AMD Radeon Vega 10 Mobile vs NVIDIA Tesla P100 SXM2
Graphics Processor
| GPU model | Picasso | GP100 |
|---|---|---|
| Architecture | GCN 5.0 | Pascal |
| Foundry | GlobalFoundries | TSMC |
| Manufacturing process | 14 nm | 16 nm |
| Number of transistors | 4,940 million | 15,300 million |
| Die size | 210 mm² | 610 mm² |
| GPU variant | — | GP100-890-A1 |
Integrated Graphics
| Release date | Apr 8th, 2019 | — |
|---|---|---|
| Generation | Picasso (Vega Mobile) | — |
| Production | Active | — |
| Interface | IGP | — |
| Predecessor | Raven Ridge | — |
| Successor | Renoir | — |
Clocks
| Base clock | 300 MHz | 1328 MHz |
|---|---|---|
| Boost clock | 1400 MHz | 1480 MHz |
| Memory clock | System Shared | 715 MHz 1430 Mbps effective |
Memory Configuration
| Memory size | System Shared | 16 GB |
|---|---|---|
| Memory type | System Shared | HBM2 |
| Memory bus width | System Shared | 4096 bit |
| Bandwidth | System Dependent | 732.2 GB/s |
Render Configuration
| Shading units | 640 | 3584 |
|---|---|---|
| TMUs | 40 | 224 |
| ROPs | 8 | 96 |
| Compute units | 10 | — |
| SM count | — | 56 |
| Cache L1 | — | 24 KB (per SM) |
| Cache L2 | — | 4 MB |
Performance
| Pixel rate | 11.20 GPixel/s | 142.1 GPixel/s |
|---|---|---|
| Texture rate | 56.00 GTexel/s | 331.5 GTexel/s |
| FP16 (half) performance | 3.584 TFLOPS (2:1) | 21.22 TFLOPS (2:1) |
| FP32 (float) performance | 1.792 TFLOPS | 10.61 TFLOPS |
| FP64 (double) performance | 112.0 GFLOPS (1:16) | 5.304 TFLOPS (1:2) |
Dimensions & Outputs
| Slot width | IGP | — |
|---|---|---|
| TDP | 15 W | 300 W |
| Outputs | No outputs | No outputs |
| Suggested PSU | — | 700 W |
| Power connectors | — | None |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.4 |
| CUDA | — | 6.0 |
Other Features
Graphics Card
| Release date | — | Apr 5th, 2016 |
|---|---|---|
| Generation | — | Tesla |
| Production | — | End-of-life |
| Interface | — | PCIe 3.0 x16 |
