AMD Radeon R9 390 vs NVIDIA Tesla K20X
What is the difference between AMD Radeon R9 390 and NVIDIA Tesla K20X. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Grenada | GPU Name | GK110 |
| GCN 2.0 | Architecture | Kepler |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 28 nm |
| 6,200 million | Transistors | 7,080 million |
| 438 mm² | Die Size | 561 mm² |
Graphics Card
| Jun 18th, 2015 | Release Date | Nov 12th, 2012 |
| Pirate Islands (R9 300) | Family | Tesla (Kxx) |
| Active | Production | End-of-life |
| 329 USD | Launch Price | 7,699 USD |
| PCIe 3.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 8 GB | Memory Size | 6 GB |
| GDDR5 | Memory Type | GDDR5 |
| 512 bit | Memory Bus | 384 bit |
| 384.0 GB/s | Bandwidth | 249.6 GB/s |
Performance
| 64.00 GPixel/s | Pixel fillrate | 40.99 GPixel/s |
| 160.0 GTexel/s | Texture fillrate | 164.0 GTexel/s |
| 5.120 TFLOPS | FP32 (float) performance | 3.935 TFLOPS |
| 640.0 GFLOPS (1:8) | FP64 (double) performance | 1,312 GFLOPS (1:3) |
Clock Speeds
| 1500 MHz 6 Gbps effective | Memory Clock | 1300 MHz 5.2 Gbps effective |
| 1000 MHz | GPU Clock | 732 MHz |
Render Config
| 2560 | Shading Units | 2688 |
| 160 | TMUs | 224 |
| 64 | ROPs | 48 |
| 16 KB (per CU) | L1 Cache | 16 KB (per SMX) |
| 1024 KB | L2 Cache | 1536 KB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 275 mm 10.8 inches | Length | 267 mm 10.5 inches |
| 275 W | Thermal design power (TDP) | 235 W |
| 600 W | Suggested PSU | 550 W |
| 2x DVI 1x HDMI 1x DisplayPort | Display Connectors | No outputs |
| 1x 6-pin + 1x 8-pin | Power Connectors | 1x 6-pin + 1x 8-pin |
| C679 | Board Number | P2081 |
API support
| 12 (12_0) | DirectX | 12 (11_0) |
| 4.6 | OpenGL | 4.6 |
| 2.0 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.1 |
| 6.3 | Shader Model | 5.1 |