AMD Radeon Instinct MI250X vs NVIDIA GeForce GTX 960
Graphics Processor
| GPU model | Aldebaran | GM206 |
|---|---|---|
| GPU variant | Aldebaran XT | GM206-300-A1 |
| Architecture | CDNA 2.0 | Maxwell 2.0 |
| Foundry | TSMC | TSMC |
| Manufacturing process | 6 nm | 28 nm |
| Number of transistors | 58,200 million | 2,940 million |
| Die size | unknown | 228 mm² |
Graphics Card
| Release date | Nov 8th, 2021 | Jan 22nd, 2015 |
|---|---|---|
| Generation | Radeon Instinct | GeForce 900 |
| Production | unknown | End-of-life |
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Launch price | — | 199 USD |
| Reviews | — | 124 in our database |
| Predecessor | — | GeForce 700 |
| Successor | — | GeForce 10 |
Clocks
| Base clock | 1000 MHz | 1127 MHz |
|---|---|---|
| Boost clock | 1700 MHz | 1178 MHz |
| Memory clock | 1600 MHz 3.2 Gbps effective | 1753 MHz 7 Gbps effective |
Memory Configuration
| Memory size | 128 GB | 2 GB |
|---|---|---|
| Memory type | HBM2E | GDDR5 |
| Memory bus width | 8192 bit | 128 bit |
| Bandwidth | 3,277 GB/s | 112.2 GB/s |
Render Configuration
| Shading units | 14080 | 1024 |
|---|---|---|
| TMUs | 880 | 64 |
| ROPs | 0 | 32 |
| Compute units | 220 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SMM) |
| Cache L2 | 16 MB | 1024 KB |
| gpu.details.mcm | 2 | — |
| SMM count | — | 8 |
Performance
| Pixel rate | 0 MPixel/s | 37.70 GPixel/s |
|---|---|---|
| Texture rate | 1,496 GTexel/s | 75.39 GTexel/s |
| FP16 (half) performance | 383.0 TFLOPS (8:1) | — |
| FP32 (float) performance | 47.87 TFLOPS | 2.413 TFLOPS |
| FP64 (double) performance | 47.87 TFLOPS (1:1) | 75.39 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 241 mm 9.5 inches |
| Width | 111 mm 4.4 inches | — |
| TDP | 500 W | 120 W |
| Suggested PSU | 900 W | 300 W |
| Outputs | No outputs | 1x DVI1x HDMI3x DisplayPort |
| Power connectors | 2x 8-pin | 1x 6-pin |
| Board number | — | PG301 |
API Support & Features
| DirectX | — | 12 (12_1) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | — | 1.1 |
| Shader model | — | 6.4 |
| CUDA | — | 5.2 |
