B100 vs Radeon R7 384 Cores (Kaveri Desktop)
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 864 | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Architecture | GCN (2012−2015) | Blackwell (2024−2025) |
| GPU code name | Kaveri Spectre | GB102 |
| Market segment | Desktop | Workstation |
| Release date | 14 January 2014 (11 years ago) | November 2024 (1 year 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 | 384 | 16896 ×2 |
| Core clock speed | 720 MHz | 1665 MHz |
| Boost clock speed | no data | 1837 MHz |
| Number of transistors | no data | 104,000 million |
| Manufacturing process technology | 28 nm | 5 nm |
| Power consumption (TDP) | no data | 1000 Watt |
| Texture fill rate | no data | 969.9 ×2 |
| Floating-point processing power | no data | 62.08 TFLOPS ×2 |
| ROPs | no data | 24 ×2 |
| TMUs | no data | 528 ×2 |
| Tensor Cores | no data | 528 ×2 |
| L1 Cache | no data | 33 MB |
| L2 Cache | no data | 50 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 | no data | PCIe 5.0 x16 |
| Width | no data | SXM Module |
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 | no data | HBM3e |
| Maximum RAM amount | no data | 96 GB ×2 |
| Memory bus width | no data | 4096 Bit ×2 |
| Memory clock speed | no data | 2000 MHz |
| Memory bandwidth | no data | 4.1 TB/s ×2 |
| Shared memory | + | - |
| 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 data | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (FL 12_0) | N/A |
| Shader Model | no data | N/A |
| OpenGL | no data | N/A |
| OpenCL | no data | 3.0 |
| Vulkan | - | N/A |
| CUDA | - | 10.1 |
| DLSS | - | + |
Pros & cons summary
| Chip lithography | 28 nm | 5 nm |
B100 has a 460% more advanced lithography process.
We couldn't decide between Radeon R7 384 Cores (Kaveri Desktop) and B100. We've got no test results to judge.
Be aware that Radeon R7 384 Cores (Kaveri Desktop) is a desktop graphics card while B100 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.
