NVIDIA GeForce GT 630 vs NVIDIA GRID A100B
Graphics Processor
| GPU model | GF108 | GA100 |
|---|---|---|
| GPU variant | GF108-400-A1 | — |
| Architecture | Fermi | Ampere |
| Foundry | TSMC | TSMC |
| Manufacturing process | 40 nm | 7 nm |
| Number of transistors | 585 million | 54,200 million |
| Die size | 116 mm² | 826 mm² |
Graphics Card
| Release date | May 15th, 2012 | May 14th, 2020 |
|---|---|---|
| Generation | GeForce 600 | GRID |
| Production | End-of-life | Active |
| Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Predecessor | GeForce 500 | — |
| Successor | GeForce 700 | — |
Clocks
| GPU clock | 810 MHz | — |
|---|---|---|
| Shader clock | 1620 MHz | — |
| Memory clock | 900 MHz 1800 Mbps effective | 1215 MHz 2.4 Gbps effective |
| Base clock | — | 900 MHz |
| Boost clock | — | 1005 MHz |
Memory Configuration
| Memory size | 1024 MB | 48 GB |
|---|---|---|
| Memory type | DDR3 | HBM2E |
| Memory bus width | 128 bit | 6144 bit |
| Bandwidth | 28.80 GB/s | 1,866 GB/s |
Render Configuration
| Shading units | 96 | 6912 |
|---|---|---|
| TMUs | 16 | 432 |
| ROPs | 4 | 192 |
| SM count | 2 | 108 |
| Cache L1 | 64 KB (per SM) | 192 KB (per SM) |
| Cache L2 | 256 KB | 48 MB |
| Tensor cores | — | 432 |
Performance
| Pixel rate | 3.240 GPixel/s | 193.0 GPixel/s |
|---|---|---|
| Texture rate | 12.96 GTexel/s | 434.2 GTexel/s |
| FP32 (float) performance | 311.0 GFLOPS | 13.89 TFLOPS |
| FP64 (double) performance | 25.92 GFLOPS (1:12) | 6.947 TFLOPS (1:2) |
| FP16 (half) performance | — | 55.57 TFLOPS (4:1) |
Dimensions & Outputs
| Slot width | Single-slot | IGP |
|---|---|---|
| Length | 145 mm 5.7 inches | — |
| TDP | 65 W | 400 W |
| Suggested PSU | 250 W | 800 W |
| Outputs | 1x DVI1x HDMI1x VGA | No outputs |
| Power connectors | None | None |
| Board number | P1071 | — |
API Support & Features
| DirectX | 12 (11_0) | — |
|---|---|---|
| OpenGL | 4.6 | — |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | — |
| CUDA | 2.1 | 8.0 |
| Shader model | 5.1 | — |
