NVIDIA CMP 40HX vs AMD Radeon R9 370X
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 2GB VRAM Radeon R9 370X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 5 years and 6 months late
Boost Clock has increased by 60% (1650MHz vs 1030MHz)
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (448.0GB/s vs 179.2GB/s)
1024 additional rendering cores
AMD Radeon R9 370X 's Advantages
Lower TDP (180W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+188%
7.603 TFLOPS
Radeon R9 370X
2.637 TFLOPS
Graphics Card
Feb 2021
Release Date
Aug 2015
Mining GPUs
Generation
Pirate Islands
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 3.0 x16
Clock Speeds
1470 MHz
Base Clock
980 MHz
1650 MHz
Boost Clock
1030 MHz
1750 MHz
Memory Clock
1400 MHz
Memory
8GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
179.2GB/s
Render Config
-
Compute Units
24
36
SM Count
-
2304
Shading Units
1280
144
TMUs
80
64
ROPs
32
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
32.96 GPixel/s
237.6 GTexel/s
Texture Rate
82.40 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
2.637 TFLOPS
237.6 GFLOPS
FP64 (double)
164.8 GFLOPS
Board Design
185W
TDP
180W
450 W
Suggested PSU
450 W
No outputs
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
1x 8-pin
Power Connectors
2x 6-pin
Graphics Processor
TU106
GPU Name
Trinidad
TU106-100-A1
GPU Variant
Trinidad XT
Turing
Architecture
GCN 1.0
TSMC
Foundry
TSMC
12 nm
Process Size
28 nm
10.8 billion
Transistors
2.8 billion
445 mm²
Die Size
212 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
1.2
1.3
Vulkan
1.2
7.5
CUDA
-
6.8
Shader Model
5.1
