NVIDIA GeForce4 Ti 4200-8X vs NVIDIA P102-100
Graphics Processor
| GPU model | NV28 | GP102 |
|---|---|---|
| Architecture | Kelvin | Pascal |
| Foundry | TSMC | TSMC |
| Manufacturing process | 150 nm | 16 nm |
| Number of transistors | 36 million | 11,800 million |
| Die size | 101 mm² | 471 mm² |
| GPU variant | Ti 4200-8X | GP102-100-A1 |
Graphics Card
| Release date | Feb 6th, 2002 | Feb 12th, 2018 |
|---|---|---|
| Generation | GeForce 4 Ti | Mining GPUs |
| Production | End-of-life | End-of-life |
| Interface | AGP 8x | PCIe 3.0 x4 |
| Predecessor | GeForce 4 MX | — |
| Successor | GeForce FX | — |
Clocks
| GPU clock | 250 MHz | — |
|---|---|---|
| Memory clock | 250 MHz | 1376 MHz 11 Gbps effective |
| Base clock | — | 1582 MHz |
| Boost clock | — | 1683 MHz |
Memory Configuration
| Memory size | 64 MB | 5 GB |
|---|---|---|
| Memory type | SDR | GDDR5X |
| Memory bus width | 128 bit | 320 bit |
| Bandwidth | 4.000 GB/s | 440.3 GB/s |
Render Configuration
| Pixel shaders | 4 | — |
|---|---|---|
| Vertex shaders | 2 | — |
| TMUs | 8 | 200 |
| ROPs | 4 | 80 |
| Shading units | — | 3200 |
| SM count | — | 25 |
| Cache L1 | — | 48 KB (per SM) |
| Cache L2 | — | 2.5 MB |
Performance
| Pixel rate | 1.000 GPixel/s | 134.6 GPixel/s |
|---|---|---|
| Vertex rate | 125.0 MVertices/s | — |
| Texture rate | 2.000 GTexel/s | 336.6 GTexel/s |
| FP16 (half) performance | — | 168.3 GFLOPS (1:64) |
| FP32 (float) performance | — | 10.77 TFLOPS |
| FP64 (double) performance | — | 336.6 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Single-slot | Dual-slot |
|---|---|---|
| TDP | unknown | 250 W |
| Suggested PSU | 200 W | 600 W |
| Outputs | 1x DVI1x VGA1x S-Video | No outputs |
| Power connectors | None | 2x 8-pin |
| Length | — | 267 mm 10.5 inches |
| Board number | — | PG611 SKU 100 |
API Support & Features
| DirectX | 8.1 | 12 (12_1) |
|---|---|---|
| OpenGL | 1.5 | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.2 |
| Pixel shader | 1.3 | — |
| Vertex shader | 1.1 | — |
| CUDA | — | 6.1 |
| Shader model | — | 6.4 |
