NVIDIA GRID RTX T10-8 vs NVIDIA Quadro P600
Graphics Processor
| GPU model | TU102 | GP107 |
|---|---|---|
| GPU variant | TU102-875-A1 | — |
| Architecture | Turing | Pascal |
| Foundry | TSMC | Samsung |
| Manufacturing process | 12 nm | 14 nm |
| Number of transistors | 18,600 million | 3,300 million |
| Die size | 754 mm² | 132 mm² |
Graphics Card
| Release date | Unknown | Feb 7th, 2017 |
|---|---|---|
| Generation | GRID | Quadro |
| Production | Active | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1065 MHz | 1329 MHz |
|---|---|---|
| Boost clock | 1395 MHz | 1557 MHz |
| Memory clock | 1750 MHz 14 Gbps effective | 1002 MHz 4 Gbps effective |
Memory Configuration
| Memory size | 8 GB | 2 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR5 |
| Memory bus width | 384 bit | 128 bit |
| Bandwidth | 672.0 GB/s | 64.13 GB/s |
Render Configuration
| Shading units | 4608 | 384 |
|---|---|---|
| TMUs | 288 | 24 |
| ROPs | 96 | 16 |
| SM count | 72 | 3 |
| Tensor cores | 576 | — |
| RT cores | 72 | — |
| Cache L1 | 64 KB (per SM) | 48 KB (per SM) |
| Cache L2 | 6 MB | 1024 KB |
Performance
| Pixel rate | 133.9 GPixel/s | 24.91 GPixel/s |
|---|---|---|
| Texture rate | 401.8 GTexel/s | 37.37 GTexel/s |
| FP16 (half) performance | 25.71 TFLOPS (2:1) | 18.68 GFLOPS (1:64) |
| FP32 (float) performance | 12.86 TFLOPS | 1,196 GFLOPS |
| FP64 (double) performance | 401.8 GFLOPS (1:32) | 37.37 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Single-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 150 mm 5.9 inches |
| TDP | 260 W | 40 W |
| Suggested PSU | 600 W | 200 W |
| Outputs | No outputs | 4x mini-DisplayPort |
| Power connectors | 1x 6-pin + 1x 8-pin | None |
| Board number | PG150 SKU 220 | PG212 SKU 501 |
| Width | — | 69 mm 2.7 inches |
API Support & Features
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 7.5 | 6.1 |
| Shader model | 6.6 | 6.4 |
