18

Theoretical Performance

Pixel Rate
85.68 GPixel/s
22.40 GPixel/s
Texture Rate
157.1 GTexel/s
50.40 GTexel/s
FP16 (half)
10.05 TFLOPS
-
FP32 (float)
5.027 TFLOPS
2.016 TFLOPS
FP64 (double)
157.1 GFLOPS
403.2 GFLOPS

Graphics Processor

GPU Name
TU116
Cypress
GPU Variant
TU116-100-A1
Cypress PRO GL
Architecture
Turing
TeraScale 2
Foundry
TSMC
TSMC
Process Size
12 nm
40 nm
Transistors
6.6 billion
2.154 billion
Die Size
284 mm²
334 mm²

Board Design

TDP
125W
150W
Suggested PSU
300 W
450 W
Outputs
No outputs
1x DisplayPort 1.1
Power Connectors
1x 8-pin
1x 6-pin

Graphics Features

DirectX
12 (12_1)
11.2 (11_0)
OpenGL
4.6
4.4
OpenCL
3.0
1.2
Vulkan
1.3
N/A
CUDA
7.5
-
Shader Model
6.8
5.0