AMD Radeon Instinct MI8 vs NVIDIA GeForce GTX 1070 Ti
What is the difference between AMD Radeon Instinct MI8 and NVIDIA GeForce GTX 1070 Ti. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Fiji | GPU Name | GP104 |
| Fiji XT | Model number | GP104-300-A1 |
| GCN 3.0 | Architecture | Pascal |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 16 nm |
| 8,900 million | Transistors | 7,200 million |
| 596 mm² | Die Size | 314 mm² |
Graphics Card
| Dec 12th, 2016 | Release Date | Nov 2nd, 2017 |
| Radeon Instinct (MIx) | Family | GeForce 10 |
| Active | Production | Active |
| PCIe 3.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 4 GB | Memory Size | 8 GB |
| HBM | Memory Type | GDDR5 |
| 4096 bit | Memory Bus | 256 bit |
| 512.0 GB/s | Bandwidth | 256.3 GB/s |
Performance
| 64.00 GPixel/s | Pixel fillrate | 107.7 GPixel/s |
| 256.0 GTexel/s | Texture fillrate | 255.8 GTexel/s |
| 8.192 TFLOPS (1:1) | FP16 (half) performance | 127.9 GFLOPS (1:64) |
| 8.192 TFLOPS | FP32 (float) performance | 8.186 TFLOPS |
| 512.0 GFLOPS (1:16) | FP64 (double) performance | 255.8 GFLOPS (1:32) |
Clock Speeds
| 500 MHz 1000 Mbps effective | Memory Clock | 2002 MHz 8 Gbps effective |
Render Config
| 4096 | Shading Units | 2432 |
| 256 | TMUs | 152 |
| 64 | ROPs | 64 |
| 16 KB (per CU) | L1 Cache | 48 KB (per SM) |
| 2 MB | L2 Cache | 2 MB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 152 mm 6 inches | Length | 267 mm 10.5 inches |
| 111 mm 4.4 inches | Width | 112 mm 4.4 inches |
| 175 W | Thermal design power (TDP) | 180 W |
| 450 W | Suggested PSU | 450 W |
| No outputs | Display Connectors | 1x DVI 1x HDMI 3x DisplayPort |
| 1x 8-pin | Power Connectors | 1x 8-pin |
API support
| 12 (12_0) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 2.0 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.2 |
| 6.3 | Shader Model | 6.4 |