GPU model | Eclipse | GA106 |
---|---|---|
GPU variant | MGA-G200A-B | GA106-150-A1 |
Architecture | G200 | Ampere |
Foundry | UMC | Samsung |
Manufacturing process | 350 nm | 8 nm |
Number of transistors | 10 million | 13,250 million |
Die size | unknown | 276 mm² |
Release date | 1998 | 2022 |
---|---|---|
Generation | G Series | GeForce 30 |
Production | End-of-life | Unreleased |
Interface | PCI | PCIe 4.0 x16 |
Reviews | 5 in our database | — |
gpu.details.availability | — | 2022 |
Predecessor | — | GeForce 20 |
GPU clock | 84 MHz | — |
---|---|---|
Memory clock | 143 MHz | 1750 MHz 14 Gbps effective |
Base clock | — | 1552 MHz |
Boost clock | — | 1777 MHz |
Memory size | 8 MB | 8 GB |
---|---|---|
Memory type | SGR | GDDR6 |
Memory bus width | 64 bit | 128 bit |
Bandwidth | 1.144 GB/s | 224.0 GB/s |
Pixel shaders | 1 | — |
---|---|---|
Vertex shaders | 1 | — |
TMUs | 1 | 80 |
ROPs | 1 | 48 |
Shading units | — | 2560 |
SM count | — | 20 |
Tensor cores | — | 80 |
RT cores | — | 20 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 2 MB |
Pixel rate | 84.00 MPixel/s | 85.30 GPixel/s |
---|---|---|
Vertex rate | 21.00 MVertices/s | — |
Texture rate | 84.00 MTexel/s | 142.2 GTexel/s |
FP16 (half) performance | — | 9.098 TFLOPS (1:1) |
FP32 (float) performance | — | 9.098 TFLOPS |
FP64 (double) performance | — | 142.2 GFLOPS (1:64) |
Slot width | Single-slot | Dual-slot |
---|---|---|
Length | 150 mm 5.9 inches | 242 mm 9.5 inches |
TDP | unknown | 90 W |
Suggested PSU | 200 W | 250 W |
Outputs | 1x DVI1x VGA | 1x HDMI3x DisplayPort |
Power connectors | None | 1x 6-pin |
Width | — | 112 mm 4.4 inches |
DirectX | 5.0 | 12 Ultimate (12_2) |
---|---|---|
OpenGL | None | 4.6 |
OpenCL | None | 3.0 |
Vulkan | — | 1.2 |
Pixel shader | None | — |
Vertex shader | None | — |
CUDA | — | 8.6 |
Shader model | — | 6.6 |