NVIDIA Quadro P620 vs NVIDIA T400
Graphics Processor
| GPU model | GP107 | TU117 |
|---|---|---|
| Architecture | Pascal | Turing |
| Foundry | Samsung | TSMC |
| Manufacturing process | 14 nm | 12 nm |
| Number of transistors | 3,300 million | 4,700 million |
| Die size | 132 mm² | 200 mm² |
Graphics Card
| Release date | Feb 1st, 2018 | May 6th, 2021 |
|---|---|---|
| Generation | Quadro | Quadro |
| Production | End-of-life | Active |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1266 MHz | 420 MHz |
|---|---|---|
| Boost clock | 1354 MHz | 1425 MHz |
| Memory clock | 1252 MHz 5 Gbps effective | 1250 MHz 10 Gbps effective |
Memory Configuration
| Memory size | 2 GB | 2 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR6 |
| Memory bus width | 128 bit | 64 bit |
| Bandwidth | 80.13 GB/s | 80.00 GB/s |
Render Configuration
| Shading units | 512 | 384 |
|---|---|---|
| TMUs | 32 | 24 |
| ROPs | 16 | 16 |
| SM count | 4 | 6 |
| Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 1024 KB |
Performance
| Pixel rate | 21.66 GPixel/s | 22.80 GPixel/s |
|---|---|---|
| Texture rate | 43.33 GTexel/s | 34.20 GTexel/s |
| FP16 (half) performance | 21.66 GFLOPS (1:64) | 2.189 TFLOPS (2:1) |
| FP32 (float) performance | 1,386 GFLOPS | 1,094 GFLOPS |
| FP64 (double) performance | 43.33 GFLOPS (1:32) | 34.20 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Single-slot | Single-slot |
|---|---|---|
| Length | 145 mm 5.7 inches | — |
| Width | 69 mm 2.7 inches | — |
| TDP | 40 W | 30 W |
| Suggested PSU | 200 W | 200 W |
| Outputs | 4x mini-DisplayPort | 3x mini-DisplayPort |
| Power connectors | None | None |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 6.1 | 7.5 |
| Shader model | 6.4 | 6.6 |
