NVIDIA CMP 170HX Mining Card
Product status: Official | Last Update: 2021-09-02 | Report Error
NVIDIA CMP 170HX
Overview
Manufacturer
NVIDIA
Original Series
CMP HX
Launch Date
September 2nd, 2021
Graphics Processing Unit
GPU Model
GA100-100 (GA100)
Architecture
Ampere
Fabrication Process
7 nm
Die Size
826 mm2
Transistors Count
54.2B
CUDAs
4480
Tensor Cores
280
Clocks
Base Clock
1140 MHz
Boost Clock
1410 MHz
Memory Clock
1458 MHz
Effective Memory Clock
2916 Mbps
Memory Configuration
Memory Size
8192 MB
Memory Type
HBM2
Memory Bus Width
4096-bit
Memory Bandwidth
1,493.0 GB/s
Physical
Interface
PCI-Express 4.0 x4
Height
2-slot
Power Connectors
1× 8-pin
TDP/TBP
250 W
Recommended PSU
600 W
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
2.1
Performance
Peak FP32
12.6 TFLOPS
FP32 Perf. per Watt
50.5 GFLOPS/W
FP32 Perf. per mm2
15.3 GFLOPS/mm2
| Model | Cores | Boost Clock | Memory Clock | Memory Config. | |
|---|---|---|---|---|---|
 | NVIDIA CMP 90HX | TBC | TBC | TBC | TBC |
 | NVIDIA CMP 170HX | ||||
 | NVIDIA CMP 50HX | ||||
 | NVIDIA CMP 40HX | TBC | TBC | TBC | TBC |
 | NVIDIA CMP 30HX |
| Model | Cores | Boost Clock | Memory Clock | Memory Config. | |
|---|---|---|---|---|---|
 | NVIDIA HGX A100 (16-GPU) | ||||
| | NVIDIA DGX A100 | ||||
| | NVIDIA HGX A100 (8-GPU) | ||||
| | NVIDIA HGX A100 (4-GPU) "Redstone" | ||||
 | NVIDIA A100 SXM 80GB | ||||
| | NVIDIA A100 PCIe 80GB | ||||
| | NVIDIA EGX A100 | TBC | TBC | TBC | TBC |
 | NVIDIA A100 SXM 40GB | ||||
| | NVIDIA A100 PCIe 40GB | ||||
| | NVIDIA CMP 170HX | ||||
 | NVIDIA A30 |