A100 SXM4 vs Radeon HD 6870 1600SP Edition
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Architecture | TeraScale 2 (2009−2015) | Ampere (2020−2025) |
| GPU code name | Cypress | GA100 |
| Market segment | Desktop | Workstation |
| Release date | 14 January 2013 (12 years ago) | 14 May 2020 (5 years ago) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 1600 | 6912 |
| Core clock speed | 850 MHz | 1410 MHz |
| Number of transistors | 2,154 million | 54,200 million |
| Manufacturing process technology | 40 nm | 7 nm |
| Power consumption (TDP) | 175 Watt | 400 Watt |
| Texture fill rate | 68.00 | 609.1 |
| Floating-point processing power | 2.72 TFLOPS | 19.49 TFLOPS |
| ROPs | 32 | 160 |
| TMUs | 80 | 432 |
| Tensor Cores | no data | 432 |
| L1 Cache | 160 KB | 20.3 MB |
| L2 Cache | 512 KB | 40 MB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Length | 282 mm | no data |
| Width | 2-slot | IGP |
| Supplementary power connectors | 2x 6-pin | None |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR5 | HBM2E |
| Maximum RAM amount | 1 GB | 40 GB |
| Memory bus width | 256 Bit | 5120 Bit |
| Memory clock speed | 1050 MHz | 1215 MHz |
| Memory bandwidth | 134.4 GB/s | 1,555 GB/s |
| Resizable BAR | - | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 2x DVI, 1x HDMI, 2x mini-DisplayPort | No outputs |
| HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
| Shader Model | 5.0 | 6.5 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 2.0 |
| Vulkan | N/A | 1.2.140 |
| CUDA | - | 8.0 |
| DLSS | - | + |
Pros & cons summary
| Recency | 14 January 2013 | 14 May 2020 |
| Maximum RAM amount | 1 GB | 40 GB |
| Chip lithography | 40 nm | 7 nm |
| Power consumption (TDP) | 175 Watt | 400 Watt |
HD 6870 1600SP Edition has 128.6% lower power consumption.
A100 SXM4, on the other hand, has an age advantage of 7 years, a 3900% higher maximum VRAM amount, and a 471.4% more advanced lithography process.
We couldn't decide between Radeon HD 6870 1600SP Edition and A100 SXM4. We've got no test results to judge.
Be aware that Radeon HD 6870 1600SP Edition is a desktop graphics card while A100 SXM4 is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
