Compare
This is a comprehensive analysis comparing the NVIDIA A10G on one side and NVIDIA GeForce RTX 3090 on the other side.
The first video card was released on Apr 12th, 2021. This GPU is equipped with 12 GB of GDDR6 memory, with a bandwidth of 600.2 GB/s. The architecture of this card: base clock of 1320 MHz and a boost clock of 1710 MHz, TDP of this video card is 150 W.
The second video card was released on Sep 1st, 2020 and comes with 24 GB of GDDR6X memory, with a bandwidth of 936.2 GB/s. This GPU also has a base clock of 1395 MHz and a boost clock of 1695 MHz, and it has a TDP of 350 W.
This table also comprises board specifications, pixel and texture filtration, launch price, and benchmarks such as G3DMark, PassMark G2D, 3DMark Firestrike, FPS, and Hashrate.
| NVIDIA A10G |
NVIDIA GeForce RTX 3090 |
|
|---|---|---|
| Graphics Processor | ||
| GPU Name: | NVIDIA A10G | NVIDIA GeForce RTX 3090 |
| GPU Variant: | GA102-890-A1 | GA102-300-A1 |
| Processor: | Ampere | Ampere |
| Foundry: | Samsung | Samsung |
| Technology: | 8 nm | 8 nm |
| Transistors: | 28,300 million | 28,300 million |
| Die Size: | 628 mm² | 628 mm² |
| General information | ||
| Release Date: | Apr 12th, 2021 | Sep 1st, 2020 |
| Availability: | 2021 | Sep 24th, 2020 |
| Generation: | Tesla (Axx) | GeForce 30 |
| Predecessor: | - | GeForce 20 |
| Successor: | - | GeForce 40 |
| Production: | Active | Active |
| Launch Price: | - | 1,499 USD |
| Current Price: | - | Amazon / Newegg |
| Bus Interface: | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Reviews: | - | 58 in our database |
| Clock Speeds | ||
| Base Clock Speed: | 1320 MHz | 1395 MHz |
| Boost Clock Speed: | 1710 MHz | 1695 MHz |
| SOC clock: | - | - |
| UVD clock: | - | - |
| Memory Clock: | 1563 MHz 12.5 Gbps effective | 1219 MHz 19.5 Gbps effective |
| Memory specs | ||
| RAM: | 12 GB | 24 GB |
| Type of memory: | GDDR6 | GDDR6X |
| Memory Bus: | 384 bit | 384 bit |
| Memory Bandwidth: | 600.2 GB/s | 936.2 GB/s |
| Render Config | ||
| Shading Units: | 9216 | 10496 |
| TMUs: | 288 | 328 |
| ROPs: | 96 | 112 |
| Compute units: | - | - |
| Tensor Cores: | - | - |
| RT Cores: | 72 | 82 |
| L0 Cache: | - | - |
| L1 Cache: | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache: | 6 MB | 6 MB |
| L3 Cache: | - | - |
| Theoretical Performance | ||
| Pixel Fillrate: | 164.2 GPixel/s | 189.8 GPixel/s |
| Texture Fillrate: | 492.5 GTexel/s | 556.0 GTexel/s |
| FP32 (float): | 31.52 TFLOPS | 35.58 TFLOPS |
| Board specs | ||
| Slot Width: | Single-slot | Triple-slot |
| Length: | 267 mm 10.5 inches | 336 mm 13.2 inches |
| Width: | 112 mm 4.4 inches | 140 mm 5.5 inches |
| Height: | - | 61 mm 2.4 inches |
| TDP: | 150 W | 350 W |
| Suggested PSU: | 450 W | 750 W |
| Outputs: | No outputs | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors: | 8-pin EPS | 1x 12-pin |
| Part Number: | - | - |
| Board Number: | PG133 SKU 215 | PG132 SKU 10 |
| Technology Support | ||
| DirectX: | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 126737 | 204921 |
| Vulkan: | - | 138859 |
| CUDA: | 187763 | 238123 |
| Shader Model: | - | - |
© 2023
