AMD Radeon Pro Vega 16 vs AMD Radeon Vega 10 Mobile
Graphics Processor
| GPU model | Vega 12 | Picasso |
|---|---|---|
| GPU variant | Vega 12 XLA | — |
| Architecture | GCN 5.0 | GCN 5.0 |
| Foundry | GlobalFoundries | GlobalFoundries |
| Manufacturing process | 14 nm | 14 nm |
| Number of transistors | unknown | 4,940 million |
| Die size | unknown | 210 mm² |
Mobile graphics
| Release date | Nov 14th, 2018 | — |
|---|---|---|
| Generation | Radeon Pro Mac (Vega Series) | — |
| Production | Active | — |
| Interface | PCIe 3.0 x16 | — |
Clocks
| Base clock | 815 MHz | 300 MHz |
|---|---|---|
| Boost clock | 1190 MHz | 1400 MHz |
| Memory clock | 1200 MHz 2.4 Gbps effective | System Shared |
Memory Configuration
| Memory size | 4 GB | System Shared |
|---|---|---|
| Memory type | HBM2 | System Shared |
| Memory bus width | 1024 bit | System Shared |
| Bandwidth | 307.2 GB/s | System Dependent |
Render Configuration
| Shading units | 1024 | 640 |
|---|---|---|
| TMUs | 64 | 40 |
| ROPs | 32 | 8 |
| Compute units | 16 | 10 |
| Cache L1 | 16 KB (per CU) | — |
| Cache L2 | 1024 KB | — |
Performance
| Pixel rate | 38.08 GPixel/s | 11.20 GPixel/s |
|---|---|---|
| Texture rate | 76.16 GTexel/s | 56.00 GTexel/s |
| FP16 (half) performance | 4.874 TFLOPS (2:1) | 3.584 TFLOPS (2:1) |
| FP32 (float) performance | 2.437 TFLOPS | 1.792 TFLOPS |
| FP64 (double) performance | 152.3 GFLOPS (1:16) | 112.0 GFLOPS (1:16) |
Dimensions & Outputs
| Slot width | IGP | IGP |
|---|---|---|
| TDP | 75 W | 15 W |
| Outputs | No outputs | No outputs |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 2.1 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.3 | 6.4 |
Other Features
Integrated Graphics
| Release date | — | Apr 8th, 2019 |
|---|---|---|
| Generation | — | Picasso (Vega Mobile) |
| Production | — | Active |
| Interface | — | IGP |
| Predecessor | — | Raven Ridge |
| Successor | — | Renoir |
