NVIDIA CMP 50HX: GPU Specs & Benchmarks
The CMP 50HX is a graphics card by NVIDIA, built on the 12 nm process and based on the TU102 graphics processor (GPU). The video card specifications and performance tests (benchmarks) are listed below.
Recommended Gaming Resolutions 640x480 1280x720 1366x768 1600x900 1920x1080 2560x1440 3840x2160
Graphics Processor (GPU)
- GPU Name
- TU102
- Model number
- TU102-100-A1
- Architecture
- Turing
- Foundry
- TSMC
- Process Size
- 12 nm
- Transistors
- 18,600 million
- Die Size
- 754 mm²
Graphics Card
- Release Date
- Jun 24th, 2021
- Family
- Mining GPUs
- Production
- Active
- Bus Interface
- PCIe 3.0 x16
Memory
- Memory Size
- 10 GB
- Memory Type
- GDDR6
- Memory Bus
- 320 bit
- Bandwidth
- 560.0 GB/s
Performance
- Pixel fillrate
- 123.6 GPixel/s
- Texture fillrate
- 296.6 GTexel/s
- FP16 (half) performance
- 22.15 TFLOPS (2:1)
- FP32 (float) performance
- 11.07 TFLOPS
- FP64 (double) performance
- 346.1 GFLOPS (1:32)
Clock Speeds
- Base Clock
- 1350 MHz
- Boost Clock
- 1545 MHz
- Memory Clock
- 1750 MHz
14 Gbps effective
Render Config
- Shading Units
- 3584
- TMUs
- 192
- ROPs
- 80
- RT Cores
- 56
- L1 Cache
- 64 KB (per SM)
- L2 Cache
- 5 MB
- SM Count
- 56
- Tensor Cores
- 448
Board Design
- Slot Width
- Dual-slot
- Length
- 267 mm
10.5 inches - Width
- 116 mm
4.6 inches - Height
- 35 mm
1.4 inches - Thermal design power (TDP)
- 250 W
- Suggested PSU
- 600 W
- Display Connectors
- No outputs
- Power Connectors
- 2x 8-pin
- Board Number
- PG150 SKU 100
API support
- DirectX
- 12 Ultimate (12_2)
- OpenGL
- 4.6
- OpenCL
- 3.0
- Vulkan
- 1.2
- Shader Model
- 6.6
- CUDA
- 7.5