NVIDIA A2 vs NVIDIA RTX A4000
Graphics Processor
| GPU model | GA107 | GA104 |
|---|---|---|
| Architecture | Ampere | Ampere |
| Foundry | Samsung | Samsung |
| Manufacturing process | 8 nm | 8 nm |
| Number of transistors | unknown | 17,400 million |
| Die size | unknown | 392 mm² |
| GPU variant | — | GA104-875-A1 |
Graphics Card
| Release date | Nov 10th, 2021 | Apr 12th, 2021 |
|---|---|---|
| Generation | Quadro | Quadro |
| Production | Active | Active |
| Interface | PCIe 4.0 x8 | PCIe 4.0 x16 |
Clocks
| Base clock | 1440 MHz | 735 MHz |
|---|---|---|
| Boost clock | 1770 MHz | 1560 MHz |
| Memory clock | 1563 MHz 12.5 Gbps effective | 1750 MHz 14 Gbps effective |
Memory Configuration
| Memory size | 16 GB | 16 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR6 |
| Memory bus width | 128 bit | 256 bit |
| Bandwidth | 200.1 GB/s | 448.0 GB/s |
Render Configuration
| Shading units | 1280 | 6144 |
|---|---|---|
| TMUs | 40 | 192 |
| ROPs | 32 | 96 |
| SM count | 10 | 48 |
| Tensor cores | 40 | 192 |
| RT cores | 10 | 48 |
| Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 2 MB | 4 MB |
Performance
| Pixel rate | 56.64 GPixel/s | 149.8 GPixel/s |
|---|---|---|
| Texture rate | 70.80 GTexel/s | 299.5 GTexel/s |
| FP16 (half) performance | 4.531 TFLOPS (1:1) | 19.17 TFLOPS (1:1) |
| FP32 (float) performance | 4.531 TFLOPS | 19.17 TFLOPS |
| FP64 (double) performance | 70.80 GFLOPS (1:64) | 599.0 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Single-slot | Single-slot |
|---|---|---|
| TDP | 60 W | 140 W |
| Suggested PSU | 250 W | 300 W |
| Outputs | No outputs | 4x DisplayPort |
| Power connectors | None | 1x 6-pin |
| Board number | PG179 SKU 220 | — |
| Length | — | 241 mm 9.5 inches |
| Width | — | 112 mm 4.4 inches |
API Support & Features
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 8.6 | 8.6 |
| Shader model | 6.6 | 6.6 |
