NVIDIA CMP 90HX vs NVIDIA Tesla P40
What is the difference between NVIDIA CMP 90HX and NVIDIA Tesla P40. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA102 | GPU Name | GP102 |
| Ampere | Architecture | Pascal |
| Samsung | Foundry | TSMC |
| 8 nm | Process Size | 16 nm |
| 28,300 million | Transistors | 11,800 million |
| 628 mm² | Die Size | 471 mm² |
Graphics Card
| 2021 | Release Date | Sep 13th, 2016 |
| Mining GPUs | Family | Tesla (Pxx) |
| Unreleased | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 10 GB | Memory Size | 24 GB |
| GDDR6X | Memory Type | GDDR5X |
| 320 bit | Memory Bus | 384 bit |
| 760.3 GB/s | Bandwidth | 694.3 GB/s |
Performance
| 136.8 GPixel/s | Pixel fillrate | 147.0 GPixel/s |
| 342.0 GTexel/s | Texture fillrate | 367.4 GTexel/s |
| 21.89 TFLOPS (1:1) | FP16 (half) performance | 183.7 GFLOPS (1:64) |
| 21.89 TFLOPS | FP32 (float) performance | 11.76 TFLOPS |
| 342.0 GFLOPS (1:64) | FP64 (double) performance | 367.4 GFLOPS (1:32) |
Clock Speeds
| 1440 MHz | Base Clock | 1303 MHz |
| 1710 MHz | Boost Clock | 1531 MHz |
| 1188 MHz 19 Gbps effective | Memory Clock | 1808 MHz 14.5 Gbps effective |
Render Config
| 6400 | Shading Units | 3840 |
| 200 | TMUs | 240 |
| 80 | ROPs | 96 |
| 128 KB (per SM) | L1 Cache | 48 KB (per SM) |
| 5 MB | L2 Cache | 3 MB |
| 50 | SM Count | 30 |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 285 mm 11.2 inches | Length | 267 mm 10.5 inches |
| 112 mm 4.4 inches | Width | 111 mm 4.4 inches |
| 320 W | Thermal design power (TDP) | 250 W |
| 700 W | Suggested PSU | 600 W |
| No outputs | Display Connectors | No outputs |
| 2x 8-pin | Power Connectors | 1x 6-pin + 1x 8-pin |
| PG132 SKU 100 | Board Number | PG610 SKU 200 |
API support
| 12 Ultimate (12_2) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.2 |
| 6.6 | Shader Model | 6.4 |
| 8.6 | CUDA | 6.1 |