AMD Radeon Pro WX 5100 vs NVIDIA Quadro P2000
Graphics Processor
| GPU model | Ellesmere | GP106 |
|---|---|---|
| GPU variant | Polaris 10 PRO GL (215-0876144) | GP106-875-A1 |
| Architecture | GCN 4.0 | Pascal |
| Foundry | GlobalFoundries | TSMC |
| Manufacturing process | 14 nm | 16 nm |
| Number of transistors | 5,700 million | 4,400 million |
| Die size | 232 mm² | 200 mm² |
Graphics Card
| Release date | Nov 18th, 2016 | Feb 6th, 2017 |
|---|---|---|
| Generation | Radeon Pro | Quadro |
| Production | Active | End-of-life |
| Launch price | 499 USD | — |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 713 MHz | 1076 MHz |
|---|---|---|
| Boost clock | 1086 MHz | 1480 MHz |
| Memory clock | 1250 MHz 5 Gbps effective | 1752 MHz 7 Gbps effective |
Memory Configuration
| Memory size | 8 GB | 5 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 256 bit | 160 bit |
| Bandwidth | 160.0 GB/s | 140.2 GB/s |
Render Configuration
| Shading units | 1792 | 1024 |
|---|---|---|
| TMUs | 112 | 64 |
| ROPs | 32 | 40 |
| Compute units | 28 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
| Cache L2 | 2 MB | 1280 KB |
| SM count | — | 8 |
Performance
| Pixel rate | 34.75 GPixel/s | 59.20 GPixel/s |
|---|---|---|
| Texture rate | 121.6 GTexel/s | 94.72 GTexel/s |
| FP16 (half) performance | 3.892 TFLOPS (1:1) | 47.36 GFLOPS (1:64) |
| FP32 (float) performance | 3.892 TFLOPS | 3.031 TFLOPS |
| FP64 (double) performance | 243.3 GFLOPS (1:16) | 94.72 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Single-slot | Single-slot |
|---|---|---|
| Length | 173 mm 6.8 inches | 196 mm 7.7 inches |
| Width | 112 mm 4.4 inches | 111 mm 4.4 inches |
| TDP | 75 W | 75 W |
| Suggested PSU | 250 W | 250 W |
| Outputs | 4x DisplayPort | 4x DisplayPort |
| Power connectors | None | None |
| Board number | C954 | PG410 SKU 502 |
API Support & Features
| DirectX | 12 (12_0) | 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 | — | 6.1 |
