NVIDIA RTX A5000 vs NVIDIA Tesla K80
Graphics Processor
| GPU model | GA102 | GK210 |
|---|---|---|
| Architecture | Ampere | Kepler 2.0 |
| Foundry | Samsung | TSMC |
| Manufacturing process | 8 nm | 28 nm |
| Number of transistors | 28,300 million | 7,100 million |
| Die size | 628 mm² | 561 mm² |
| GPU variant | — | GK210-885-A1 |
Graphics Card
| Release date | Apr 12th, 2021 | Nov 17th, 2014 |
|---|---|---|
| Generation | Quadro | Tesla |
| Production | Active | End-of-life |
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1170 MHz | 562 MHz |
|---|---|---|
| Boost clock | 1695 MHz | 824 MHz |
| Memory clock | 2000 MHz 16 Gbps effective | 1253 MHz 5 Gbps effective |
Memory Configuration
| Memory size | 24 GB | 12 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR5 |
| Memory bus width | 384 bit | 384 bit |
| Bandwidth | 768.0 GB/s | 240.6 GB/s |
Render Configuration
| Shading units | 8192 | 2496 |
|---|---|---|
| TMUs | 256 | 208 |
| ROPs | 96 | 48 |
| SM count | 64 | — |
| Tensor cores | 256 | — |
| RT cores | 64 | — |
| Cache L1 | 128 KB (per SM) | 16 KB (per SMX) |
| Cache L2 | 6 MB | 1536 KB |
| SMX count | — | 13 |
Performance
| Pixel rate | 162.7 GPixel/s | 42.85 GPixel/s |
|---|---|---|
| Texture rate | 433.9 GTexel/s | 171.4 GTexel/s |
| FP16 (half) performance | 27.77 TFLOPS (1:1) | — |
| FP32 (float) performance | 27.77 TFLOPS | 4.113 TFLOPS |
| FP64 (double) performance | 867.8 GFLOPS (1:32) | 1,371 GFLOPS (1:3) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 267 mm 10.5 inches |
| Width | 112 mm 4.4 inches | — |
| TDP | 230 W | 300 W |
| Suggested PSU | 550 W | 700 W |
| Outputs | 4x DisplayPort | No outputs |
| Power connectors | 1x 8-pin | 1x 8-pin |
| Board number | — | P2080 SKU 200 |
API Support & Features
| DirectX | 12 Ultimate (12_2) | 12 (11_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| CUDA | 8.6 | 3.7 |
| Shader model | 6.6 | 5.1 |
