NVIDIA GRID A100A vs NVIDIA Quadro 6000
Graphics Processor
| GPU model | GA100 | GF100 |
|---|---|---|
| Architecture | Ampere | Fermi |
| Foundry | TSMC | TSMC |
| Manufacturing process | 7 nm | 40 nm |
| Number of transistors | 54,200 million | 3,100 million |
| Die size | 826 mm² | 529 mm² |
| GPU variant | — | GF100-850-A3 |
Graphics Card
| Release date | May 14th, 2020 | Dec 10th, 2010 |
|---|---|---|
| Generation | GRID | Quadro |
| Production | Active | End-of-life |
| Interface | PCIe 4.0 x16 | PCIe 2.0 x16 |
| Launch price | — | 4,399 USD |
| Reviews | — | 26 in our database |
Clocks
| Base clock | 900 MHz | — |
|---|---|---|
| Boost clock | 1005 MHz | — |
| Memory clock | 1215 MHz 2.4 Gbps effective | 747 MHz 3 Gbps effective |
| GPU clock | — | 574 MHz |
| Shader clock | — | 1147 MHz |
Memory Configuration
| Memory size | 48 GB | 6 GB |
|---|---|---|
| Memory type | HBM2E | GDDR5 |
| Memory bus width | 6144 bit | 384 bit |
| Bandwidth | 1,866 GB/s | 143.4 GB/s |
Render Configuration
| Shading units | 6912 | 448 |
|---|---|---|
| TMUs | 432 | 56 |
| ROPs | 192 | 48 |
| SM count | 108 | 14 |
| Tensor cores | 432 | — |
| Cache L1 | 192 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 48 MB | 768 KB |
Performance
| Pixel rate | 193.0 GPixel/s | 16.07 GPixel/s |
|---|---|---|
| Texture rate | 434.2 GTexel/s | 32.14 GTexel/s |
| FP16 (half) performance | 55.57 TFLOPS (4:1) | — |
| FP32 (float) performance | 13.89 TFLOPS | 1,028 GFLOPS |
| FP64 (double) performance | 6.947 TFLOPS (1:2) | 513.9 GFLOPS (1:2) |
Dimensions & Outputs
| Slot width | IGP | Dual-slot |
|---|---|---|
| TDP | 400 W | 204 W |
| Suggested PSU | 800 W | 550 W |
| Outputs | No outputs | 1x DVI2x DisplayPort1x S-Video |
| Power connectors | None | 1x 6-pin + 1x 8-pin |
| Length | — | 248 mm 9.8 inches |
| Width | — | 111 mm 4.4 inches |
| Board number | — | P1030 |
API Support & Features
| DirectX | — | 12 (11_0) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 3.0 | 1.1 |
| Vulkan | — | — |
| CUDA | 8.0 | 2.0 |
| Shader model | — | 5.1 |
