AMD Radeon Pro 5500 XT vs NVIDIA GeForce GTX 1650 TU106
Graphics Processor
| GPU model | Navi 14 | TU106 |
|---|---|---|
| GPU variant | Navi 14 PRO XL | TU106-125-A1 |
| Architecture | RDNA 1.0 | Turing |
| Foundry | TSMC | TSMC |
| Manufacturing process | 7 nm | 12 nm |
| Number of transistors | 6,400 million | 10,800 million |
| Die size | 158 mm² | 445 mm² |
Graphics Card
| Release date | Aug 4th, 2020 | Jun 18th, 2020 |
|---|---|---|
| Generation | Radeon Pro Mac | GeForce 16 |
| Production | Active | Active |
| Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |
| Predecessor | — | GeForce 10 |
| Successor | — | GeForce 20 |
Clocks
| Base clock | 1187 MHz | 1410 MHz |
|---|---|---|
| Boost clock | 1757 MHz | 1590 MHz |
| Memory clock | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Memory Configuration
| Memory size | 8 GB | 4 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR6 |
| Memory bus width | 128 bit | 128 bit |
| Bandwidth | 224.0 GB/s | 192.0 GB/s |
Render Configuration
| Shading units | 1536 | 896 |
|---|---|---|
| TMUs | 96 | 56 |
| ROPs | 32 | 32 |
| Compute units | 24 | — |
| Cache L2 | 2 MB | 1024 KB |
| SM count | — | 14 |
| Tensor cores | — | 112 |
| RT cores | — | 14 |
| Cache L1 | — | 64 KB (per SM) |
Performance
| Pixel rate | 56.22 GPixel/s | 50.88 GPixel/s |
|---|---|---|
| Texture rate | 168.7 GTexel/s | 89.04 GTexel/s |
| FP16 (half) performance | 10.80 TFLOPS (2:1) | 5.699 TFLOPS (2:1) |
| FP32 (float) performance | 5.398 TFLOPS | 2.849 TFLOPS |
| FP64 (double) performance | 337.3 GFLOPS (1:16) | 89.04 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | IGP | Dual-slot |
|---|---|---|
| TDP | 125 W | 90 W |
| Suggested PSU | 300 W | 250 W |
| Outputs | No outputs | 1x DVI1x HDMI1x DisplayPort |
| Power connectors | None | 1x 6-pin |
| Length | — | 229 mm 9 inches |
| Width | — | 111 mm 4.4 inches |
| Height | — | 35 mm 1.4 inches |
API Support & Features
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.5 | 6.6 |
| CUDA | — | 7.5 |
