NVIDIA CMP 30HX vs AMD Radeon R9 390
What is the difference between NVIDIA CMP 30HX and AMD Radeon R9 390. Find out which graphics card has better performance.
Graphics Processor (GPU)
| TU116 | GPU Name | Grenada |
| TU116-100-A1 | Model number | Grenada PRO (215-0880030) |
| Turing | Architecture | GCN 2.0 |
| TSMC | Foundry | TSMC |
| 12 nm | Process Size | 28 nm |
| 6,600 million | Transistors | 6,200 million |
| 284 mm² | Die Size | 438 mm² |
Graphics Card
| Feb 25th, 2021 | Release Date | Jun 18th, 2015 |
| Mining GPUs | Family | Pirate Islands (R9 300) |
| Active | Production | Active |
| 799 USD | Launch Price | 329 USD |
| PCIe 3.0 x4 | Bus Interface | PCIe 3.0 x16 |
Memory
| 6 GB | Memory Size | 8 GB |
| GDDR6 | Memory Type | GDDR5 |
| 192 bit | Memory Bus | 512 bit |
| 336.0 GB/s | Bandwidth | 384.0 GB/s |
Performance
| 85.68 GPixel/s | Pixel fillrate | 64.00 GPixel/s |
| 157.1 GTexel/s | Texture fillrate | 160.0 GTexel/s |
| 5.027 TFLOPS | FP32 (float) performance | 5.120 TFLOPS |
| 157.1 GFLOPS (1:32) | FP64 (double) performance | 640.0 GFLOPS (1:8) |
Clock Speeds
| 1750 MHz 14 Gbps effective | Memory Clock | 1500 MHz 6 Gbps effective |
Render Config
| 1408 | Shading Units | 2560 |
| 88 | TMUs | 160 |
| 48 | ROPs | 64 |
| 64 KB (per SM) | L1 Cache | 16 KB (per CU) |
| 1536 KB | L2 Cache | 1024 KB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 229 mm 9 inches | Length | 275 mm 10.8 inches |
| 111 mm 4.4 inches | Width | 109 mm 4.3 inches |
| 35 mm 1.4 inches | Height | 36 mm 1.4 inches |
| 125 W | Thermal design power (TDP) | 275 W |
| 300 W | Suggested PSU | 600 W |
| No outputs | Display Connectors | 2x DVI 1x HDMI 1x DisplayPort |
| 1x 8-pin | Power Connectors | 1x 6-pin + 1x 8-pin |
| PG161 SKU 90 | Board Number | C679 |
API support
| 12 (12_1) | DirectX | 12 (12_0) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.0 |
| 1.2 | Vulkan | 1.2 |
| 6.6 | Shader Model | 6.3 |