Radeon Pro W6900X vs A100 SXM4 40 GB
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | 102 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 3.34 |
| Power efficiency | no data | 10.65 |
| Architecture | Ampere (2020−2025) | RDNA 2.0 (2020−2025) |
| GPU code name | GA100 | Navi 21 |
| Market segment | Workstation | Workstation |
| Release date | 14 May 2020 (5 years ago) | 3 August 2021 (4 years ago) |
| Launch price (MSRP) | no data | $4,999 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 6912 | 5120 |
| Core clock speed | 1095 MHz | 1825 MHz |
| Boost clock speed | 1410 MHz | 2150 MHz |
| Number of transistors | 54,200 million | 26,800 million |
| Manufacturing process technology | 7 nm | 7 nm |
| Power consumption (TDP) | 400 Watt | 300 Watt |
| Texture fill rate | 609.1 | 688.0 |
| Floating-point processing power | 19.49 TFLOPS | 22.02 TFLOPS |
| ROPs | 160 | 128 |
| TMUs | 432 | 320 |
| Tensor Cores | 432 | no data |
| Ray Tracing Cores | no data | 80 |
| L0 Cache | no data | 1.3 MB |
| L1 Cache | 20.3 MB | 1 MB |
| L2 Cache | 40 MB | 4 MB |
| L3 Cache | no data | 128 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 4.0 x16 | PCIe 4.0 x16 |
| Length | 267 mm | 267 mm |
| Width | IGP | Quad-slot |
| Supplementary power connectors | None | 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 | HBM2e | GDDR6 |
| Maximum RAM amount | 40 GB | 32 GB |
| Memory bus width | 5120 Bit | 256 Bit |
| Memory clock speed | 1215 MHz | 2000 MHz |
| Memory bandwidth | 1,555 GB/s | 512.0 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 | No outputs | 1x HDMI, 4x Thunderbolt |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | N/A | 12 Ultimate (12_2) |
| Shader Model | N/A | 6.5 |
| OpenGL | N/A | 4.6 |
| OpenCL | 2.0 | 2.1 |
| Vulkan | N/A | 1.2 |
| CUDA | 8.0 | - |
| DLSS | + | - |
Pros & cons summary
| Recency | 14 May 2020 | 3 August 2021 |
| Maximum RAM amount | 40 GB | 32 GB |
| Power consumption (TDP) | 400 Watt | 300 Watt |
A100 SXM4 40 GB has a 25% higher maximum VRAM amount.
Pro W6900X, on the other hand, has an age advantage of 1 year, and 33.3% lower power consumption.
We couldn't decide between A100 SXM4 40 GB and Radeon Pro W6900X. We've got no test results to judge.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
