NVIDIA CMP 30HX vs AMD FireStream 9370
We compared two Desktop platform GPUs: 6GB VRAM CMP 30HX and 4GB VRAM FireStream 9370 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 30HX 's Advantages
Released 10 years and 8 months late
Boost Clock1785MHz
More VRAM (6GB vs 4GB)
Larger VRAM bandwidth (336.0GB/s vs 147.2GB/s)
Lower TDP (125W vs 225W)
AMD FireStream 9370 's Advantages
192 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 30HX
+90%
5.027 TFLOPS
FireStream 9370
2.64 TFLOPS
Graphics Card
Feb 2021
Release Date
Jun 2010
Mining GPUs
Generation
FireStream
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 2.0 x16
Clock Speeds
1530 MHz
Base Clock
-
1785 MHz
Boost Clock
-
1750 MHz
Memory Clock
1150 MHz
Memory
6GB
Memory Size
4GB
GDDR6
Memory Type
GDDR5
192bit
Memory Bus
256bit
336.0GB/s
Bandwidth
147.2GB/s
Render Config
-
Compute Units
20
22
SM Count
-
1408
Shading Units
1600
88
TMUs
80
48
ROPs
32
-
-
-
-
-
-
64 KB (per SM)
L1 Cache
8 KB (per CU)
1536 KB
L2 Cache
512 KB
-
-
-
Theoretical Performance
85.68 GPixel/s
Pixel Rate
26.40 GPixel/s
157.1 GTexel/s
Texture Rate
66.00 GTexel/s
10.05 TFLOPS
FP16 (half)
-
5.027 TFLOPS
FP32 (float)
2.640 TFLOPS
157.1 GFLOPS
FP64 (double)
528.0 GFLOPS
Board Design
125W
TDP
225W
300 W
Suggested PSU
550 W
No outputs
Outputs
1x DisplayPort 1.1
1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
TU116
GPU Name
Cypress
TU116-100-A1
GPU Variant
Cypress XT GL
Turing
Architecture
TeraScale 2
TSMC
Foundry
TSMC
12 nm
Process Size
40 nm
6.6 billion
Transistors
2.154 billion
284 mm²
Die Size
334 mm²
Graphics Features
12 (12_1)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
7.5
CUDA
-
6.8
Shader Model
5.0
