GPU Wiki
Compare NVIDIA GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | CMP 40HX |
|---|---|
| Overview | |
| Product name | NVIDIA CMP 40HX |
| Architecture | Turing |
| Generation / family | Mining GPUs |
| GPU codename | TU106 |
| Launch date | 2021-02-25 |
| Market segment | Desktop in Mining GPUs |
| Board type / entry type | Reference GPU |
| GPU | |
| Process node | TSMC 12 nm |
| Die size | 445 mm² |
| Transistor count | 10.8 billion |
| GPU chip | TU106 |
| SM / multiprocessor count | 36 |
| CUDA Cores | 2304 |
| Tensor Cores | 288 |
| RT Cores | 36 |
| ROPs | 64 |
| TMUs | 144 |
| Clocks | |
| Base / Core clock | 1,470 MHz |
| Boost clock | 1,650 MHz |
| Memory clock | 1,750 MHz |
| Memory | |
| Memory size | 8 GB |
| Memory type | GDDR6 |
| Memory bus width | 256-bit |
| Memory bandwidth | 448 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 1.0 x4 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 185 W |
| Recommended PSU | 450 W |
| Power connectors | 1x 8-pin |
| Slot width | Dual-slot, 229 mm length, 35 mm width |
| Features | |
| DirectX support | DirectX 12.2 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| CUDA support | 7.5 |
| Shader Model | 6.8 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 7.6 TFLOPS |
| FP16 throughput | 15.21 TFLOPS |
Overview
Product name
CMP 40HX
NVIDIA CMP 40HX
Architecture
CMP 40HX
Turing
Generation / family
CMP 40HX
Mining GPUs
GPU codename
CMP 40HX
TU106
Launch date
CMP 40HX
2021-02-25
Market segment
CMP 40HX
Desktop in Mining GPUs
Board type / entry type
CMP 40HX
Reference GPU
GPU
Process node
CMP 40HX
TSMC 12 nm
Die size
CMP 40HX
445 mm²
Transistor count
CMP 40HX
10.8 billion
GPU chip
CMP 40HX
TU106
SM / multiprocessor count
CMP 40HX
36
CUDA Cores
CMP 40HX
2304
Tensor Cores
CMP 40HX
288
RT Cores
CMP 40HX
36
ROPs
CMP 40HX
64
TMUs
CMP 40HX
144
Clocks
Base / Core clock
CMP 40HX
1,470 MHz
Boost clock
CMP 40HX
1,650 MHz
Memory clock
CMP 40HX
1,750 MHz
Memory
Memory size
CMP 40HX
8 GB
Memory type
CMP 40HX
GDDR6
Memory bus width
CMP 40HX
256-bit
Memory bandwidth
CMP 40HX
448 GB/s
Bus / Interface
Bus interface
CMP 40HX
PCIe 1.0 x4
AGP / PCI / PCIe distinction
CMP 40HX
PCIe
Power
TDP / TBP / board power
CMP 40HX
185 W
Recommended PSU
CMP 40HX
450 W
Power connectors
CMP 40HX
1x 8-pin
Slot width
CMP 40HX
Dual-slot, 229 mm length, 35 mm width
Display / Media
Features
DirectX support
CMP 40HX
DirectX 12.2
OpenGL support
CMP 40HX
OpenGL 4.6
Vulkan support
CMP 40HX
Vulkan 1.4
CUDA support
CMP 40HX
7.5
Shader Model
CMP 40HX
6.8
Ray tracing support
CMP 40HX
Hardware RT units present
Performance / Benchmarks
FP32 throughput
CMP 40HX
7.6 TFLOPS
FP16 throughput
CMP 40HX
15.21 TFLOPS