NVIDIA GeForce RTX 3090 vs NVIDIA RTX A6000
What is the difference between NVIDIA GeForce RTX 3090 and NVIDIA RTX A6000. Find out which graphics card has better performance.
Benchmarks
25855 | PassMark G3D | 23382 |
989 | PassMark G2D | 842 |
Graphics Processor (GPU)
GA102 | GPU Name | GA102 |
Ampere | Architecture | Ampere |
Samsung | Foundry | Samsung |
8 nm | Process Size | 8 nm |
28,300 million | Transistors | 28,300 million |
628 mm² | Die Size | 628 mm² |
Graphics Card
Sep 1st, 2020 | Release Date | Oct 5th, 2020 |
GeForce 30 | Family | Quadro (Ax000) |
Active | Production | Active |
1,499 USD | Launch Price | 4,649 USD |
Sep 24th, 2020 | Availability | Dec 15th, 2020 |
PCIe 4.0 x16 | Bus Interface | PCIe 4.0 x16 |
Memory
24 GB | Memory Size | 48 GB |
GDDR6X | Memory Type | GDDR6 |
384 bit | Memory Bus | 384 bit |
936.2 GB/s | Bandwidth | 768.0 GB/s |
Performance
189.8 GPixel/s | Pixel fillrate | 208.3 GPixel/s |
556.0 GTexel/s | Texture fillrate | 625.0 GTexel/s |
35.58 TFLOPS (1:1) | FP16 (half) performance | 40.00 TFLOPS (1:1) |
35.58 TFLOPS | FP32 (float) performance | 40.00 TFLOPS |
556.0 GFLOPS (1:64) | FP64 (double) performance | 1,250 GFLOPS (1:32) |
Clock Speeds
1395 MHz | Base Clock | 1455 MHz |
1695 MHz | Boost Clock | 1860 MHz |
1219 MHz 19.5 Gbps effective | Memory Clock | 2000 MHz 16 Gbps effective |
Render Config
10496 | Shading Units | 10752 |
328 | TMUs | 336 |
112 | ROPs | 112 |
82 | RT Cores | 84 |
128 KB (per SM) | L1 Cache | 128 KB (per SM) |
6 MB | L2 Cache | 6 MB |
82 | SM Count | 84 |
328 | Tensor Cores | 336 |
Board Design
Triple-slot | Slot Width | Dual-slot |
336 mm 13.2 inches | Length | 267 mm 10.5 inches |
140 mm 5.5 inches | Width | 112 mm 4.4 inches |
350 W | Thermal design power (TDP) | 300 W |
750 W | Suggested PSU | 700 W |
1x HDMI 3x DisplayPort | Display Connectors | 4x DisplayPort |
1x 12-pin | Power Connectors | 8-pin EPS |
API support
12 Ultimate (12_2) | DirectX | 12 Ultimate (12_2) |
4.6 | OpenGL | 4.6 |
3.0 | OpenCL | 3.0 |
1.2 | Vulkan | 1.2 |
6.6 | Shader Model | 6.6 |
8.6 | CUDA | 8.6 |