NVIDIA CMP 40HX
- Graphics Processor
- TU106
- Cores
- 2304
- TMUs
- 144
- ROPs
- 64
- Memory Size
- 8 GB
- Memory Type
- GDDR6
- Bus Width
- 256 bit
The CMP 40HX is a professional graphics card by NVIDIA, launched in February 2021. Built on the 12 nm process, and based on the TU106 graphics processor, in its TU106-100-A1 variant, the card supports DirectX 12 Ultimate. The TU106 graphics processor is a large chip with a die area of 445 mm² and 10,800 million transistors. It features 2304 shading units, 144 texture mapping units, and 64 ROPs. Also included are 288 tensor cores which help improve the speed of machine learning applications. The card also has 36 raytracing acceleration cores. NVIDIA has paired 8 GB GDDR6 memory with the CMP 40HX, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1470 MHz, which can be boosted up to 1650 MHz, memory is running at 1750 MHz (14 Gbps effective).
Being a dual-slot card, the NVIDIA CMP 40HX draws power from 1x 8-pin power connector, with power draw rated at 185 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. CMP 40HX is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card's dimensions are 229 mm x 111 mm x 35 mm, and it features a dual-slot cooling solution.
Being a dual-slot card, the NVIDIA CMP 40HX draws power from 1x 8-pin power connector, with power draw rated at 185 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. CMP 40HX is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card's dimensions are 229 mm x 111 mm x 35 mm, and it features a dual-slot cooling solution.
Graphics Processor
Graphics Card
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- Base Clock
- 1470 MHz
- Boost Clock
- 1650 MHz
- Memory Clock
-
1750 MHz
14 Gbps effective
Memory
- Memory Size
- 8 GB
- Memory Type
- GDDR6
- Memory Bus
- 256 bit
- Bandwidth
- 448.0 GB/s
Render Config
- Shading Units
- 2304
- TMUs
- 144
- ROPs
- 64
- SM Count
- 36
- Tensor Cores
- 288
- RT Cores
- 36
- L1 Cache
- 64 KB (per SM)
- L2 Cache
- 4 MB
Theoretical Performance
- Pixel Rate
- 105.6 GPixel/s
- Texture Rate
- 237.6 GTexel/s
- FP16 (half) performance
- 15.21 TFLOPS (2:1)
- FP32 (float) performance
- 7.603 TFLOPS
- FP64 (double) performance
- 237.6 GFLOPS (1:32)
Board Design
- Slot Width
- Dual-slot
- Length
- 229 mm
9 inches
- Width
- 111 mm
4.4 inches
- Height
- 35 mm
1.4 inches
- TDP
- 185 W
- Suggested PSU
- 450 W
- Outputs
- No outputs
- Power Connectors
- 1x 8-pin
- Board Number
- PG161 SKU 100
Graphics Features
- DirectX
- 12 Ultimate (12_2)
- OpenGL
- 4.6
- OpenCL
- 1.2
- Vulkan
- 1.2
- CUDA
- 7.5
- Shader Model
- 6.5